DETAILED ACTION
Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
This final action is in response to Applicant’s filing dated September 8, 2026. Claims 1-20 are currently pending and have been considered, as provided in more detail below. Claims 1-13 have been amended and claims 14-20 have been newly added.
*Examiner Note: Claim language is bolded. Cited References and Applicant’s arguments are italicized. Examiner interpretations are preceded with an asterisk *.
Response to Arguments
Applicant’s arguments filed 9/8/26 have been considered but are moot because the arguments are directed toward subject matter that has not been previously considered and has necessitated a new ground of rejection as outlined below. While the new ground of rejection may rely on some of the previous references applied in the prior rejection of record, new additional references have been added to the combination and introduced for Applicant’s consideration given the amended independent claims and newly added claims as discussed in detail below.
Applicant’s arguments and amendments regarding the rejection under 35 USC 101 have been fully considered, but they are not persuasive. The amendments to claim 1 require controlling an actuator system based on the evaluation. Therefore, the eligibility analysis additionally addresses that limitation. The added limitation does not change the conclusion for the reasons discussed in detail below. The newly added limitation is “controlling an actuator system of the vehicle based on the evaluation by either causing the suggested trajectory to be implemented by the actuator system or preventing the suggested trajectory from being implemented by the actuator system”. This step recites only that the actuator system either implements the trajectory or does not, according to the evaluation. This limitation fails to identify the actuator system’s components; any parameter or manner of control or any way the content of the evaluation determines how the vehicle operates. Every monitoring method that evaluates a proposal and lets it proceed or blocks it ends in the same outcome. Therefore, attempting to connect the step to the evaluation does not make it a particular application. See MPEP 2106.05(e), (f).
The Examiner respectfully does not agree with Applicant’s argument that “The claimed
arrangement improves automated vehicle operation by providing an independent check” because the claim does not recite an independent monitor, a separate safety path or any architecture, etc. The added limitation of “independently of any suggested trajectory” merely describes how the behaviors are derived and not how the system is or isn’t implemented. Additionally, the claims do not “recite substantially more than a mental process” as argued by Applicant. As discussed below, the additional elements, generic computer implementation, data gathering and acting on the result do not amount to significantly more, alone or in combination. Finally, for the reasons above and those discussed in detail below, the claim does not integrate the exception into a practical application. Therefore, claims 1-20 remain rejected under 35 USC 101.
Response to Amendment
Regarding the rejection under 35 USC 101, the amendments made to the claims fail to overcome the rejection. The rejections under 35 USC 101 are maintained as outlined below.
Regarding the rejections under 35 USC 103, the amendments made to the claims have necessitated new grounds of rejection as outlined below.
Claim Rejections - 35 USC § 101
35 U.S.C. 101 reads as follows:
Whoever invents or discovers any new and useful process, machine, manufacture, or composition of matter, or any new and useful improvement thereof, may obtain a patent therefor, subject to the conditions and requirements of this title.
Claims 1-20 are rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without significantly more.
101 Analysis – Step 1
Regarding Step 1 of the Revised Guidance, it must be considered whether the claims are directed to one of the four statutory classes of invention. In the instant case, claims 1-8, 16-20 are directed to a computer-implemented method (i.e., a method) and claims 9-15 are directed to a computer-implemented system (i.e., a machine).
Therefore, claims 1-20 are within at least one of the four statutory categories (processes, machines, manufactures and compositions of matter.
101 Analysis – Step 2A, Prong 1
Regarding Prong 1 of the Step 2A analysis in the 2019 PEG, the claims are to be analyzed to determine whether they recite a judicial exception (subject matter that falls within one of the follow groups of abstract ideas: a) mathematical concepts, b) mental processes, and/or c) certain methods of organizing human activity).
Independent claim 1 includes limitations that recite an abstract idea (bolded below) and will be used as a representative claim for the remainder of the 101 rejection. Claim 1 recites:
A computer-implemented method for monitoring trajectories suggested by at least one planning module for an automated operating mode of a vehicle, the method comprising the following steps:
aggregating situation-specific information;
generating a surroundings model based on the situation-specific information;
ascertaining a plurality of possible behaviors of the vehicle for a current traffic situation based on the situation-specific information and the surroundings model and independently of any suggested trajectory, wherein each behavior of the possible behaviors represents a different possible response of the vehicle to the current traffic situation and is described by a respective set of boundary conditions that collectively defines the different possible response; and
prioritizing the possible behaviors of the vehicle by arranging the possible behaviors in a list in an order of descending priority based on the boundary conditions in conjunction with a predefined set of rules;
wherein one or more compatibility checks are carried out between a suggested trajectory and respective ones of the ascertained behaviors by checking whether the suggested trajectory satisfies the boundary conditions of each respective behavior, and the suggested trajectory is then evaluated based on the results of the compatibility checks and the priorities of the respective behaviors; and
controlling an actuator system of the vehicle based on the evaluation by either causing the suggested trajectory to be implemented by the actuator system or preventing the suggested trajectory from being implemented by the actuator system.
The Examiner submits that the foregoing bolded limitations constitute a judicial exception in terms of “mental process” because under its broadest reasonable interpretation, the claim limitations can be “performed in the human mind, or by a human using a pen and paper”. See MPEP 2106.04(a)(2)(III).
The independent claim 1 recites the limitations of (1) ascertaining a plurality of possible
behaviors of the vehicle for a current traffic situation based on the situation-specific information and the surroundings model and independently of any suggested trajectory, wherein each behavior of the possible behaviors represents a different possible response of the vehicle to the current traffic situation and is described by a respective set of boundary conditions that collectively defines the different possible response; (2) prioritizing the possible behaviors of the vehicle by arranging the possible behaviors in a list in an order of descending priority based on the boundary conditions in conjunction with a predefined set of rules; (3) wherein one or more compatibility checks are carried out between a suggested trajectory and respective ones of the ascertained behaviors by checking whether the suggested trajectory satisfies the boundary conditions of each respective behavior, and (4) the suggested trajectory is then evaluated based on the results of the compatibility checks and the priorities of the respective behaviors. The ascertaining possible behaviors, prioritizing the possible behaviors and checking whether the suggested trajectory satisfies the boundary conditions of the respective behavior limitations, as drafted, are processes that, under their broadest reasonable interpretation, encompass determining possible behaviors, evaluating whether conditions are satisfied, prioritizing behaviors according to rules, and comparing trajectories against behavioral conditions. Such activities are capable of practical performance in the human mind or by a human using pen and paper. Given a described traffic situation, a person can enumerate candidate responses (i.e., staying in lane, changing lanes, stopping), state conditions definiens each, rank them by applying a rule set, compare a proposed path with each response’s conditions and assign the path an evaluation. The claim recites no limitation requiring computation speed or volume that would prevent this. For example, a person examining a road scene representation and a proposed path can identify alternative responses such as passing an obstacle within the lane, passing using another lane or stopping before the obstacle. A person may also describe those responses through lane and stopping conditions; order them under stated rules; and determine which conditions the proposed path satisfies. The person can then evaluate the path according to the priorities of the compatible responses. The requirement that the responses be determined independently of the proposed trajectory is included in this analysis: the person can identify and rank the available responses from the traffic scene before examining the proposed path. The claimed limitations cover rule evaluation, prioritization and judgment. The claim recites the result of determining behaviors and applying rules, without reciting any specific technological mechanisms for performing those determinations.
Accordingly, the claim recites at least one abstract idea. The additional recitations of
“aggregating situation-specific information” and “generating a surroundings model based on the situation-specific information” merely gather and organize information for use by the recited abstract evaluation process and do not remove the claimed invention from the mental process grouping because the claim does not recite any specific improvement to trajectory monitoring or electric vehicle operation itself. The new and additional recitation of “controlling an actuator system of the vehicle based on the evaluation by either causing the suggested trajectory to be implemented by the actuator system or preventing the suggested trajectory from being implemented by the actuator system” is directed to an actuator system that implements the trajectory or does not implement the trajectory. It does not name and actuator (steering, braking, drive, etc.), no parameters and no manner of implementation. Under the broadest reasonable interpretation, “preventing the suggested trajectory from being implemented” can be met by withholding a command, which does not need physical operation.
Thus, the claim recites a mental process.
101 Analysis – Step 2A, Prong 2 evaluation: Practical Application - No
In Step 2A, Prong two of the 2019 PEG, a claim is to be evaluated whether, as a whole, it integrates the recited judicial exception into a practical application. As noted in MPEP 2106.04(d), it must be determined whether any additional elements in the claim beyond the abstract idea integrate the exception into a practical application in a manner that imposes a meaningful limit on the judicial exception, such that the claim is more than a drafting effort designed to monopolize the judicial exception. The courts have indicated that additional elements such as: merely using a computer to implement an abstract idea, adding insignificant extra solution activity, or generally linking use of a judicial exception to a particular technological environment or field of use do not integrate a judicial exception into a “practical application.”
The Office submits that the foregoing underlined limitation(s) recite additional elements that do not integrate the recited judicial exception into a practical application. In the instant application, the additional limitations beyond the above-noted abstract ideas are as follows (where the underlined portions are the “additional limitations” while the bolded portions continue to represent the “abstract idea”):
In Claim 1:
A computer-implemented method for monitoring trajectories suggested by at least one planning module for an automated operating mode of a vehicle, the method comprising the following steps:
aggregating situation-specific information;
generating a surroundings model based on the situation-specific information;
ascertaining a plurality of possible behaviors of the vehicle for a current traffic situation based on the situation-specific information and the surroundings model and independently of any suggested trajectory, wherein each behavior of the possible behaviors represents a different possible response of the vehicle to the current traffic situation and is described by a respective set of boundary conditions that collectively defines the different possible response; and
prioritizing the possible behaviors of the vehicle by arranging the possible behaviors in a list in an order of descending priority based on the boundary conditions in conjunction with a predefined set of rules;
wherein one or more compatibility checks are carried out between a suggested trajectory and respective ones of the ascertained behaviors by checking whether the suggested trajectory satisfies the boundary conditions of each respective behavior, and the suggested trajectory is then evaluated based on the results of the compatibility checks and the priorities of the respective behaviors; and
controlling an actuator system of the vehicle based on the evaluation by either causing the suggested trajectory to be implemented by the actuator system or preventing the suggested trajectory from being implemented by the actuator system.
The claim recites the additional elements of “aggregating situation-specific information” and “generating a surroundings model based on the situation-specific information” and “controlling an actuator system of the vehicle”.
The method recites the additional elements of aggregating situation-specific information and generating a surroundings model which merely gathers and organize information for use in the recited abstract evaluation process. The claim does not recite any specific technique for generating the surrounding model, and improvement to vehicle operation, any improvement to computer functionality or any specialized machine implementation. The Examiner acknowledges that the newly added limitation requires causing or preventing trajectory implementation through the vehicle’s actuator system. It is not construed as merely displaying an evaluation or recommendation. However, the Examiner finds that the claimed application remains results oriented. The claim identifies the categories of information considered in the assessment (behavior conditions, priorities and compatibility results). But the rules, the substantive conditions, the way compatibility and priority determine the evaluation and the criteria by which the evaluation causes implementation or prevention remain unspecified.
The limitations require constructing and applying an ordered assessment framework and then acting on the result. The control imitation specifies the desired execution outcome but does not further define how the claimed assessment is integrated into a particular control decision. Under the broadest reasonable interpretation, the computer and actuator system are used to perform and apply the assessment rather than to implement a particular technological solution reflected in the claim. Applicant’s specification includes a limited discussion of the actuator system at paragraph [0004] which discloses “ A first path, the so-called performance path, comprises at least one planning module for generating trajectories that each describe a possible behavior of the automated vehicle for the given situation and can be implemented by the actuator system of the vehicle”; paragraph [0031] which discloses “According to an example embodiment of the present invention, the evaluation module is preferably configured to make the results of the compatibility checks and/or evaluation of the suggested trajectory available via at least one interface, in particular to a downstream control module for selecting a trajectory that is then to be implemented by the actuator system of the vehicle”; and paragraph [0059] which discloses “In the selection module 130, the evaluation results are compared with one another in order to select exactly one trajectory for the control 140 of the actuator system of the vehicle”. The Examiner has considered this vague description of the trajectory monitoring arrangement these paragraphs which connect evaluation results to downstream selection and actuator control. These paragraphs support the operation connection, but do not overcome the result-oriented scope of the claimed application identified above. The Examiner has also considered the combination of trajectory independent response ascertainment, response defined condition sets, descending priorities and compatibility-based evaluation. The asserted improvement, as broadly as recited, is organizing the criteria used to judge a trajectory. The claim does not further specify how that organization changes the operation of the planning or control technology beyond requiring execution to depend on the resulting assessment.
Accordingly, even in combination, these additional elements do not integrate the abstract idea into a practical application because they do not impose any meaningful limits on practicing the abstract idea.
101 Analysis – Step 2B evaluation: Inventive Concept: - No
In Step 2B of the 2019 PEG, the claim(s) is to be evaluated as to whether the claim, as a whole, amounts to significantly more than the recited exception, i.e., whether any additional element, or combination of additional elements, adds an inventive concept to the claim. See MPEP 2106.05.
As discussed with respect to Step 2A Prong Two, the additional elements in the claim amount to no more than mere aggregating situation-specific information and generating a surrounding model based on that information and mere generic implementation, data gathering and a generic recitation of acting on the result, for the reasons above. The same analysis applies here in 2B, i.e., mere data gathering to generate a basic model cannot integrate a judicial exception into a practical application at Step 2A or provide an inventive concept in Step 2B, MPEP 2106.05(f). Paragraph [0059] of Applicant’s specification discloses “In the selection module 130, the evaluation results are compared with one another in order to select exactly one trajectory for the control 140 of the actuator system of the vehicle”. But under the broadest reasonable interpretation, the actuator system could merely be a display to a driver for a selection. There is no explanation in the specification detailing the components of the actuator system and how it functions to control the vehicle. The computer implementation language provides a platform for performing that process. The final limitation requires using the resulting evaluation to cause or prevent implementation of the suggested trajectory through the vehicle’s actuator system. The Examiner acknowledges that this final limitation requires implementation control, rather than merely displaying a recommendation. However, for the reasons explained under Prong 2, the Examiner maintains that the claim recites the application at a generalized, result orientated level. The evaluation is used to permit or prevent implementation, without further defining the criteria translating the compatibility results and behavior priorities into that control decision. The additional elements provide information for the assessment, computer implementation of the assessment and a generalized instruction to apply its result to trajectory execution. Therefore, the additional elements amount to mere instruction to apply the identified exception and do not supply significantly more.
Under the 2019 PEG, a conclusion that an additional element is insignificant extra-solution activity in Step 2A should be re-evaluated in Step 2B. Here, the steps of aggregating situation-specific information and generating a surroundings model based on the situation-specific information were considered to be additional elements in Step 2A, and thus they are re-evaluated in Step 2B to determine if they are more than what is well-understood, routine, conventional activity in the field. MPEP 2106.05(d)(II), and the cases cited therein, including Intellectual Ventures I, LLC v. Symantec Corp., 838 F.3d 1307, 1321 (Fed. Cir. 2016), TLI Communications LLC v. AV Auto. LLC, 823 F.3d 607, 610 (Fed. Cir. 2016), and OIP Techs., Inc., v. Amazon.com, Inc., 788 F.3d 1359, 1363 (Fed. Cir. 2015), indicate that mere collection or receipt of data over a network is a well‐understood, routine, and conventional function when it is claimed in a merely generic manner. Further, the Federal Circuit in Trading Techs. Int’l v. IBG LLC, 921 F.3d 1084, 1093 (Fed. Cir. 2019), and Intellectual Ventures I LLC v. Erie Indemnity Co., 850 F.3d 1315, 1331 (Fed. Cir. 2017), for example, indicated that the mere displaying of data is a well understood, routine, and conventional function. The cited cases indicate that generic information gathering, collection and processing functions performed by conventional computer technology are well-understood, routine and conventional activities. Accordingly, a conclusion that the steps of aggregating situation-specific information and generating a surroundings model based on the situation-specific information constitute well-understood, routine and conventional information gathering and information processing activities is supported under Berkheimer.
Thus, claims 1 and 9 are ineligible.
101 Analysis – Dependent Claims
Dependent claims 2-8 and 10-20 do not recite any further limitations that cause the claims to be patent eligible. Rather, the limitations of the dependent claims are directed toward additional aspects of the judicial exception and/or well-understood, routine and conventional additional elements that do not integrate the judicial exception into a practical application [these dependent claims inherit the abstract idea set forth in claims 1 and 9, respectively. No other technology or action has been recited in claims 2-8 and 10-13 to integrate the abstract idea into a practical application nor to amount to significantly more than the abstract idea. Thus, claims 2-8 and 10-20 also do not confer eligibility on the claimed invention and are ineligible for reasons stated above and for similar reasons to claims 1 and 9. Therefore, dependent claims 2-8 and 10-20 are not patent eligible under the same rationale as provided for in the rejection of independent claim 1 and 9.
Therefore, claims 2-8 and 10-20 are also ineligible under 35 USC §101.
Claim Rejections - 35 USC § 112
The following is a quotation of the first paragraph of 35 U.S.C. 112(a):
(a) IN GENERAL.—The specification shall contain a written description of the invention, and of the manner and process of making and using it, in such full, clear, concise, and exact terms as to enable any person skilled in the art to which it pertains, or with which it is most nearly connected, to make and use the same, and shall set forth the best mode contemplated by the inventor or joint inventor of carrying out the invention.
The following is a quotation of the first paragraph of pre-AIA 35 U.S.C. 112:
The specification shall contain a written description of the invention, and of the manner and process of making and using it, in such full, clear, concise, and exact terms as to enable any person skilled in the art to which it pertains, or with which it is most nearly connected, to make and use the same, and shall set forth the best mode contemplated by the inventor of carrying out his invention.
Claims 1 and 9 are rejected under 35 U.S.C. 112(a) or 35 U.S.C. 112 (pre-AIA ), first paragraph, as failing to comply with the written description requirement. The claims contains subject matter which was not described in the specification in such a way as to reasonably convey to one skilled in the relevant art that the inventor or a joint inventor, or for applications subject to pre-AIA 35 U.S.C. 112, the inventor(s), at the time the application was filed, had possession of the claimed invention.
The newly added limitations set forth in claims 1 and 9 regarding “controlling an actuator system of the vehicle based on the evaluation by either causing the suggested trajectory to be implemented by the actuator system or preventing the suggested trajectory from being implemented by the actuator system” and “control an actuator system of the vehicle based on the evaluation by either causing the suggested trajectory to be implemented by the actuator system or preventing the suggested trajectory from being implemented by the actuator system” are new matter because the specification contains no language describing how the actuator system implements the suggested trajectory or how the implementation of the suggested trajectory is prevented by the actuator system. The configuration of the actuator system permitting or preventing the suggested trajectory is not described in the specification and it is not clear how the actuator system relates to the other components of the invention for the purpose of implementing or preventing the trajectory. Since such a configuration does not have support in the originally filed specification, this lacks written description support. Additionally, controlling the actuator system of the vehicle based on the evaluation by either causing the suggested trajectory to be implemented by the actuator system or preventing the suggested trajectory from being implemented by the actuator system is new matter because there is no discussion of exactly how the implementation is permitted or how the implementation of the suggested trajectory is prevented.
The following is a quotation of 35 U.S.C. 112(b):
(b) CONCLUSION.—The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the inventor or a joint inventor regards as the invention.
The following is a quotation of 35 U.S.C. 112 (pre-AIA ), second paragraph:
The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the applicant regards as his invention.
Claims 1-20 are rejected under 35 U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA ), second paragraph, as being indefinite for failing to particularly point out and distinctly claim the subject matter which the inventor or a joint inventor (or for applications subject to pre-AIA 35 U.S.C. 112, the applicant), regards as the invention.
In claim 1, the phrase “controlling an actuator system of the vehicle based on the evaluation
by either causing the suggested trajectory to be implemented by the actuator system or preventing the suggested trajectory from being implemented by the actuator system” is unclear and confusing since it is not explained as to how the actuator system can prevent implementation and it is not clear as to how the actuator system is controlled to permit or prevent implementation of the suggested trajectory. The specification fails to provide a description of how to prevent the actuator system from implementing the suggested trajectory and there is not positively recited control step.
In claim 9, the phrase “control an actuator system of the vehicle based on the evaluation by
either causing the suggested trajectory to be implemented by the actuator system or preventing the suggested trajectory from being implemented by the actuator system” is unclear and confusing since it is not explained as to how the actuator system can prevent implementation and it is not clear as to how the actuator system is controlled to permit or prevent implementation of the suggested trajectory. The specification fails to provide a description of how to prevent the actuator system from implementing the suggested trajectory and there is not positively recited control step.
Claim Rejections - 35 USC § 103
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
The factual inquiries for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or nonobviousness.
Claims 1-6, 9-12, 14 and 16-20 are rejected under 35 U.S.C. 103 as being unpatentable over Ford (US20190250617A1) in view of Ditty (US20190258251A1) in view of Kazemi (US20190235499A1) and further in view of Censi (US20210356962A1).
Regarding amended claim 1, Ford discloses A computer-implemented method for
monitoring (see at least para. [0052] of Ford which discloses “The attributes of the trajectory selected by the local optimization are compared with the safety and comfort limits, at 255” and see at least para. [0056] of Ford which discloses “the trajectory planning system 10 determines that the trajectory 710 is both uncomfortable and unsafe (block 240 in FIG. 2)”, * and see at least para. [0065] of Ford which discloses “the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions/acts specified in the flowchart and/or block diagram block or blocks”) trajectories suggested by at least one planning module (see at least para. [0037] of Ford which discloses “the trajectory planner 10 receives the path and generates one or more trajectories corresponding to the path, and further determines one or more maneuvers to follow the trajectory. As used herein, a ‘maneuver’ is an operation that may be performed by the vehicle 50 via multiple different trajectories”) for an automated operating mode of a vehicle (Fig. 1, 50 and see at least para. [0022] of Ford which discloses “The vehicle 50 may be an autonomous vehicle or a semi-autonomous vehicle”), the method comprising the following steps: aggregating situation-specific information (see at least para. [0027] of Ford which discloses “A processor 16 processes the image data captured by the image capture device 12 and the sensed data captured by the sensing device 14. The processor 16 analyzes the respective data and identifies objects in the road of travel which the trajectory planning module must avoid for collision free maneuvers” and see at least para. [0032] of Ford which discloses “fuses the data into an object map for generating the host vehicle's path waypoints for a short distance ahead”, *This fusion of information concerning the vehicle’s surrounding lanes and objects corresponds to the claimed aggregation of situation-specific information”); generating a surroundings model based on the situation-specific information (see at least para. [0032] of Ford which discloses “The trajectory planning method uses lane data detected from the image capture device 12 and sensing device from the sensor-based device 14 and fuses the data into an object map for generating the host vehicle's path waypoints for a short distance ahead”, *The resulting object map corresponds to the claimed surrounding model, and producing that map from the detected lane and sensing data corresponds to generating the surroundings model based on the situation specific information); ascertaining a plurality of possible behaviors of the vehicle for a current traffic situation (see at least para. [0035] of Ford which discloses “the trajectory planner 10 generates a ranked list 217 of maneuvers, at 210. In one or more examples, the list of maneuvers 217 may be a predetermined list of maneuvers that the trajectory planner 10 can select a maneuver from. For example, the list 217 may include different lane change options, such as changing the lane in which the host vehicle 50 is traveling to a lane-0, or lane-1 etc. The list 217 further includes keeping the current lane” and see at least para. [0037] of Ford which discloses “a ‘maneuver’ is an operation that may be performed by the vehicle 50 via multiple different trajectories”, *The maneuvers correspond to possible behaviors), wherein each behavior of the possible behaviors represents a different possible response of the vehicle to the current traffic situation (see at least para. [0022] of Ford which discloses “The path planner 30 determines the route for the host vehicle 50 from a source location to a route destination taking into account factors such as historic road-speed, traffic conditions, weather forecasts etc. The route may be considered as a graph that includes multiple nodes and paths from one node to another node in the graph. The nodes represent a location along the route that is generated. There may be multiple paths between two such nodes and the path planner determines which of these paths to take to move the host vehicle between two such nodes. The path planner 30 provides path planning inputs to the trajectory planning system 10 based on the generated route and the determined path between nodes” and see at least para. [0048] of Ford which discloses “the trajectory planning system 10 improves the safety of the host vehicle 50 by taking the local environment into consideration when producing one or more trajectories in response to input from the path planner 30. Various other factors may be computed and included in the safety score”)
Ford may not explicitly disclose the plurality of possible behaviors of the vehicle for the
current traffic situation is based on the situation-specific information and the surroundings model and independently of any suggested trajectory.
However, Ditty discloses the plurality of possible behaviors of the vehicle for the current
traffic situation is based on the situation-specific information and the surroundings model (see at least para. [0654] of Ditty which discloses “The behavior planners 3004 determine feasibility of the basic behaviors such as staying in lane or changing lanes left or right, so that the feasible behaviors can be matched up with the most desired behavior from the lane planner 3004 c. If a lane change is not determined to be safe and available, the default behavior is to stay in lane. The main three behaviors tested by the basic behavior planner 3004 a is staying in lane and following any forks or choices in the lane graph to maximize the match with what the lane planner requested, or changing lane left or right and maximizing the match” and see at least para. [0655] of Ditty which discloses “The basic behavior planner 3004 a takes a tracked lane graph with wait conditions and in-path objects as input. The tracked lane graph can come either from mapping or live perception”, *Ditty teaches determining the feasibility of different vehicle behaviors using a tracked lane graph, wait conditions and in-path objects. The proposed modification to Ford would apply that scene-based assessment before trajectory generation without using a suggested trajectory as an input to the preliminary ascertainment) and independently of any suggested trajectory (see at least para. [0636] of Ditty which discloses “This has the benefit that it clearly separates the parameterization, the likelihood determination and prior definition, and the search/optimization approach. The lane changes are estimated in a second step after establishing the basic lane graph, by using statistics of lane changes in drives as well as the type of road markings and freespace detected in the drives”).
It would have been obvious to one of ordinary skill in the art before the effective filing date
of the claimed invention to modify the trajectories monitoring method of Ford to include the plurality of possible behaviors of the vehicle for the current traffic situation based on the situation-specific information and the surroundings model and independently of any suggested trajectory, as taught in Ditty with a reasonable expectation of success to provide ascertaining a plurality of possible behaviors of the vehicle for a current traffic situation based on the situation specific information and the surrounding model and independently of any suggested trajectory by applying Ditty’s scene based behavior feasibility assessment at Ford’s maneuver identification stage; such that lane keeping and lane change alternatives are assessed using the represented lanes applicable wait conditions and in path objects before generating a trajectory implementing a selected alterative. The purpose would have been to make Ford’s maneuver alternatives responsive to the current local traffic situation and to avoid unnecessary trajectory generation attempts for maneuvers determined to be unavailable from environmental information. This modification is consistent with Ford’s stated objective of reducing trajectory planning complexity and improving responsiveness to environmental changes. One of ordinary skill in the art would have been this modification with a reasonable expectation of success because Ford already processes lane and object information.
Ford, as modified by Ditty may not explicitly disclose a different possible response of the
vehicle to the current traffic situation and is described by a respective set of boundary conditions that collectively defines the different possible response.
However, Kazemi discloses the different possible response of the vehicle to the current
traffic situation and is described by a respective set of boundary conditions that collectively defines the different possible response (see at least para. [0028] of Kazemi which discloses “The first severity level (L0) can be associated with the highest level of severity of vehicle stoppage conditions including vehicle stoppage conditions in which the vehicle must come to an immediate stop (e.g., a hard stop using maximum braking force) without performing any additional maneuvers (e.g., changing lanes)” and see at least para. [0029] of Kazemi which discloses “The second severity level (L1) can be associated with a second highest level of severity for vehicle stoppage conditions including vehicle stoppage conditions in which the vehicle must come to a near immediate stop (e.g., stopping the vehicle when an emergency vehicle is in close proximity to the vehicle) without changing the trajectory of the vehicle (e.g., not rerouting the vehicle path, changing lane, or guiding the vehicle to a road shoulder)” and see at least para. [0030] of Kazemi which discloses “The third severity level (L2) can be associated with an intermediate level of severity for vehicle stoppage conditions. L2 can include vehicle stoppage conditions in which the vehicle does not have to come to an immediate or near-immediate stop and can travel to a nearby (e.g., within a specified distance range) location to stop within an intermediate time period (e.g., twenty seconds) or an intermediate distance (e.g., within fifty meters of the current location of the vehicle). Further, L2 can be associated with guiding a vehicle to a permissible location (e.g., a stopping location within a predetermined distance to which the vehicle can travel and stop without obstructing other vehicles) in a leftmost or rightmost lane relative to the vehicle's current location” and see at least para. [0032] of Kazemi which discloses “Determination of the severity level can be based on analysis of a set of conditions (e.g., one or more conditions in an environment proximate to the vehicle) that are subject to one or more constraints (e.g., whether a vehicle path is obstructed by one or more objects) that can be used to constrain a search space used to determine a vehicle path for inclusion in a motion plan. Further, the vehicle computing system can use one or more cost functions to determine various outputs including a minimum stopping distance for the vehicle”, *The respective requirements constrain the way each corresponding response is performed and are mapped to the claimed boundary conditions collectively defining that response. Also see at least para. [0204] of Kazemi which discloses “constraining the search space can include constraining the area (e.g., a radius around the vehicle or a set of locations that determine the boundary of the area) within which the vehicle will travel when the motion plan is executed”).
It would have been obvious to one of ordinary skill in the art before the effective filing date
of the claimed invention to further modify Ford, as modified by Ditty, to provide a different possible response of the vehicle to the current traffic situation and is described by a respective set of boundary conditions that collectively defines the different possible response; as taught in Kazemi’s technique of specifying different response categories through respective constraint sets. The reason would have been to provide explicit, checkable specifications governing the motion plans generated to implement the alternatives, rather than relying only on maneuver labels. Kazemi expressly uses its respective constraint sets to govern the generation of compliant motion plans. One of ordinary skill in the art would have made this modification with a reasonable expectation of success because Ford already distinguishes a maneuver from the multiple trajectories capable of implementing it, Ditty determines the feasibility of different maneuvers using lane and object information and Kazemi demonstrates generating vehicle motion plans subject to response associated constrain sets. The proposed modification would apply that constraint-based representation to the identified alternatives while retaining Ford’s distinction between a response level maneuver and its implementing trajectory.
Ford, as modified by Ditty and Kazemi, further discloses and prioritizing the possible
behaviors of the vehicle by arranging the possible behaviors in a list in an order of descending priority (see at least para. [0040]-[0041] of Ford which discloses “The trajectory planner 10 ranks the maneuvers in the list 217, with maneuvers for the received command from the path planner 30 ranked higher. For example, if the host vehicle 50 is traveling in a middle lane of a highway, and if the received command from the path planner 30 is to take an exit off the highway, the maneuver to change to the exit lane may be the first ranked maneuver on the list, followed by other maneuvers, such as changing to other lanes. It should be noted that in case of other commands, the ranking can be different … The method further includes selecting the highest ranked untried maneuver from the ranked list of maneuvers 217, at 215. Initially, each entry in the list 217 is marked as ‘untried’, for example using a flag or any other binary attribute associated with the entries in the list 217. Accordingly, the first time the ranked list 217 is accessed, the very first entry in the list 217 is selected as the highest ranked untried entry. As the method proceeds, the other entries in the list 217 are selected for analysis as described further”) based on the boundary conditions (see at least para. [0204] of Kazemi which discloses “constraining the search space can include constraining the area (e.g., a radius around the vehicle or a set of locations that determine the boundary of the area) within which the vehicle will travel when the motion plan is executed”) in conjunction with a predefined set of rules (see at least para. [0057] of Kazemi which discloses “The plurality of paths can then be ranked (e.g., arranged in an ascending or descending order according to the extent to which the one or more path criteria that are satisfied). In some embodiments, generating the motion plan (e.g., the motion plan that complies with the set of constraints associated with the severity level) can include determining a path of the plurality of paths that has the ranking that is highest (i.e., the highest ranking path of the plurality of paths). In some embodiments, the one or more adverse conditions can include a road with a direction of travel opposite to a direction of travel of the vehicle, an intersection (e.g., an area in which two or more roads intersect), a railroad crossing, a public transportation pick-up area (e.g., a bus stop), a blind curve (e.g., a curve around which there is no visibility or around which visibility is limited), a blind corner (e.g., a corner around which there is no visibility or around which visibility is limited), an on-ramp for a highway, and/or an off-ramp for a highway” and see at least para. [0186]-[0187] of Kazemi which discloses “At 1004, the method 1000 can include determining (e.g., determining based at least in part on the state data of the method 900) a highest ranked path of the plurality of paths based at least in part on one or more path criteria associated with one or more adverse conditions for the autonomous vehicle to avoid. For example, the vehicle computing system 112 can determine a ranking of the plurality of paths based at least in part on one or more path criteria associated with one or more adverse conditions for the vehicle to avoid … By way of further example, the vehicle computing system 112 can analyze (e.g., analyze based in part on the state data) each of the plurality of paths based in part on the one or more path criteria. Analyzing each of the plurality of paths can include determining which of the plurality of paths include the one or more adverse conditions and/or the extent to which each of the one or more adverse conditions is present in each of the plurality of paths. The plurality of paths can then be ranked (e.g., arranged in an ascending or descending order according to the extent to which the one or more path criteria that are satisfied” and see at least para. [0082] of Kazemi which discloses “Additionally, by leveraging a system that can use rules-based techniques and/or machine-learned models, the disclosed technology can better determine a safe and unobtrusive stopping location based on both environmental cues (e.g., the position of roads, road-shoulders, and other vehicles) and/or the state of the vehicle (e.g., an amount of fuel remaining and/or a vehicle door being opened in transit). For example, the disclosed technology can use dedicated computational resources (e.g., a custom designed processor) that can be used to stop the vehicle more efficiently and effectively than other more generalized approaches to stopping the vehicle”, *Kazemi discloses ranking alternative paths in ascending or descending order according to satisfaction of criteria associated with adverse conditions to avoid, based in part on vehicle/environment state data. Kazemi further discloses using rules-based techniques to determine a safe and unobtrusive stopping location based on environmental cues, including roads, shoulders and other vehicle state information. Therefore, Kazemi teaches criterion-based ordering and rules-based decision making responsive to environmental and vehicle conditions).
It would have been obvious to one of ordinary skill in the art before the effective filing date
of the claimed invention to further modify the maneuver ranking process of Ford, as modified by Ditty, to additionally account for the applicable response constraints and adverse condition criteria using Kazemi’s disclosed criterion based ranking and rules based decision techniques with a reasonable expectation of success. The purpose would have been to favor maneuver alternatives that provide safer and less obstructive vehicle responses under the current environmental and vehicle conditions, rather than rank alternatives solely according to correspondence with the navigation command. One of ordinary kill in the art before the effective filing date of the claimed invention would have made this modification with a reasonable expectation of success because Ford already maintains a ranked maneuver list and processes local lane and object information, while Kazemi expressly uses environmental and vehicle state information in constrained motion planning and criterion-based ordering.
Ford, as modified by Ditty and Kazemi as discussed above, provides the previously identified
vehicle behaviors, their applicable constraints and their priorities. Kazemi additionally teaches analyzing environmental conditions and using constraints to restrict a search space for determining a vehicle path (see at least para. [0032] of Kazemi which discloses “Determination of the severity level can be based on analysis of a set of conditions (e.g., one or more conditions in an environment proximate to the vehicle) that are subject to one or more constraints (e.g., whether a vehicle path is obstructed by one or more objects) that can be used to constrain a search space used to determine a vehicle path for inclusion in a motion plan. Further, the vehicle computing system can use one or more cost functions to determine various outputs including a minimum stopping distance for the vehicle”).
Ford, as modified by Ditty and Kazemi may not explicitly disclose wherein one or more
compatibility checks are carried out between a suggested trajectory and respective ones of the ascertained behaviors by checking whether the suggested trajectory satisfies the boundary conditions of each respective behavior, and the suggested trajectory is then evaluated based on the results of the compatibility checks and the priorities of the respective behaviors.
However, Censi discloses wherein one or more compatibility checks (see at least para.
[0170] of Censi which discloses “Implementations of the guideline processor may include a deviation analysis (322 in FIG. 3) determining a deviation metric (340 in FIG. 3) for a strategic guideline. In some cases, the deviation metric may be a function of one or more strategic factors associated with the condition or proper action or both of the strategic guideline. For example in FIG. 5, a basic principle expressed by a strategic guideline may state: avoid stress to a bicyclist 553 when an AV system 551 passes by the bicyclist. The strategic factor analysis 320 based on learning algorithms may infer that: the smaller the distance 555 (denoted mathematically as d), the higher the stress to the bicyclist 553. Thus, the deviation metric may be an inverse function of the distance: J=1/d. In other words, when the AV system 551 becomes too close to the bicyclist 553 (i.e., d is a small number), the basic principle associated with the strategic guideline of avoiding the stress to bicyclists may be deviated from or violated. The deviation metric J=1/d quantifies the degree of the deviation or violation. A threshold may be applied to the deviation metric to indicate that the basic principle associated with the strategic guideline is not considered to be deviated from or violated. In this example, if the distance d is determined to be at least 0.5 m for obeying the strategic guideline, the deviation metric may be set to 0 when d>0.5 m (i.e., the threshold for the deviation metric is J=1/0.5=2)”) are carried out between a suggested trajectory and respective ones of the ascertained behaviors by checking whether the suggested trajectory satisfies the boundary conditions of each respective behavior, and the suggested trajectory is then evaluated based on the results of the compatibility checks and the priorities of the respective behaviors (see at least para. [0163] of Censi which discloses “Implementations of the guideline processor 300 may include a strategic factor analysis (320 in FIG. 3), which characterizes strategic guidelines using one or more strategic factors (338 in FIG. 3), such as distances, speeds, accelerations, decelerations, orientations, times, temperatures, seasons, chemical concentrations, zones, heights, and weights, to name a few. Strategic factors can relate to basic principles, conditions, proper actions, priority levels, obeyance, violations, and deviations. The strategic factor analysis may be realized by machine learning algorithms. For example, the proper action “yield to a detected pedestrian” specified by a strategic guideline may be associated with one or more or all of the following strategic factors: a speed of the autonomous system, an orientation of the autonomous system, a height of the autonomous system, a deceleration of the autonomous system, a time to a stop, a buffer zone, a distance to another object (e.g., a moving vehicle, a parked vehicle, another pedestrian, a tree, a curb, a building, or an obstacle), or a distance to a pedestrian crossing, or combinations of them. FIG. 5 illustrates examples of distances and a buffer zone. The pedestrian crossing 510 may be assigned a buffer zone 520 characterized by distance strategic factors (e.g., 511, 512, 513, and 514) between the edges of the crossing and the buffer zone boundary. When an autonomous system (e.g., an AV system 501) approaches a pedestrian crossing 510, the autonomous system may consider the strategic factors to evaluate its proper actions”, *Censi teaches characterizing strategic guidelines using measurable strategic factors associated with proper actions. For example, the proper action of yielding to a detected pedestrian is associated with vehicle speed, deceleration, time to stop, distances to objects or a pedestrian crossing and a buffer zone defined by distance factors. Therefore, Censi teaches associating a proper vehicle action with quantitative and spatial requirements used to evaluate that action. Censi’s teaching concerning priority classification and deviation analysis additionally provide priority groups for strategic guidelines and metrics based on factors associated with guideline conditions or proper actions. These teachings support the proposed use of condition satisfaction results and priority information in trajectory evaluation, subject to identifying the planner disclosure that actually combines those inputs).
It would have been obvious to one of ordinary skill in the art before the effective filing date
of the claimed invention to further modify the method of Ford, as modified by Ditty and Kazemi to include wherein one or more compatibility checks are carried out between a suggested trajectory and respective ones of the ascertained behaviors by checking whether the suggested trajectory satisfies the boundary conditions of each respective behavior, and the suggested trajectory is then evaluated based on the results of the compatibility checks and the priorities of the respective behaviors; as taught in Censi with a reasonable expectation of success in order to check a suggested trajectory against the conditions defining the respective previously ascertained behaviors and use the resulting satisfaction determinations together with the corresponding behavior priorities to evaluate that trajectory. The reason for the modification would have been to distinguish trajectories according to whether they satisfy higher priority response requirements when applicable requirements compete, instead of evaluating constraint satisfaction without regard to the priority of the associated response. A person of ordinary skill would have reasonably expected this modification to success because the proposed system already represents behavior constraints and priorities, while Censi expressly teaches candidate trajectory planning that evaluates proper action compliance and priority, with deviation assessment extending over a trajectory. The proposed modification applies that evaluation technique to the previously established behavior condition sets and it does not replace those behaviors with candidate trajectories.
Ford, as modified by Ditty, Kazemi and Censi further discloses controlling an actuator
system of the vehicle based on the evaluation by either causing the suggested trajectory to be implemented by the actuator system (see at least para. [0050] of Ford which discloses “Executing the maneuver includes executing the one or more motion commands using the one or more actuators and other vehicle subsystems of the host vehicle 50 to move the host vehicle 50 according to the selected trajectory to perform the maneuver”, *This teaches controlling an actuator system of the vehicle to implement a selected trajectory. In the proposed combination, the suggested trajectory selected through the previously established compatibility and priority evaluation would be implemented using Ford’s disclosed motion commands and actuators. Therefore, the evaluation determines the trajectory to be executed, and Ford’s actuator control arrangement causes the vehicle to follow that trajectory, *Examiner interprets that since these limitations are cited in the alternative only 1 limitation is required, i.e., causing the suggested trajectory to be implemented by the actuator system).
It would have been obvious to one of ordinary skill in the art before the effective filing date
of the claimed invention to modify Ford, as modified by Ditty, Kazemi and Censi so that the suggested trajectory selected based on the previously established compatibility checks and behavior priorities is implemented through Ford’s disclosed motion commands and vehicle actuators with a reasonable expectation of success in order to make the vehicle’s executed motion reflect the applicable behavior constraints and priorities used in evaluating the trajectory, thereby giving effect to the evaluation in actual vehicle operation. A person of ordinary skill would have reasonably expected success because Ford already teaches executing motion commands through vehicle actuators to follow a selected trajectory. The proposed modification changes the basis for selecting the trajectory supplied to that execution stage while retaining the disclosed function of the motion commands and actuators.
Regarding amended claim 2, Ford, as modified by Ditty, Kazemi and Censi discloses
wherein the evaluation (see at least para. [0043] of Ford which discloses “the maneuver pattern is marked as tried, and a next maneuver pattern in the list 215 is evaluated”) of the suggested trajectory (see at least para. [0043] of Ford which discloses “Once a sufficiently comfortable trajectory has been found, a corresponding set of operations are determined for that trajectory”) is based on one or both of: (i) a highest priority among the checked behaviors whose boundary conditions are satisfied by the suggested trajectory, and (ii) a lowest priority among the checked behaviors whose boundary conditions are not satisfied by the suggested trajectory (see at least para. [0040]-[0041] of Ford which discloses “The trajectory planner 10 ranks the maneuvers in the list 217, with maneuvers for the received command from the path planner 30 ranked higher. For example, if the host vehicle 50 is traveling in a middle lane of a highway, and if the received command from the path planner 30 is to take an exit off the highway, the maneuver to change to the exit lane may be the first ranked maneuver on the list, followed by other maneuvers, such as changing to other lanes. It should be noted that in case of other commands, the ranking can be different … The method further includes selecting the highest ranked untried maneuver from the ranked list of maneuvers 217, at 215. Initially, each entry in the list 217 is marked as ‘untried’, for example using a flag or any other binary attribute associated with the entries in the list 217. Accordingly, the first time the ranked list 217 is accessed, the very first entry in the list 217 is selected as the highest ranked untried entry. As the method proceeds, the other entries in the list 217 are selected for analysis as described further”).
Regarding amended claim 3, Ford, as modified by Ditty, Kazemi and Censi discloses wherein
the compatibility checks (see at least para. [0059] of Ford which discloses “This facilitates the vehicle to produce trajectory updates much more quickly and to respond more rapidly to changes in its environment compared to typical solutions that analyze the full space of trajectories before executing the maneuver”) are carried out and an evaluation is assigned for each of multiple trajectories (see at least para. [0037] of Ford which discloses “the trajectory planner 10 receives the path and generates one or more trajectories corresponding to the path, and further determines one or more maneuvers to follow the trajectory. As used herein, a ‘maneuver’ is an operation that may be performed by the vehicle 50 via multiple different trajectories” and see at least para. [0012] of Censi which discloses “identifying candidate trajectories) suggested by one or more planning modules (see at least para. [0037] of Ford which discloses “the trajectory planner 10 receives the path and generates one or more trajectories corresponding to the path, and further determines one or more maneuvers to follow the trajectory. As used herein, a ‘maneuver’ is an operation that may be performed by the vehicle 50 via multiple different trajectories” and see Fig. 2, 225 of Censi and see at least para. [0144] of Censi which discloses “a motion planner 225 can quantitatively evaluate candidate trajectories (each of which corresponds to a sequence of motion actions) that it has under consideration and then select an optimal trajectory 227 from the candidates”), and the multiple trajectories are compared to one another based on results of the compatibility checks or the evaluations of the suggested trajectories, or both, in order to select a trajectory for implementation (see at least para. [0657] of Ditty which discloses “The advanced behavior planner 3004 b considers more free form forward trajectories than the basic behavior planner 3004 a. To do that, advanced behavior planner 3004 b takes the dynamic occupancy grid 3102 as input in addition to the input to the basic short-term planner 3004 a. The advanced behavior planner 3004 b then generates a fan of paths around the nominal path for the behavior in question, such as paths that are slightly laterally offset at the end with varying amounts of turning. In principle, any family of paths can be used, but a two or three-dimensional family of paths may a reasonable choice. The advanced behavior can also take object tracks into account. The paths are compared to the dynamic occupancy grid and is thereby checked for safety and what is desirable”) in the automated operating mode based on the comparison, and wherein the selected trajectory is caused to be implemented by the actuator system (see at least para. [0721] of Ditty which discloses “The processor in any of these ADAS implementations can itself include a CPU, and/or an ASIC. The supervisory MCU is further configured in preferred embodiments to control at least one actuator of the vehicle in accordance with the first signal if the outputs from the primary computer and the secondary computer are consistent”).
Regarding amended claim 4, Ford, as modified by Ditty, Kazemi and Censi discloses wherein
the results of the compatibility checks (Fig. 10, 1000 and see at least para. [0196] of Censi which discloses “a report generator 1000 to record motion data 1004 (e.g., trajectories, or decision making on trajectory selections, or motion actions, or motion factors, or combinations of them) of an autonomous system in a report 1010. The report generator 1000 may record the strategic guidelines or components of strategic guidelines 1002 (e.g., conditions, proper actions, strategic factors, or deviation metrics J, or combinations of them) guiding the decision of the trajectories and motion actions of the autonomous system”) or the evaluation of the suggested trajectory, or both, are cached or stored (see at least para. [0013] of Censi which further discloses “recording trajectories and motion actions, recording decisions on planning the motion actions for the machine, recording logical expressions used to plan the motion actions for the machine, recording deviation metrics of a motion action of the machine, detecting a risky event, generating an alert regarding the risky event, transmitting the report to a remote computing device, detecting a deviation away from a logical expression or away from a basic principle, determining a liability, integrating the report to the data associated with basic principles, or using the report to adjust processes”, This describes recording and storing the planning decisions in a report and a report generator 1000 recording trajectories, trajectory selection decisions and guideline components including deviation metrics in report 1010 is described. Therefore, Censi teaches retaining evaluation related results in a recorded report).
It would have been obvious to one of ordinary skill in the art before the effective filing date
of the claimed invention to apply Censi’s reporting technique to store the compatibility check results or trajectory evaluation produced by the previously established combination with a reasonable expectation of success in order to preserve the basis for trajectory selection decisions for subsequent review and analysis.
Regarding amended claim 5, Ford, as modified by Ditty, Kazemi and Censi discloses wherein
the results of the compatibility checks or the evaluation of the suggested trajectory, or both, are made available to the planning module that suggested the trajectory (Fig. 10, 1000 and see at least para. [0196] of Censi which discloses “a report generator 1000 to record motion data 1004 (e.g., trajectories, or decision making on trajectory selections, or motion actions, or motion factors, or combinations of them) of an autonomous system in a report 1010. The report generator 1000 may record the strategic guidelines or components of strategic guidelines 1002 (e.g., conditions, proper actions, strategic factors, or deviation metrics J, or combinations of them) guiding the decision of the trajectories and motion actions of the autonomous system” and see at least para. [0013] of Censi which further discloses “recording trajectories and motion actions, recording decisions on planning the motion actions for the machine, recording logical expressions used to plan the motion actions for the machine, recording deviation metrics of a motion action of the machine, detecting a risky event, generating an alert regarding the risky event, transmitting the report to a remote computing device, detecting a deviation away from a logical expression or away from a basic principle, determining a liability, integrating the report to the data associated with basic principles, or using the report to adjust processes”, This describes recording and storing the planning decisions in a report and a report generator 1000 recording trajectories, trajectory selection decisions and guideline components including deviation metrics in report 1010 is described. Therefore, Censi teaches retaining evaluation related results in a recorded report).
Regarding amended claim 6, Ford, as modified by Ditty, Kazemi and Censi discloses wherein
the results of the compatibility checks or the evaluation of the suggested trajectory, or both, are used to determine whether a critical situation exists (see at least para. [0104] of Censi which discloses “One or more data sources 142 for providing historical, or real-time, or predictive information, or combinations of them about the environment 190, including, in the case of a vehicle, for example, maps, driving performance, motion performance, traffic congestion updates or weather conditions. Such data may be stored on a data storage unit 142 or memory 144 on the machine 100, or may be transmitted to the machine 100 via a communications channel from a remote database 134 or a combination of them. 8. One or more data sources 136 for providing map data; e.g., digital road map data; geographic information system databases; maps of flight paths; maps of navigational channels; maps of the roadway geometric properties; maps describing road network connectivity properties; maps describing properties (such as traffic speed, traffic volume, the number of vehicular and cyclist traffic lanes, lane width, lane traffic directions, or lane marker types and locations, or combinations of them) of roads, flight paths, or navigational channels; and maps describing the spatial locations of road or navigational channel features such as, in the case of road vehicles, crosswalks, traffic signs or other travel signals of various”).
Regarding amended claim 9, Ford discloses A computer-implemented system for
monitoring (see at least para. [0052] of Ford which discloses “The attributes of the trajectory selected by the local optimization are compared with the safety and comfort limits, at 255” and see at least para. [0056] of Ford which discloses “the trajectory planning system 10 determines that the trajectory 710 is both uncomfortable and unsafe (block 240 in FIG. 2)”, * and see at least para. [0065] of Ford which discloses “the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions/acts specified in the flowchart and/or block diagram block or blocks”) trajectories suggested by at least one planning module (see at least para. [0037] of Ford which discloses “the trajectory planner 10 receives the path and generates one or more trajectories corresponding to the path, and further determines one or more maneuvers to follow the trajectory. As used herein, a ‘maneuver’ is an operation that may be performed by the vehicle 50 via multiple different trajectories”) for an automated operating mode of a vehicle (Fig. 1, 50 and see at least para. [0022] of Ford which discloses “The vehicle 50 may be an autonomous vehicle or a semi-autonomous vehicle”), the system comprising: a perception layer (see at least para. [0032] of Ford which discloses “the sensor-based device 14 and fuses the data into an object map for generating the host vehicle's path waypoints”) configured to aggregate situation-specific information see at least para. [0027] of Ford which discloses “A processor 16 processes the image data captured by the image capture device 12 and the sensed data captured by the sensing device 14. The processor 16 analyzes the respective data and identifies objects in the road of travel which the trajectory planning module must avoid for collision free maneuvers” and see at least para. [0032] of Ford which discloses “fuses the data into an object map for generating the host vehicle's path waypoints for a short distance ahead”, *This fusion of information concerning the vehicle’s surrounding lanes and objects corresponds to the claimed aggregation of situation-specific information”) from vehicle- internal and vehicle-external information sources; a model-generation module configured to generate a surroundings model based on the situation-specific information (see at least para. [0032] of Ford which discloses “The trajectory planning method uses lane data detected from the image capture device 12 and sensing device from the sensor-based device 14 and fuses the data into an object map for generating the host vehicle's path waypoints for a short distance ahead”, *The resulting object map corresponds to the claimed surrounding model, and producing that map from the detected lane and sensing data corresponds to generating the surroundings model based on the situation specific information); an analysis module configured to ascertain a plurality of possible behaviors of the vehicle for a current traffic situation (see at least para. [0035] of Ford which discloses “the trajectory planner 10 generates a ranked list 217 of maneuvers, at 210. In one or more examples, the list of maneuvers 217 may be a predetermined list of maneuvers that the trajectory planner 10 can select a maneuver from. For example, the list 217 may include different lane change options, such as changing the lane in which the host vehicle 50 is traveling to a lane-0, or lane-1 etc. The list 217 further includes keeping the current lane” and see at least para. [0037] of Ford which discloses “a ‘maneuver’ is an operation that may be performed by the vehicle 50 via multiple different trajectories”, *The maneuvers correspond to possible behaviors) wherein each behavior of the possible behaviors represents a different possible response of the vehicle to the current traffic situation (see at least para. [0022] of Ford which discloses “The path planner 30 determines the route for the host vehicle 50 from a source location to a route destination taking into account factors such as historic road-speed, traffic conditions, weather forecasts etc. The route may be considered as a graph that includes multiple nodes and paths from one node to another node in the graph. The nodes represent a location along the route that is generated. There may be multiple paths between two such nodes and the path planner determines which of these paths to take to move the host vehicle between two such nodes. The path planner 30 provides path planning inputs to the trajectory planning system 10 based on the generated route and the determined path between nodes” and see at least para. [0048] of Ford which discloses “the trajectory planning system 10 improves the safety of the host vehicle 50 by taking the local environment into consideration when producing one or more trajectories in response to input from the path planner 30. Various other factors may be computed and included in the safety score”)
Ford may not explicitly disclose the plurality of possible behaviors of the vehicle for the
current traffic situation is based on the situation-specific information and the surroundings model and independently of any suggested trajectory.
However, Ditty discloses the plurality of possible behaviors of the vehicle for the current
traffic situation is based on the situation-specific information and the surroundings model (see at least para. [0654] of Ditty which discloses “The behavior planners 3004 determine feasibility of the basic behaviors such as staying in lane or changing lanes left or right, so that the feasible behaviors can be matched up with the most desired behavior from the lane planner 3004 c. If a lane change is not determined to be safe and available, the default behavior is to stay in lane. The main three behaviors tested by the basic behavior planner 3004 a is staying in lane and following any forks or choices in the lane graph to maximize the match with what the lane planner requested, or changing lane left or right and maximizing the match” and see at least para. [0655] of Ditty which discloses “The basic behavior planner 3004 a takes a tracked lane graph with wait conditions and in-path objects as input. The tracked lane graph can come either from mapping or live perception”, *Ditty teaches determining the feasibility of different vehicle behaviors using a tracked lane graph, wait conditions and in-path objects. The proposed modification to Ford would apply that scene-based assessment before trajectory generation without using a suggested trajectory as an input to the preliminary ascertainment) and independently of any suggested trajectory (see at least para. [0636] of Ditty which discloses “This has the benefit that it clearly separates the parameterization, the likelihood determination and prior definition, and the search/optimization approach. The lane changes are estimated in a second step after establishing the basic lane graph, by using statistics of lane changes in drives as well as the type of road markings and freespace detected in the drives”).
It would have been obvious to one of ordinary skill in the art before the effective filing date
of the claimed invention to modify the trajectories monitoring method of Ford to include the plurality of possible behaviors of the vehicle for the current traffic situation based on the situation-specific information and the surroundings model and independently of any suggested trajectory, as taught in Ditty with a reasonable expectation of success to provide ascertaining a plurality of possible behaviors of the vehicle for a current traffic situation based on the situation specific information and the surrounding model and independently of any suggested trajectory by applying Ditty’s scene based behavior feasibility assessment at Ford’s maneuver identification stage; such that lane keeping and lane change alternatives are assessed using the represented lanes applicable wait conditions and in path objects before generating a trajectory implementing a selected alterative. The purpose would have been to make Ford’s maneuver alternatives responsive to the current local traffic situation and to avoid unnecessary trajectory generation attempts for maneuvers determined to be unavailable from environmental information. This modification is consistent with Ford’s stated objective of reducing trajectory planning complexity and improving responsiveness to environmental changes. One of ordinary skill in the art would have been this modification with a reasonable expectation of success because Ford already processes lane and object information.
Ford, as modified by Ditty may not explicitly disclose a different possible response of the
vehicle to the current traffic situation and is described by a respective set of boundary conditions that collectively defines the different possible response.
However, Kazemi discloses the different possible response of the vehicle to the current
traffic situation and is described by a respective set of boundary conditions that collectively defines the different possible response (see at least para. [0028] of Kazemi which discloses “The first severity level (L0) can be associated with the highest level of severity of vehicle stoppage conditions including vehicle stoppage conditions in which the vehicle must come to an immediate stop (e.g., a hard stop using maximum braking force) without performing any additional maneuvers (e.g., changing lanes)” and see at least para. [0029] of Kazemi which discloses “The second severity level (L1) can be associated with a second highest level of severity for vehicle stoppage conditions including vehicle stoppage conditions in which the vehicle must come to a near immediate stop (e.g., stopping the vehicle when an emergency vehicle is in close proximity to the vehicle) without changing the trajectory of the vehicle (e.g., not rerouting the vehicle path, changing lane, or guiding the vehicle to a road shoulder)” and see at least para. [0030] of Kazemi which discloses “The third severity level (L2) can be associated with an intermediate level of severity for vehicle stoppage conditions. L2 can include vehicle stoppage conditions in which the vehicle does not have to come to an immediate or near-immediate stop and can travel to a nearby (e.g., within a specified distance range) location to stop within an intermediate time period (e.g., twenty seconds) or an intermediate distance (e.g., within fifty meters of the current location of the vehicle). Further, L2 can be associated with guiding a vehicle to a permissible location (e.g., a stopping location within a predetermined distance to which the vehicle can travel and stop without obstructing other vehicles) in a leftmost or rightmost lane relative to the vehicle's current location” and see at least para. [0032] of Kazemi which discloses “Determination of the severity level can be based on analysis of a set of conditions (e.g., one or more conditions in an environment proximate to the vehicle) that are subject to one or more constraints (e.g., whether a vehicle path is obstructed by one or more objects) that can be used to constrain a search space used to determine a vehicle path for inclusion in a motion plan. Further, the vehicle computing system can use one or more cost functions to determine various outputs including a minimum stopping distance for the vehicle”, *The respective requirements constrain the way each corresponding response is performed and are mapped to the claimed boundary conditions collectively defining that response. Also see at least para. [0204] of Kazemi which discloses “constraining the search space can include constraining the area (e.g., a radius around the vehicle or a set of locations that determine the boundary of the area) within which the vehicle will travel when the motion plan is executed”).
It would have been obvious to one of ordinary skill in the art before the effective filing date
of the claimed invention to further modify Ford, as modified by Ditty, to provide a different possible response of the vehicle to the current traffic situation and is described by a respective set of boundary conditions that collectively defines the different possible response; as taught in Kazemi’s technique of specifying different response categories through respective constraint sets. The reason would have been to provide explicit, checkable specifications governing the motion plans generated to implement the alternatives, rather than relying only on maneuver labels. Kazemi expressly uses its respective constraint sets to govern the generation of compliant motion plans. One of ordinary skill in the art would have made this modification with a reasonable expectation of success because Ford already distinguishes a maneuver from the multiple trajectories capable of implementing it, Ditty determines the feasibility of different maneuvers using lane and object information and Kazemi demonstrates generating vehicle motion plans subject to response associated constrain sets. The proposed modification would apply that constraint-based representation to the identified alternatives while retaining Ford’s distinction between a response level maneuver and its implementing trajectory.
Ford, as modified by Ditty and Kazemi, further discloses a predefined set of rules (see at
least para. [0057] of Kazemi which discloses “The plurality of paths can then be ranked (e.g., arranged in an ascending or descending order according to the extent to which the one or more path criteria that are satisfied). In some embodiments, generating the motion plan (e.g., the motion plan that complies with the set of constraints associated with the severity level) can include determining a path of the plurality of paths that has the ranking that is highest (i.e., the highest ranking path of the plurality of paths). In some embodiments, the one or more adverse conditions can include a road with a direction of travel opposite to a direction of travel of the vehicle, an intersection (e.g., an area in which two or more roads intersect), a railroad crossing, a public transportation pick-up area (e.g., a bus stop), a blind curve (e.g., a curve around which there is no visibility or around which visibility is limited), a blind corner (e.g., a corner around which there is no visibility or around which visibility is limited), an on-ramp for a highway, and/or an off-ramp for a highway” and see at least para. [0186]-[0187] of Kazemi which discloses “At 1004, the method 1000 can include determining (e.g., determining based at least in part on the state data of the method 900) a highest ranked path of the plurality of paths based at least in part on one or more path criteria associated with one or more adverse conditions for the autonomous vehicle to avoid. For example, the vehicle computing system 112 can determine a ranking of the plurality of paths based at least in part on one or more path criteria associated with one or more adverse conditions for the vehicle to avoid … By way of further example, the vehicle computing system 112 can analyze (e.g., analyze based in part on the state data) each of the plurality of paths based in part on the one or more path criteria. Analyzing each of the plurality of paths can include determining which of the plurality of paths include the one or more adverse conditions and/or the extent to which each of the one or more adverse conditions is present in each of the plurality of paths. The plurality of paths can then be ranked (e.g., arranged in an ascending or descending order according to the extent to which the one or more path criteria that are satisfied” and see at least para. [0082] of Kazemi which discloses “Additionally, by leveraging a system that can use rules-based techniques and/or machine-learned models, the disclosed technology can better determine a safe and unobtrusive stopping location based on both environmental cues (e.g., the position of roads, road-shoulders, and other vehicles) and/or the state of the vehicle (e.g., an amount of fuel remaining and/or a vehicle door being opened in transit). For example, the disclosed technology can use dedicated computational resources (e.g., a custom designed processor) that can be used to stop the vehicle more efficiently and effectively than other more generalized approaches to stopping the vehicle”, *Kazemi discloses ranking alternative paths in ascending or descending order according to satisfaction of criteria associated with adverse conditions to avoid, based in part on vehicle/environment state data. Kazemi further discloses using rules-based techniques to determine a safe and unobtrusive stopping location based on environmental cues, including roads, shoulders and other vehicle state information. Therefore, Kazemi teaches criterion-based ordering and rules-based decision making responsive to environmental and vehicle conditions) for evaluating (see at least para. [0043] of Ford which discloses “the maneuver pattern is marked as tried, and a next maneuver pattern in the list 215 is evaluated”) and prioritizing the possible behaviors by arranging the possible behaviors in a list in an order of descending priority (see at least para. [0040]-[0041] of Ford which discloses “The trajectory planner 10 ranks the maneuvers in the list 217, with maneuvers for the received command from the path planner 30 ranked higher. For example, if the host vehicle 50 is traveling in a middle lane of a highway, and if the received command from the path planner 30 is to take an exit off the highway, the maneuver to change to the exit lane may be the first ranked maneuver on the list, followed by other maneuvers, such as changing to other lanes. It should be noted that in case of other commands, the ranking can be different … The method further includes selecting the highest ranked untried maneuver from the ranked list of maneuvers 217, at 215. Initially, each entry in the list 217 is marked as ‘untried’, for example using a flag or any other binary attribute associated with the entries in the list 217. Accordingly, the first time the ranked list 217 is accessed, the very first entry in the list 217 is selected as the highest ranked untried entry. As the method proceeds, the other entries in the list 217 are selected for analysis as described further”) based on their respective boundary conditions (see at least para. [0204] of Kazemi which discloses “constraining the search space can include constraining the area (e.g., a radius around the vehicle or a set of locations that determine the boundary of the area) within which the vehicle will travel when the motion plan is executed”).
It would have been obvious to one of ordinary skill in the art before the effective filing date
of the claimed invention to further modify the maneuver ranking process of Ford, as modified by Ditty, to additionally account for the applicable response constraints and adverse condition criteria using Kazemi’s disclosed criterion based ranking and rules based decision techniques with a reasonable expectation of success. The purpose would have been to favor maneuver alternatives that provide safer and less obstructive vehicle responses under the current environmental and vehicle conditions, rather than rank alternatives solely according to correspondence with the navigation command. One of ordinary kill in the art before the effective filing date of the claimed invention would have made this modification with a reasonable expectation of success because Ford already maintains a ranked maneuver list and processes local lane and object information, while Kazemi expressly uses environmental and vehicle state information in constrained motion planning and criterion based ordering.
Ford, as modified by Ditty and Kazemi as discussed above, provides the previously identified
vehicle behaviors, their applicable constraints and their priorities. Kazemi additionally teaches analyzing environmental conditions and using constraints to restrict a search space for determining a vehicle path (see at least para. [0032] of Kazemi which discloses “Determination of the severity level can be based on analysis of a set of conditions (e.g., one or more conditions in an environment proximate to the vehicle) that are subject to one or more constraints (e.g., whether a vehicle path is obstructed by one or more objects) that can be used to constrain a search space used to determine a vehicle path for inclusion in a motion plan. Further, the vehicle computing system can use one or more cost functions to determine various outputs including a minimum stopping distance for the vehicle”).
Ford, as modified by Ditty and Kazemi may not explicitly disclose an evaluation module for
the suggested trajectories, which is configured to: carry out one or more compatibility checks between a suggested trajectory and respective ones of the ascertained behaviors by checking whether the suggested trajectory satisfies the boundary conditions of each respective behavior; and after the carrying out of the compatibility checks, evaluate the suggested trajectory based on the results of the compatibility checks and the priorities of the respective behaviors;
However, Censi discloses an evaluation module (Fig. 3, 320 and see at least para. [0169] of
Censi which discloses “the strategic factor analysis (320 in FIG. 3) may use real data or simulated data or both types of data (e.g., map 304 and sensor data 306) to determine strategic factors and relevant values of the strategic factors. Some real data is collected by operating autonomous systems in real environments. Some simulations may be computationally derived from hypothetical environments for operating the autonomous systems, e.g., road configurations, air space scenarios, navigation paths, traffic speeds, traffic volumes, traffic lights, traffic signs, objects, and weather conditions. The use of the data may include statistically evaluating the strategic guidelines, such as frequency of invoking strategic guidelines, prioritization relations, and values of strategic factors. The statistical evaluation may be fed back to the guideline processor to adjust the strategic guidelines. The feedback adjustment and the guideline processing, which may be performed iteratively, will cause the strategic guidelines to converge to a steady state”) for the suggested trajectories, which is configured to: carry out one or more compatibility checks (see at least para. [0170] of Censi which discloses “Implementations of the guideline processor may include a deviation analysis (322 in FIG. 3) determining a deviation metric (340 in FIG. 3) for a strategic guideline. In some cases, the deviation metric may be a function of one or more strategic factors associated with the condition or proper action or both of the strategic guideline. For example in FIG. 5, a basic principle expressed by a strategic guideline may state: avoid stress to a bicyclist 553 when an AV system 551 passes by the bicyclist. The strategic factor analysis 320 based on learning algorithms may infer that: the smaller the distance 555 (denoted mathematically as d), the higher the stress to the bicyclist 553. Thus, the deviation metric may be an inverse function of the distance: J=1/d. In other words, when the AV system 551 becomes too close to the bicyclist 553 (i.e., d is a small number), the basic principle associated with the strategic guideline of avoiding the stress to bicyclists may be deviated from or violated. The deviation metric J=1/d quantifies the degree of the deviation or violation. A threshold may be applied to the deviation metric to indicate that the basic principle associated with the strategic guideline is not considered to be deviated from or violated. In this example, if the distance d is determined to be at least 0.5 m for obeying the strategic guideline, the deviation metric may be set to 0 when d>0.5 m (i.e., the threshold for the deviation metric is J=1/0.5=2)”) between a suggested trajectory and respective ones of the ascertained behaviors by checking whether the suggested trajectory satisfies the boundary conditions of each respective behavior and after the carrying out of the compatibility checks, evaluate the suggested trajectory based on the results of the compatibility checks and the priorities of the respective behaviors (see at least para. [0163] of Censi which discloses “Implementations of the guideline processor 300 may include a strategic factor analysis (320 in FIG. 3), which characterizes strategic guidelines using one or more strategic factors (338 in FIG. 3), such as distances, speeds, accelerations, decelerations, orientations, times, temperatures, seasons, chemical concentrations, zones, heights, and weights, to name a few. Strategic factors can relate to basic principles, conditions, proper actions, priority levels, obeyance, violations, and deviations. The strategic factor analysis may be realized by machine learning algorithms. For example, the proper action “yield to a detected pedestrian” specified by a strategic guideline may be associated with one or more or all of the following strategic factors: a speed of the autonomous system, an orientation of the autonomous system, a height of the autonomous system, a deceleration of the autonomous system, a time to a stop, a buffer zone, a distance to another object (e.g., a moving vehicle, a parked vehicle, another pedestrian, a tree, a curb, a building, or an obstacle), or a distance to a pedestrian crossing, or combinations of them. FIG. 5 illustrates examples of distances and a buffer zone. The pedestrian crossing 510 may be assigned a buffer zone 520 characterized by distance strategic factors (e.g., 511, 512, 513, and 514) between the edges of the crossing and the buffer zone boundary. When an autonomous system (e.g., an AV system 501) approaches a pedestrian crossing 510, the autonomous system may consider the strategic factors to evaluate its proper actions”, *Censi teaches characterizing strategic guidelines using measurable strategic factors associated with proper actions and checks the validity of the proposed trajectory. For example, the proper action of yielding to a detected pedestrian is associated with vehicle speed, deceleration, time to stop, distances to objects or a pedestrian crossing and a buffer zone defined by distance factors. Therefore, Censi teaches associating a proper vehicle action with quantitative and spatial requirements used to evaluate that action. Censi’s teaching concerning priority classification and deviation analysis additionally provide priority groups for strategic guidelines and metrics based on factors associated with guideline conditions or proper actions. These teachings support the proposed use of condition satisfaction results and priority information in trajectory evaluation, subject to identifying the planner disclosure that actually combines those inputs).
It would have been obvious to one of ordinary skill in the art before the effective filing date
of the claimed invention to further modify the method of Ford, as modified by Ditty and Kazemi to include carrying out one or more compatibility checks between a suggested trajectory and respective ones of the ascertained behaviors by checking whether the suggested trajectory satisfies the boundary conditions of each respective behavior; and after the carrying out of the compatibility checks, evaluate the suggested trajectory based on the results of the compatibility checks and the priorities of the respective behaviors; as taught in Censi with a reasonable expectation of success in order to check a suggested trajectory against the conditions defining the respective previously ascertained behaviors and use the resulting satisfaction determinations together with the corresponding behavior priorities to evaluate that trajectory. The reason for the modification would have been to distinguish trajectories according to whether they satisfy higher priority response requirements when applicable requirements compete, instead of evaluating constraint satisfaction without regard to the priority of the associated response. A person of ordinary skill would have reasonably expected this modification to success because the proposed system already represents behavior constraints and priorities, while Censi expressly teaches candidate trajectory planning that evaluates proper action compliance and priority, with deviation assessment extending over a trajectory. The proposed modification applies that evaluation technique to the previously established behavior condition sets and it does not replace those behaviors with candidate trajectories.
Ford, as modified by Ditty, Kazemi and Censi further discloses a control module (see at least
para. [0306] of Ditty which discloses “control modules), and send command signals to vehicle actuators including but not limited to braking actuators, steering actuators, engine throttle actuator, other engine control actuators, transmission control actuators and other types of vehicle actuators”) configured to control an actuator system of the vehicle based on the evaluation by either causing the suggested trajectory to be implemented by the actuator system (see at least para. [0050] of Ford which discloses “Executing the maneuver includes executing the one or more motion commands using the one or more actuators and other vehicle subsystems of the host vehicle 50 to move the host vehicle 50 according to the selected trajectory to perform the maneuver”, *This teaches controlling an actuator system of the vehicle to implement a selected trajectory. In the proposed combination, the suggested trajectory selected through the previously established compatibility and priority evaluation would be implemented using Ford’s disclosed motion commands and actuators. Therefore, the evaluation determines the trajectory to be executed and Ford’s actuator control arrangement causes the vehicle to follow that trajectory, *Examiner interprets that since these limitations are cited in the alternative only 1 limitation is required, i.e., causing the suggested trajectory to be implemented by the actuator system).
It would have been obvious to one of ordinary skill in the art before the effective filing date
of the claimed invention to modify Ford, as modified by Ditty, Kazemi and Censi so that the suggested trajectory selected based on the previously established compatibility checks and behavior priorities is implemented through Ford’s disclosed motion commands and vehicle actuators with a reasonable expectation of success in order to make the vehicle’s executed motion reflect the applicable behavior constraints and priorities used in evaluating the trajectory, thereby giving effect to the evaluation in actual vehicle operation. A person of ordinary skill would have reasonably expected success because Ford already teaches executing motion commands through vehicle actuators to follow a selected trajectory. The proposed modification changes the basis for selecting the trajectory supplied to that execution stage while retaining the disclosed function of the motion commands and actuators.
Regarding amended claim 10, Ford, as modified by Ditty, Kazemi and Censi discloses
wherein the evaluation module is configured to evaluate multiple trajectories (see at least para. [0037] of Ford which discloses “ multiple different trajectories”) suggested by one or more planning modules in parallel and compare the results of the compatibility checks or the evaluations of the suggested trajectories, or both, with one another (see at least para. [0022] of Ford which discloses “There may be multiple paths between two such nodes and the path planner determines which of these paths to take to move the host vehicle between two such nodes. The path planner 30 provides path planning inputs to the trajectory planning system 10 based on the generated route and the determined path between nodes” and see at least para. [0180] of Censi which discloses “The samples that are in the non-drivable regions 811-818 or blocked by an object (e.g., the vehicle 820) are then removed; e.g., the sampling points 832 and 833 will be removed and the point 831 will remain. Referring to FIG. 8C, based on the remaining sampling points, the trajectory may identify multiple candidate trajectories (e.g., 850, 860 and 870)”).
Regarding amended claim 11, Ford, as modified by Ditty, Kazemi and Censi discloses
wherein the evaluation module is configured to make the results of the compatibility checks or the evaluation of the suggested trajectory, or both, available via at least one interface to one or both of the control module and the planning module that suggested the trajectory (see at least para. [0169] of Censi which discloses “the strategic factor analysis (320 in FIG. 3) may use real data or simulated data or both types of data (e.g., map 304 and sensor data 306) to determine strategic factors and relevant values of the strategic factors. Some real data is collected by operating autonomous systems in real environments. Some simulations may be computationally derived from hypothetical environments for operating the autonomous systems, e.g., road configurations, air space scenarios, navigation paths, traffic speeds, traffic volumes, traffic lights, traffic signs, objects, and weather conditions. The use of the data may include statistically evaluating the strategic guidelines, such as frequency of invoking strategic guidelines, prioritization relations, and values of strategic factors. The statistical evaluation may be fed back to the guideline processor to adjust the strategic guidelines” and see at least para. [0200] of Censi which discloses “Implementations of the report generator may feed the report back to the guideline processor, see 221 in FIG. 2. For example, the report may be treated as past experiences 205, and may include information of sensor data 207 or motion environment 209 or both. Thus, the guideline processor may extract new information from the report to adjust algorithms (e.g., natural language analysis 334, sensor data analysis 316, priority classifier 318, strategic factor analysis 320, deviation analysis 322, or machine instructions translator 324, or combinations of them) in the guideline processor to achieve a better motion planning system”).
Regarding amended claim 12, Ford, as modified by Ditty, Kazemi and Censi discloses further
comprising: at least one memory module (see at least para. [0061] of Ford which discloses “A non-exhaustive list of more specific examples of the computer readable storage medium includes the following: a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), a static random access memory (SRAM), a portable compact disc read-only memory (CD-ROM), a digital versatile disk (DVD), a memory stick, a floppy disk, and any suitable combination of the foregoing” and see at least para. [0104] of Censi which discloses “Data storage units 142 or memory 144 or both for storing machine instructions”) for storing selected trajectories (see at least para. [0012] of Censi which discloses “identifying candidate trajectories, specifying sequences of the motion actions along a trajectory, evaluating a priority level of a motion action of the machine, evaluating a motion action of the machine complying with a proper action of a logical expression, or evaluating a deviation metric of a motion action of the machine deviating from a proper action of a logical expression” and see at least para. [0197] of Censi which discloses “the autonomous system may execute a motion action not following strategic guidelines 1002, and such scenarios may be inferred by deviation metrics”, *This corresponds to monitoring trajectories because Censi teaches a system that monitors for deviations/risky actions including predicted risky events) together with the associated results of the compatibility checks or the associated evaluations, or both (see at least para. [0657] of Ditty which discloses “The advanced behavior planner 3004 b considers more free form forward trajectories than the basic behavior planner 3004 a. To do that, advanced behavior planner 3004 b takes the dynamic occupancy grid 3102 as input in addition to the input to the basic short-term planner 3004 a. The advanced behavior planner 3004 b then generates a fan of paths around the nominal path for the behavior in question, such as paths that are slightly laterally offset at the end with varying amounts of turning. In principle, any family of paths can be used, but a two or three-dimensional family of paths may a reasonable choice. The advanced behavior can also take object tracks into account. The paths are compared to the dynamic occupancy grid and is thereby checked for safety and what is desirable” and see at least para. [0170] of Censi which discloses “Implementations of the guideline processor may include a deviation analysis (322 in FIG. 3) determining a deviation metric (340 in FIG. 3) for a strategic guideline. In some cases, the deviation metric may be a function of one or more strategic factors associated with the condition or proper action or both of the strategic guideline”).
Regarding newly added claim 14, Ford, as modified by Ditty, Kazemi and Censi discloses
wherein: the model-generation module is configured to generate a zone graph (see at least para. [0022] of Ford which discloses “The route may be considered as a graph that includes multiple nodes and paths from one node to another node in the graph. The nodes represent a location along the route that is generated. There may be multiple paths between two such nodes and the path planner determines which of these paths to take to move the host vehicle between two such nodes. The path planner 30 provides path planning inputs to the trajectory planning system 10 based on the generated route and the determined path between nodes. In one or more examples, the path planner 30 determines the route for the host vehicle 50 at the beginning of a trip, for example when a user inputs a destination (and a source), the route providing navigation guidance for the host vehicle 50 to reach the destination“) that abstracts the current traffic situation by representing a real road situation using an abstract traffic infrastructure element corresponding to static road geometry and having a plurality of zones relevant to realization of a driving intention of the vehicle (see at least para. [0022] of Ford which discloses “a trajectory planning system 10 for a vehicle 50. The vehicle 50 may be an autonomous vehicle or a semi-autonomous vehicle. The vehicle 50 (hereinafter referred to as the host vehicle) includes a vehicle-based image capture device 12 and at least one sensing-based device 14. It should be noted that in one or more examples, the trajectory planning described herein may be performed without image capture devices. FIG. 1 further depicts a path planner 30, which generates a path or route for the host vehicle 50. The path planner 30 determines the route for the host vehicle 50 from a source location to a route destination taking into account factors such as historic road-speed, traffic conditions, weather forecasts etc.”), the plurality of zones being unspecified as to both size and position before application of data of situation-specific parameters; and the analysis module is configured to use the zone graph to morphologically analyze (see at least para. [0039] of Ford which discloses “The determined path is received by the trajectory planner 10. The path planner 30 determines the path using one or more route determining algorithms, for example using a graph-based approach that includes using path determining algorithms such as Bellman-Ford, Djikstra, and the like. In one or more examples, the path is split into one or more commands that are provided to the trajectory planner 10 as the path planning inputs”) possible developments or behaviors of road users to determine the respective sets of boundary conditions (see at least para. [0529] of Ditty which discloses “there is also a left and right lane boundary with each edge in the lane graph, which may also be represented by a cubic spline with its own end points and tangents. For simplicity, the data for lane boundaries need not be shared between lane graph edges in some exemplary embodiments, so there is nothing in the representation explicitly enforcing that boundaries are continuous between edges or that they match up between neighboring lanes. This approach simplifies indexing, and limits the graph structure to the graph of drivable segments. The lane graph may also include data structure placeholders for in-path objects and wait conditions”), the respective sets of boundary conditions initially applying to traffic situations represented by the same zone graph and subsequently being specified for the current traffic situation by applying the data of the situation-specific parameters (see at least para. [0049] of Ford which discloses “the vehicle is constrained to operate under a set of comfort limits which restrict its maximal acceleration, deceleration, and jerk. It is understood that in other embodiments other parameters can also be used to determine comfort limits than those described herein. The comfort limits are more conservative than the performance limits of the host vehicle 50. For example, if limits are provided for a turning radius, the comfort limit can dictate a larger turning radius as compared to the performance limit (at given same speed). In one or more examples”).
Regarding newly added claim 16, Ford, as modified by Ditty, Kazemi and Censi discloses
wherein: the model-generation module is configured to generate a zone graph (see at least para. [0022] of Ford which discloses “The route may be considered as a graph that includes multiple nodes and paths from one node to another node in the graph. The nodes represent a location along the route that is generated. There may be multiple paths between two such nodes and the path planner determines which of these paths to take to move the host vehicle between two such nodes. The path planner 30 provides path planning inputs to the trajectory planning system 10 based on the generated route and the determined path between nodes. In one or more examples, the path planner 30 determines the route for the host vehicle 50 at the beginning of a trip, for example when a user inputs a destination (and a source), the route providing navigation guidance for the host vehicle 50 to reach the destination“) that abstracts the current traffic situation by representing a real road situation using an abstract traffic infrastructure element corresponding to static road geometry and having a plurality of zones relevant to realization of a driving intention of the vehicle (see at least para. [0022] of Ford which discloses “a trajectory planning system 10 for a vehicle 50. The vehicle 50 may be an autonomous vehicle or a semi-autonomous vehicle. The vehicle 50 (hereinafter referred to as the host vehicle) includes a vehicle-based image capture device 12 and at least one sensing-based device 14. It should be noted that in one or more examples, the trajectory planning described herein may be performed without image capture devices. FIG. 1 further depicts a path planner 30, which generates a path or route for the host vehicle 50. The path planner 30 determines the route for the host vehicle 50 from a source location to a route destination taking into account factors such as historic road-speed, traffic conditions, weather forecasts etc.”), the plurality of zones being unspecified as to both size and position before application of data of situation-specific parameters; and the analysis module is configured to use the zone graph to morphologically analyze (see at least para. [0039] of Ford which discloses “The determined path is received by the trajectory planner 10. The path planner 30 determines the path using one or more route determining algorithms, for example using a graph-based approach that includes using path determining algorithms such as Bellman-Ford, Djikstra, and the like. In one or more examples, the path is split into one or more commands that are provided to the trajectory planner 10 as the path planning inputs”) possible developments or behaviors of road users to determine the respective sets of boundary conditions (see at least para. [0529] of Ditty which discloses “there is also a left and right lane boundary with each edge in the lane graph, which may also be represented by a cubic spline with its own end points and tangents. For simplicity, the data for lane boundaries need not be shared between lane graph edges in some exemplary embodiments, so there is nothing in the representation explicitly enforcing that boundaries are continuous between edges or that they match up between neighboring lanes. This approach simplifies indexing, and limits the graph structure to the graph of drivable segments. The lane graph may also include data structure placeholders for in-path objects and wait conditions”), the respective sets of boundary conditions initially applying to traffic situations represented by the same zone graph and subsequently being specified for the current traffic situation by applying the data of the situation-specific parameters (see at least para. [0049] of Ford which discloses “the vehicle is constrained to operate under a set of comfort limits which restrict its maximal acceleration, deceleration, and jerk. It is understood that in other embodiments other parameters can also be used to determine comfort limits than those described herein. The comfort limits are more conservative than the performance limits of the host vehicle 50. For example, if limits are provided for a turning radius, the comfort limit can dictate a larger turning radius as compared to the performance limit (at given same speed). In one or more examples”).
Regarding newly added claim 17, Ford, as modified by Ditty, Kazemi and Censi discloses
wherein: the plurality of zones represents different map regions, possible traffic flows, or objects; and ascertaining the plurality of possible behaviors comprises using the zone graph to morphologically analyze (see at least para. [0039] of Ford which discloses “The determined path is received by the trajectory planner 10. The path planner 30 determines the path using one or more route determining algorithms, for example using a graph-based approach that includes using path determining algorithms such as Bellman-Ford, Djikstra, and the like. In one or more examples, the path is split into one or more commands that are provided to the trajectory planner 10 as the path planning inputs”) possible developments or behaviors of road users involved in the current traffic situation to determine the respective sets of boundary conditions (see at least para. [0529] of Ditty which discloses “there is also a left and right lane boundary with each edge in the lane graph, which may also be represented by a cubic spline with its own end points and tangents. For simplicity, the data for lane boundaries need not be shared between lane graph edges in some exemplary embodiments, so there is nothing in the representation explicitly enforcing that boundaries are continuous between edges or that they match up between neighboring lanes. This approach simplifies indexing, and limits the graph structure to the graph of drivable segments. The lane graph may also include data structure placeholders for in-path objects and wait conditions”), the respective sets of boundary conditions initially applying to traffic situations represented by the same zone graph and subsequently being specified for the current traffic situation by applying the data of the situation-specific parameters (see at least para. [0049] of Ford which discloses “the vehicle is constrained to operate under a set of comfort limits which restrict its maximal acceleration, deceleration, and jerk. It is understood that in other embodiments other parameters can also be used to determine comfort limits than those described herein. The comfort limits are more conservative than the performance limits of the host vehicle 50. For example, if limits are provided for a turning radius, the comfort limit can dictate a larger turning radius as compared to the performance limit (at given same speed). In one or more examples”).
Regarding newly added claim 18, Ford, as modified by Ditty, Kazemi and Censi discloses
wherein: the predefined set of rules categorizes, as functional degradation, violation of traffic rules, or endangering or harming road users, a relaxation according to which the respective set of boundary conditions of a lower-priority possible behavior permits at least one response of the vehicle that is not permitted by the respective set of boundary conditions of a higher-priority possible behavior (see at least para. [0529] of Ditty which discloses “there is also a left and right lane boundary with each edge in the lane graph, which may also be represented by a cubic spline with its own end points and tangents. For simplicity, the data for lane boundaries need not be shared between lane graph edges in some exemplary embodiments, so there is nothing in the representation explicitly enforcing that boundaries are continuous between edges or that they match up between neighboring lanes. This approach simplifies indexing, and limits the graph structure to the graph of drivable segments. The lane graph may also include data structure placeholders for in-path objects and wait conditions”); and a suggested trajectory that satisfies the respective set of boundary conditions of the lower-priority possible behavior but does not satisfy the respective set of boundary conditions of the higher-priority possible behavior is classified as invalid and prevented from being implemented when the relaxation is categorized as violation of traffic rules or as endangering or harming road users (see at least para. [0106] of Kazemi which discloses “By way of example, the motion planning system 128 can determine that the vehicle 108 can perform a certain action (e.g., pass an object) without increasing the potential risk to the vehicle 108 and/or violating any traffic laws (e.g., speed limits, lane boundaries, signage). The motion plan data 134 can include a planned trajectory, velocity, acceleration, and/or other actions of the vehicle 108”), unless an absolute emergency is identified in which the vehicle has no other recourse, in which case the suggested trajectory is caused to be implemented by the actuator system and is stored in a log file (see at least para. [0104] of Censi which discloses “Data storage units 142 or memory 144 or both for storing machine instructions, or various types of data, or both”) together with the results of the compatibility checks and the evaluation.
Regarding newly added claim 19, Ford, as modified by Ditty, Kazemi and Censi discloses
wherein the respective set of boundary conditions of at least one lower-priority possible behavior is less restrictive than the respective set of boundary conditions of a higher-priority possible behavior in that the respective set of boundary conditions of the lower-priority possible behavior permits at least one response of the vehicle that is not permitted by the respective set of boundary conditions of the higher- priority possible behavior (see at least para. [0057] of Kazemi which discloses “The plurality of paths can then be ranked (e.g., arranged in an ascending or descending order according to the extent to which the one or more path criteria that are satisfied). In some embodiments, generating the motion plan (e.g., the motion plan that complies with the set of constraints associated with the severity level) can include determining a path of the plurality of paths that has the ranking that is highest (i.e., the highest ranking path of the plurality of paths). In some embodiments, the one or more adverse conditions can include a road with a direction of travel opposite to a direction of travel of the vehicle, an intersection (e.g., an area in which two or more roads intersect), a railroad crossing, a public transportation pick-up area (e.g., a bus stop), a blind curve (e.g., a curve around which there is no visibility or around which visibility is limited), a blind corner (e.g., a corner around which there is no visibility or around which visibility is limited), an on-ramp for a highway, and/or an off-ramp for a highway” and see at least para. [0186]-[0187] of Kazemi which discloses “At 1004, the method 1000 can include determining (e.g., determining based at least in part on the state data of the method 900) a highest ranked path of the plurality of paths based at least in part on one or more path criteria associated with one or more adverse conditions for the autonomous vehicle to avoid. For example, the vehicle computing system 112 can determine a ranking of the plurality of paths based at least in part on one or more path criteria associated with one or more adverse conditions for the vehicle to avoid … By way of further example, the vehicle computing system 112 can analyze (e.g., analyze based in part on the state data) each of the plurality of paths based in part on the one or more path criteria. Analyzing each of the plurality of paths can include determining which of the plurality of paths include the one or more adverse conditions and/or the extent to which each of the one or more adverse conditions is present in each of the plurality of paths. The plurality of paths can then be ranked (e.g., arranged in an ascending or descending order according to the extent to which the one or more path criteria that are satisfied” and see at least para. [0082] of Kazemi which discloses “Additionally, by leveraging a system that can use rules-based techniques and/or machine-learned models, the disclosed technology can better determine a safe and unobtrusive stopping location based on both environmental cues (e.g., the position of roads, road-shoulders, and other vehicles) and/or the state of the vehicle (e.g., an amount of fuel remaining and/or a vehicle door being opened in transit). For example, the disclosed technology can use dedicated computational resources (e.g., a custom designed processor) that can be used to stop the vehicle more efficiently and effectively than other more generalized approaches to stopping the vehicle”).
Regarding newly added claim 20, Ford, as modified by Ditty, Kazemi and Censi discloses
wherein the compatibility checks are carried out for respective ascertained behaviors in descending order of priority, beginning with the highest-priority behavior, until a first behavior whose boundary conditions are satisfied by the suggested trajectory is identified, and wherein the priority of the first behavior is assigned as the evaluation of the suggested trajectory (see at least para. [0057] of Kazemi which discloses “The plurality of paths can then be ranked (e.g., arranged in an ascending or descending order according to the extent to which the one or more path criteria that are satisfied). In some embodiments, generating the motion plan (e.g., the motion plan that complies with the set of constraints associated with the severity level) can include determining a path of the plurality of paths that has the ranking that is highest (i.e., the highest ranking path of the plurality of paths). In some embodiments, the one or more adverse conditions can include a road with a direction of travel opposite to a direction of travel of the vehicle, an intersection (e.g., an area in which two or more roads intersect), a railroad crossing, a public transportation pick-up area (e.g., a bus stop), a blind curve (e.g., a curve around which there is no visibility or around which visibility is limited), a blind corner (e.g., a corner around which there is no visibility or around which visibility is limited), an on-ramp for a highway, and/or an off-ramp for a highway” and see at least para. [0186]-[0187] of Kazemi which discloses “At 1004, the method 1000 can include determining (e.g., determining based at least in part on the state data of the method 900) a highest ranked path of the plurality of paths based at least in part on one or more path criteria associated with one or more adverse conditions for the autonomous vehicle to avoid. For example, the vehicle computing system 112 can determine a ranking of the plurality of paths based at least in part on one or more path criteria associated with one or more adverse conditions for the vehicle to avoid … By way of further example, the vehicle computing system 112 can analyze (e.g., analyze based in part on the state data) each of the plurality of paths based in part on the one or more path criteria. Analyzing each of the plurality of paths can include determining which of the plurality of paths include the one or more adverse conditions and/or the extent to which each of the one or more adverse conditions is present in each of the plurality of paths. The plurality of paths can then be ranked (e.g., arranged in an ascending or descending order according to the extent to which the one or more path criteria that are satisfied” and see at least para. [0082] of Kazemi which discloses “Additionally, by leveraging a system that can use rules-based techniques and/or machine-learned models, the disclosed technology can better determine a safe and unobtrusive stopping location based on both environmental cues (e.g., the position of roads, road-shoulders, and other vehicles) and/or the state of the vehicle (e.g., an amount of fuel remaining and/or a vehicle door being opened in transit). For example, the disclosed technology can use dedicated computational resources (e.g., a custom designed processor) that can be used to stop the vehicle more efficiently and effectively than other more generalized approaches to stopping the vehicle”).
Claims 7 and 13 are rejected under 35 U.S.C. 103 as being unpatentable over Ford (US20190250617A1) in view of Ditty (US20190258251A1) in view of Kazemi (US20190235499A1) and further in view of Censi (US20210356962A1) and further in view of Dolgov (US 2014/0303827 A1).
Regarding amended claim 7, Ford, as modified by Ditty, Kazemi and Censi discloses the
automated operating mode (see at least para. [0095] of Censi which discloses “The term “autonomous machine” or “motion machine” or simply “machine” is used broadly to include, for example, any kind of robot, vehicle, aerial vehicle, airplane, space shuttle, helicopter, marine device, or ship, among others, having one or more autonomous motion capabilities” and see at least para. [0102] of Censi which discloses “A category of autonomous systems comprises autonomous vehicles (AVs), vehicles having one or more autonomous motion capabilities in the form of autonomous driving capabilities, including fully autonomous vehicles, highly autonomous vehicles, and conditionally autonomous vehicles”).
Ford, as modified by Ditty, Kazemi and Censi may not explicitly disclose wherein a signal to
terminate the automated operating mode and transition to a manual operating mode is generated when-a in response to determining that the critical situation exists.
However, in the same field of endeavor, Dolgov discloses a computing device configured to
generate a signal to terminate the automated operating mode and transition to a manual operating mode is generated when-a in response to determining that the critical situation exists (see at least para. [0071] of Dolgov which discloses “receiving, via a computing device, an indication for a transition of control of a vehicle operating in an autonomous mode, and the computing device is configured to control the vehicle in the autonomous mode. A computing device autonomously controlling a vehicle may be configured to continuously monitor for various types of indications from the driver requesting a switch to manual control of the vehicle. The computing device may be configured to detect and receive various indications from the driver, such as manual application of the throttle, brakes, or steering wheel, etc. In one implementation, a vehicle may be configured with a button, switch, or similar interface for receiving an indication from the driver for a transition from autonomous mode to manual mode”).
It would have been obvious to one of ordinary skill in the art before the effective filing date
of the claimed invention to modify the computing device of Ford, as modified by Ditty, Kazemi and Censi, to be configured to generate a signal to terminate the automated operating mode and transition to a manual operating mode is generated in response to determining that the critical situation exists, as taught in Dolgov with a reasonable expectation of success in order to improve vehicle safety by permitting human intervention when dangerous or critical trajectory situations are identified during autonomous operation, thereby reducing the likelihood of unsafe autonomous vehicle behavior.
Regarding amended claim 13, Ford, as modified by Ditty, Kazemi and Censi discloses
wherein the evaluation module is configured to use the results of the compatibility checks or the evaluation of the suggested trajectory, or both, to determine whether a critical situation exists (see at least para. [0104] of Censi which discloses “One or more data sources 142 for providing historical, or real-time, or predictive information, or combinations of them about the environment 190, including, in the case of a vehicle, for example, maps, driving performance, motion performance, traffic congestion updates or weather conditions. Such data may be stored on a data storage unit 142 or memory 144 on the machine 100, or may be transmitted to the machine 100 via a communications channel from a remote database 134 or a combination of them. 8. One or more data sources 136 for providing map data; e.g., digital road map data; geographic information system databases; maps of flight paths; maps of navigational channels; maps of the roadway geometric properties; maps describing road network connectivity properties; maps describing properties (such as traffic speed, traffic volume, the number of vehicular and cyclist traffic lanes, lane width, lane traffic directions, or lane marker types and locations, or combinations of them) of roads, flight paths, or navigational channels; and maps describing the spatial locations of road or navigational channel features such as, in the case of road vehicles, crosswalks, traffic signs or other travel signals of various”).
Ford, as modified by Ditty, Kazemi and Censi may not explicitly disclose wherein the
evaluation module is further configured to generate a signal to terminate the automated operating mode and transition to a manual operating mode in response to determining that the critical situation exists.
However, in the same field of endeavor, Dolgov discloses a computing device configured to
generate a signal to terminate the automated operating mode and transition to a manual operating mode is generated in response to determining that the critical situation exists (see at least para. [0071] of Dolgov which discloses “receiving, via a computing device, an indication for a transition of control of a vehicle operating in an autonomous mode, and the computing device is configured to control the vehicle in the autonomous mode. A computing device autonomously controlling a vehicle may be configured to continuously monitor for various types of indications from the driver requesting a switch to manual control of the vehicle. The computing device may be configured to detect and receive various indications from the driver, such as manual application of the throttle, brakes, or steering wheel, etc. In one implementation, a vehicle may be configured with a button, switch, or similar interface for receiving an indication from the driver for a transition from autonomous mode to manual mode”).
It would have been obvious to one of ordinary skill in the art before the effective filing date
of the claimed invention to modify the computing device of Ford, as modified by Ditty, Kazemi and Censi, to be configured to generate a signal to terminate the automated operating mode and transition to a manual operating mode is generated in response to determining that the critical situation exists, as taught in Dolgov with a reasonable expectation of success in order to improve vehicle safety by permitting human intervention when dangerous or critical trajectory situations are identified during autonomous operation, thereby reducing the likelihood of unsafe autonomous vehicle behavior.
Claim 8 is rejected under 35 U.S.C. 103 as being unpatentable over Ford (US20190250617A1) in view of Ditty (US20190258251A1) in view of Kazemi (US20190235499A1) and further in view of Censi (US20210356962A1) and further in view of Golov (DE112020000611).
Regarding amended claim 8, Ford, as modified by Ditty, Kazemi and Censi discloses the
aggregated situation –specific information (see at least para. [0169] of Censi which discloses “the strategic factor analysis (320 in FIG. 3) may use real data or simulated data or both types of data (e.g., map 304 and sensor data 306) to determine strategic factors and relevant values of the strategic factors. Some real data is collected by operating autonomous systems in real environments. Some simulations may be computationally derived from hypothetical environments for operating the autonomous systems, e.g., road configurations, air space scenarios, navigation paths, traffic speeds, traffic volumes, traffic lights, traffic signs, objects, and weather conditions. The use of the data may include statistically evaluating the strategic guidelines, such as frequency of invoking strategic guidelines, prioritization relations, and values of strategic factors”).
Ford, as modified by Ditty, Kazemi and Censi may not explicitly disclose wherein the
aggregated situation-specific information is continuously cached and the cached situation-specific information is permanently stored in response to determining that the critical situation exists.
However, Golov discloses specific information is continuously cached and the cached
situation-specific information is permanently stored in response to determining that the critical situation exists (see at least the translation of Golov which discloses “The caching at block 303 and saving at block 309 can parallel to the receipt of the next new section at block 301 and to get the next oldest section at block 305 be performed. Thus, the new, incoming sections of the sensor data stream ( 151 ) are continuously cached in the cyclic buffer memory, while an older, delayed section of the sensor data stream ( 151 ) to save in the non-volatile memory ( 165 ) can be called up from the cyclic buffer memory”).
It would have been obvious to one of ordinary skill in the art before the effective filing date
of the claimed invention to further modify the aggregated situation-specific information of Ford, as modified by Ditty, Kazemi and Censi to be continuously cached and the cached situation-specific information is permanently stored in response to determining that the critical situation exists, as taught in Golov with a reasonable expectation of success in order to preserver sensor and trajectory evaluation information associated with critical autonomous driving situations for additional analysis, diagnostics and improvement of the autonomous vehicle operation along specified trajectories.
Claim 15 is rejected under 35 U.S.C. 103 as being unpatentable over Ford (US20190250617A1) in view of Ditty (US20190258251A1) in view of Kazemi (US20190235499A1) and further in view of Censi (US20210356962A1) and further in view of Koopman (US 20190056735A1).
Regarding newly added claim 15, Ford, as modified by Ditty, Kazemi and Censi discloses
wherein: the one or more planning modules comprise a plurality of planning modules (see at least para. [0037] of Ford which discloses “the trajectory planner 10 receives the path and generates one or more trajectories corresponding to the path, and further determines one or more maneuvers to follow the trajectory. As used herein, a ‘maneuver’ is an operation that may be performed by the vehicle 50 via multiple different trajectories” and see Fig. 2, 225 of Censi and see at least para. [0144] of Censi which discloses “a motion planner 225 can quantitatively evaluate candidate trajectories (each of which corresponds to a sequence of motion actions) that it has under consideration and then select an optimal trajectory 227 from the candidates”) configured to suggest respective trajectories independently of one another and in parallel based on the situation-specific information(see at least para. [0022] of Ford which discloses “There may be multiple paths between two such nodes and the path planner determines which of these paths to take to move the host vehicle between two such nodes. The path planner 30 provides path planning inputs to the trajectory planning system 10 based on the generated route and the determined path between nodes” and see at least para. [0180] of Censi which discloses “The samples that are in the non-drivable regions 811-818 or blocked by an object (e.g., the vehicle 820) are then removed; e.g., the sampling points 832 and 833 will be removed and the point 831 will remain. Referring to FIG. 8C, based on the remaining sampling points, the trajectory may identify multiple candidate trajectories (e.g., 850, 860 and 870)”); the evaluation module comprises a plurality of evaluation modules each associated with a respective one of the planning modules, disposed in a respective performance path of the associated planning module, and configured to receive the list of possible behaviors and to carry out the compatibility checks (see at least para. [0170] of Censi which discloses “Implementations of the guideline processor may include a deviation analysis (322 in FIG. 3) determining a deviation metric (340 in FIG. 3) for a strategic guideline. In some cases, the deviation metric may be a function of one or more strategic factors associated with the condition or proper action or both of the strategic guideline. For example in FIG. 5, a basic principle expressed by a strategic guideline may state: avoid stress to a bicyclist 553 when an AV system 551 passes by the bicyclist. The strategic factor analysis 320 based on learning algorithms may infer that: the smaller the distance 555 (denoted mathematically as d), the higher the stress to the bicyclist 553. Thus, the deviation metric may be an inverse function of the distance: J=1/d. In other words, when the AV system 551 becomes too close to the bicyclist 553 (i.e., d is a small number), the basic principle associated with the strategic guideline of avoiding the stress to bicyclists may be deviated from or violated. The deviation metric J=1/d quantifies the degree of the deviation or violation. A threshold may be applied to the deviation metric to indicate that the basic principle associated with the strategic guideline is not considered to be deviated from or violated. In this example, if the distance d is determined to be at least 0.5 m for obeying the strategic guideline, the deviation metric may be set to 0 when d>0.5 m (i.e., the threshold for the deviation metric is J=1/0.5=2)”) and assign the evaluation for the trajectory suggested by the associated planning module (see at least para. [0037] of Ford which discloses “the trajectory planner 10 receives the path and generates one or more trajectories corresponding to the path, and further determines one or more maneuvers to follow the trajectory. As used herein, a ‘maneuver’ is an operation that may be performed by the vehicle 50 via multiple different trajectories” and see at least para. [0012] of Censi which discloses “identifying candidate trajectories).
Ford, as modified by Ditty, Kazemi and Censi may not explicitly disclose the system further
comprises a selection module configured to receive, from each of the plurality of evaluation modules, the respective suggested trajectory together with the respective evaluation, compare the respective evaluations, and select exactly one of the suggested trajectories for implementation by the actuator system.
However, Koopman discloses the system further comprises a selection module (Fig. 5, 530
and see at least para. [0083] of Koopman which discloses “the Priority Selector 530 is instantiated at the output of the Trajectory Execution Stage 506. The Priority Selector 530 is implemented as a node in the Robot Operating System (ROS) and receives the outputs of both the Primary Trajectory Executor Safety Gate 524 and the Safing Trajectory Executor Safety Gate 528 within the Trajectory Execution Stage 506. The outputs of the Priority Selector 530 includes vehicle velocity and curvature commands, which are translated by another ROS node, known as the Vehicle Controller 532, into commands to the vehicle's braking, steering, and throttle actuators”, *Koopman teaches a selection component 530 that arbitrates between checked primary and outputs for downstream vehicle control) configured to receive, from each of the plurality of evaluation modules, the respective suggested trajectory together with the respective evaluation, compare the respective evaluations, and select exactly one of the suggested trajectories for implementation by the actuator system (see at least para. [0082] – [0083] of Koopman which discloses “a Priority Selector 410 selects between the Primary and Safing Outputs, typically at the final stage of the architecture. For example, the Priority Selector 410 may decide which trajectory commands to send to the vehicle actuators. The logic of the Priority Selector 410 is such that if the Primary Output is inhibited, then the Safing Output is transmitted. If the Safing Output is inhibited, then an MSTOP is triggered. The Priority Selector 410 assumes that the safety gates 404, 408 fail silently” and
“Referring to FIG. 5 in the context of AGV system implementations, the Priority Selector 530 is instantiated at the output of the Trajectory Execution Stage 506. The Priority Selector 530 is implemented as a node in the Robot Operating System (ROS) and receives the outputs of both the Primary Trajectory Executor Safety Gate 524 and the Safing Trajectory Executor Safety Gate 528 within the Trajectory Execution Stage 506. The outputs of the Priority Selector 530 includes vehicle velocity and curvature commands, which are translated by another ROS node, known as the Vehicle Controller 532, into commands to the vehicle's braking, steering, and throttle actuators”).
It would have been obvious to one of ordinary skill in the art before the effective filing date
of the claimed invention to modify the system of Ford, as modified by Ditty, Kazemi and Censi, to include a selection module configured to receive, from each of the plurality of evaluation modules, the respective suggested trajectory together with the respective evaluation, compare the respective evaluations, and select exactly one of the suggested trajectories for implementation by the actuator system, as taught in Koopman with a reasonable expectation of success in order to provide a single execution output from the available checked planning channels while preserving a fallback vehicle control capability when a planning channel fails or produces an unacceptable output.
Additional Prior Art
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure. Zhang (US 2019/0072965A1) discloses a prediction-based system and method for trajectory planning of autonomous vehicles is disclosed herein. Specifically, the present disclosure relates to trajectory planning for autonomous vehicles using a prediction-based method. In one aspect, the system herein may include various sensors, configured to collect perception data, a computing device, and a trajectory prediction module for predicting a trajectory of other vehicles and/or dynamic objects in the vicinity of (proximate to) a host autonomous vehicle. Initially, the computing device generates a trajectory option, while the trajectory prediction module predicts reactions of vehicles and/or dynamic objects examined using data concerning likely trajectories of each vehicle and/or dynamic objects respectively. Kazemi (US 2019/0294170A1) discloses a prediction system 130 that can receive state data from perception system 128 and can predict (e.g., based at least in part on such state data, and/or the like) one or more future locations for each object. For example, prediction system 130 can predict where each object will be located within the next five seconds, ten seconds, twenty seconds, and/or the like. As one example, an object can be predicted to adhere to its current trajectory according to its current speed. Additionally or alternatively, other prediction techniques, modeling, and/or the like can be used.
Conclusion
Applicant's amendment necessitated the new ground(s) of rejection presented in this Office action. Accordingly, THIS ACTION IS MADE FINAL. See MPEP § 706.07(a). Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any nonprovisional extension fee (37 CFR 1.17(a)) pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the mailing date of this final action.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to DANA IVEY whose telephone number is (313)446-4896. The examiner can normally be reached 9-5:30 EST Monday-Friday.
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Jelani Smith can be reached at 571-270-3969. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of published or unpublished applications may be obtained from Patent Center. Unpublished application information in Patent Center is available to registered users. To file and manage patent submissions in Patent Center, visit: https://patentcenter.uspto.gov. Visit https://www.uspto.gov/patents/apply/patent-center for more information about Patent Center and https://www.uspto.gov/patents/docx for information about filing in DOCX format. For additional questions, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/DANA D IVEY/Examiner, Art Unit 3662
/D.D.I/October 30, 2026
/JELANI A SMITH/Supervisory Patent Examiner, Art Unit 3662