Detailed Office 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 is a non-final Office Action on the merits. Claims 1-20 are currently pending and are addressed below.
Priority
Acknowledgment is made of applicant's claim priority for KR10-2023-0171336 filed November 30th, 2023.
Information Disclosure Statement
The information disclosure statements (IDS) submitted on 11/19/2024 is being considered by the examiner.
Claim Rejections - 35 USC § 112
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.
Claim 3 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.
Claim 3 recites “and the plurality of levels further includes ignore that does not need to be considered for constraints”, the term “ignore” in the claim is not consistent with its regular meaning nor can its intended meaning be interpreted using the context of the claim language. As such, the claim as presented is indefinite for failing to distinctly claim the subject matter the inventor regards as the invention.
Claim 20 is 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.
Claim 20 recites the limitation "The Computer Device of Claim 16" in the preamble. There is insufficient antecedent basis for this limitation in the claim, as claim 16 makes no mention of “The Computer Device”.
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. The analysis of the claims’ subject matter eligibility will follow the 2019 Revised Patent Subject Matter Eligibility Guidance, 84 Fed. Reg. 50-57 (January 7, 2019) (“2019 PEG”).
101 Analysis - With respect to Claim 1
Claim 1, 16, and 17 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:
Claim 1 is directed towards a method which is directed to the statutory category of a process. Claim 16 is directed towards a non-transitory computer readable medium which is directed to the statutory category of a manufacture. Claim 17 is directed towards a computer device which is directed to the statutory category of a machine. Therefore Claims 1, 16, and 17 are within at least one of the four statutory categories.
101 Analysis- Step 2A Prong One:
Regarding Prong One of the Step 2A analysis in the 2019 PEG, the claims are to be analyzed to determine whether they recite subject matter that falls within one of the following groups of abstract ideas: a) mathematical concepts, b) certain methods of organizing human activity, and/or c) mental process.
Independent claim 1 includes limitations that recite an abstract idea (emphasized below) and will be used as a representative claim for the remainder of the 101 rejection.
Claim 1 recites, inter alai:
“A real-time model predictive control-based planning method of a computer device comprising at least one processor, the method comprising:
generating, by the at least one processor, a class prediction decision value that determines an upper bound and a lower bound of constraints in an optimal control problem through an observation value for a driving environment; and
receiving, by the at least one processor, the class prediction decision value and the observation value from the driving environment and generating a main trajectory.”
The examiner submits that the foregoing bolded limitation(s) constitute a “mental process” because under its broadest reasonable interpretation, the claim covers performance of the limitation in the human mind.
For example, “generating” in the context of this claim, encompass a person looking at available data and forming a simple judgement (determination, analysis, comparison, etc.) either manually or using a pen and paper. Accordingly, the claim recites at least one abstract idea. The examiner notes that under MPEP 2106.04(a)(2)(III), the courts consider a mental process (thinking) that "can be performed in the human mind, or by a human using a pen and paper" to be an abstract idea. CyberSource Corp. v. Retail Decisions, Inc., 654 F.3d 1366, 1372, 99 USPQ2d 1690, 1695 (Fed. Cir. 2011). As the Federal Circuit explained, "methods which can be performed mentally, or which are the equivalent of human mental work, are unpatentable abstract ideas the ‘basic tools of scientific and technological work’ that are open to all.’" 654 F.3d at 1371, 99 USPQ2d at 1694 (citing Gottschalk v. Benson, 409 U.S. 63, 175 USPQ 673 (1972)). See also Mayo Collaborative Servs. v. Prometheus Labs. Inc., 566 U.S. 66, 71, 101 USPQ2d 1961, 1965 ("‘[M]ental processes[] and abstract intellectual concepts are not patentable, as they are the basic tools of scientific and technological work’" (quoting Benson, 409 U.S. at 67, 175 USPQ at 675)); Parker v. Flook, 437 U.S. 584, 589, 198 USPQ 193, 197 (1978) (same).
As drafted, the above claims, under their broadest reasonable interpretation, cover mental processes performed in the human mind (including an observation, evaluation, judgement, opinion), that are merely completed via generic computer components. Accordingly, the claims recite an abstract idea.
Step 2A Prong Two Analysis:
Regarding Prong Two of the Step 2A analysis in the 2019 PEG, the claims are to be analyzed to determine whether the claim, as a whole, integrates the abstract idea into a practical application. As noted in the 2019 PEG, 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. The courts have indicated that additional elements 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”.
In the present case, the additional limitations beyond the above-noted abstract idea are as follows (where the underlined portions are the “additional limitations” while the bolded portions continue to represent the “abstract idea”):
Claim 1 recites, inter alai:
“A real-time model predictive control-based planning method of a computer device comprising at least one processor, the method comprising:
generating, by the at least one processor, a class prediction decision value that determines an upper bound and a lower bound of constraints in an optimal control problem through an observation value for a driving environment; and
receiving, by the at least one processor, the class prediction decision value and the observation value from the driving environment and generating a main trajectory.”
For the following reason(s), the examiner submits that the above identified additional limitations do not integrate the above-noted abstract idea into a practical application.
Regarding the additional limitation of “by the at least one processor…”, this limitation merely describes how to generally “apply” the otherwise mental judgements in a generic or general purpose vehicle control environment. See Alice Corp. Pty. Ltd. v. CLS Bank Int'l, 573 U.S. at 223 (“[T]he mere recitation of a generic computer cannot transform a patent-ineligible abstract idea into a patent-eligible invention.”). The device(s) and processor(s) are recited at a high level of generality and merely automates the steps.
Regarding the additional limitation of “receiving…the class prediction decision”, this limitation merely describes the sending and receiving of data which is in insignificant extra solution activity. See MPEP § 2106.05(g).
Thus, taken alone, the additional elements do not integrate the abstract idea into a practical application. Further, looking at the additional limitation(s) as an ordered combination or as a whole, the limitation(s) add nothing that is not already present when looking at the elements taken individually. Accordingly, the additional limitation(s) do/does not integrate the abstract idea into a practical application because it does not impose any meaningful limits on practicing the abstract idea.
Step 2B Analysis:
The claims do not include additional elements (considered both individually and as an ordered combination) that are sufficient to amount to significantly more than the judicial exception for the same reasons to those discussed above with respect to determining that the claim does not integrate the abstract idea into a practical application. As discussed above with respect to integration of the abstract idea into a practical application, the additional element of using generic computer components to perform the abstract idea amounts to no more than mere instructions to apply the exception using a generic computer component. Mere instructions to apply an exception using a generic computer component cannot provide an inventive concept. The claims are not patent eligible.
Regarding dependent claims 2-15 and 18-20, no claim further adds a limitation that introduces any practical applications to the claimed invention, the dependent claims merely add more mental process, mathematical concepts, and post-solution activities and are thus not patent eligible.
Therefore, Claims 1-20 are ineligible under 35 USC §101.
Claim Rejections - 35 USC § 102
The following is a quotation of the appropriate paragraphs of 35 U.S.C. 102 that form the basis for the rejections under this section made in this Office action:
A person shall be entitled to a patent unless –
(a)(1) the claimed invention was patented, described in a printed publication, or in public use, on sale, or otherwise available to the public before the effective filing date of the claimed invention.
(a)(2) the claimed invention was described in a patent issued under section 151, or in an application for patent published or deemed published under section 122(b), in which the patent or application, as the case may be, names another inventor and was effectively filed before the effective filing date of the claimed invention.
Claims 1-3, 5 and 16-18 are rejected under 35 U.S.C. 102(a)(2) as being anticipated by Li et al (CN 112498366 A), hereafter referred to as Li.
Regarding Claim 1, Li teaches a real-time model predictive control-based planning method of a computer device comprising at least one processor (see at least Li [English Translation Abstract and pg.6 para.4] The embodiment of the specification claims an automatic driving vehicle, control method,…the method comprises: obtaining the driving path of the vehicle...confirming whether it satisfies the preset condition; the target road section is the section of the driving route of the current vehicle; when the dynamic road condition information does not satisfy the preset condition, performing local speed planning to the target road section…controlling the driving of the vehicle… the embodiment of the specification further provides a sub-device, comprising a memory, a processor, and a computer program stored on the memory, the computer program is executed by the processor to realize the control method)
the method comprising:
generating, by the at least one processor, a class prediction decision value that determines an upper bound and a lower bound of constraints in an optimal control problem through an observation value for a driving environment (see at least Li [English Translation pg.10 para.11, pg.11 para.2, pg.13 para.7, pg.6 para.4] it also can combine the obtained movement state of the obstacle around the vehicle with the high precision map information, and using the depth learning algorithm to predict the movement state of the obstacle around the vehicle. when predicting the movement state of the obstacle around the vehicle, it also can use the history information of the obstacle, and the related relation of the obstacle and the lane...in order to avoid the vehicle collision to the obstacle in the driving process, it also needs to consider the safety distance of the vehicle and the surrounding obstacles...S11 and S12 are respectively the obstacle avoidance upper limit position line predicted at t0 time; the obstacle avoidance lower limit position line…the computer program is executed by the processor to realize the control method)
receiving, by the at least one processor, the class prediction decision value and the observation value from the driving environment and generating a main trajectory (see at least Li [English Translation pg.10 para.11, pg.11 para.2, pg.14 para.2, pg.9 para.2] it also can combine the obtained movement state of the obstacle around the vehicle with the high precision map information, and using the depth learning algorithm to predict the movement state of the obstacle around the vehicle… it also needs to consider the safety distance of the vehicle and the surrounding obstacles …the constraint of the cost function not only considers the obstacle limit factor around the vehicle; further considering the initial position of the vehicle (i.e. the position of the current time of the vehicle), the terminal position (i.e., the expected arrival position of the vehicle); and traffic rule limit…so as to improve the energy utilization efficiency of the automatic driving vehicle…the navigation positioning device can receive the starting point and end point of the stroke set by the user, so as to automatically plan a driving path according to the starting point and the end point (also can plan a plurality of driving paths for user selection)) The predicted movement state of the obstacle is analogous to the class prediction decision value, the state information of the ego vehicle and its surroundings is analogous to the observation value, and the automatic planning of the driving path is analogous to generating a main trajectory.
Regarding Claim 2, Li teaches all limitations of Claim 1 as set forth above. Li further teaches wherein the class prediction decision value includes a value for identifying a surrounding object in the driving environment and classifying the same into a plurality of levels including the upper bound and the lower bound to determine whether an ego vehicle gives way to the surrounding object or passes before the surrounding object (see at least Li [English Translation pg.10 para.5-7, pg.11 para.2, pg.13 para.7] obtaining the movement state of the obstacle around the vehicle, and determining the obstacle avoiding position of the vehicle according to the movement state of the obstacle around the vehicle…determining the local speed curve of the vehicle in the target road section by optimizing the cost function, wherein the cost function is used for calculating the minimum driving cost of the vehicle from the initial position to the terminal position; the optimized constraint comprises the obstacle avoiding position and the traffic rule limit....in order to avoid the vehicle collision to the obstacle in the driving process, it also needs to consider the safety distance of the vehicle and the surrounding obstacles. Therefore, in some embodiments, can according to the preset safety distance parameter and the motion track of the obstacle around the vehicle to generate the obstacle position of the vehicle, as the obstacle-avoiding constraint condition of the vehicle…in order to avoid the vehicle collision to the obstacle in the driving process, it also needs to consider the safety distance of the vehicle and the surrounding obstacles...S11 and S12 are respectively the obstacle avoidance upper limit position line predicted at t0 time; the obstacle avoidance lower limit position line).
Regarding Claim 3, Li teaches all limitations of Claim 2 as set forth above. Li further teaches wherein the upper bound includes an upper bound of longitudinal distance constraints, the lower bound includes a lower bound of longitudinal distance constraints, and the plurality of levels further includes ignore that does not need to be considered for constraints (see at least Li [English Translation pg.7 para.9-11, pg.11 para.2, pg.9 para.5] S11, the obstacle avoidance upper limit position line predicted at t0 time...S12, the obstacle avoidance lower limit position line predicted at t0 time;….in order to avoid the vehicle collision to the obstacle in the driving process, it also needs to consider the safety distance of the vehicle and the surrounding obstacles...the safety distance of the front vehicle can be 100 meter…. The global reference speed curve of the static road information generating driving route mainly considers the static road information of the driving route, and does not consider the dynamic road condition information of the driving route).
Regarding Claim 5, Li teaches all limitations of Claim 1 as set forth above. Li further teaches wherein the generating of the class prediction decision value comprises generating the class prediction decision value by identifying and classifying a surrounding object in the driving environment using a trained deep learning network, in order to provide a high level decision maker function (see at least Li [English Translation pg.10 para.10-11, pg.2 para.5] using the depth learning algorithm to predict the movement state of the obstacle around the vehicle. when predicting the movement state of the obstacle around the vehicle, it also can use the history information of the obstacle, and the related relation of the obstacle and the lane...the present specification provides a control method of an automatic driving vehicle...when using a plurality of obstacle sensing device detects the obstacle around the vehicle, it can carry out multi-obstacle sensing device fusion, namely can the plurality of multi-obstacle sensing device obtains the data information set together for comprehensive analysis, so as to more accurately; reliably describing the external environment around the vehicle, so as to improve the correctness of the system speed decision).
Regarding Claim 16, Li teaches a non-transitory computer-readable recording medium storing instructions that when executed by a processor, cause the processor to perform a real-time model predictive control-based planning method (see at least Li [English Translation Abstract, pg.18 para.2, pg.6 para.4] The information may be a computer readable instruction, a data structure, a module of a program or other data...or any other non-transmission medium, which can be used for storing information which can be accessed by the computing device. According to the definition of the invention, a computer readable medium does not include a temporary computer readable medium (transitory media), such as modulated data signal and carrier….The embodiment of the specification claims an automatic driving vehicle, control method,…the method comprises: obtaining the driving path of the vehicle...confirming whether it satisfies the preset condition; the target road section is the section of the driving route of the current vehicle; when the dynamic road condition information does not satisfy the preset condition, performing local speed planning to the target road section…controlling the driving of the vehicle… the embodiment of the specification further provides a sub-device, comprising a memory, a processor, and a computer program stored on the memory, the computer program is executed by the processor to realize the control method)
comprising:
generating a class prediction decision value that determines an upper bound and a lower bound of constraints in an optimal control problem through an observation value for a driving environment (see at least Li [English Translation pg.10 para.11, pg.11 para.2, pg.13 para.7, pg.6 para.4] it also can combine the obtained movement state of the obstacle around the vehicle with the high precision map information, and using the depth learning algorithm to predict the movement state of the obstacle around the vehicle. when predicting the movement state of the obstacle around the vehicle, it also can use the history information of the obstacle, and the related relation of the obstacle and the lane...in order to avoid the vehicle collision to the obstacle in the driving process, it also needs to consider the safety distance of the vehicle and the surrounding obstacles...S11 and S12 are respectively the obstacle avoidance upper limit position line predicted at t0 time; the obstacle avoidance lower limit position line…the computer program is executed by the processor to realize the control method)
receiving the class prediction decision value and the observation value from the driving environment and generating a main trajectory (see at least Li [English Translation pg.10 para.11, pg.11 para.2, pg.14 para.2, pg.9 para.2] it also can combine the obtained movement state of the obstacle around the vehicle with the high precision map information, and using the depth learning algorithm to predict the movement state of the obstacle around the vehicle… it also needs to consider the safety distance of the vehicle and the surrounding obstacles …the constraint of the cost function not only considers the obstacle limit factor around the vehicle; further considering the initial position of the vehicle (i.e. the position of the current time of the vehicle), the terminal position (i.e., the expected arrival position of the vehicle); and traffic rule limit…so as to improve the energy utilization efficiency of the automatic driving vehicle…the navigation positioning device can receive the starting point and end point of the stroke set by the user, so as to automatically plan a driving path according to the starting point and the end point (also can plan a plurality of driving paths for user selection)) The predicted movement state of the obstacle is analogous to the class prediction decision value, the state information of the ego vehicle and its surroundings is analogous to the observation value, and the automatic planning of the driving path is analogous to generating a main trajectory.
Regarding Claim 17, Li teaches a computer device comprising:
at least one processor configured to execute computer-readable instructions (see at least Li [English Translation pg.6 para.4] the embodiment of the specification further provides a sub-device, comprising a memory, a processor, and a computer program stored on the memory, the computer program is executed by the processor to realize the control method
wherein the at least one processor causes the computer device to
generate a class prediction decision value that determines an upper bound and a lower bound of constraints in an optimal control problem through an observation value for a driving environment (see at least Li [English Translation pg.10 para.11, pg.11 para.2, pg.13 para.7, pg.6 para.4] it also can combine the obtained movement state of the obstacle around the vehicle with the high precision map information, and using the depth learning algorithm to predict the movement state of the obstacle around the vehicle. when predicting the movement state of the obstacle around the vehicle, it also can use the history information of the obstacle, and the related relation of the obstacle and the lane...in order to avoid the vehicle collision to the obstacle in the driving process, it also needs to consider the safety distance of the vehicle and the surrounding obstacles...S11 and S12 are respectively the obstacle avoidance upper limit position line predicted at t0 time; the obstacle avoidance lower limit position line…the computer program is executed by the processor to realize the control method)
receive the class prediction decision value and the observation value from the driving environment and generate a main trajectory (see at least Li [English Translation pg.10 para.11, pg.11 para.2, pg.14 para.2, pg.9 para.2] it also can combine the obtained movement state of the obstacle around the vehicle with the high precision map information, and using the depth learning algorithm to predict the movement state of the obstacle around the vehicle… it also needs to consider the safety distance of the vehicle and the surrounding obstacles …the constraint of the cost function not only considers the obstacle limit factor around the vehicle; further considering the initial position of the vehicle (i.e. the position of the current time of the vehicle), the terminal position (i.e., the expected arrival position of the vehicle); and traffic rule limit…so as to improve the energy utilization efficiency of the automatic driving vehicle…the navigation positioning device can receive the starting point and end point of the stroke set by the user, so as to automatically plan a driving path according to the starting point and the end point (also can plan a plurality of driving paths for user selection)) The predicted movement state of the obstacle is analogous to the class prediction decision value, the state information of the ego vehicle and its surroundings is analogous to the observation value, and the automatic planning of the driving path is analogous to generating a main trajectory.
Regarding Claim 18, Li teaches all limitations of Claim 17 as set forth above. Li further teaches wherein the class prediction decision value includes a value for identifying a surrounding object in the driving environment and classifying the same into a plurality of levels including the upper bound and the lower bound to determine whether an ego vehicle gives way to the surrounding object or passes before the surrounding object (see at least Li [English Translation pg.10 para.5-6, pg.11 para.2, pg.13 para.7] obtaining the movement state of the obstacle around the vehicle, and determining the obstacle avoiding position of the vehicle according to the movement state of the obstacle around the vehicle…determining the local speed curve of the vehicle in the target road section by optimizing the cost function, wherein the cost function is used for calculating the minimum driving cost of the vehicle from the initial position to the terminal position; the optimized constraint comprises the obstacle avoiding position and the traffic rule limit....in order to avoid the vehicle collision to the obstacle in the driving process, it also needs to consider the safety distance of the vehicle and the surrounding obstacles. Therefore, in some embodiments, can according to the preset safety distance parameter and the motion track of the obstacle around the vehicle to generate the obstacle position of the vehicle, as the obstacle-avoiding constraint condition of the vehicle…in order to avoid the vehicle collision to the obstacle in the driving process, it also needs to consider the safety distance of the vehicle and the surrounding obstacles...S11 and S12 are respectively the obstacle avoidance upper limit position line predicted at t0 time; the obstacle avoidance lower limit position line).
Claim Rejections - 35 USC § 103
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.
Claim 4 and 19 are rejected under 35 U.S.C. 103 as being unpatentable over Li et al (CN 112498366 A) in view of Sun et al (CN 115544888 A). Hereafter referred to as Li and Sun respectively.
Regarding Claim 4 and Claim 19, Li teaches all limitations of the method Claim 2 and the computer device of Claim 18 as set forth above. However, Li does not explicitly teach wherein the generating of the class prediction decision value comprises generating the class prediction decision value by identifying and classifying the surrounding object into one of the plurality of levels and by simplifying a problem through convexification of non-convex constraints of model predictive control-based planning into convex constraints.
Sun, in the same field as the endeavor, teaches wherein the generating of the class prediction decision value comprises generating the class prediction decision value by identifying and classifying the surrounding object into one of the plurality of levels and by simplifying a problem through convexification of non-convex constraints of model predictive control-based planning into convex constraints (see at least Sun [English Translation pg.5 para.10, pg.8 para.14, pg.17 para.10, pg.26 para.1] a frame-based space three-dimensional point cloud generated by the laser radar, an obstacle state list generated by the millimeter-wave radar as unit...solving the risk boundary of different levels in the dynamic scene risk domain by supporting vector regression, firstly, extracting the scene boundary point in the joint distribution of the scene risk index with good classification effect...the optimization problem about the formula (18) can be further converted into the convex secondary optimization of the parameter alpha i optimization pair problem...summarizing all scene risk boundary to obtain the risk boundary of different levels in the dynamic scene risk domain...the risk of the scene is represented by some of the vehicle state quantity, if the vehicle-mounted bus alignment signal obtained in step 1 and the vehicle state alignment signal in the vehicle longitudinal speed, longitudinal acceleration, lateral acceleration and yaw rate, because the same driving operation will cause different scene risk in different longitudinal speed, so the longitudinal speed of the vehicle is divided into a plurality of intervals, longitudinal acceleration, lateral acceleration and yaw rate as scene risk index, establishing the index in dangerous scene condition extracting standard of different vehicle speed interval).
Therefore, it would have been obvious to one of ordinary skill in the art, before the effective filing date of the claimed invention to have modified the system set forth in Li to contain a system for wherein the generating of the class prediction decision value comprises generating the class prediction decision value by identifying and classifying the surrounding object into one of the plurality of levels and by simplifying a problem through convexification of non-convex constraints of model predictive control-based planning into convex constraints with reasonable expectation of success. One of ordinary skill in the art would have been motivated to make such a modification for benefit of improving collision detection and managing the risk of the vehicle’s surroundings as discussed in Sun (see at least Sun [English Translation pg.11 para.4] The method is based on the vehicle kinematics model, solving the running track of each outline point of the vehicle in the target scene, compared with the method for calculating the driving track of the vehicle centre, the method is more convenient for vehicle collision detection and solving the scene risk).
Claim 6 and Claim 20 are rejected under 35 U.S.C. 103 as being unpatentable over Li et al (CN 112498366 A) in view of Narang et al (US 11124204 B1). Hereafter referred to as Li and Narang respectively.
Regarding Claim 6, Li teaches all limitations of Claim 5 as set forth above. However, while Li teaches deep learning, it does not explicitly teach wherein the deep learning network is trained through deep reinforcement learning based on a state for an ego vehicle and the surrounding object, an action of identifying and classifying a class based on the state, and a reward generated based on results of the action.
Narang, in the same field as the endeavor, teaches wherein the deep learning network is trained through deep reinforcement learning based on a state for an ego vehicle and the surrounding object, an action of identifying and classifying a class based on the state, and a reward generated based on results of the action (see at least Narang [English Translation C28 L39-60, C16 L40-50] the method 200 includes: receiving a set of inputs, wherein the set of inputs includes a high definition, labeled (e.g., hand-labeled, automatically-labeled, etc.) map which prescribes the context of the autonomous agent at any given time based on its location and/or orientation (e.g., pose) within the map, a set of detected dynamic objects and associated information (e.g., current position, size, previous path, and predicted path into the future), a set of all static objects and their current states, routing information required to reach the destination, the current ego state, and/or any other suitable information; determining a latent space representation based on the set of input and determining a full environmental representation based on the latent space representation; selecting a first learning module based on the context of the agent...the 1.sup.st learning module includes a deep Q-learning network trained based on an inverse reinforcement learning algorithm; selecting an action for the agent with the 1.sup.st learning module and the full environmental representation...Each of the learning modules is further preferably trained with inverse reinforcement learning, which functions to determine a reward function and/or an optimal driving policy for each of the context-aware learning modules).
Therefore, it would have been obvious to one of ordinary skill in the art, before the effective filing date of the claimed invention to have modified the system set forth in Li to contain a system for wherein the deep learning network is trained through deep reinforcement learning based on a state for an ego vehicle and the surrounding object, an action of identifying and classifying a class based on the state, and a reward generated based on results of the action with reasonable expectation of success. One of ordinary skill in the art would have been motivated to make such a modification for benefit of improving the the safety of the vehicle by implementing deep learning approaches (see at least Narang [English Translation C3 L35-40] the system and/or method confer the benefit of capturing the flexibility of machine learning (e.g., deep learning) approaches while ensuring safety and maintaining a level of interpretability and/or explainability).
Regarding Claim 20, Li teaches all limitations of Claim 16 as set forth above. Li further teaches wherein, to generate the class prediction decision value, the at least one processor causes the computer device to generate the class prediction decision value by identifying and classifying a surrounding object in the driving environment using a trained deep learning network, in order to provide a high level decision maker function (see at least Li [English Translation pg.10 para.10-11, pg.2 para.5] using the depth learning algorithm to predict the movement state of the obstacle around the vehicle. when predicting the movement state of the obstacle around the vehicle, it also can use the history information of the obstacle, and the related relation of the obstacle and the lane...the present specification provides a control method of an automatic driving vehicle...when using a plurality of obstacle sensing device detects the obstacle around the vehicle, it can carry out multi-obstacle sensing device fusion, namely can the plurality of multi-obstacle sensing device obtains the data information set together for comprehensive analysis, so as to more accurately; reliably describing the external environment around the vehicle, so as to improve the correctness of the system speed decision).
However, Li does not explicitly teach wherein the deep learning network is trained through deep reinforcement learning based on a state for an ego vehicle and the surrounding object, an action of identifying and classifying a class based on the state, and a reward generated based on results of the action, or is trained through supervised machine learning that generates a trajectory through search-based model predictive control-based planning using a state transmitted from a simulator for an arbitrary driving environment, generates classification data by identifying and classifying classes of surrounding objects based on the generated trajectory, and stores the same in a dataset.
Narang, in the same field as the endeavor teaches wherein the deep learning network is trained through deep reinforcement learning based on a state for an ego vehicle and the surrounding object, an action of identifying and classifying a class based on the state, and a reward generated based on results of the action, or is trained through supervised machine learning that generates a trajectory through search-based model predictive control-based planning using a state transmitted from a simulator for an arbitrary driving environment, generates classification data by identifying and classifying classes of surrounding objects based on the generated trajectory, and stores the same in a dataset (see at least Narang [English Translation C28 L39-60, C16 L40-50] the method 200 includes: receiving a set of inputs, wherein the set of inputs includes a high definition, labeled (e.g., hand-labeled, automatically-labeled, etc.) map which prescribes the context of the autonomous agent at any given time based on its location and/or orientation (e.g., pose) within the map, a set of detected dynamic objects and associated information (e.g., current position, size, previous path, and predicted path into the future), a set of all static objects and their current states, routing information required to reach the destination, the current ego state, and/or any other suitable information; determining a latent space representation based on the set of input and determining a full environmental representation based on the latent space representation; selecting a first learning module based on the context of the agent...the 1.sup.st learning module includes a deep Q-learning network trained based on an inverse reinforcement learning algorithm; selecting an action for the agent with the 1.sup.st learning module and the full environmental representation...Each of the learning modules is further preferably trained with inverse reinforcement learning, which functions to determine a reward function and/or an optimal driving policy for each of the context-aware learning modules).
Therefore, it would have been obvious to one of ordinary skill in the art, before the effective filing date of the claimed invention to have modified the system set forth in Li to contain a system for wherein the deep learning network is trained through deep reinforcement learning based on a state for an ego vehicle and the surrounding object, an action of identifying and classifying a class based on the state, and a reward generated based on results of the action, or is trained through supervised machine learning that generates a trajectory through search-based model predictive control-based planning using a state transmitted from a simulator for an arbitrary driving environment, generates classification data by identifying and classifying classes of surrounding objects based on the generated trajectory, and stores the same in a dataset with reasonable expectation of success. One of ordinary skill in the art would have been motivated to make such a modification for benefit of improving the the safety of the vehicle by implementing deep learning approaches (see at least Narang [English Translation C3 L35-40] the system and/or method confer the benefit of capturing the flexibility of machine learning (e.g., deep learning) approaches while ensuring safety and maintaining a level of interpretability and/or explainability).
Claim 7 is rejected under 35 U.S.C. 103 as being unpatentable over Li et al (CN 112498366 A) in view of Narang et al (US 11124204 B1) and Wu et al (WO 2023024542 A1). Hereafter referred to as Li, Narang, and Wu respectively.
Regarding Claim 7, Li in view of Narang teaches all limitations of Claim 6 as set forth above. However, Li does not explicitly teach wherein longitudinal constraints of convex nature of model predictive control-based planning are determined through class identification and classification that is the action,
a trajectory is generated based on the longitudinal constraints through the model predictive control-based planning
Wu, in the same field as the endeavor, teaches wherein longitudinal constraints of convex nature of model predictive control-based planning are determined through class identification and classification that is the action (see at least Wu [English Translation pg.12 para.4] based on the target convex-hull obstacle information, label the target convex-hull obstacle that satisfies the preset filtering conditions with no avoidance label or no lateral avoidance label, including: when the target convex-hull obstacle is outside the road, mark the target convex-hull obstacle Label the obstacle without avoidance; when the movement state of the obstacle with convex hull meets the condition of avoidance without lateral avoidance or the obstacle with convex hull is located on the leading line of the vehicle, label the obstacle with avoidance without lateral avoidance...The trajectory of the detour can be marked on the pedestrian without a lateral avoidance label; another example is that the target convex obstacle changes lanes to the vehicle lane, or the longitudinal speed of the target convex obstacle is greater than the vehicle speed)
a trajectory is generated based on the longitudinal constraints through the model predictive control-based planning (see at least Wu [English Translation pg.4 para.10, pg.12 para.4, pg.14 para.5] to accelerate the generation of driving trajectories and realize fast avoidance of obstacles…The trajectory of the detour can be marked on the pedestrian without a lateral avoidance label; another example is that the target convex obstacle changes lanes to the vehicle lane, or the longitudinal speed of the target convex obstacle is greater than the vehicle speed...the environmental perception information includes the position information of the vehicle and the longitudinal velocity information of the vehicle, as well as the obstacle position information and the longitudinal velocity information of the obstacle closest to the vehicle in each lane...When the longitudinal speed of the obstacle is less than the longitudinal speed of the vehicle, according to the longitudinal distance, the longitudinal speed information of the vehicle and the longitudinal speed information of the obstacle, the collision time when the vehicle collides with the obstacle in front is predicted, and the collision time is determined as the passing time cost).
Therefore, it would have been obvious to one of ordinary skill in the art, before the effective filing date of the claimed invention to have modified the system set forth in Li to contain a system for wherein longitudinal constraints of convex nature of model predictive control-based planning are determined through class identification and classification that is the action and a trajectory is generated based on the longitudinal constraints through the model predictive control-based planning with reasonable expectation of success. One of ordinary skill in the art would have been motivated to make such a modification for benefit of improve the speed at which future trajectories can be generated and at which obstacles can be detected (see at least Wu [English Translation pg.4 para.10] the technical solutions provided by the embodiments of the present disclosure have the following advantages: to accelerate the generation of driving trajectories and realize fast avoidance of obstacles).
Further, Li does not explicitly teach wherein the reward for at least one of success, collision, failure, and driving performance of the generated trajectory is computed through evaluation for the generated trajectory.
Narang, in the same field as the endeavor, teaches the reward for at least one of success, collision, failure, and driving performance of the generated trajectory is computed through evaluation for the generated trajectory (see at least Narang [C16 L40-50, C26 L45-50] functions to determine a reward function and/or an optimal driving policy for each of the context-aware learning modules. The output of this training is further preferably a compact fully-connected network model that represents the reward function and an optimal policy for each learning module…These constraints are used to build the localized environmental representation around the safety tunnel which is used as an input to the network, wherein the DTN is trained on the trajectory from the training data).
Therefore, it would have been obvious to one of ordinary skill in the art, before the effective filing date of the claimed invention to have modified the system set forth in Li to contain a system for wherein the reward for at least one of success, collision, failure, and driving performance of the generated trajectory is computed through evaluation for the generated trajectory with reasonable expectation of success. One of ordinary skill in the art would have been motivated to make such a modification for benefit of improving the training of the learning of the vehicle as discussed in Narang (see at least Narang [English Translation C3 L63-67] the system and/or method confers the benefit of utilizing an awareness of the vehicle's context to hypertune loss functions of the learning modules to these particular contexts when training them).
Claim 8 is rejected under 35 U.S.C. 103 as being unpatentable over Li et al (CN 112498366 A) in view of Palanisamy et al (US 20190278282 A1). Hereafter referred to as Li and Palanisamy respectively.
Regarding Claim 8, Li teaches all limitations of Claim 5 as set forth above. However, Li does not explicitly teach wherein the deep learning network is trained through supervised machine learning using a dataset generated by a search-based model predictive control-based planning, the search-based model predictive control-based planning generating a trajectory using a state transmitted from a simulator for an arbitrary driving environment, generating classification data by identifying and classifying classes of surrounding objects based on the generated trajectory, and storing the classification data in a dataset.
Palanisamy, in the same field as the endeavor, teaches wherein the deep learning network is trained through supervised machine learning using a dataset generated by a search-based model predictive control-based planning, the search-based model predictive control-based planning generating a trajectory using a state transmitted from a simulator for an arbitrary driving environment, generating classification data by identifying and classifying classes of surrounding objects based on the generated trajectory, and storing the classification data in a dataset (see at least Palanisamy [¶ 65, 29, 38, 59, 33] The system is operative to use reinforcement learning (RL) to generate a control algorithm for autonomous vehicle control by applying deep reinforcement learning (DRL) methods to train a control algorithm that can autonomously learn how to approach and traverse an urban stop-sign intersection by collecting information on surrounding vehicles and the road...the computer 64 can maintain a searchable database and database management system that permits entry, removal, and modification of data as well as the receipt of requests to locate data within the database…Object position within a map is represented by a Gaussian probability distribution centered around the object's predicted path…A path planning module 50 processes and synthesizes the object prediction output 39, the interpreted output 49, and additional routing information 79 received from an online database or live expert of the remote access center 78 to determine a vehicle path to be followed to maintain the vehicle on the desired route while obeying traffic laws and avoiding any detected obstacles…A classification and segmentation module 36 receives the preprocessed sensor output 35 and performs object classification, image classification, traffic light classification, object segmentation, ground segmentation, and object tracking processes. Object classification includes, but is not limited to, identifying and classifying objects in the surrounding environment including identification and classification of traffic signals and signs).
Therefore, it would have been obvious to one of ordinary skill in the art, before the effective filing date of the claimed invention to have modified the system set forth in Li to contain a system for wherein the deep learning network is trained through supervised machine learning using a dataset generated by a search-based model predictive control-based planning, the search-based model predictive control-based planning generating a trajectory using a state transmitted from a simulator for an arbitrary driving environment, generating classification data by identifying and classifying classes of surrounding objects based on the generated trajectory, and storing the classification data in a dataset with reasonable expectation of success. One of ordinary skill in the art would have been motivated to make such a modification for benefit of improving the autonomous driving of the vehicle at intersections by implementing deep learning trained through reinforcement as discussed in Palanisamy (see at least Palanisamy [¶ 65] The system is operative to use reinforcement learning (RL) to generate a control algorithm for autonomous vehicle control by applying deep reinforcement learning (DRL) methods to train a control algorithm that can autonomously learn how to approach and traverse an urban stop-sign intersection by collecting information on surrounding vehicles and the road).
Claim 9 is rejected under 35 U.S.C. 103 as being unpatentable over Li et al (CN 112498366 A) in view of Palanisamy et al (US 20190278282 A1), Funke et al (US 11999380 B1), and Dix et al (US 20210365036 A1). Hereafter referred to as Li, Palanisamy, Funke, and Dix respectively.
Regarding Claim 9, Li in view of Palanisamy teaches all limitations of Claim 8 as set forth above. However, Li does not explicitly teach wherein the search-based model predictive control-based planning combines an A* algorithm with model predictive control-based planning, where the A* algorithm supports MPP(Model Predictive Planning) convergence and enables convexification.
Funke, in the same field as the endeavor, teaches wherein the search-based model predictive control-based planning combines an A* algorithm with model predictive control-based planning (see at least Funke [C23 L23-27, C9 L30-43] Graph traversal algorithms can include algorithms for unweighted graphs (e.g., breadth first search, depth first search, greedy best first, A* search, etc.) and/or weighted graphs (e.g., Dijkstra's algorithm, weighted A* search, etc.)...By taking trajectory inconsistency into account as a cost or other factor within temporal optimization, the resulting optimized trajectories for the vehicle 102 may provide improved efficiency and vehicle safety. For example, selecting trajectories with greater consistency may result in improved passenger comfort metrics (e.g., less vehicle jerkiness, fewer instances of rapid acceleration or deceleration, etc.) and fewer potential vehicle safety hazards. Additionally, trajectories with greater consistency may improve computational efficiency and reduce process loading for vehicle navigation systems such as object detection, trajectory prediction, and object tracking).
Dix, in the same field as the endeavor, teaches where the A* algorithm supports MPP(Model Predictive Planning) convergence and enables convexification (see at least Dix [¶ 48, 21, 57] vehicle control system 110 may implement a pathfinding algorithm such as Dijkstra's algorithm, A* search algorithm, D* search algorithm, RRT algorithm, and/or the like...a vehicle control system associated with a first vehicle may model both the first vehicle and an obstacle as a positive magnetic monopole, thereby generating a modeled repulsive force between the first vehicle and the obstacle that may be used to facilitate obstacle avoidance (e.g., because the first vehicle and the obstacle have a modeled repulsion from one another). In various embodiments, the vehicle control system uses the modeled repulsive field to facilitate path planning....vehicle control system 110 optimizes repulsive fields by converting concave repulsive fields into convex repulsive fields (e.g., determining the smallest possible convex repulsive field that will encapsulate the concave repulsive field, etc.). Additionally or alternatively, vehicle control system 110 may optimize repulsive fields by analyzing obstacle model 600. For example, vehicle control system 110 may determine a test route between first vehicle 630 and second vehicle 620 and generate a repulsive field that steers first vehicle 630 away from an obstacle along the test route).
Therefore, it would have been obvious to one of ordinary skill in the art, before the effective filing date of the claimed invention to have modified the system set forth in Li to contain a system for wherein the search-based model predictive control-based planning combines an A* algorithm with model predictive control-based planning, where the A* algorithm supports MPP(Model Predictive Planning) convergence and enables convexification with reasonable expectation of success. One of ordinary skill in the art would have been motivated to make such a modification for benefit of improving the predictive control of the vehicle by employing algorithms commonly used in the art.
Claim 10 is rejected under 35 U.S.C. 103 as being unpatentable over Li et al (CN 112498366 A) in view of Palanisamy et al (US 20190278282 A1) and Blaes et al (US 12221115 B1). Hereafter referred to as Li, Palanisamy, and Blaes respectively.
Regarding Claim 10, Li in view of Palanisamy teaches all limitations of Claim 8 as set forth above. However, Li does not explicitly teach wherein the deep learning network is trained using the classification data as ground truth.
Blaes, in the same field as the endeavor, teaches wherein the deep learning network is trained using the classification data as ground truth (see at least Blaes [C3 L19-33] a machine learning model (e.g., deep neural network or convolutional neural network) may be trained to output semantic information and/or state information by reviewing data logs to identify sensor data representing objects in an environment. In some cases, the objects can be identified, and attributes can be determined for the object (e.g., a pedestrian, a vehicle, a bicyclist, etc.) and the environment, and data representing the objects can be identified as training data. The training data can be input to a machine learning model where a known result (e.g., a ground truth, such as a known bounding box, velocity information, pose information, classification, etc.) can be used to adjust weights and/or parameters of the machine learning model to minimize a loss or error).
Therefore, it would have been obvious to one of ordinary skill in the art, before the effective filing date of the claimed invention to have modified the system set forth in Li to contain a system for wherein the deep learning network is trained using the classification data as ground truth with reasonable expectation of success. One of ordinary skill in the art would have been motivated to make such a modification for benefit of minimizing loss or error as discussed in Blaes (see at least Blaes [C3 L19-33] The training data can be input to a machine learning model where a known result (e.g., a ground truth, such as a known bounding box, velocity information, pose information, classification, etc.) can be used to adjust weights and/or parameters of the machine learning model to minimize a loss or error).
Claim 11 is rejected under 35 U.S.C. 103 as being unpatentable over Li et al (CN 112498366 A) in view of Palanisamy et al (US 20190278282 A1), Blaes et al (US 12221115 B1) and Nishitani et al (US 20210001857 A1). Hereafter referred to as Li, Palanisamy, Blaes, and Nishitani respectively.
Regarding Claim 11, Li in view of Palanisamy and Blaes teaches all limitations of Claim 10 as set forth above. However, Li does not explicitly teach wherein the deep learning network is trained through a random batch of the dataset.
Nishitani, in the same field as the endeavor, teaches wherein the deep learning network is trained through a random batch of the dataset (see at least Nishitani [¶ 77] during training of the deep merging network 620 (e.g., Q-network), instead of using the current experience in standard temporal-difference learning (TD-learning), the deep merging network 620 is trained by sampling (e.g., uniformly at random) mini-batches of experiences s, α, r, s′ from the experience replay memory (e.g., replay database 740)).
Therefore, it would have been obvious to one of ordinary skill in the art, before the effective filing date of the claimed invention to have modified the system set forth in Li to contain a system for wherein the deep learning network is trained through a random batch of the dataset with reasonable expectation of success. One of ordinary skill in the art would have been motivated to make such a modification for benefit of using a training technique for deep learning that is commonly used in the art.
Claim 12 is rejected under 35 U.S.C. 103 as being unpatentable over Li et al (CN 112498366 A) in view of Palanisamy et al (US 20190278282 A1) and Pronovost (US 12434737 B2). Hereafter referred to as Li, Palanisamy, and Pronovost respectively.
Regarding Claim 12, Li in view of Palanisamy teaches all limitations of Claim 8 as set forth above. However, Li does not explicitly teach wherein the search-based model predictive control-based planning sets constraints by generating the trajectory and identifying and classifying the surrounding object through a heuristic method.
Pronovost, in the same field as the endeavor, teaches wherein the search-based model predictive control-based planning sets constraints by generating the trajectory and identifying and classifying the surrounding object through a heuristic method (see at least Pronovost [C8 L36-45, C25 L30-37] To determine the subset of objects associated with the agent 110, the prediction component 104 may use a number of techniques including heuristics and/or machine-learning models. For example, the prediction component 104 may use one or more heuristics based on object type, object size, object distance from the agent 110, orientation offset relative to the agent 110, and/or velocity offset relative to the agent 110, to determine a fixed-sized (n) subset of objects that are likely to be relevant to the agent 110...the vehicle 702 can be controlled based at least in part on the maps 724. That is, the maps 724 can be used in connection with the localization component 720, the perception component 722, and/or the planning component 730 to determine a location of the vehicle 702, identify objects in an environment, and/or generate routes and/or trajectories to navigate within an environment).
Therefore, it would have been obvious to one of ordinary skill in the art, before the effective filing date of the claimed invention to have modified the system set forth in Li to contain a system for wherein the search-based model predictive control-based planning sets constraints by generating the trajectory and identifying and classifying the surrounding object through a heuristic method with reasonable expectation of success. One of ordinary skill in the art would have been motivated to make such a modification for benefit of improving the flexibility of the vehicle while predicting trajectories as discussed in Pronovost (see at least Pronovost [C6 L17-18] The techniques herein also provide improved flexibility when predicting agent trajectories over periods of time).
Claims 13-15 are rejected under 35 U.S.C. 103 as being unpatentable over Li et al (CN 112498366 A) in view of Levinson et al (US 20170123429 A1). Hereafter referred to as Li and Levinson respectively.
Regarding Claim 13, Li teaches all limitations of Claim 1 as set forth above. However, Li does not explicitly teach wherein the generating of the main trajectory comprises generating the main trajectory using model predictive control-based planning among optimization-based planning methods.
Levinson, in the same field as the endeavor, teaches wherein the generating of the main trajectory comprises generating the main trajectory using model predictive control-based planning among optimization-based planning methods (see at least Levinson [¶ 60, 66] a planner of an autonomous vehicle controller may calculate and evaluate large numbers of trajectories (e.g., thousands or greater) per unit time, such as a second. In some embodiments, candidate trajectories are a subset of the trajectories that provide for relatively higher confidence levels that an autonomous vehicle may move forward safely in view of the event...the classification type can be used to predict or otherwise determine the likelihood that an external object may, for example, interfere with an autonomous vehicle traveling along a planned path).
Therefore, it would have been obvious to one of ordinary skill in the art, before the effective filing date of the claimed invention to have modified the system set forth in Li to contain a system for wherein the generating of the main trajectory comprises generating the main trajectory using model predictive control-based planning among optimization-based planning methods with reasonable expectation of success. One of ordinary skill in the art would have been motivated to make such a modification for benefit of improving trajectory generation to improve the safe travel of the vehicle as discussed in Levinson (see at least Levinson [¶ 60, 72] candidate trajectories are a subset of the trajectories that provide for relatively higher confidence levels that an autonomous vehicle may move forward safely in view of the event…assist planner 464 in planning routes and generating trajectories by identifying objects of interest in a surrounding environment in which autonomous vehicle 430 is transiting. Further, probabilities may be associated with each of the object of interest, whereby a probability may represent a likelihood that an object of interest may be a threat to safe travel).
Regarding Claim 14, Li teaches all limitations of Claim 1 as set forth above. However, Li does not explicitly teach generating, by the at least one processor, a contingency trajectory through the observation value for the driving environment.
Levinson, in the same field as the endeavor, teaches generating, by the at least one processor, a contingency trajectory through the observation value for the driving environment (see at least Levinson [¶ 150] Trajectory generator 3624 may be configured to generate data representing a trajectory with which to control motion of the autonomous vehicle based on the path data, and generate data representing a contingent trajectory. According to various examples, a trajectory provides for intermediate navigation of an autonomous vehicle (e.g. incrementally from road segment portion to road segment, such as along a first 200 m trajectory to the next), whereas a contingent trajectory may provide, for example, a trajectory that directs an autonomous vehicle in a “safe-stop” maneuver).
Therefore, it would have been obvious to one of ordinary skill in the art, before the effective filing date of the claimed invention to have modified the system set forth in Li to contain a system for generating, by the at least one processor, a contingency trajectory through the observation value for the driving environment. with reasonable expectation of success. One of ordinary skill in the art would have been motivated to make such a modification for benefit of improving trajectory generation to improve the safe travel of the vehicle as discussed in Levinson (see at least Levinson [¶ 60, 72] candidate trajectories are a subset of the trajectories that provide for relatively higher confidence levels that an autonomous vehicle may move forward safely in view of the event…assist planner 464 in planning routes and generating trajectories by identifying objects of interest in a surrounding environment in which autonomous vehicle 430 is transiting. Further, probabilities may be associated with each of the object of interest, whereby a probability may represent a likelihood that an object of interest may be a threat to safe travel).
Regarding Claim 15, Li in view of Levinson teaches all limitations of Claim 14 as set forth above. However, Li does not explicitly teach determining, by the at least one processor, one of the main trajectory and the contingency trajectory as a final trajectory.
Levinson, in the same field as the endeavor, teaches determining, by the at least one processor, one of the main trajectory and the contingency trajectory as a final trajectory (see at least Levinson [¶ 67] Planner 364 selects an optimal trajectory based on a variety of criteria over which to direct the autonomous vehicle in way that provides for collision-free travel).
Therefore, it would have been obvious to one of ordinary skill in the art, before the effective filing date of the claimed invention to have modified the system set forth in Li to contain a system for determining, by the at least one processor, one of the main trajectory and the contingency trajectory as a final trajectory with reasonable expectation of success. One of ordinary skill in the art would have been motivated to make such a modification for benefit of improving trajectory generation and selection to improve the safe travel of the vehicle as discussed in Levinson (see at least Levinson [¶ 60, 72] candidate trajectories are a subset of the trajectories that provide for relatively higher confidence levels that an autonomous vehicle may move forward safely in view of the event…assist planner 464 in planning routes and generating trajectories by identifying objects of interest in a surrounding environment in which autonomous vehicle 430 is transiting. Further, probabilities may be associated with each of the object of interest, whereby a probability may represent a likelihood that an object of interest may be a threat to safe travel).
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to JOSEPH A YANOSKA whose telephone number is (703)756-5891. The examiner can normally be reached M-F 9:00am to 5:00pm (Pacific Time).
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, Rachid Bendidi can be reached on (571) 272-4896. 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.
/JOSEPH ANDERSON YANOSKA/Examiner, Art Unit 3664
/RACHID BENDIDI/Supervisory Patent Examiner, Art Unit 3664
Prosecution Insights