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 .
Response to Arguments
Regarding the previous 35 U.S.C. 103 rejection, Applicant’s arguments with respect to claims have been considered but are moot because the new ground of rejection does not rely on the combination of references applied in the prior rejection of record for any teaching or matter specifically challenged in the arguments. A new ground of rejection is made in view of US 20210300350 (“Yasui”) necessitated by amendment.
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.
Claim(s) 1, 3, 5, 7 is/are rejected under 35 U.S.C. 103 as being unpatentable over US 20200064842 (“Kentley”) in view of US 20220185295 (“Zheng”) and US 20210300350 (“Yasui”).
As per claim(s) 1, Kentley discloses a control device comprising:
a storage that stores a plurality of trained control models (see at least [0048]: vehicle system 202 may include memory 206), and
a controller (see at least [0016]: a vehicle controller that includes one or more machine-learning models);
wherein the controller is configured to perform:
generating one or more paths by performing calculations on one or more trained control models of the plurality of trained control models (see at least [0016]: a vehicle controller that includes one or more machine-learning models…ML models of the vehicle controller may be configured to perform various operations such as, for example, localizing the autonomous vehicle, detecting objects, classifying objects, tracking objects, generating trajectories, selecting one or more trajectories for controlling the autonomous vehicle),
selecting one path from the generated one or more paths according to a result of monitoring the behavior of the target user (see at least [0016]: a vehicle controller that includes one or more machine-learning models…ML models of the vehicle controller may be configured to perform various operations such as, for example, localizing the autonomous vehicle, detecting objects, classifying objects, tracking objects, generating trajectories, selecting one or more trajectories for controlling the autonomous vehicle), and
controlling a movement of a mobile body according to the selected path (see at least [0016]: a vehicle controller that includes one or more machine-learning models…ML models of the vehicle controller may be configured to perform various operations such as, for example, localizing the autonomous vehicle, detecting objects, classifying objects, tracking objects, generating trajectories, selecting one or more trajectories for controlling the autonomous vehicle, [0061]: ML models configured to perform various operations such as, for example, localizing the autonomous vehicle, detecting objects, classifying objects, tracking objects, generating trajectories, selecting one or more trajectories for controlling the autonomous vehicle).
Kentley does not explicitly disclose monitoring a behavior of a target user; wherein each of the plurality of trained control models has acquired an ability to generate a path for controlling a movement of the mobile body related to a corresponding behavior of a user by machine learning.
However, Zheng teaches monitoring a behavior of a target user (see at least [0134]: Recorded human driving data 430 are utilized to train models so that the models can capture characteristics related to motion planning that are more human-like);
wherein each of the plurality of trained control models has acquired an ability to generate a plan for controlling a movement of the mobile body related to a corresponding behavior of a user by machine learning (see at least [0114]: personalized motion planning (e.g., not only with respect to sub-categories but also with respect to individuals), [0135]: individual passenger models 1430 may also include models that characterize impact of vehicle motions on individual passengers observed from the reaction or feedback of passengers, [0136]: To obtain impact based models for individuals, the real-time data 480, which capture the passenger characteristics in terms of their behavioral, visual, acoustic cues as well as their conditions (including mental, physical and functional states during vehicle movement), may be segmented based on individuals and such segmented data may then be used to derive models that characterize how certain motions impact passengers, [0145]: achieve human-like lane planning behavior, large volume of human driving data are collected and used to train lane control models that, when used for lane planning, are to exhibit human-like behavior in maneuvering the vehicles. Although the lane detection models and the lane planning models are trained separately, in operation, the two sets of models are used in a cascade manner for inference in order to produce robust behavior in diverse types of environment or conditions with human-like operational behavior).
It would have been obvious to one of ordinary skill in the art before the effective filing date to provide the invention as disclosed by Kentley by incorporating the teachings of Zheng with a reasonable expectation of success in order to characterize preferences of individuals.
Kentley does not explicitly disclose generating one or more paths by performing calculated on all of the plurality of trained control models that are likely to be used regardless of whether or not each of the plurality of trained control models is used.
However, Yasui teaches generating one or more paths by performing calculated on all of the plurality of trained control models that are likely to be used regardless of whether or not each of the plurality of trained control models is used (see at least [0097]: target trajectory generator 146 inputs the risk area RA calculated by the risk area calculator 144 to each of the plurality of DNN models MDL2, and generates one or more target trajectories TR on the basis of an output result of each DNN model MDL2 to which the risk area RA is input, [0115]: target trajectory generator 146 generates a plurality of target trajectories TR by using the DNN model MDL2 defined by the DNN model data 184 (step S106), [0117]: when four DNN models MDL2 are defined by the DNN model data 184, the target trajectory generator 146 inputs the risk area RA calculated by the risk area calculator 144 in the process of S102 to each of the four DNN models MDL2. In response to this, each DNN model MDL2 outputs one target trajectory TR. That is, as shown in FIG. 13, the total four target trajectories TR such as TR1, TR2, TR3, and TR4 are generated).
It would have been obvious to one of ordinary skill in the art before the effective filing date to provide the invention as disclosed by Kentley by incorporating the teachings of Yasui with a reasonable expectation of success in order to more safely control driving of a vehicle.
As per claim(s) 3, Kentley does not explicitly disclose wherein the plurality of trained control models include one or more second trained control models, each of which has acquired an ability to generate a path in a situation with corresponding instructions by the user, and the selecting one path includes selecting a path generated by any of the one or more second trained control models in response to instructions by the target user.
However, Zheng teaches wherein the plurality of trained control models include one or more second trained control models, each of which has acquired an ability to generate a path in a situation with corresponding instructions by the user (see at least [0099]: route selection engine 1230 may also take the preferences estimated by the route selection preference determiner 1030 as input and use that in its route selection operation. In some embodiments, the route selection engine 1230 may rely on the preferences from 1030 without considering the personalized preferences of a driver, i.e., it may rely on merely the preferences identified by the route selection preference determiner 1030 in its route selection), and
the selecting one path includes selecting a path generated by any of the one or more second trained control models in response to instructions by the target user (see at least [0099]: route selection engine 1230 may also take the preferences estimated by the route selection preference determiner 1030 as input and use that in its route selection operation. In some embodiments, the route selection engine 1230 may rely on the preferences from 1030 without considering the personalized preferences of a driver, i.e., it may rely on merely the preferences identified by the route selection preference determiner 1030 in its route selection).
It would have been obvious to one of ordinary skill in the art before the effective filing date to provide the invention as disclosed by Kentley by incorporating the teachings of Zheng with a reasonable expectation of success in order to provide improved vehicle control.
As per claim(s) 5, Kentley does not explicitly disclose wherein the controller is configured to further perform evaluating a safety degree of each of the generated one or more paths, and the selecting one path comprises selecting one path from the generated one or more paths after excluding a path evaluated as having a low safety degree.
However, Yasui teaches wherein the controller is configured to further perform evaluating a safety degree of each of the generated one or more paths (see at least [0119]: since the DNN model MDL2 stochastically determines the target trajectory TR, it is not possible to deny the possibility of generation of a trajectory that passes through an area where the risk potential p is higher than the threshold value Th, [0120]: target trajectory generator 146 determines whether the generated each target trajectory TR exists outside or inside the travelable area DA calculated using the rule-based model MDL1, excludes target trajectories TR outside the travelable area DA, and leaves target trajectories TR inside the travelable area DA), and
the selecting one path comprises selecting one path from the generated one or more paths after excluding a path evaluated as having a low safety degree (see at least [0123]: select a target trajectory TR having the highest evaluation as the optimal target trajectory TR).
It would have been obvious to one of ordinary skill in the art before the effective filing date to provide the invention as disclosed by Kentley by incorporating the teachings of Yasui with a reasonable expectation of success in order to more safely control driving of a vehicle.
As per claim(s) 7, Kentley discloses wherein the plurality of trained control models include a first trained control model that has acquired an ability to generate a path in a situation without instructions by the user (see at least [0016]: a vehicle controller that includes one or more machine-learning models…ML models of the vehicle controller may be configured to perform various operations such as, for example, localizing the autonomous vehicle, detecting objects, classifying objects, tracking objects, generating trajectories, selecting one or more trajectories for controlling the autonomous vehicle).
Kentley does not explicitly disclose
wherein the plurality of trained control models include a first trained control model that has acquired an ability to generate a path in a situation without instructions by the user, and
one or more second trained control models, each of which has acquired an ability to generate a path in a situation with corresponding instructions by the user, and
the controller is configured to further perform evaluating a safety degree of each of the generated one or more paths,
the selecting one path comprises:
excluding a path of a second trained control model corresponding to a specific instruction by the target user, the path being evaluated as having a low safety degree; and
in response to the path evaluated as having the low safety degree being excluded, selecting a path generated by the first trained control model from the generated one or more paths.
However, Yasui teaches wherein the plurality of trained control models include a first trained control model that has acquired an ability to generate a path in a situation without instructions by the user, the controller is configured to further perform evaluating a safety degree of each of the generated one or more paths, the selecting one path comprises: excluding a path of a second trained control model, the path being evaluated as having a low safety degree; and in response to the path evaluated as having the low safety degree being excluded, selecting a path generated by the first trained control model from the generated one or more paths (see at least [0119]: since the DNN model MDL2 stochastically determines the target trajectory TR, it is not possible to deny the possibility of generation of a trajectory that passes through an area where the risk potential p is higher than the threshold value Th, [0120]: target trajectory generator 146 determines whether the generated each target trajectory TR exists outside or inside the travelable area DA calculated using the rule-based model MDL1, excludes target trajectories TR outside the travelable area DA, and leaves target trajectories TR inside the travelable area DA, [0123]: select a target trajectory TR having the highest evaluation as the optimal target trajectory TR).
It would have been obvious to one of ordinary skill in the art before the effective filing date to provide the invention as disclosed by Kentley by incorporating the teachings of Yasui with a reasonable expectation of success in order to more safely control driving of a vehicle.
However, Zheng teaches one or more second trained control models, each of which has acquired an ability to generate a path in a situation with corresponding instructions by the user (see at least [0099]: route selection engine 1230 may also take the preferences estimated by the route selection preference determiner 1030 as input and use that in its route selection operation. In some embodiments, the route selection engine 1230 may rely on the preferences from 1030 without considering the personalized preferences of a driver, i.e., it may rely on merely the preferences identified by the route selection preference determiner 1030 in its route selection, [0114]: personalized motion planning (e.g., not only with respect to sub-categories but also with respect to individuals), [0125]: trump the estimated desire (of the passenger) to be faster in order to ensure safety of the children, [0134]: Recorded human driving data 430 are utilized to train models so that the models can capture characteristics related to motion planning that are more human-like, [0135]: individual passenger models 1430 may also include models that characterize impact of vehicle motions on individual passengers observed from the reaction or feedback of passengers, [0136]: To obtain impact based models for individuals, the real-time data 480, which capture the passenger characteristics in terms of their behavioral, visual, acoustic cues as well as their conditions (including mental, physical and functional states during vehicle movement), may be segmented based on individuals and such segmented data may then be used to derive models that characterize how certain motions impact passengers, [0145]: achieve human-like lane planning behavior, large volume of human driving data are collected and used to train lane control models that, when used for lane planning, are to exhibit human-like behavior in maneuvering the vehicles. Although the lane detection models and the lane planning models are trained separately, in operation, the two sets of models are used in a cascade manner for inference in order to produce robust behavior in diverse types of environment or conditions with human-like operational behavior).
It would have been obvious to one of ordinary skill in the art before the effective filing date to provide the invention as disclosed by Kentley by incorporating the teachings of Zheng with a reasonable expectation of success in order to characterize preferences of individuals.
Further, Zheng teaches excluding a motion plan corresponding to a specific instruction by the target user (see at least [0125]: motion planned may need to be based on safety…trump the estimated desire (of the passenger) to be faster in order to ensure safety of the children…if the current vehicle motion is already pretty fast and the passenger keeps demanding to be even faster, given the age and known health condition of the passenger, the motion planning module may use such information to make an appropriate motion planning decision).
It would have been obvious to one of ordinary skill in the art before the effective filing date to provide the invention as disclosed by Kentley by incorporating the teachings of Zheng with a reasonable expectation of success in order for improved safety.
Claim(s) 2 is/are rejected under 35 U.S.C. 103 as being unpatentable over Kentley in view of Zheng and Yasui, and further in view of US 20220034678 (“Chintakindi”).
As per claim(s) 2, Kentley discloses wherein the plurality of trained control models include a first trained control model that has acquired an ability to generate a path in a situation without instructions by the user, and the selecting one path includes selecting a path generated by the first trained control model in an absence of instructions from the target user (see at least [0016]: a vehicle controller that includes one or more machine-learning models…ML models of the vehicle controller may be configured to perform various operations such as, for example, localizing the autonomous vehicle, detecting objects, classifying objects, tracking objects, generating trajectories, selecting one or more trajectories for controlling the autonomous vehicle) but Kentley does not explicitly disclose a target user
However, Chintakindi teaches a first trained control model that has acquired an ability to generate a path in a situation without instructions by the user, and the selecting one path includes selecting a path generated by the first trained control model in an absence of instructions from the target user (see at least [0135]: driver frustration level may be determined using one or more sensors (e.g., in the vehicle, outside the vehicle, as part of the driver's smartphone, or the like), based on feedback from the driver (e.g., by providing input in a user interface, by speaking their current frustration level), or the like. The driver frustration level may be monitored over a period of time, such as during a driving task, [0140]: prompt may comprise, for example, a request for approval to engage one or more autonomous driving algorithms, an indication of the frustration level of the user and a recommendation to use calming strategies, a prompt checking in to inquire as to the frustration level of the driver, information about a road segment currently traveled or projected to be traveled by the vehicle, or the like…If the driver does not respond to the prompt within a period of time, then it may be desirable to automatically select and/or engage the one or more autonomous driving algorithms).
It would have been obvious to one of ordinary skill in the art before the effective filing date to provide the invention as disclosed by Kentley by incorporating the teachings of Chintakindi with a reasonable expectation of success in order to improve driver frustration levels.
Claim(s) 4 is/are rejected under 35 U.S.C. 103 as being unpatentable over Kentley in view of Zheng and Yasui, and further in view of US 20180281819 (“Akaba”).
As per claim(s) 4, Kentley discloses wherein the mobile body is a vehicle (see at least abstract).
Kentley does not explicitly disclose the one or more second trained control models include a trained lane change model, and the selecting one path includes selecting a path generated by the trained lane change model in response to a lane change instruction by the target user.
However, Zheng teaches the one or more second trained control models include a trained lane change model (see at least [0156]: If the current task is for lane changing, then models for lane changing are to be used).
It would have been obvious to one of ordinary skill in the art before the effective filing date to provide the invention as disclosed by Kentley by incorporating the teachings of Zheng with a reasonable expectation of success in order to provide improved vehicle control.
However, Akaba teaches the selecting one path includes selecting a path generated by the trained lane change model in response to a lane change instruction by the target user (see at least [0089]: [0089]: when a movement distance D of the right hand Hr of the occupant P is equal to or more than a threshold value D2, the occupant command determination part 170 determines that a command to perform a lane change to a lane L2 on the right side of the travel lane L1 of the vehicle M is received. In this case, the action plan generation unit 123 generates a target trajectory 324 used for causing the vehicle M to perform a lane change to the lane L2. In this way, the occupant P performs a predetermined motion and thereby can perform automated driving in which the target trajectory is changed).
It would have been obvious to one of ordinary skill in the art before the effective filing date to provide the invention as disclosed by Kentley by incorporating the teachings of Akaba with a reasonable expectation of success in order to perform automated driving in which a target trajectory is changed by occupant preference and motion.
Claim(s) 6, 8 is/are rejected under 35 U.S.C. 103 as being unpatentable over Kentley in view of Zheng and Yasui, and further in view of US 20200023891 (“Lin”).
As per claim(s) 6, Kentley does not explicitly disclose wherein the controller is configured to further feed back to the target user that the path evaluated as having the low safety degree has been excluded in response to the path evaluated as having the low safety degree being excluded.
However, Lin teaches wherein the controller is configured to further feed back to the target user that the path evaluated as having the low safety degree has been excluded in response to the path evaluated as having the low safety degree being excluded (see at least [0043]: step of issuing a notification that none of the possible routes are system compliant routes is generally indicated by box 108 in FIG. 2. The computing device 40 may issue the notification in a suitable manner, such as but not limited to flashing a warning light, displaying a message to an occupant of the vehicle, transmitting a communication to a remote location, etc…when none of the possible routes are identified as a system compliant route, the computing device 40 may automatically park the vehicle in a suitable location, or transfer control of the vehicle to a human operator).
It would have been obvious to one of ordinary skill in the art before the effective filing date to provide the invention as disclosed by Kentley by incorporating the teachings of Lin with a reasonable expectation of success in order to improve driving safety.
As per claim(s) 8, Kentley does not explicitly disclose wherein the controller is configured to further perform: evaluating a safety degree of each of the generated one or more paths, excluding a path evaluated as having a low safety degree; in response to all of the generated one or more paths being excluded switching a control mode of the mobile body from an automatic control mode to a manual control mode; and outputting a notification prompting the target user to manually operate the mobile body.
However, Yasui teaches wherein the controller is configured to further perform: evaluating a safety degree of each of the generated one or more paths, excluding a path evaluated as having a low safety degree (see at least [0119]: since the DNN model MDL2 stochastically determines the target trajectory TR, it is not possible to deny the possibility of generation of a trajectory that passes through an area where the risk potential p is higher than the threshold value Th, [0120]: target trajectory generator 146 determines whether the generated each target trajectory TR exists outside or inside the travelable area DA calculated using the rule-based model MDL1, excludes target trajectories TR outside the travelable area DA, and leaves target trajectories TR inside the travelable area DA, [0123]: select a target trajectory TR having the highest evaluation as the optimal target trajectory TR).
It would have been obvious to one of ordinary skill in the art before the effective filing date to provide the invention as disclosed by Kentley by incorporating the teachings of Yasui with a reasonable expectation of success in order to more safely control driving of a vehicle.
However, Lin teaches in response to all of the generated one or more paths being excluded switching a control mode of the mobile body from an automatic control mode to a manual control mode (see at least [0043]: step of issuing a notification that none of the possible routes are system compliant routes is generally indicated by box 108 in FIG. 2. The computing device 40 may issue the notification in a suitable manner, such as but not limited to flashing a warning light, displaying a message to an occupant of the vehicle, transmitting a communication to a remote location, etc…when none of the possible routes are identified as a system compliant route, the computing device 40 may automatically park the vehicle in a suitable location, or transfer control of the vehicle to a human operator); and
outputting a notification prompting the target user to manually operate the mobile body (see at least [0043]: step of issuing a notification that none of the possible routes are system compliant routes is generally indicated by box 108 in FIG. 2. The computing device 40 may issue the notification in a suitable manner, such as but not limited to flashing a warning light, displaying a message to an occupant of the vehicle, transmitting a communication to a remote location, etc…when none of the possible routes are identified as a system compliant route, the computing device 40 may automatically park the vehicle in a suitable location, or transfer control of the vehicle to a human operator).
It would have been obvious to one of ordinary skill in the art before the effective filing date to provide the invention as disclosed by Kentley by incorporating the teachings of Lin with a reasonable expectation of success in order to improve driving safety.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure. US 20180043901 (see at least [0007], [0029]: personalized medical emergency autopilot system may instead prioritize the vehicle control inputs of the ADAS system over the vehicle control inputs of the driver (which may in fact be totally ignored as unreliable or unsafe));
US 20180201273 (see at least [0130]: above process may be adapted to use both personalized information and a default profile. For example, if the user drives way over the speed limit in construction zones, the speed of the automated vehicle may be limited to the speed limit for safety reasons. Alternatively, if the system has determined that is safer to not tailgate another driver, the system may adjust how the automated vehicle 100 follows another car);
US 20210253135 (see at least claim 1: detecting a gesture in a transport; responsive to the gesture being detected, identifying an action to be performed by the transport; identifying currently engaged transport operations; determining whether performing the action will exceed a threshold transport operation level based on the currently engaged transport operations; and determining whether to perform or cancel the action corresponding to the detected gesture based on whether the threshold transport operation level will be exceeded);
US 11537134 (see at least column 5 lines 30-35: term “autonomous vehicle” may be used broadly herein to refer to vehicles for which at least some motion-related decisions (e.g., whether to accelerate, slow down, change lanes, etc.) may be made, at least at some points in time, without direct input from the vehicle's occupants, column 9 lines 48-55: wide variety of sensors may be included in collection 112 in the depicted embodiment, including externally-oriented cameras, occupant-oriented sensors (which may, for example, include cameras pointed primarily towards occupants' faces, or physiological signal detectors such as heart rate detectors and the like, and may be able to provide evidence of the comfort level or stress level of the occupants, column 10 lines 1-10: managing the movements of vehicle 110, the behavior planner 117 may use the state predictions of model(s) 133 to generate relatively longer-term plans comprising sequences of conditional actions and states which may be reached as a result of the actions, and provide the alternatives together with associated metadata (e.g., reward or value metrics indicating the “relative goodness” of the alternatives based on currently-known information) to the motion selector 118, Figure 1);
US 20220324449 (see at least abstract, [0011]: driver can select a driving style model from the driving style model library in a form of human-computer interaction such as a voice).
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 ANGELINA M SHUDY whose telephone number is (571)272-6757. The examiner can normally be reached M - F 10am - 6pm.
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, Fadey Jabr can be reached at 571-272-1516. 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.
Angelina Shudy
Primary Examiner
Art Unit 3668
/Angelina M Shudy/Primary Examiner, Art Unit 3668