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 .
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 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.
Introduction
Claims 1-14 and 16-21 are pending. Claims 1-11, 16, and 19-21 and have been examined in this Office Action. Claims 12-14, 17, and 18 are withdrawn. Claim 15 has been cancelled and claim 21 has been added since the last Office Action.
Continued Examination Under 37 CFR 1.114
A request for continued examination under 37 CFR 1.114, including the fee set forth in 37 CFR 1.17(e), was filed in this application after final rejection. Since this application is eligible for continued examination under 37 CFR 1.114, and the fee set forth in 37 CFR 1.17(e) has been timely paid, the finality of the previous Office action has been withdrawn pursuant to 37 CFR 1.114. Applicant's submission filed on 01/26/2026 has been entered.
Examiner’s Note
Examiner has cited particular paragraphs / columns and line numbers or figures in the references as applied to the claims below for the convenience of the applicant. Although the specified citations are representative of the teachings in the art and are applied to the specific limitations within the individual claim, other passages and figures may apply as well. It is respectfully requested from the applicant, in preparing the responses, to fully consider the references in their entirety as potentially teaching all or part of the claimed invention, as well as the context of the passage as taught by the prior art or disclosed by the examiner. Applicant is reminded that the Examiner is entitled to give the broadest reasonable interpretation to the language of the claims. Furthermore, the Examiner is not limited to Applicants' definition which is not specifically set forth in the disclosure.
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.
Claim(s) 1-11, 16, 19, and 20 is/are rejected under 35 U.S.C. 103 as being unpatentable over by U.S. Patent Application Publication 2020/0064842 to Kentley-Klay in view of U.S. Patent Application Publication 2023/0269766 to Guo et al. and U.S. Patent Application Publication 2023/0205951 to Jiang et al.
As per claim 1, Kentley-Klay discloses a method for on-vehicle modeling (Kentley-Klay; At least the abstract), comprising:
at a first vehicle having one or more processors, memory, and a plurality of sensors (Kentley-Klay; At least figure 2):
collecting, locally at the first vehicle, training data via the plurality of sensors (Kentley-Klay; At least paragraph(s) 62 and 63; the training uses vehicle sensor data 320);
locally at the first vehicle, training a first vehicle driving model using only the locally collected training data and computing resources that are not being used to at least partially autonomously drive the first vehicle, wherein the computing resources are prioritized for driving of the first vehicle over training of the first vehicle driving model, and wherein the training further includes subjecting the first vehicle driving model to different offline simulated driving scenarios to train the first vehicle driving model (Kentley-Klay; At least paragraph(s) 12, 14, 17, 24, and 32; the system trains models multiple times until a validated model is created using unused computing resources and can train the model while the vehicle is parked, i.e., offline);
Kentley-Klay does not explicitly disclose with different driving styles. However, this feature(s) is taught by Jiang (Jiang; At least paragraph(s) 23 and 26). At the time of filing, it would have been obvious to one of ordinary skill in the art to have incorporated the teachings of Jiang into the invention of Kentley-Klay with a reasonable expectation of success with the motivation of using a known technique to improve a similar device in the same way with predictable results. Training the models with different driving styles makes the simulation environment more resemble a real-world driving environment and thus, provides more realistic training.
Kentley-Klay further discloses transmitting the locally trained first vehicle driving model to a server (Kentley-Klay; At least paragraph(s) 43 and 60; “the remote computing device may receive a trained target ML model from the one or more vehicles”);
subsequent to the transmitting, receiving from the server an aggregated vehicle driving model that is trained using a plurality of locally trained vehicle driving models from a plurality of vehicles, including the locally trained first vehicle driving model, wherein each of the plurality of locally trained vehicle driving models is independently trained at a respective vehicle using only respective training data that is locally collected at the respective vehicle (Kentley-Klay; At least paragraph(s) 25, 44, 60, 73, 81, and 82; the remote computing device sends the validated ML model to the vehicles. The validated model is trained on multiple vehicle each running a model independently only using locally collected sensor data);
Kentley-Klay discloses the server receiving driving models from a plurality of vehicles and determining whether performance was improved or degraded by the individual model (Kentley-Klay; At least paragraph(s) 60) and the server sending validated driving models to the plurality of vehicle (Kentley-Klay; At least paragraph(s) 25), but does not explicitly disclose the aggregated [validated] model is generated by the server.
However, the above feature(s) are taught by Guo (Guo; At least paragraph(s) 17). At the time of filing, it would have been obvious to one of ordinary skill in the art to have incorporated the teachings of Guo into the invention of Kentley-Klay with a reasonable expectation of success with the motivation of using a known technique to improve a similar device in the same way with predictable results. Aggregating the various models at the server would save processing power in the vehicles, where processing power is at a premium. For example, Kentley-Klay discloses sending a model out to multiple vehicles (Kentley-Klay; At least paragraph(s) 44). Comparing and aggregating those tested models in the server would provide a central location and would save the processing power in the vehicles.
subsequently collecting sensor data from the plurality of sensors (Kentley-Klay; At least paragraph(s) 62); and
at least partially autonomously driving the first vehicle using the aggregated vehicle driving model based on the collected sensor data from the plurality of sensors (Kentley-Klay; At least paragraph(s) 24 and 59).
As per claim 2, Kentley-Klay discloses wherein: the locally collected training data includes data one or more vehicle, including the first vehicle (Kentley-Klay; At least paragraph(s) paragraph(s) 62 and 63);
the first vehicle driving model includes a vehicle driving behavior model configured to predict behavior of the first vehicle (Kentley-Klay; At least paragraph(s) 16, 24, and 59); and
the method comprises applying the first vehicle driving behavior model to the collected sensor data to predict vehicle behavior of the first vehicle (Kentley-Klay; At least paragraph(s) 17, 37, and 59).
As per claim 3, Kentley-Klay discloses wherein: the locally collected training data includes data for one or more vehicles, including the first vehicle and a plurality of second vehicles that are near the first vehicle (Kentley-Klay; At least paragraph(s) 16 and 63);
the first vehicle driving model includes a vehicle driving behavior model configured to predict behavior of a third vehicle that appears near the first vehicle (Kentley-Klay; At least paragraph(s) 61-63); and
the method comprises applying the first vehicle driving behavior model to the collected sensor data to predict vehicle behavior of the third vehicle (Kentley-Klay; At least paragraph(s) 61-63).
As per claim 4, Kentley-Klay discloses wherein: the plurality of sensors include a camera, and the locally collected training data includes a plurality of images captured by the camera (Kentley-Klay; At least paragraph(s) 52);
the locally collected training data includes data for one or more vehicles include, including a plurality of second vehicles that are near the first vehicle and corresponding to a plurality of vehicle types, the plurality of vehicle types including a plurality of: one or more trucks, one or more vans, one or more passenger cars, and one or more driver-less cars (Kentley-Klay; At least paragraph(s) 61); and
the first vehicle driving model is trained using the plurality of images to predict behavior of the plurality of second vehicles based on the plurality of vehicle types (Kentley-Klay; At least paragraph(s) 65).
As per claim 5, Kentley-Klay discloses wherein the locally collected training data includes a first set of training data captured during a first duration of time and a second set of training data captured during a second duration of time following the first duration of time (Kentley-Klay; At least paragraph(s) 17), and training the first vehicle driving model further includes:
determining behavior of one or more vehicles from the first set of training data using the vehicle driving behavior model (Kentley-Klay; At least paragraph(s) 16 and 63);
comparing the behavior of the one or more vehicles with the second set of training data (Kentley-Klay; At least paragraph(s) 23, 24, and 63); and
modifying one or more weights of a neural network of the first vehicle driving model based on a comparison result (Kentley-Klay; At least paragraph(s) 17 and 63).
As per claim 6, Kentley-Klay discloses wherein: the locally collected training data includes data for one or more vehicles, including one or more second vehicles near the first vehicle during a collection period (Kentley-Klay; At least paragraph(s) 16 and 61);
the plurality of sensors includes at least a light detection and ranging (LiDAR) scanner and an inertial navigation system (INS) including accelerometers and gyroscopes (Kentley-Klay; At least paragraph(s) 52); and
the training data includes relative positions that are measured between the first vehicle and the one or more second vehicles by the LiDAR scanner and relative motions measured between the first vehicle and the one or more second vehicles by the INS during the collection period (Kentley-Klay; At least paragraph(s) 16 and 61-63).
As per claim 7, Kentley-Klay discloses wherein at least partially autonomously driving the first vehicle further includes applying the aggregated vehicle driving model to predict vehicle behavior based on the collected sensor data using a subset of the computing resources (Kentley-Klay; At least paragraph(s) 24 and 27).
As per claim 8, Kentley-Klay discloses wherein: the first vehicle driving model is trained, before the sensor data are collected from the plurality of sensors and the first vehicle driving model is used to predict vehicle behavior (Kentley-Klay; At least paragraph(s) 16); and
the sensor data are added to the training data to iteratively train the first vehicle driving model, after applying the vehicle driving model to predict the first vehicle behavior (Kentley-Klay; At least paragraph(s) 13, 24, and 37).
As per claim 9, Kentley-Klay discloses wherein the first vehicle driving model is trained using the locally collected training data to generate a second vehicle driving model, concurrently when the first vehicle driving model is used to predict vehicle behavior from the collected sensor data (Kentley-Klay; At least paragraph(s) 55 and 57), the method further comprising:
adding the locally collected sensor data to the collected training data (Kentley-Klay; At least paragraph(s) 55 and 59).
As per claim 10, Kentley-Klay discloses the collected sensor data including first sensor data (Kentley-Klay; At least paragraph(s) 52), the method further comprising:
collecting second sensor data from the plurality of sensors after collecting the first sensor data (Kentley-Klay; At least paragraph(s) 52); and
while continuing to train the second vehicle driving model with the training data added with the first sensor data, applying the second vehicle driving model to predict the vehicle behavior based on the second sensor data (Kentley-Klay; At least paragraph(s) 59).
As per claim 11, Kentley-Klay discloses a vehicle (Kentley-Klay; At least figure 2), comprising:
a plurality of sensors (Kentley-Klay; At least paragraph(s) 52 and 62, and figure 2);
one or more processors (Kentley-Klay; At least figure 2); and
memory storing one or more programs configured for execution by the one or more processors (Kentley-Klay; At least figure 2), the one or more programs comprising instructions for:
collecting, locally at the vehicle training data via the plurality of sensors (Kentley-Klay; At least paragraph(s) 52, 62, and 63);
locally at the vehicle, training a first vehicle driving model using only the locally collected training data and computing resources that are not being used to at least partially autonomously drive the vehicle, wherein the computing resources are prioritized for driving of the vehicle over training of the first vehicle driving model, and wherein the training further includes subjecting the first vehicle driving model to different offline simulated driving scenarios to train the first vehicle driving model (Kentley-Klay; At least paragraph(s) 12, 14, 17, 24, and 32; the system trains models multiple times until a validated model is created using unused computing resources and can train the model while the vehicle is parked, i.e., offline);
Kentley-Klay does not explicitly disclose with different driving styles. However, this feature(s) is taught by Jiang (Jiang; At least paragraph(s) 23 and 26). At the time of filing, it would have been obvious to one of ordinary skill in the art to have incorporated the teachings of Jiang into the invention of Kentley-Klay with a reasonable expectation of success with the motivation of using a known technique to improve a similar device in the same way with predictable results. Training the models with different driving styles makes the simulation environment more resemble a real-world driving environment and thus, provides more realistic training.
Kentley-Klay further discloses transmitting the locally trained first vehicle driving model to a server (Kentley-Klay; At least paragraph(s) 43 and 60; “the remote computing device may receive a trained target ML model from the one or more vehicles”);
subsequent to the transmitting, receiving from the server an aggregated vehicle driving model that is trained using a plurality of locally trained vehicle driving models from a plurality of vehicles, including the locally trained first vehicle driving model, wherein each of the plurality of locally trained vehicle driving models is independently trained at a respective vehicle using only respective training data that is locally collected at the respective vehicle (Kentley-Klay; At least paragraph(s) 25, 44, 60, 73, 81, and 82; the remote computing device sends the validated ML model to the vehicles. The validated model is trained on multiple vehicle each running a model independently only using locally collected sensor data);
Kentley-Klay discloses the server receiving driving models from a plurality of vehicles and determining whether performance was improved or degraded by the individual model (Kentley-Klay; At least paragraph(s) 60) and the server sending validated driving models to the plurality of vehicle (Kentley-Klay; At least paragraph(s) 25), but does not explicitly disclose the aggregated [validated] model is generated by the server.
However, the above feature(s) are taught by Guo (Guo; At least paragraph(s) 17). At the time of filing, it would have been obvious to one of ordinary skill in the art to have incorporated the teachings of Guo into the invention of Kentley-Klay with a reasonable expectation of success with the motivation of using a known technique to improve a similar device in the same way with predictable results. Aggregating the various models at the server would save processing power in the vehicles, where processing power is at a premium. For example, Kentley-Klay discloses sending a model out to multiple vehicles (Kentley-Klay; At least paragraph(s) 44). Comparing and aggregating those tested models in the server would provide a central location and would save the processing power in the vehicles.
subsequently collecting sensor data from the plurality of sensors (Kentley-Klay; At least paragraph(s) 52 and 62); and
at least partially autonomously driving the vehicle using the aggregated vehicle driving model based on the collected sensor data from the plurality of sensors (Kentley-Klay; At least paragraph(s) 24 and 59).
As per claim 16, Kentley-Klay discloses a non-transitory computer-readable storage medium storing one or more programs configured for execution by one or more processors of a vehicle (Kentley-Klay; At least the abstract and figure 2), the vehicle further including a plurality of sensors, the one or more programs comprising instructions for:
Collecting, locally at the vehicle, training data via the plurality of sensors (Kentley-Klay; At least paragraph(s) 52 and 62);
locally at the vehicle, training a first vehicle driving model using only the locally collected training data and computing resources that are not being used to at least partially autonomously drive the vehicle, wherein the computing resources are prioritized for driving of the vehicle over training of the first vehicle driving model, and wherein the training further includes subjecting the first vehicle driving model to different offline simulated driving scenarios to train the first vehicle driving model (Kentley-Klay; At least paragraph(s) 12, 14, 17, 24, and 32; the system trains models multiple times until a validated model is created using unused computing resources and can train the model while the vehicle is parked, i.e., offline);
Kentley-Klay does not explicitly disclose with different driving styles. However, this feature(s) is taught by Jiang (Jiang; At least paragraph(s) 23 and 26). At the time of filing, it would have been obvious to one of ordinary skill in the art to have incorporated the teachings of Jiang into the invention of Kentley-Klay with a reasonable expectation of success with the motivation of using a known technique to improve a similar device in the same way with predictable results. Training the models with different driving styles makes the simulation environment more resemble a real-world driving environment and thus, provides more realistic training.
Kentley-Klay further discloses transmitting the locally trained first vehicle driving model to a server (Kentley-Klay; At least paragraph(s) 43 and 60; “the remote computing device may receive a trained target ML model from the one or more vehicles”);
subsequent to the transmitting, receiving from the server an aggregated vehicle driving model that is trained using a plurality of locally trained vehicle driving models from a plurality of vehicles, including the locally trained first vehicle driving model, wherein each of the plurality of locally trained vehicle driving models is independently trained at a respective vehicle using only respective training data that is locally collected at the respective vehicle (Kentley-Klay; At least paragraph(s) 25, 44, 60, 73, 81, and 82; the remote computing device sends the validated ML model to the vehicles. The validated model is trained on multiple vehicle each running a model independently only using locally collected sensor data);
Kentley-Klay discloses the server receiving driving models from a plurality of vehicles and determining whether performance was improved or degraded by the individual model (Kentley-Klay; At least paragraph(s) 60) and the server sending validated driving models to the plurality of vehicle (Kentley-Klay; At least paragraph(s) 25), but does not explicitly disclose the aggregated [validated] model is generated by the server.
However, the above feature(s) are taught by Guo (Guo; At least paragraph(s) 17). At the time of filing, it would have been obvious to one of ordinary skill in the art to have incorporated the teachings of Guo into the invention of Kentley-Klay with a reasonable expectation of success with the motivation of using a known technique to improve a similar device in the same way with predictable results. Aggregating the various models at the server would save processing power in the vehicles, where processing power is at a premium. For example, Kentley-Klay discloses sending a model out to multiple vehicles (Kentley-Klay; At least paragraph(s) 44). Comparing and aggregating those tested models in the server would provide a central location and would save the processing power in the vehicles.
subsequently collecting sensor data from the plurality of sensors (Kentley-Klay; At least paragraph(s) 52 and 62); and
at least partially autonomously driving the vehicle using the aggregated vehicle driving model based on the collected sensor data from the plurality of sensors (Kentley-Klay; At least paragraph(s) 24 and 59).
As per claim 19, Kentley-Klay discloses the one or more programs further comprising instructions for: collecting data for road objects that appear on a road and in measurement ranges of the plurality of sensors, the road objects including one or more of: lane lines, shoulder lines, road dividers, traffic lights, traffic signs, road signs, cones, a pedestrian, a bicycle, and a driver of the vehicle, wherein the data for road objects is applied to train one or more vehicle models (Kentley-Klay; At least paragraph(s) 61, 63, and 65).
As per claim 20, Kentley-Klay discloses wherein the plurality of sensors include one or more of: a global positioning system (GPS), a light detection and ranging (LiDAR) scanner, one or more cameras, a radio detection and ranging (RADAR) sensor, an infrared sensor, one or more ultrasonic sensors, a dedicated short-range communication (DSRC) module, an inertial navigation system (INS) including accelerometers and gyroscopes, and an odometry sensor (Kentley-Klay; At least paragraph(s) 52).
Claim Rejections - 35 USC § 103
Claim(s) 21 is/are rejected under 35 U.S.C. 103 as being unpatentable over Kentley-Klay, in view of Guo and Jiang as applied to claim 1, and in further view of U.S. Patent Application Publication 2021/0107488 to Jeong.
As per claim 21, Kentley-Klay discloses wherein at least partially autonomously driving the first vehicle using the aggregated vehicle driving model based on the collected sensor data from the plurality of sensors includes:
using the aggregated vehicle driving model to determine a behavior of the first vehicle (Kentley-Klay; At least paragraph(s) 25-27); and
Kentley-Klay discloses using the aggregated (validated) model for level 5 autonomous control (i.e., full autonomous control), but does not explicitly disclose adjusting a sensitivity of a first sensor of the plurality of sensors of the first vehicle in accordance with the determined behavior of the first vehicle.
However, the above feature(s) are taught by Jeong (Jeong; At least paragraph(s) 38-41). At the time of filing, it would have been obvious to one of ordinary skill in the art to have incorporated the teachings of Jeong into the invention of Kentley-Klay with a reasonable expectation of success with the motivation of using a known technique to improve a similar device in the same way with predictable results. Adjusting the sensor sensitivity would allow faster and further detection during high-risk situations to provide safe driving in the current driving state.
Response to Arguments
Applicant’s arguments, see pages 10-12, filed 01/26/2026, have been considered but are moot because the new ground of rejection does not rely on any reference applied in the prior rejection of record for any teaching or matter specifically challenged in the argument.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to DAVID P MERLINO whose telephone number is (571)272-8362. The examiner can normally be reached M-Th 5:30am-3:00pm F 5:30-9:00 am ET.
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, Erin Bishop can be reached on 571-270-3713. 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.
/David P. Merlino/Primary Examiner, Art Unit 3665C