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 .
Status of Claims
This Office Action is in response to the Office Action Response dated June 16, 2026. Claims 1-20 are presently pending and are presented for examination.
Response to Arguments
Applicant’s amendments have overcome the claim objections and rejection under 35 USC 112(b). With respect to the prior art rejections, Applicant’s arguments are moot in view of new grounds of rejection.
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.
Claims 1, 2, 4-6 and 8-20 are rejected under 35 U.S.C. 103 as being unpatentable over U.S. Patent Publication No. 2024/0362923, to Xu et al. (hereinafter Xu), in view of U.S. Patent No. 12,485,898, to Sun et al. (hereinafter Sun), and in further view of U.S. Patent Publication No. 2024/0326873, to Gupta et al. (hereinafter Gupta).
As per Claim 1, Xu discloses a system (e.g. see Abstract, Fig. 1 and para 0054, wherein trajectory of road users are determined with respect to a host vehicle 100 via a perception system 110) comprising: one or more processors; and one or more non-transitory computer-readable media storing computer-executable instructions that, when executed, cause the system to perform operations comprising: receiving data indicating information about an environment in a vicinity of an autonomous vehicle, wherein the environment comprises a movement of traffic (e.g. see Fig. 1, and para 0055, wherein the perception system monitors external environment or surroundings of the vehicle including the dynamic context 125 (i.e. movement) of a plurality of road users 130); determining, based at least in part on the data and via a machine learning model, a first set of vectors…, wherein the vectors in the first set of vectors are associated with the respective positions and have directions indicative of a direction of the movement of traffic at the respective positions and magnitudes indicative of a speed of the movement of traffic at the respective positions (e.g. see at least paras 0058, 0112 and 0184, wherein a deep neural network 210 receives the dynamic context and forms dynamics of each road user in the form of vectors (i.e. a first set of vectors determined by the received data and machine learning model; the Office further notes that vectors include an origin, direction and magnitude (i.e. speed)); and controlling the autonomous vehicle based at least in part on the first set of vectors (e.g. see para 0004, which teaches autonomous vehicles plans future trajectory based upon external environment, which would include the determined vectors)…
Xu fails to specifically disclose all of the features of wherein the machine learning model is trained by: receiving training data comprising: scene data representing a scene wherein an example movement of traffic; and an expected set of vectors, wherein vectors in the expected set of vectors have directions indicative of a known direction of the example movement of traffic and magnitudes indicative of a known speed associated with the example movement of traffic at respective positions within the scene; inputting the scene data into the machine learning model to generate a second set of vectors; and updating parameters of the machine learning model based on the second set of vectors and the expected set of vectors.
However, Sun teaches an autonomous vehicle 100 is provided capable of performing lane estimation and tracking procedures (e.g. see Fig. 1, and col. 4, lines 60-63), wherein the vehicle includes a sensing system 110 configured for sensing objects in a driving environment 101 including position, direction and velocity (e.g. see Fig. 1, and col. 6, lines 18-47), and wherein the lane estimation and tracking module 132 which is trained via a training server 240 (i.e. machine learning model) (e.g. see e.g. see Figs. 1-2, and col. 12, line 34, to col. 15, line 2). Sun further teaches wherein the machine learning model is trained by: receiving training data comprising: scene data representing a scene wherein an example movement of traffic (e.g. see Fig. 2, and col. 13, line 66, to col. 16, line 24, wherein the tracking module is trained by the training server which includes a training engine 242 which receives camera images 252 (i.e. scene) from a data repository 250); and an expected set of vectors, wherein vectors in the expected set of vectors have directions indicative of a known direction of the example movement of traffic and magnitudes indicative of a known speed associated with the example movement of traffic at respective positions within the scene (e.g. see Fig. 2, and col. 13, line 66, to col. 16, line 24, wherein the training server further includes mapping data including location, speed and direction of traffic (i.e. vectors) from the data repository); inputting the scene data into the machine learning model to generate a second set of vectors; and updating parameters of the machine learning model based on the second set of vectors and the expected set of vectors (e.g. see col. 13, line 66, to col. 16, line 24, wherein the tracking module includes a lane tracking module 230 which receives updated mapping during travel, the Office further notes that a second set of vectors for the new location would be obtained from the training server to update the machine learning of the tracking module). It would have been obvious to a person of ordinary skill in the art at the time of Applicants’ invention to modify the perception system of Xu to include training of the machine learning model to ensure the most updated historical data is utilized to improve accuracy of the perception system and to account for new location encountered during travel.
Xu fails to particularly disclose determining, based at least in part on the data and via a machine learning model, a first set of vectors comprising a vector for each position of a plurality of positions in the vicinity of the autonomous vehicle. However, Gupta teaches a machine learning model receiving image data configured to determine head positions and associated vectors of surrounding vehicles (e.g. see para 0148). It would have been obvious to a person of ordinary skill in the art at the time of Applicants’ invention to modify the perception system of Xu to include using real-time image data of surrounding vehicles for the purpose of ascertaining areas to be avoided so as to generate a safe traveling path.
As per Claim 2, Xu, as modified by Sun and Gupta, teaches the features of claim 1, and Sun further teaches wherein: the known direction of the example movement of traffic is a direction associated with a lane of a road in the scene (e.g. see col 21, line 26, to col. 22, line 12, wherein the machine learning models lanes and lane states), and the known speed associated with the example movement of traffic is a speed limit of the road (e.g. see at least col. 11, lines 48-67, wherein vectorization includes lane speed limits). It would have been obvious to a person of ordinary skill in the art at the time of Applicants’ invention to modify the perception system of Xu to include historical traffic lane usage and speed limits to improve expected lane usage and speed to better predict future movement patterns.
As per Claim 4, Xu, as modified by Sun and Gupta, teaches the features of claim 1, and Xu further discloses wherein the scene comprises: a road; a vehicle; and a signal that is not being adhered to by the vehicle (e.g. see Fig. 1, and paras 0005, 0056 and 0059, wherein the vehicle monitors static context including road, traffic signs and dynamic context including other vehicles; the Office further notes that the other vehicles disregarding traffic signs/signals would be captured).
As per Claim 5, Xu, as modified by Sun and Gupta, teaches the features of a method comprising: receiving data associated with an environment in a vicinity of a vehicle; determining, based on the data, a set of vectors comprising a vector for each position of a plurality of positions in the environment, the set of vectors associated with a vector field that is indicative of a traffic direction in the environment, such that the vectors in the set of vectors are indicative of the traffic direction at the respective positions in the environment; and generating instructions to control the vehicle based at least in part on the set of vectors (e.g. see rejection of claim 1).
As per Claim 6, Xu, as modified by Sun and Gupta, teaches the features of claim 5, and Xu further discloses wherein the vectors have magnitudes indicative of a traffic speed at the respective positions (e.g. see at least paras 0058, 0112 and 0184, wherein a deep neural network 210 receives the dynamic context and forms dynamics of each road user in the form of vectors (i.e. a first set of vectors determined by the received data and machine learning model; the Office further notes that vectors include an origin, direction and magnitude (i.e. speed)).
As per Claim 8, Xu, as modified by Sun and Gupta, teaches the features of claim 5, and Xu further discloses wherein the data is sensor data generated by a sensor associated with the vehicle, and the method comprises: inputting at least a portion of the sensor data into a machine learning model to determine the set of vectors (e.g. Fig. 2 and paras 0036, 0057-0058, wherein the perception system 110 transmits dynamic and static context to the deep neural network of the vehicle 100 to generate vectors of surrounding environment).
As per Claim 9, Xu, as modified by Sun and Gupta, teaches the features of claim 5, and Xu further discloses wherein the instructions to control the vehicle cause the vehicle to change its speed based on a difference between a current speed of the vehicle and a magnitude of a vector in the set of vectors in a planned trajectory of the vehicle (e.g. see para 0004, which teaches autonomous vehicles plans future trajectory based upon external environment, which would include the determined vectors; the Office further notes that the trajectory of a host vehicle must include a vehicle speed to avoid collision).
As per Claim 10, Xu, as modified by Sun and Gupta, teaches the features of claim 5, and Xu further discloses wherein no other vehicles are in motion in the environment (e.g. see Fig. 1, and para 0055, wherein the object may comprise only pedestrians 150).
As per Claim 11, Xu, as modified by Sun and Gupta, teaches the features of claim 5, and further teaches wherein the environment comprises a further vehicle and the data comprises sensor data received from a sensor associated with the vehicle (e.g. see Xu, Fig. 1, and para 0055, wherein the object may comprise vehicles 140), the method comprising: determining, based on the sensor data, a direction and speed of the further vehicle (e.g. see Xu, at least paras 0058, 0112 and 0184, wherein a deep neural network 210 receives the dynamic context and forms dynamics of each road user in the form of vectors (i.e. a first set of vectors determined by the received data and machine learning model; the Office further notes that vectors include an origin, direction and magnitude (i.e. speed)); updating the set of vectors based on the direction and speed of the further vehicle to generate an updated set of vectors; and generating further instructions to control the vehicle based at least in part on the updated set of vectors (e.g. see Sun, col. 13, line 66, to col. 16, line 24, wherein the tracking module includes a lane tracking module 230 which receives updated mapping during travel, the Office further notes that a second set of vectors for the new location would be obtained from the training server to update the machine learning of the tracking module, which are used to control the vehicle). It would have been obvious to a person of ordinary skill in the art at the time of Applicants’ invention to modify the perception system of Xu to include training of the machine learning model to ensure the most updated historical data is utilized to improve accuracy of the perception system and to account for new location encountered during travel.
As per Claim 12, Xu, as modified by Sun and Gupta, teaches the features of claim 5, and Xu further discloses wherein the set of vectors is a first set of vectors, the vector field is a first vector field that is indicative of a first traffic direction, the first traffic direction being the traffic direction (e.g. see rejection of claim 1 regarding the first set of vectors), the method further comprising: determining, based on the data, a second set of vectors that is indicative of a second traffic direction in the environment, such that vectors in the second set of vectors are indicative of a second traffic direction at respective positions in the environment (e.g. see Sun, col. 13, line 66, to col. 16, line 24, wherein the tracking module includes a lane tracking module 230 which receives updated mapping during travel, the Office further notes that a second set of vectors for the new location would be obtained from the training server to update the machine learning of the tracking module, which are used to control the vehicle). It would have been obvious to a person of ordinary skill in the art at the time of Applicants’ invention to modify the perception system of Xu to include training of the machine learning model to ensure the most updated historical data is utilized to improve accuracy of the perception system and to account for new location encountered during travel.
As per Claim 13, Xu, as modified by Sun and Gupta, teaches the features of claim 12, and Xu further discloses wherein a first vector in the first set of vectors is associated with a same position as a second vector in the second set of vectors (e.g. the Office notes that the first vector is based upon captured data and the second vector is based upon historic data of the same position/region).
As per Claim 14, Xu, as modified by Sun and Gupta, teaches the features of claim 5, and Xu further discloses wherein the set of vectors is determined using a machine learning model, the set of vectors is a second set of vectors, the traffic direction is a second traffic direction, and the environment is a second environment (e.g. see rejection of claim 1 regarding machine learning model; the Office further notes that continual data streams into the machine learning model generating first and second vectors), the method comprising: receiving training data representing a first environment comprising traffic; generating a first set of vectors by inputting the training data into the machine learning model, wherein vectors in the first set of vectors represent an estimate of a first traffic direction in the first environment (e.g. see rejection of claim 1); and training the machine learning model based on the first set of vectors and a third set of vectors, each vector in the third set of vectors representing a known first traffic direction at respective positions in the first environment (e.g. see rejection of claim 1; the Office further notes that the third set of vectors would be based upon the continuous stream of perception data).
As per Claim 15, Xu, as modified by Sun and Gupta, teaches the features of claim 14, and Sun further teaches wherein the training data comprises map data, the map data indicating: a portion of transportation network; an indication of a lane direction of the portion of transportation network; and a speed limit associated with the portion of transportation network (e.g. see col. 14, line 32, to col. 15, line 2, wherein the training engine utilizes map data indicating driving lanes; also see col. 10, lines 3-41, wherein a lane module provides speed limit information of the road). It would have been obvious to a person of ordinary skill in the art at the time of Applicants’ invention to modify the perception system of Xu to include road information for the purpose of providing an improved prediction model of traffic.
As per Claim 16, Xu, as modified by Sun and Gupta, teaches the features of claim 5, and further teaches wherein the data comprises sensor data received from a sensor associated with the vehicle, the method further comprising: detecting, based on the sensor data and the set of vectors, an anomaly in the environment in the vicinity of the vehicle associated with an object having an actual behavior that differs from an expected behavior (e.g. see rejection of claim 1; the Office notes that an anomaly could comprise any change in direction of a vehicle, which the sensors and associated vectorization would identify).
As per Claim 17, Xu, as modified by Sun and Gupta, teaches the features of claim 5, and further teaches comprising: determining a first planned trajectory of the vehicle through the environment; and determining, based on the set of vectors, a second planned trajectory of the vehicle through the environment, different from the first planned trajectory, wherein the instructions to control the vehicle are associated with the second planned trajectory (e.g. the Office notes that the first planned trajectory would be based upon a first sensor analysis and vectors and a second planned trajectory would be based upon a subsequent sensor analysis and vectors wherein a most recent control of the host vehicle is based upon the subsequent sensor analysis and vectors).
As per Claim 18, Xu, as modified by Sun and Gupta, teaches the features of claim 17, and further teaches comprising: receiving sensor data from a sensor associated with the vehicle, wherein the first planned trajectory is determined based at least on part on the sensor data and a predefined traffic rule (e.g. see rejection of claim 1; with respect to a predetermined traffic rule, Sun teaches that the system further uses speed limit information (e.g. see col. 10, lines 3-41).
As per Claim 19, Xu, as modified by Sun and Gupta, teaches the features of claim 5, and further teaches comprising: receiving sensor data from a sensor associated with the vehicle, determining, based on at least the sensor data the set of vectors, a planned trajectory for the vehicle through the environment, wherein the instructions to control the vehicle are associated with the planned trajectory (e.g. see rejection of claim 1).
As per Claim 20, Xu, as modified by Sun and Gupta, teaches the features of One or more non-transitory computer-readable media storing instructions that, when executed, cause one or more processors to perform operations comprising: receiving data associated with an environment in a vicinity of a vehicle; determining, based on the data, a set of vectors comprising a vector for each position of a plurality of positions in the environment, the sset of vecotrs associated with a vector field that is indicative of a traffic direction in the environment, such that vectors in the set of vectors are indicative of the traffic direction at respective positions in the environment; and generating instructions to control the vehicle based at least in part on the set of vectors (e.g. see rejection of claim 1).
Claims 3 and 7 are rejected under 35 U.S.C. 103 as being unpatentable over U.S. Patent Publication No. 2024/0362923, to Xu et al. (hereinafter Xu), in view of U.S. Patent No. 12,485,898, to Sun et al. (hereinafter Sun), in view of U.S. Patent Publication No. 2024/0326873, to Gupta et al. (hereinafter Gupta), and in further view of U.S. Patent Publication No. 2024/537194, to Takashima et al. (hereinafter Takashima).
As per Claim 3, Xu, as modified by Sun and Gupta, teaches the features of claim 1, but fails to teach wherein the first set of vectors is precomputed, and the instructions cause the system to perform further operations comprising: receiving the first set of vectors from a remote computing device. However, Takashima teaches a machine learning model, such as a support vector machine, which is remote from the vehicle (i.e. remote computing device) and provides traffic data to the vehicle (i.e. precomputed) which is used for trajectory planning of the vehicle (e.g. see at least paras 0108 and 0149). It would have been obvious to a person of ordinary skill in the art at the time of Applicants’ invention to modify the perception system of Xu to include performing traffic analysis from a remote computing device for the purpose of reducing vehicle components and resource allocation.
As per Claim 7, Xu, as modified by Sun and Gupta, teaches the features of claim 5, but fails to teach wherein: the data comprises location data indicative of a location of the vehicle, and the set of vectors are predetermined for an area comprising the location. However, Takashima teaches a machine learning model, such as a support vector machine for a particular control area, which is remote from the vehicle (i.e. remote computing device) and provides traffic data to the vehicle (i.e. predetermined) which is used for trajectory planning of the vehicle (e.g. see at least paras 0108 and 0149). It would have been obvious to a person of ordinary skill in the art at the time of Applicants’ invention to modify the perception system of Xu to include performing traffic analysis from a remote computing device for the purpose of reducing vehicle components and resource allocation.
Conclusion
Applicant's amendment necessitated the new ground(s) of rejection presented in this Office action. Accordingly, THIS ACTION IS MADE FINAL. See MPEP § 706.07(a). Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any nonprovisional extension fee (37 CFR 1.17(a)) pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the mailing date of this final action.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to James M. McPherson whose telephone number is (313) 446-6543. The examiner can normally be reached on 7:30 AM - 5PM Mon-Fri Eastern Alt Fri. If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Abby Flynn can be reached on 571 272-9855. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of an application may be obtained from the Patent Application Information Retrieval (PAIR) system. Status information for published applications may be obtained from either Private PAIR or Public PAIR. Status information for unpublished applications is available through Private PAIR only. For more information about the PAIR system, see http://pair-direct.uspto.gov. Should you have questions on access to the Private PAIR system, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative or access to the automated information system, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/JAMES M MCPHERSON/Primary Examiner, Art Unit 3663B
Prosecution Insights