DETAILED ACTION
Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
This office action is in response to applicant amendment/remarks filed 07/30/2026. Claims 1-8 have been amended. No claim have been cancelled and no claim have been newly added. Accordingly, claims 1-8 are pending.
Response to Arguments
The corrected drawing sheet of Fig. 1 (filed 07/30/2026) overcomes the drawing objections and therefore the drawing objections have been removed.
Applicant’s arguments, see pages 9-11 filed 07/30/2026, with respect to the 35 U.S.C. 112(a) and 112(b) rejection due to invoking 35 U.S.C. 112(f) have been fully considered and are persuasive, since the applicant has removed the “prompt generator” and the “evaluation module” limitations from the claims. The 35 U.S.C 112(a) and 112(b) of claims 7-8 has been withdrawn.
Applicant’s arguments, see pages 11-15 filed 07/30/2026, with respect to the 35 U.S.C. 101 rejection have been fully considered and are persuasive, since the claims have been amended such that the vehicle is now operated based on the behavioral planning of the rule-based planner. The specifications discloses “The result of the planning is then implemented by correspondingly controlling the ego vehicle’s actuators” (Para. 0006 of the specifications filed 03/27/2025) that this includes lane changing, braking, avoiding an obstacle, and following a lane with lane deviations (Para. 0019 of the specifications filed 03/27/2025). Since the operating of the vehicle is positively recited, the amendments overcomes the 35 U.S.C. 101 rejection on record. The 35 U.S.C. 101 rejection of claims 1-8 has been withdrawn.
Applicant’s arguments, see pages 16-20 filed 07/30/2026 with respect to the 35 U.S.C. 102 rejection have been fully considered and are persuasive. Therefore, the rejection has been withdrawn. However, upon further consideration, a new ground(s) of rejection is made with regards to Sharan et al. “LLM-Assist: Enhancing Closed-Loop Planning with Language-Based Reasoning, 2023” in view of Zhu et al. US20190084571A1.
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.
Claims 1-8 are rejected under 35 U.S.C. 103 as being unpatentable over Sharan et al. “LLM-Assist: Enhancing Closed-Loop Planning with Language-Based Reasoning, 2023” (henceforth Sharan) in view of Zhu et al. US20190084571A1 (henceforth Zhu).
Regarding claim 1,
Sharan discloses:
A computer-implemented method for operating of a vehicle in a traffic scene, the method comprising: generating a scene representation of the traffic scene based on aggregated scene-specific information; (Fig. 1 shows an aggregated scene-specific representation of the traffic scene that is generated. Further see Section 3.2, “We access the assets provided by the nuPlan API to input the lane geometry and states of all agents, including the ego-vehicle”.)
generating, based on the scene representation, at least one text query for a text-based neural network that describes the traffic scene (See at least Page 4 Section 3.3, which states that the system prompt of Listing 2 is provided at each time step. The query is the listing 2 prompt with the current scene (i.e. the scene representation) inserted. The listing 2 prompt is shown in Page 3.) and requests a behavioral recommendation (See the listing 2 prompt in Page 3, wherein the “Task Requirement” includes “In a python code bloc, propose only the parameters that you want to change” and “to provide a short one sentence brief explanation for your parameter choice”, therefore, the text query requests a behavioral recommendation.)
providing the at least one text query to the text-based neural network (See at least Section 3.3. “we provide the system prompt shown in Listing 2 at each time step. As in for LLM-ASSISTUNC , we at each time step, provide scene information including the history of vehicle, pedestrian, and object positions, headings, and speeds, and their current lane ID” The text-query is provided to the text-based neural network) and receiving the behavioral recommendation from the text-based neural network; (See at least Fig. 6, wherein the behavioral recommendation is received from the text-based neural network.)
performing behavioral planning, using a rule-based planner, based on the scene representation (See at least Page 4 Section 3.1, wherein PDM-closed is a rule-based planner performs behavioral planning based on the scene representation.)
Sharan does not specifically state a behavioral recommendation that corresponds to one of a planner-specific set of predefined planning scenarios; assigning the received behavioral recommendation to a respective planning scenario of the planner-specific set of predefined planning scenarios; performing planning based on the respective planning scenario to which the received behavioral recommendation was assigned and operating the vehicle based on the behavioral planning of the rule-based planner. However, Zhu teaches:
a behavioral recommendation that corresponds to one of a planner-specific set of predefined planning scenarios; (See at least Para. 0037, “each of scenario/path tables 124 is associated with one of a set of predefined driving scenarios, such as, for example, a driving straight scenario, a turning scenario, and a lane changing scenario. A turning scenario may further include a left-turning scenario, a right-turning scenario, and a U-turning scenario. A lane changing scenario may further include a left lane changing scenario and a right lane changing scenario. A driving scenario is also referred to as a driving intention, which represents an intention to drive a vehicle in a particular way such as driving straight, making a turn, or changing lane, etc.” The behavioral recommendation corresponds to one of a planner-specific set of predefined planning scenarios.)
assigning the received behavioral recommendation to a respective planning scenario of the planner-specific set of predefined planning scenarios; (See at least Para. 0060, “In response to a route received from routing module 307, path segmenting module 321 parses and analyzes the route to identify a list of one or more driving scenarios along the route that match one or more predefined driving scenarios.“ Further see Para. 0061 and Fig. 6 steps 602 and 604. The received behavioral recommendation is assigned to a respective planning scenario of the predefined planning scenarios.)
performing planning based on the respective planning scenario to which the received behavioral recommendation was assigned. (See at least Para. 0060 and Fig. 6 step 604, wherein planning is performed based on the respective planning scenario to which the behavioral recommendation was assigned.)
and operating the vehicle based on the behavioral planning of the rule-based planner. (See at least Fig. 6. Step 606, wherein the vehicle is operated based on the behavioral planning.)
It would have been obvious to one of the ordinary skill in the art before the effective filing date of the claimed invention to have modified Sharan to incorporate the teachings of Zhu in which the requested behavioral recommendation is assigned to Zhu’s planner-specific set of predefined driving scenarios so that the planning is performed on the basis of that assigned scenario which would avoid “time and resource consumption during real-time driving” (Para. 0062, Zhu). Furthermore, Zhu’s planner only executes behavior from its predefined set and matches to one before planning. Sharan discloses the LLM (i.e. it reads the scene and returns a recommendation) and discloses PDM-closed (i.e. a rule-based planner that plans a trajectory). Zhu’s matching step is inserted between them, which assigns the recommendation to a predefined planning scenario such that PDM-closed can plan a trajectory from that assigned scenario and Zhu operates the vehicle based on the result. Additionally, a person having ordinary skill in the art would have a reasonable expectation of success in combining the teachings of Sharan and Zhu. The claimed invention is merely a combination of known elements and in combination each element merely would have performed the same function as it did separately, and one of ordinary skill in the art before the effective filing date of the claimed invention would have recognized that the results of the combination would have been predictable.
Regarding claim 2,
Sharan discloses:
wherein the text-based neural network is a large language model. (See at least Section 1, “we allow the LLM to define the planner parameters to safely navigate a scenario” and Section 3.3. “LLM-ASSISTPAR considers a parameterized version of the planning problem. Rather than directly returning a future trajectory for the ego car, the LLM instead returns a set of parameters to be used by the base planner, PDM-Closed, to plan a safe trajectory for the ego car.” The text-based neural network (i.e. the Large Language Learning Model) selects at least one of the predefined planning scenarios.)
Regarding claim 3,
Sharan does not specifically state wherein the planner-specific set of predefined planning scenarios includes at least one of (i) driving along a target line in a lane, (ii) adjusting to a predefined minimum distance from a vehicle ahead, (iii) adjusting to a target speed, (iv) changing lanes, and (v) avoiding an obstacle.
However, Zhu teaches:
wherein the planner-specific set of predefined planning scenarios includes at least one of (i) driving along a target line in a lane, (ii) adjusting to a predefined minimum distance from a vehicle ahead, (iii) adjusting to a target speed, (iv) changing lanes, and (v) avoiding an obstacle. (See at least Para. 0021, “set of driving scenarios are defined including, but are not limited to, a driving straight scenario, a turning scenario (e.g., left turn, right turn, or U-turn), and a lane changing scenario (e.g., left or right lane changing).” The planner-specific set of predefined planning scenarios include changing lanes.)
It would have been obvious to one of the ordinary skill in the art before the effective filing date of the claimed invention to have modified Sharan to incorporate the teachings of Zhu in which the requested behavioral recommendation is assigned to Zhu’s planner-specific set of predefined driving scenarios so that the planning is performed on the basis of that assigned scenario which would avoid “time and resource consumption during real-time driving” (Para. 0062, Zhu). Furthermore, Zhu’s planner only executes behavior from its predefined set and matches to one before planning. Sharan discloses the LLM (i.e. it reads the scene and returns a recommendation) and discloses PDM-closed (i.e. a rule-based planner that plans a trajectory). Zhu’s matching step is inserted between them, which assigns the recommendation to a predefined planning scenario such that PDM-closed can plan a trajectory from that assigned scenario and Zhu operates the vehicle based on the result. Additionally, a person having ordinary skill in the art would have a reasonable expectation of success in combining the teachings of Sharan and Zhu. The claimed invention is merely a combination of known elements and in combination each element merely would have performed the same function as it did separately, and one of ordinary skill in the art before the effective filing date of the claimed invention would have recognized that the results of the combination would have been predictable.
Regarding claim 4,
Sharan discloses:
generating the at least one text query for the text-based neural network in a rule-based manner, wherein the at least one text query includes a uniform, fixed, and predefined structure with predefined semantic blocks in a specified format.
(See at least Section 3.3. “For this task, we provide the system prompt shown in Listing 2 at each time step” and Page 3, Listing 2, wherein the structure never changes between time steps. The structure in Listing 2 (i.e. #Task Overview, #Parameters that can be changed, #Simulation environment, #Inputs, #Task Requirements, and #Tips for Good Proposal) is a uniform, fixed, predefined structure with predefined semantic blocks in a specified format.)
Regarding claim 5,
Sharan does not specifically state assigning the received behavioral recommendation by analyzing the received behavioral recommendation in a rule-based manner.
However, Zhu teaches:
assigning the received behavioral recommendation by analyzing the received behavioral recommendation in a rule-based manner. (See at least Para. 0042 and 0061, wherein the assignment is performed in a rule-based manner.)
It would have been obvious to one of the ordinary skill in the art before the effective filing date of the claimed invention to have modified Sharan to incorporate the teachings of Zhu in which the requested behavioral recommendation is assigned to Zhu’s planner-specific set of predefined driving scenarios so that the planning is performed on the basis of that assigned scenario which would avoid “time and resource consumption during real-time driving” (Para. 0062, Zhu). Furthermore, Zhu’s planner only executes behavior from its predefined set and matches to one before planning. Sharan discloses the LLM (i.e. it reads the scene and returns a recommendation) and discloses PDM-closed (i.e. a rule-based planner that plans a trajectory). Zhu’s matching step is inserted between them, which assigns the recommendation to a predefined planning scenario such that PDM-closed can plan a trajectory from that assigned scenario and Zhu operates the vehicle based on the result. Additionally, a person having ordinary skill in the art would have a reasonable expectation of success in combining the teachings of Sharan and Zhu. The claimed invention is merely a combination of known elements and in combination each element merely would have performed the same function as it did separately, and one of ordinary skill in the art before the effective filing date of the claimed invention would have recognized that the results of the combination would have been predictable.
Regarding claim 6,
Sharan discloses the neural network whose behavioral recommendation is received, but does not specifically state generating at least one target line for movement of the vehicle as input for the rule-based planner, and providing trajectory data describing a spatial and temporal movement of the vehicle along the at least one target line.
However, Zhu teaches:
generating at least one target line for movement of the vehicle as input for the rule-based planner, (See at least Para. 0053, wherein the reference line is provided to the planning module 305.)
and providing trajectory data describing a spatial and temporal movement of the vehicle along the at least one target line. (See at least Para. 0022, 0054, and 0056.)
It would have been obvious to one of the ordinary skill in the art before the effective filing date of the claimed invention to have modified Sharan to incorporate the teachings of Zhu in which the requested behavioral recommendation is assigned to Zhu’s planner-specific set of predefined driving scenarios so that the planning is performed on the basis of that assigned scenario which would avoid “time and resource consumption during real-time driving” (Para. 0062, Zhu). Furthermore, Zhu’s planner only executes behavior from its predefined set and matches to one before planning. Sharan discloses the LLM (i.e. it reads the scene and returns a recommendation) and discloses PDM-closed (i.e. a rule-based planner that plans a trajectory). Zhu’s matching step is inserted between them, which assigns the recommendation to a predefined planning scenario such that PDM-closed can plan a trajectory from that assigned scenario and Zhu operates the vehicle based on the result. Additionally, a person having ordinary skill in the art would have a reasonable expectation of success in combining the teachings of Sharan and Zhu. The claimed invention is merely a combination of known elements and in combination each element merely would have performed the same function as it did separately, and one of ordinary skill in the art before the effective filing date of the claimed invention would have recognized that the results of the combination would have been predictable.
Regarding claim 7,
Sharan and Zu discloses the same limitations as recited in claim 1 above, and is therefore rejected under the same rejection and obviousness rational.
Regarding claim 8,
Sharan and Zu discloses the same limitations as recited in claim 2 above, and is therefore rejected under the same rejection and obviousness rational.
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 GABRIEL J LAMBERT whose telephone number is (571)272-4334. The examiner can normally be reached M-F 10:00 am- 6:00 pm MDT.
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 Piateski can be reached at (571) 270-7429. 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.
/Erin M Piateski/Supervisory Patent Examiner, Art Unit 3669
/G.J.L./
Examiner
Art Unit 3669
Prosecution Insights