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 (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.
Claim Status
This action is in response to applicant’s response and claim amendment filed 8/7/2026. Claims 1-20 are pending and considered below.
Response to Arguments
Claims 1-2 and 4-20 were rejected under 35 U.S.C. 102(a)(2) as being anticipated by Durant (US-2025/0259554-A1). Applicant has amended the independent claims to include the limitation “the generative AI model is configured to maximize the reward function”. Applicant argued that this amended limitation is not disclosed in Durant. However, Choi et al. (TrajGAIL: Generating urban vehicle trajectories using generative adversarial imitation learning, Transportation Research Part C, Volume 128, 2021, pp. 1-22) discloses that a generative model for urban vehicle trajectories should be trained by a generative adversarial framework, which uses a reward function from an adversarial discriminator (Abstract). Choi further discloses that the generative AI model is configured to maximize the reward function (2.2. Model framework). It would have been obvious for a person of ordinary skill in the art at the time of the effective filing date of the claimed invention to incorporate the generative model which uses a reward function of Choi into the system of determining a flight trajectory which mitigates contrail formation based on historical weather data of Durant. A person of ordinary skill would have been motivated to do so, with a reasonable expectation of success, for the purpose of analyzing flight trajectories and minimizing the greenhouse gas impact of aircraft. Claims 1-2 and 4-20 are rejected under 35 U.S.C. 103 as being unpatentable over Durant in view of Choi for the reasons given below.
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 and 4-20 are rejected under 35 U.S.C. 103 as being unpatentable over Durant (US-2025/0259554-A1, hereinafter Durant) in view of Choi et al. (TrajGAIL: Generating urban vehicle trajectories using generative adversarial imitation learning, Transportation Research Part C, Volume 128, 2021, pp. 1-22, hereinafter Choi).
Regarding claim 1, Durant discloses:
obtaining travel pathway data for a vehicle, the travel pathway data comprising environmental data in accordance with a plurality of travel pathway candidates for traversing between an origin and a destination (paragraphs [0016-0024] and [0110]; and FIG. 1, receive one or more weather parameters to determine contrail forecast-102, receive one or more flight parameters associated with at least one aircraft to determine flight data of at least one aircraft-104, receive flight schedule comprising at least one flight plan of at least one aircraft-106, and determine, based on contrail forecast data, flight data and at least one flight plan, contrail likelihood associated with at least one aircraft-110);
generating a travel pathway for the vehicle via a generative artificial intelligence (AI) model and based at least in part on the travel pathway data and the plurality of travel pathway candidates (paragraphs [0025], [0030] and [0041-0044]);
wherein: a reward function of the generative AI model is based at least in part on a negative weighted summation of at least one greenhouse emission estimate and an estimated efficiency of the vehicle pursuant to a respective travel pathway candidate (paragraphs [0025], [0030] and [0041-0044]);
the travel pathway is configured to optimize greenhouse gas (GHG) impact and efficiency of the vehicle as the vehicle traverses from the origin to the destination (paragraphs [0026-0028] and [0110]; and FIG. 1, alter, based on at least one navigational avoidance and contrail likelihood, one or more flight parameters of at least one aircraft to determine improved flight trajectory for at least one aircraft-112, and send at least one flight plan including improved flight trajectory to at least one aircraft-114); and
causing the vehicle to traverse from the origin to the destination in accordance with the travel pathway (paragraphs [0028-0030]).
Durant does not disclose that the generative AI model is configured to maximize the reward function. However, Choi discloses a generative model for urban vehicle trajectories that is trained by a generative adversarial framework, which uses a reward function from an adversarial discriminator, including the following features:
the generative AI model is configured to maximize the reward function (2.2. Model framework).
Choi teaches that a generative model for urban vehicle trajectories should be trained by a generative adversarial framework, which uses a reward function from an adversarial discriminator (Abstract). It would have been obvious for a person of ordinary skill in the art at the time of the effective filing date of the claimed invention to incorporate the generative model which uses a reward function of Choi into the system of determining a flight trajectory which mitigates contrail formation based on historical weather data of Durant. A person of ordinary skill would have been motivated to do so, with a reasonable expectation of success, for the purpose of analyzing flight trajectories and minimizing the greenhouse gas impact of aircraft.
Regarding claim 2, Durant further discloses:
the travel pathway data comprises a travel date (paragraph [0022], a date and time of a flight); and
the environmental data comprises historical environmental data and forecasted environmental data associated with a season comprising the travel date (paragraphs [0016-0022]).
Regarding claim 4, Durant further discloses:
the historical environmental data comprises historical GHG absorption pursuant to the season and in accordance with the plurality of travel pathway candidates (paragraphs [0016] and [0019]).
Regarding claim 5, Durant further discloses:
the historical environmental data comprises historical GHG emission data pursuant to the season and in accordance with the plurality of travel pathway candidates (paragraphs [0016], [0026-0028], [0042-0044] and [0047-0049]).
Regarding claim 6, Durant further discloses:
the historical environmental data comprises historical GHG concentrations pursuant to the season and in accordance with the plurality of travel pathway candidates (paragraphs [0016], [0047-0049] and [0054-0056]); and
the forecasted environmental data comprises at least one GHG concentration prediction pursuant to the season and in accordance with the plurality of travel pathway candidates (paragraphs [0016], [0047-0049] and [0054-0056]).
Regarding claim 7, Durant further discloses:
the historical environmental data comprises historical weather conditions pursuant to the season and in accordance with the plurality of travel pathway candidates (paragraphs [0016-0019]); and
the forecasted environmental data comprises at least one weather condition forecast pursuant to the season and in accordance with the plurality of travel pathway candidates (paragraphs [0016-0019]).
Regarding claim 8, Durant further discloses:
the historical environmental data comprises historical vehicle traffic pursuant to the season and in accordance with the plurality of travel pathway candidates (paragraphs [0016] and [0023-0024]); and
the forecasted environmental data comprises at least one vehicle traffic prediction pursuant to the season and in accordance with the plurality of travel pathway candidates (paragraphs [0016] and [0025]).
Regarding claim 9, Durant further discloses:
obtaining additional travel pathway data in real-time as the vehicle traverses the travel pathway (paragraphs [0028-0030]);
wherein: the additional travel pathway data is associated with at least a portion of the travel pathway and a respective geographic region comprising the at least a portion of the travel pathway (paragraphs [0028-0030]);
an atmospheric GHG concentration within the respective geographic region satisfies a predetermined threshold (paragraphs [0047-0049] and [0054-0056]);
generating, via the generative AI model, at least one travel pathway adjustment based at least in part on the additional travel pathway data (paragraphs [0025-0030]);
modifying the travel pathway based at least in part on the at least one travel pathway adjustment (paragraphs [0025-0030]);
wherein: the at least one travel pathway adjustment is configured to reduce a GHG impact of the vehicle pursuant to the respective geographic region (paragraphs [0022], [0028-0030] and [0054-0056]); and
causing the vehicle to move in accordance with the modified travel pathway (paragraphs [0028-0030]).
Regarding claim 10, Durant further discloses:
the at least one travel pathway adjustment is configured to reroute the vehicle around the respective geographic region (paragraph [0029]).
Regarding claim 11, Durant further discloses:
the at least one travel pathway adjustment is configured to reduce a movement speed of the vehicle as the vehicle traverses the respective geographic region (paragraph [0022]).
Regarding claim 12, Durant further discloses:
the at least one travel pathway adjustment is configured to adjust an altitude of the vehicle to avoid traversal of the vehicle through the respective geographic region (paragraph [0022]).
Regarding claim 13, Durant further discloses:
rendering the at least one travel pathway adjustment on a display of a computing device aboard the vehicle (paragraphs [0068] and [0070]).
Regarding claim 14, Durant further discloses:
generating a plurality of candidate travel pathway adjustments based at least in part on the additional travel pathway data (paragraphs [0025-0030]);
predicting a respective value of a cumulative reward function for the plurality of candidate travel pathway adjustments (paragraphs [0025], [0030] and [0041-0044]); and
determining, via at least one reinforcement learning operation, the at least one travel pathway adjustment based at least in part on the plurality of candidate travel pathway adjustments and the respective values of the cumulative reward function (paragraphs [0025], [0030] and [0041-0044]).
Regarding claim 15, Durant further discloses:
the cumulative reward function is based at least in part on a negative weighted summation of at least one greenhouse emission estimate and an estimated efficiency of the vehicle pursuant to a respective candidate travel pathway adjustment (paragraphs [0022] and [0041-0044]).
Regarding claim 16, Durant further discloses:
An apparatus comprising at least one processor and at least one non-transitory memory having computer-coded instructions stored thereon that, in execution with the at least one processor, cause the apparatus to: (paragraphs [0071], [0080] and [0091-0092]);
obtain travel pathway data for a vehicle, the travel pathway data comprising environmental data in accordance with a plurality of travel pathway candidates for traversing between an origin and a destination (paragraphs [0016-0024] and [0110]; and FIG. 1, receive one or more weather parameters to determine contrail forecast-102, receive one or more flight parameters associated with at least one aircraft to determine flight data of at least one aircraft-104, receive flight schedule comprising at least one flight plan of at least one aircraft-106, and determine, based on contrail forecast data, flight data and at least one flight plan, contrail likelihood associated with at least one aircraft-110);
generate a travel pathway for the vehicle via a generative AI model and based at least in part on the travel pathway data and the plurality of travel pathway candidates (paragraphs [0025], [0030] and [0041-0044]);
wherein: a reward function of the generative AI model is based at least in part on a negative weighted summation of at least one greenhouse emission estimate and an estimated efficiency of the vehicle pursuant to a respective travel pathway candidate (paragraphs [0025], [0030] and [0041-0044]);
the travel pathway is configured to optimize GHG impact and efficiency of the vehicle as the vehicle traverses from the origin to the destination (paragraphs [0026-0028] and [0110]; and FIG. 1, alter, based on at least one navigational avoidance and contrail likelihood, one or more flight parameters of at least one aircraft to determine improved flight trajectory for at least one aircraft-112, and send at least one flight plan including improved flight trajectory to at least one aircraft-114); and
cause the vehicle to traverse from the origin to the destination in accordance with the travel pathway (paragraphs [0028-0030]).
Durant does not disclose that the generative AI model is configured to maximize the reward function. However, Choi further discloses:
the generative AI model is configured to maximize the reward function (2.2. Model framework).
Choi teaches that a generative model for urban vehicle trajectories should be trained by a generative adversarial framework, which uses a reward function from an adversarial discriminator (Abstract). It would have been obvious for a person of ordinary skill in the art at the time of the effective filing date of the claimed invention to incorporate the generative model which uses a reward function of Choi into the system of determining a flight trajectory which mitigates contrail formation based on historical weather data of Durant. A person of ordinary skill would have been motivated to do so, with a reasonable expectation of success, for the purpose of analyzing flight trajectories and minimizing the greenhouse gas impact of aircraft.
Regarding claim 17, Durant further discloses:
the generative AI model is configured to map the travel pathway data to the plurality of travel pathway candidates (paragraph [0041], the process uses an iterative algorithm that calculates the global warming potential associated with altering one or more flight parameters);
based at least in part on a policy (paragraph [0028], the flight trajectory with the lowest global warming potential is selected as the improved flight trajectory);
the instructions, in execution with the at least one processor, further cause the apparatus to: (paragraphs [0071], [0080] and [0091-0092]); and
perform at least one reinforcement learning operation to generate an optimal iteration of the policy, the optimal iteration of the policy being configured to maximize the reward function of the generative AI model (paragraphs [0025], [0030] and [0041-0044]).
Regarding claim 18, Durant further discloses:
the instructions, in execution with the at least one processor, further cause the apparatus to: (paragraphs [0071], [0080] and [0091-0092]);
obtain at least one measurement of GHG impact pursuant to navigation of the vehicle over the travel pathway (paragraphs [0030-0033]); and
retrain the generative AI model based at least in part on the at least one measurement of GHG impact (paragraphs [0030-0033]).
Regarding claim 19, Durant further discloses:
the instructions, in execution with the at least one processor, further cause the apparatus to: (paragraphs [0071], [0080] and [0091-0092]);
generate a plurality of travel pathways for the vehicle via the generative AI model and based at least in part on the travel pathway data and the plurality of travel pathway candidates (paragraphs [0025-0030]); and
individual ones of the plurality of travel pathways are configured to optimize the GHG impact and efficiency of the vehicle in accordance with different time intervals (paragraphs [0026-0028] and [0110]; and FIG. 1, alter, based on at least one navigational avoidance and contrail likelihood, one or more flight parameters of at least one aircraft to determine improved flight trajectory for at least one aircraft-112, and send at least one flight plan including improved flight trajectory to at least one aircraft-114).
Regarding claim 20, Durant further discloses:
A computer program product comprising at least one non-transitory computer-readable storage medium having computer program code stored thereon that, in execution with at least one processor, is configured to: (paragraphs [0071], [0080] and [0091-0092]);
obtain travel pathway data for a vehicle, the travel pathway data comprising environmental data in accordance with a plurality of travel pathway candidates for traversing between an origin and a destination (paragraphs [0016-0024] and [0110]; and FIG. 1, receive one or more weather parameters to determine contrail forecast-102, receive one or more flight parameters associated with at least one aircraft to determine flight data of at least one aircraft-104, receive flight schedule comprising at least one flight plan of at least one aircraft-106, and determine, based on contrail forecast data, flight data and at least one flight plan, contrail likelihood associated with at least one aircraft-110);
generate a travel pathway for the vehicle via a generative artificial intelligence (AI) model and based at least in part on the travel pathway data and the plurality of travel pathway candidates (paragraphs [0025], [0030] and [0041-0044]);
wherein: a reward function of the generative AI model is based at least in part on a negative weighted summation of at least one greenhouse emission estimate and an estimated efficiency of the vehicle pursuant to a respective travel pathway candidate (paragraphs [0025], [0030] and [0041-0044]);
the travel pathway is configured to optimize GHG impact and efficiency of the vehicle as the vehicle traverses from the origin to the destination (paragraphs [0026-0028] and [0110]; and FIG. 1, alter, based on at least one navigational avoidance and contrail likelihood, one or more flight parameters of at least one aircraft to determine improved flight trajectory for at least one aircraft-112, and send at least one flight plan including improved flight trajectory to at least one aircraft-114); and
cause the vehicle to traverse from the origin to the destination in accordance with the travel pathway (paragraphs [0028-0030]).
Durant does not disclose that the generative AI model is configured to maximize the reward function. However, Choi further discloses:
the generative AI model is configured to maximize the reward function (2.2. Model framework).
Choi teaches that a generative model for urban vehicle trajectories should be trained by a generative adversarial framework, which uses a reward function from an adversarial discriminator (Abstract). It would have been obvious for a person of ordinary skill in the art at the time of the effective filing date of the claimed invention to incorporate the generative model which uses a reward function of Choi into the system of determining a flight trajectory which mitigates contrail formation based on historical weather data of Durant. A person of ordinary skill would have been motivated to do so, with a reasonable expectation of success, for the purpose of analyzing flight trajectories and minimizing the greenhouse gas impact of aircraft.
Claim 3 is rejected under 35 U.S.C. 103 as being unpatentable over Durant in view of Choi, as applied to claim 2 above, and further in view of Tanahashi (US-2017/0003690-A1, hereinafter Tanahashi).
Regarding claim 3, Durant in view of Choi does not disclose that the historical environmental data comprises historical photosynthetic activity pursuant to the season. However, Tanahashi discloses a system for maneuvering an unmanned airplane based on sensed data, including the following features:
the historical environmental data comprises historical photosynthetic activity pursuant to the season (paragraph [0034]; and FIG. 2, unmanned airplane-12, and shape detection sensor-34); and
in accordance with the plurality of travel pathway candidates (paragraph [0073]; and FIG. 6, Necessary inspection point Pe is present? - S23, and Move to necessary inspection point Pe - S24).
Tanahashi teaches that the flight plan for an unmanned airplane should be determined based on comparing the sensed condition of crops in an agricultural field with the expected condition of the crops (paragraphs [0034] and [0073]). It would have been obvious for a person of ordinary skill in the art at the time of the effective filing date of the claimed invention to incorporate the system of including the condition of crops in the historical environmental data of Tanahashi into the system of determining a flight trajectory which mitigates contrail formation based on historical weather data of Durant in view of Choi. A person of ordinary skill would have been motivated to do so, with a reasonable expectation of success, for the purpose of reducing greenhouse emission impacts to crops from an airplane travel pathway.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
Russo et al. (US-2025/0238813-A1) discloses an apparatus for carbon emission optimization using machine-learning (Abstract). Transportation plan templates serve as benchmarks for comparing and evaluating the efficiency, cost-effectiveness, and carbon emission implication or alternative routes or modes proposed by generative machine learning models (paragraph [0065]).
Stappen et al., Integrating Generative Artificial Intelligence in Intelligent Vehicle Systems, 2023 IEEE 26th International Conference on Intelligent Transportation Systems (ITSC), September 24-28, 2023, pp. 5790-5797, discloses the use of generative artificial intelligence and foundation models within the context of intelligent vehicles (Abstract).
Han et al., Generating and Evolving Reward Functions for Highway Driving with Large Language Models, 2024 IEEE 27th International Conference on Intelligent Transportation Systems (ITSC), September 24-27, 2024, pp. 831-836, discloses integrating Large Language Models (LLMs) with Reinforcement Learning (RL) to improve reward function design in autonomous driving (Abstract).
Afolayan et al., Emerging Trends in Machine Learning Assisted Optimization Techniques Across Intelligent Transportation Systems, IEEE Access, Volume 12, November 18, 2024, pp. 173981-174005, discloses model-based optimization approaches, reinforcement learning techniques, model-predictive control techniques, and generative artificial intelligence (AI) techniques used in Intelligent Transport Systems (ITS) (Abstract).
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 TAMARA L WEBER whose telephone number is (303)297-4249. The examiner can normally be reached 8:30-5:00 MTN.
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, Faris Almatrahi can be reached at 3134464821. 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.
TAMARA L. WEBER
Examiner
Art Unit 3667
/TAMARA L WEBER/Examiner, Art Unit 3667
Prosecution Insights