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 .
DETAILED ACTION
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Information Disclosure Statement
The information disclosure statement (IDS) submitted on 11/13/2025 is in compliance with the provisions of 37 CFR 1.97. Accordingly, the information disclosure statement is being considered by the examiner.
Response to Arguments
Applicant's arguments filed 2/4/2026 with respect to 35 USC 101 have been fully considered but they are not persuasive. Applicant asserts as follows:
Step 2A, Prong 1
The Examiner asserts that limitations such as "generating past trajectories," "encoding," "selecting a target vehicle," and "generating a future trajectory" constitute mental processes because, under a broadest reasonable interpretation, they could be performed in the human mind. Applicant respectfully disagrees.
Amended Claims 1 and 7 no longer recite generic data evaluation or subjective judgment. Instead, the claims require: extracting lane-center-line-based local routes from a high-definition map based on vehicle locations and heading angles; updating route encodings using correlation-based weighting operations that reflect interactions between a target vehicle, individual local routes, and nearby vehicles; and generating future trajectories separately for each local route on the basis of the past trajectory encoding and the updated local route encoding, wherein each future trajectory is generated from a probability distribution conditioned on the corresponding local route.
These operations require machine processing of high-dimensional spatial map data, vehicle kinematics, and route-conditioned probability structures. Such processing cannot practically be performed in the human mind and is not merely an observation or evaluation that a human could mentally perform. Accordingly, the claims do not recite a "mental process" as contemplated by MPEP §2106.04(a).
Examiner respectfully disagrees. The claims, while amended to recite processing of data with greater specificity, remain directed to the abstract idea of preforming mathematical operations/mental judgements given their broadest reasonable interpretation. Specifically, the application of a probability distribution is recited in the claims as being applied to generate possible future trajectories of surrounding road agents based on the assessed local routes available for each of said road agents, which is a mathematical evaluation/abstract idea under the broadest reasonable interpretation of the claim. Further, the limitation “encoding” in the context of the claim merely encompasses transforming data into a mathematical representation, and is similarly an abstract idea of processing data in the context of the claim. Regarding the Applicant’s assertion that these steps cannot be practically performed in the human mind, Examiner respectfully disagrees, asserting that while the claims encompass significant amounts of data processing, the evaluations are fundamentally mathematical in nature, and could be conceivably performed by a human with aid [MPEP 2106.04(a)(2)(III)]. Thus, Applicant arguments above are not persuasive.
Step 2A, Prong 2
A. Response to "mere data gathering /pre-solution activity"
The Examiner characterizes limitations such as "based on locations" and "extracting local routes" as mere data gathering or insignificant extra-solution activity. Applicant respectfully submits that this characterization does not apply to the amended claims.
In the present invention, the extraction of lane-center-line-based local routes transforms high-definition map data into physically drivable structures that define and constrain the trajectory prediction space itself. The extracted lane center lines are not merely collected data, but form the basis on which separate probabilistic prediction spaces are defined for individual local routes. Without this transformation, route-conditioned trajectory generation cannot occur. Accordingly, these steps are integral to the claimed solution and cannot be dismissed as pre-solution activity under MPEP §2106.05(g).
Examiner respectfully disagrees. While the data acquired may be integral to the claimed solution, the acquisition and extraction of said data does not appear to render the claim as a whole patent-eligible. The acquisition of data in and of itself appears, in the view of the Examiner, to be mere insignificant extra-solution activity, with any additional extraction taking place merely appearing to be a process to transform the data into a format usable in the asserted abstract idea. Defining “probabilistic prediction spaces” as set forth by the Applicant above further appears to merely indicate a use of the data in performing the steps of the abstract idea, which also appears to be pre-solution activity in the context of the claim. Thus, Applicant Arguments are not persuasive.
B. Response to "generic computer implementation"
The Examiner further asserts that the claims merely apply an abstract idea using generic computing components such as a processor and memory. Applicant respectfully disagrees.
The amended claims do not simply use a computer as a tool to implement an abstract idea. Rather, they recite a specific prediction architecture in which: (i) the prediction space is constrained by lane-center-line-based local routes extracted from a high-definition map; (ii) interactions between a target vehicle, individual local routes, and nearby vehicles are explicitly modeled through correlation-based weighting; and (iii) future trajectories are generated separately for each local route from probability distributions conditioned on the respective routes.
This architecture fundamentally differs from conventional trajectory prediction approaches that generate predictions from a single fused representation and a single probability distribution. Therefore, the claims recite a technological improvement to autonomous driving systems, not the mere application of an abstract idea on a generic computer.
Examiner respectfully disagrees. The claims, given their broadest reasonable interpretation, appear to merely use computing elements as a tool to perform the evaluation of predicted trajectories of surrounding objects, rather than inherently improving the functionality of a computer. The claimed technical improvement to “autonomous driving systems” appears, under the broadest reasonable interpretation of the claim, to encompass mere application in a field of use rather than the improvement of a specific technology. The computing architecture does not appear to be specific to the claims in such a way to render the claims directed to a specific system, nor does the functionality of the computer appear to be modified or otherwise improved by the implementation of the steps of the asserted Abstract Idea set forth above. Thus, Applicant Arguments are not persuasive.
C. Response to "no improvement to technology"
The Examiner states that the claims do not reflect an improvement to the functioning of a computer or another technology. Applicant respectfully submits that the claims are directed to a concrete improvement in autonomous vehicle perception and trajectory prediction.
By generating future trajectories separately for each lane-center-line-based local route from route-conditioned probability distributions, the claimed invention structurally prevents the averaging of incompatible driving behaviors across different lanes. This directly addresses and eliminates mode blur, a well-recognized technical problem in multi- modal trajectory prediction systems.
As a result, the claimed invention improves the accuracy, stability, and physical consistency of predicted trajectories, thereby improving downstream driving decisions such as lane keeping, lane changes, and collision avoidance. This constitutes a concrete technological improvement under the Revised Guidance and MPEP §2106.05(a).
Examiner respectfully disagrees. Applicant asserts in arguments above that the claims are directed to an improvement in autonomous vehicle perception and trajectory prediction, however Examiner respectfully asserts that the invention as claimed appears to be directed to apply to the field of use of autonomous vehicle perception/prediction, without integration into a specific technology in the field [MPEP 2106.05(h)]. The asserted improvements appear to encompass improvements in the mathematical process underlying trajectory prediction, while conceivably being implemented with any range of technologies used to support motion prediction of other vehicles for autonomous operation, directing the invention to the abstract idea rather than a specific technology. Further, the claim limitations do not appear to specifically improve the function of a computer or computer technology, appearing to merely recite a computation method for prediction implementable by a computer rather than improving the functionality of a computer by which the autonomous operations take place. Thus, Applicant Arguments are not persuasive
Step 2B
Because amended Claims 1 and 7 integrate any alleged abstract idea into a practical application under Step 2A, Prong 2, the § 101 inquiry is complete and Step 2B need not be reached.
Nevertheless, even if Step 2B were considered, the claims recite significantly more than any alleged abstract idea. The claims require a non-conventional combination of: HD- map-based lane center-line route extraction, correlation-based interaction weighting between vehicles and routes, and route-conditioned trajectory generation.
This ordered combination is neither routine nor conventional in the field of autonomous driving and therefore provides an inventive concept.
Examiner respectfully disagrees that the claims recite significantly more than the abstract idea. The combination set forth by the Applicant above appears under the broadest reasonable interpretation of the claim to encompass the performance of mathematical operations on data collected, as set forth above. The improvements asserted in Arguments above appear to only encompass improvements in the results of the mathematical process through the mathematical evaluations themselves, which is directed to the abstract idea rather than a specific technology. Thus, Applicant Arguments are not persuasive.
Dependent Claims 2-6 and 8-12
The Examiner asserts that dependent claims merely recite additional aspects of the alleged abstract idea. Applicant respectfully submits that this assertion is premised on an incorrect characterization of the independent claims.
As amended, independent Claims 1 and 7 are patent-eligible. The dependent claims further limit these claims with specific technical implementations that reinforce their practical application, including: sensor- and communication-based heading angle derivation (Claims 2 and 8); LSTM-based temporal encoding of trajectories and routes (Claims 3 and 9); concrete lane center-line segment processing algorithms (Claims 4 and 10); and route-conditioned probabilistic trajectory generation and selection (Claims 5, 6, 10, and 11).
Accordingly, the dependent claims rise and fall with the patent eligibility of the independent claims.
In view of the foregoing amendments and remarks, Applicant respectfully submits that Claims 1-12 are directed to a specific technological improvement in autonomous driving systems and are therefore patent-eligible under 35 U.S.C. § 101. Accordingly, favorable reconsideration and withdrawal of the rejection of Claims 1-12 under 35 U.S.C. § 101 are respectfully requested.
Examiner respectfully maintains the rejection(s) under 35 USC 101 for the Independent and Dependent Claims, for at least the reasons set forth above, as well as those set forth below with respect to the specific claim limitations.
Claim Rejections - 35 USC § 101
35 U.S.C. 101 reads as follows:
Whoever invents or discovers any new and useful process, machine, manufacture, or composition of matter, or any new and useful improvement thereof, may obtain a patent therefor, subject to the conditions and requirements of this title.
Claims 1 – 12 are rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without significantly more.
The determination of whether a claim recites patent ineligible subject matter is a 2 step inquiry.
STEP 1: the claim does not fall within one of the four statutory categories of invention (process, machine, manufacture or composition of matter), see MPEP 2106.03, or
STEP 2: the claim recites a judicial exception, e.g. an abstract idea, without reciting additional elements that amount to significantly more than the judicial exception, as determined using the following analysis: see MPEP 2106.04
STEP 2A (PRONG 1): Does the claim recite an abstract idea, law of nature, or natural phenomenon? see MPEP 2106.04(II)(A)(1)
STEP 2A (PRONG 2): Does the claim recite additional elements that integrate the judicial exception into a practical application? see MPEP 2106.04(II)(A)(2) and 2106.05(a) thru (d) for explanations.
STEP 2B: Does the claim recite additional elements that amount to significantly more than the judicial exception? see MPEP 2106.05
101 Analysis – Step 1
Claim 1 is directed to a method of predicting future vehicle trajectories (i.e., a process). Therefore, claim 1 is within at least one of the four statutory categories. Similarly, Independent Claim 7 is directed to an apparatus for predicting future vehicle trajectories [i.e. a machine] and is similarly within at least one of the four statutory categories.
101 Analysis – Step 2A, Prong I
Regarding Prong I of the Step 2A analysis, the claims are to be analyzed to determine whether they recite subject matter that falls within one of the follow groups of abstract ideas: a) mathematical concepts, b) certain methods of organizing human activity, and/or c) mental processes. see MPEP 2106(A)(II)(1) and MPEP 2106.04(a)-(c)
Independent claim 7 includes limitations that recite an abstract idea (emphasized below [with the category of abstract idea in brackets]) and will be used as a representative claim for the remainder of the 101 rejection. Claim 7 recites:
An apparatus for predicting future trajectories of nearby vehicles around an autonomous driving car, comprising:
a memory configured to store instructions readable by a computer; and at least one processor configured to execute the instructions, wherein the at least one processor is configured to execute the instructions so as to:
generate, based on locations of one or more nearby vehicles, past trajectories of the nearby vehicles; [mental process/step]
extract lane-center-line-based local routes along which the nearby vehicles are travelable from a high-definition map on the basis of current locations and heading angles of the nearby vehicles;
encode the past trajectories and the lane-center-line-based local routes to generate a past trajectory encoding and a local route encoding; [mental process/step]
select a target vehicle from among the nearby vehicles, and update a local route encoding of the target vehicle by applying a correlation-based weighting operation that reflects interactions between the target vehicle, the lane- center-line-based local routes, and nearby vehicles around the target vehicle; and [mental process/step]
generate a future trajectory of the target vehicle by generating future trajectories separately for each of the lane-center-line-based local routes on the basis of the past trajectory encoding and the updated local route encoding, [mental process/step]
wherein each future trajectory is generated from a probability distribution conditioned on the corresponding local route. [mental process/step]
The examiner submits that the foregoing bolded limitation(s) constitute a “mental process” because under its broadest reasonable interpretation, the claim covers performance of the limitation in the human mind. For example, “generate… past trajectories…” in the context of this claim encompasses a person looking at data collected regarding nearby vehicle location data and forming a simple judgement as to past trajectories of said vehicles. Further, “encode…” in the context of the claim encompasses a user converting data into a different formatting, which is a mental process under its broadest reasonable interpretation. The limitation “select…” in the context of the claim encompasses a user making a simple judgement as to a target vehicle, and updating a route based on gathered information, which is also a mental process of looking at data and forming judgements based on such. Finally, “generate a future trajectory…” and “wherein each future trajectory…” in the context of the claim encompasses determining a predicted future trajectory of a selected target vehicle based on data collected, as well as a probability distribution based on such, which are mental processes under the broadest reasonable interpretation of the claim. Accordingly, the claim recites at least one abstract idea.
101 Analysis – Step 2A, Prong II
Regarding Prong II of the Step 2A analysis, the claims are to be analyzed to determine whether the claim, as a whole, integrates the abstract into a practical application. see MPEP 2106.04(II)(A)(2) and MPEP 2106.04(d)(2). It must be determined whether any additional elements in the claim beyond the abstract idea integrate the exception into a practical application in a manner that imposes a meaningful limit on the judicial exception. The courts have indicated that additional elements merely using a computer to implement an abstract idea, adding insignificant extra solution activity, or generally linking use of a judicial exception to a particular technological environment or field of use do not integrate a judicial exception into a “practical application.”
In the present case, the additional limitations beyond the above-noted abstract idea are as follows (where the underlined portions are the “additional limitations” [with a description of the additional limitations in brackets], while the bolded portions continue to represent the “abstract idea”.):
An apparatus for predicting future trajectories of nearby vehicles around an autonomous driving car, comprising: [generic linking to technical field, 2106.05(h)]
a memory configured to store instructions readable by a computer; and at least one processor configured to execute the instructions, wherein the at least one processor is configured to execute the instructions so as to: [applying the abstract idea using generic computing module, Apply it 2106.05(f)]
generate, based on locations of one or more nearby vehicles [pre-solution activity (data gathering) 2106.05(g)], past trajectories of the nearby vehicles;
extract lane-center-line-based local routes along which the nearby vehicles are travelable from a high-definition map on the basis of current locations and heading angles of the nearby vehicles; [pre-solution activity (data gathering) 2106.05(g)]
encode the past trajectories and the lane-center-line-based local routes to generate a past trajectory encoding and a local route encoding;
select a target vehicle from among the nearby vehicles, and update a local route encoding of the target vehicle by applying a correlation-based weighting operation that reflects interactions between the target vehicle, the lane- center-line-based local routes, and nearby vehicles around the target vehicle; and
generate a future trajectory of the target vehicle by generating future trajectories separately for each of the lane-center-line-based local routes on the basis of the past trajectory encoding and the updated local route encoding,
wherein each future trajectory is generated from a probability distribution conditioned on the corresponding local route.
For the following reason(s), the examiner submits that the above identified additional limitations do not integrate the above-noted abstract idea into a practical application.
Regarding the additional limitations of “a memory…,” “based on locations…,” and “extract…,” the examiner submits that these limitations are insignificant extra-solution activities that merely use a computer to perform the process. In particular, the “based on locations…” and “extract…” limitations are recited at a high level of generality (i.e. as a general means of gathering data for use in the evaluating and generation of trajectories), and amounts to mere data gathering, which is a form of insignificant extra-solution activity. Further, the “memory…” and associated computing components are recited at a high-level of generality (i.e., as a generic processor and memory performing a generic computer function) such that it amounts no more than mere instructions to apply the exception using a generic computer component.
Thus, taken alone, the additional elements do not integrate the abstract idea into a practical application. Further, looking at the additional limitation(s) as an ordered combination or as a whole, the limitation(s) add nothing that is not already present when looking at the elements taken individually. For instance, there is no indication that the additional elements, when considered as a whole, reflect an improvement in the functioning of a computer or an improvement to another technology or technical field, apply or use the above-noted judicial exception to effect a particular treatment or prophylaxis for a disease or medical condition, implement/use the above-noted judicial exception with a particular machine or manufacture that is integral to the claim, effect a transformation or reduction of a particular article to a different state or thing, or apply or use the judicial exception in some other meaningful way beyond generally linking the use of the judicial exception to a particular technological environment, such that the claim as a whole is not more than a drafting effort designed to monopolize the exception. see MPEP § 2106.05. Accordingly, the additional limitation(s) do/does not integrate the abstract idea into a practical application because it does not impose any meaningful limits on practicing the abstract idea.
101 Analysis – Step 2B
Regarding Step 2B of the Revised Guidance, representative independent claim 1 does not include additional elements (considered both individually and as an ordered combination) that are sufficient to amount to significantly more than the judicial exception for the same reasons to those discussed above with respect to determining that the claim does not integrate the abstract idea into a practical application. As discussed above with respect to integration of the abstract idea into a practical application, the additional element of using a computing elements to perform the steps of the mental process amounts to nothing more than mere instructions to apply the exception using a generic computer component. Mere instructions to apply an exception using a generic computer component cannot provide an inventive concept. And as discussed above, the additional limitations of “based on locations…” and “extract…,” the examiner submits that these limitations are insignificant extra-solution activities.
Dependent claim(s) 2 – 6 & 8 – 12 do not recite any further limitations that cause the claim(s) to be patent eligible. Rather, the limitations of dependent claims are directed toward additional aspects of the judicial exception and do not integrate the judicial exception into a practical application. Specifically:
Claim 2 recites deriving heading angles through sensors or communication with an external source, which appears to merely recite the acquisition of data, and does not render the claim patent-eligible.
Claim 3 recites using a specific encoding process using a LSTM network, which merely constrains the encoding mental process to a specific embodiment using a computing element without reciting substantially more.
Claim 4 recites a plurality of steps for extracting local routes, including comparing the angles of lane-center segments to a predefined threshold to filter out segments, as well as merging and extending connected lane segments, each step of which appears to be a mental process of evaluating data and forming a simple judgement, and thus does not render the claim patent-eligible.
Claim 5 recites a plurality of mathematical evaluation steps for generating the future trajectory, including the generation of vector data, the input of such into a trained network, and the generation of a random vector, which is input into a decoder to generate the future trajectory, each step of which is a mathematical evaluation, and thus is considered a mental process under the broadest reasonable interpretation of the claim. Particularly, with reference to the use of a trained network, Example 57 Claim 2 recites in limitations (d) and (e) using the trained neural network as nothing more than mere instructions to implement an abstract idea on a generic computer, which does not render the claim patent-eligible.
Claim 6 recites wherein a local route selection probability is calculated based on a context vector, with the random vector of Claim 5 being generated for each route by applying a local route selection probability.
Dependent Claims 8 – 12 recite substantially similar limitations as those found in Dependent Claims 2 – 6, above, and are rejected under similar rationale.
Therefore, dependent claims 2 – 6 & 8 – 12 are not patent eligible under the same rationale as provided for in the rejection of Independent Claims 1 & 7.
Therefore, claim(s) 1 – 12 is/are ineligible under 35 USC §101.
Conclusion
The following prior art made of record but not relied upon is considered pertinent to the Applicant’s disclosure:
Varadarajan (US 2022/0297728 A1): Varadarajan recites a system for predicting the future behavior of surrounding road users, including the prediction of future trajectories of each on the basis of agent state information acquired from perception signals, and through the use of a neural network prediction model. The predicted future trajectory may include a series of possible waypoints for the surrounding agent after the current time point, and the trajectories may be generated based on an encoding of the relevant input variables.
Sun (US 2021/0174668 A1): Sun recites a system for predicting the location of a target vehicle, including receiving trajectory information for the target vehicle and determining a trajectory feature based on said information. A lane feature may further be determined in the vicinity of the target vehicle, and a probability associated with the lane may be determined based on the trajectory feature and the lane feature.
Yang (US 2021/0295132 A1): Yang recites a method for determining the coordinate sequence of a target object, including through the generation and use of an implicit random vector. The implicit states may be encoded, with an initial implicit state being determined by sampling.
Wang (CN 112233417 A): Wang recites a vehicle track prediction method, including the acquisition of road information and driving information of a target vehicle. Based on the combination of information, the predicted running track of the target vehicle may be determined, and used to plan the current running route of the own vehicle.
Li (US 2022/0169263 A1): Li recites a system for predicting the trajectory of a vehicle, including the acquisition of a map of the area and sensor data regarding the vehicle. A plurality of candidate trajectories may be defined, with an associated probability being determined for each based on extracted features, and the candidate trajectory with the highest probability may be selected for use.
Ling (CN 114708723 B): Ling recites a trajectory prediction method, including the acquisition of a birds-eye view of an environment, including position information of at least one target and road information of the environment. The relevant data may be encoded in order to obtain predicted track data of the surrounding vehicle.
Weisswange (NPL: Intelligent Traffic Flow Assist: Optimized Highway Driving Using Conditional Behavior Prediction) Weisswange recites a context-based prediction algorithm for predicting the future behaviors of surrounding vehicles based on a current traffic configuration. This may be based on contextual probabilities of each possible maneuver for surrounding vehicles, including assessed costs for each of the possible trajectories.
Olson (US 9,934,688 B2): Olson recites a computer system configured to determine planned trajectories for vehicles in the surrounding environment, including through the use of probability distributions of each of the plurality of potential planned trajectories. Probability of different behaviors may be weighted, in order to avoid overcorrecting for low-probability events.
Malach (US 12,151,685 B2): Malach recites a vehicle navigation system, including the identification of road topology and the determination of an estimated path based on said topology. Analysis may take place regarding the predicted movements of leading vehicles based on a weighted average of a plurality of individual analyses of potential surrounding vehicle paths.
Philion (US 2024/0092390 A1): Philion recites a model-based trajectory simulation of agents in an environment, including the generation of a plurality of navigation probability distributions for the agent to follow. Based on the simulations of the surrounding environment, a trajectory may be selected for the own vehicle to navigate using.
Kokaki (US 11,247,682 B2): Kokaki recitea a vehicle control system, including the determination of probability that a forward vehicle is cutting in, as well as corresponding index values. Control operations may be configured to take place in the own vehicle responsive to such determinations, including the deceleration of the own vehicle.
THIS ACTION IS MADE FINAL. 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 CHRISTOPHER RYAN CARDIMINO whose telephone number is (571)272-2759. The examiner can normally be reached M-Th 8:30-5:00.
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, Ramya Burgess can be reached at (571)272-6011. 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.
/CHRISTOPHER R CARDIMINO/Examiner, Art Unit 3661
/RAMYA P BURGESS/Supervisory Patent Examiner, Art Unit 3661
Prosecution Insights