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 .
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.
Claim 1-20 are rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without significantly more.
A claim that recites an abstract idea, a law of nature, or a natural phenomenon is directed to a judicial exception. Abstract ideas include the following groupings of subject matter, when recited as such in a claim limitation: (a) Mathematical concepts – mathematical relationships, mathematical formulas or equations, mathematical calculations; (b) Certain methods of organizing human activity – fundamental economic principles or practices (including hedging, insurance, mitigating risk); commercial or legal interactions (including agreements in the form of contracts; legal obligations; advertising, marketing or sales activities or behaviors; business relations); managing personal behavior or relationships or interactions between people (including social activities, teaching, and following rules or instructions); and (c) Mental processes – concepts performed in the human mind (including an observation, evaluation, judgment, opinion). See the 2019 Revised Patent Subject Matter Eligibility Guidance.
Even when a judicial element is recited in the claim, an additional claim element(s) that integrates the judicial exception into a practical application of that exception renders the claim eligible under §101. A claim that integrates a judicial exception into a practical application will apply, rely on, or use the judicial exception in a manner that imposes a meaningful limit on the judicial exception, such that the claim is more than a drafting effort designed to monopolize the judicial exception. The following examples are indicative that an additional element or combination of elements may integrate the judicial exception into a practical application:
the additional element(s) reflects an improvement in the functioning of a computer, or an improvement to other technology or technical field;
the additional element(s) that applies or uses a judicial exception to effect a particular treatment or prophylaxis for a disease or medical condition;
the additional element(s) implements a judicial exception with, or uses a judicial exception in conjunction with, a particular machine or manufacture that is integral to the claim;
the additional element(s) effects a transformation or reduction of a particular article to a different state or thing; and
the additional element(s) applies or uses 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 more than a drafting effort designed to monopolize the exception.
Examples in which the judicial exception has not been integrated into a practical application include:
the additional element(s) merely recites the words ‘‘apply it’’ (or an equivalent) with the judicial exception, or merely includes instructions to implement an abstract idea on a computer, or merely uses a computer as a tool to perform an abstract idea;
the additional element(s) adds insignificant extra-solution activity to the judicial exception; and
the additional element does no more than generally link the use of a judicial exception to a particular technological environment or field of use.
See the 2019 Revised Patent Subject Matter Eligibility Guidance.
Claims 1, 11 & 18 recite obtaining a first trajectory, the first trajectory comprises a sequence of a plurality of vehicle states, generating a second trajectory based on the at least one perturbed vehicle state, smoothening the second trajectory to correspond to the first trajectory, using the smoothened second trajectory to produce a planned trajectory for controlling a vehicle, as drafted, is a device & process that, under its broadest reasonable interpretation, covers performance of the limitation in the mind but for the recitation of generic computer elements. The claim is practically able to be performed in the mind. For example, but for the “A method, a machine learning model, perturbing at least one of the plurality of vehicle states, training the machine learning model, A system, comprising: a memory storing instructions; and one or more processors communicably coupled to the memory and configured to execute the instructions to, A computer system, the computer system comprising: a memory storing instructions; and one or more processors communicably coupled to the memory and configured to execute the instructions to, generate second trajectory data based on applying noise to first trajectory data; create a collision loss function based on the second trajectory data” language, “obtaining a first trajectory, the first trajectory comprises a sequence of a plurality of vehicle states, generating a second trajectory based on the at least one perturbed vehicle state, smoothening the second trajectory to correspond to the first trajectory, using the smoothened second trajectory to produce a planned trajectory for controlling a vehicle” in the context of this claim encompasses the user discerning and calculating a smoother route based on the first trajectory and potential obstacles. If a claim limitation, under its broadest reasonable interpretation, covers performance of the limitation in the mind but for the recitation of generic computer components, then it falls within the “Mental Processes” grouping of abstract ideas. Accordingly, the claim recites an abstract idea.
This judicial exception is not integrated into a practical application. In particular, the claim only recites additional elements – using “A method, a machine learning model, perturbing at least one of the plurality of vehicle states, training the machine learning model, A system, comprising: a memory storing instructions; and one or more processors communicably coupled to the memory and configured to execute the instructions to, A computer system, the computer system comprising: a memory storing instructions; and one or more processors communicably coupled to the memory and configured to execute the instructions to, generate second trajectory data based on applying noise to first trajectory data; create a collision loss function based on the second trajectory data”. The devices are recited at a high-level of generality (i.e., device configured to generate a smoother second trajectory) such that it amounts no more than mere instructions to apply the exception using generic computer components. Accordingly, this additional element does not integrate the abstract idea into a practical application because it does not impose any meaningful limits on practicing the abstract idea. The claim is directed to an abstract idea.
The claim(s) do not include additional elements that are sufficient to amount to significantly more than the judicial exception because the additional elements, as discussed above with respect to integration of the abstract idea into a practical application, the additional elements of using “A method, a machine learning model, perturbing at least one of the plurality of vehicle states, training the machine learning model, A system, comprising: a memory storing instructions; and one or more processors communicably coupled to the memory and configured to execute the instructions to, A computer system, the computer system comprising: a memory storing instructions; and one or more processors communicably coupled to the memory and configured to execute the instructions to, generate second trajectory data based on applying noise to first trajectory data; create a collision loss function based on the second trajectory data,”, amounts to no more than mere instructions to apply the exception using generic computer components. Mere instructions to apply an exception using generic computer components cannot provide an inventive concept. The claim is not patent eligible.
Similarly for claims 2-10, 12-17, & 19-20, is a device and process that, under its broadest reasonable interpretation, covers performance of the limitation in the mind but for the recitation of generic computer components. For example, in the context of these claim encompasses the user calculating the smoother second trajectory using AI and other data. If a claim limitation, under its broadest reasonable interpretation, covers performance of the limitation in the mind but for the recitation of generic computer components, then it falls within the “Mental Processes” grouping of abstract ideas. Accordingly, the claim recites an abstract idea.
This judicial exception is not integrated into a practical application. In particular, the claim only recites additional elements. The claim(s) do not include additional elements that are sufficient to amount to significantly more than the judicial exception. The devices are recited at a high-level of generality (i.e., device configured generate a smoother second trajectory) such that it amounts no more than mere instructions to apply the exception using generic computer components. Accordingly, this additional element does not integrate the abstract idea into a practical application because it does not impose any meaningful limits on practicing the abstract idea. Mere instructions to apply an exception using generic computer components cannot provide an inventive concept. The claim is not patent eligible.
Claim Rejections - 35 USC § 102
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 the appropriate paragraphs of 35 U.S.C. 102 that form the basis for the rejections under this section made in this Office action:
A person shall be entitled to a patent unless –
(a)(1) the claimed invention was patented, described in a printed publication, or in public use, on sale, or otherwise available to the public before the effective filing date of the claimed invention.
(a)(2) the claimed invention was described in a patent issued under section 151, or in an application for patent published or deemed published under section 122(b), in which the patent or application, as the case may be, names another inventor and was effectively filed before the effective filing date of the claimed invention.
Claim(s) 1, 4-6, 9-11, 13-14, & 16-17 is/are rejected under 35 U.S.C. 102(a)(2) as being anticipated by US 2024/0092357A1 (“Kobilarov”).
As per claim 1 Kobilarov discloses
A method comprising (see at least Kobilarov, para. [0031]: Although discussed in the context of an autonomous vehicle, the methods, apparatuses, and systems described herein may be applied to a variety of systems (e.g., a sensor system or a robotic platform), and are not limited to autonomous vehicles.):
obtaining a first trajectory for a machine learning model, the first trajectory comprises a sequence of a plurality of vehicle states (see at least Kobilarov, para. [0059]: As discussed above, there are any number of possible trajectories that the autonomous vehicle 102 can take to traverse from the start state 302 to the end state 304, with each possible trajectory having a sequence of trajectory points including a number spatiotemporal states of the vehicle (e.g., x-position, y-position, yaw, yaw rate, steering angle, steering angle rate, velocity, acceleration, etc.). In this example, baseline trajectory 306 may represent a simplified and non-optimal trajectory including a number of trajectory points (e.g., 306a-306e, and also may include the start state 302 and/or the end state 304) that follows the center line and a constant speed within the driving lane…);
perturbing at least one of the plurality of vehicle states (see at least Kobilarov, para. [0060]: FIG. 3B depicts an example perturbed trajectory 310 for traversing the driving route, that has been perturbed relative to the baseline trajectory 306. As described above, the perturbed trajectory 310 may include a number of trajectory points (e.g., 310a-310g) determined based on a variable set provided by the optimization component 202 to the perturbed trajectory generator 204. The variable set may correspond to the set of relative vehicle state parameters in the perturbed parameter table 312. Each parameter in the parameter table 312 may define any a velocity difference or a lateral offset of the perturbed trajectory 310, relative to the baseline trajectory 306, at a particular trajectory point. The perturbed trajectory generator 204 also may construct a variable vector 314 including each of the relative vehicle state parameters from the parameter table 312. As described above, the perturbed trajectory generator 204 may provide the perturbed trajectory in the form of a variable vector (e.g., vector 314) as an input to the active prediction model 206.);
generating a second trajectory based on the at least one perturbed vehicle state (see at least Kobilarov, para. [0061]: In such cases, either within the perturbed trajectory generator 204, or within the active prediction model 206, the infeasible perturbed trajectory 316 may be transformed into a feasible perturbed trajectory 318 with modified trajectory points (not shown) that correspond to same time segments and/or trajectory length segments as the trajectory points of the perturbed trajectory 316. For example, the perturbed trajectory generator 204 may determine the feasible perturbed trajectory 318 as the closest approximate trajectory to the infeasible perturbed trajectory 316, that the autonomous vehicle 102 is kino-dynamically capable of performing. Although not shown in this example, when the perturbed trajectory generator 204 modifies an infeasible perturbed trajectory 316 into a feasible perturbed trajectory 318, it also may update the variable vector 314 accordingly before providing it to the active prediction model 206.);
smoothening the second trajectory to correspond to the first trajectory (see at least Kobilarov, para. [0081]: As discussed above, the active prediction model 206 may output a feasible trajectory for the autonomous vehicle in operation 708, that may or may not be the same as the perturbed trajectory provided as input to the active prediction model 206. For instance, if a perturbed trajectory is determined that is initially kino-dynamically infeasible for the autonomous vehicle 102 to perform, the perturbed trajectory generator 204 and/or the active prediction model 206 may be configured to smooth and/or modify the perturbed trajectory in a feasible trajectory. ); and
training the machine learning model using the smoothened second trajectory to produce a planned trajectory for controlling a vehicle (see at least Kobilarov, para. [0080-0081]: As described above, the active prediction model 206 may include one or more ML models trained to output, based at least in part on the perturbed trajectory, predictions of future trajectories/states of the autonomous vehicle 102 and/or any additional agents in the driving environment. The active prediction model 206 may receive as input the perturbed trajectory (e.g., in the form of a variable vector) and/or a representation of the driving scene (e.g., a scene encoding) at an initial time point).
As per claim 4 Kobilarov discloses
wherein the plurality of vehicle states are based on vehicle data collected by a vehicle while performing a maneuver (see at least Kobilarov, para. [0035]: The planning component 108 may determine a route based at least in part on sensor data, map data, and/or based on an intended destination of a mission (e.g., received from a passenger, from a command center, etc.). As noted above, references to a “state” or “vehicle state” may include geometric state data, such as position (or location) and/or a pose (e.g., position and/or orientation/heading including yaw and steering angle) of a vehicle. Additionally, in some examples, a vehicle state may comprise any combination of a geometric state data for a vehicle, as well as temporal state data for the vehicle (e.g., a velocity, acceleration, yaw, yaw rate, steering angle, steering angle rate, etc.) and/or may include any other status data associated with the vehicle (e.g., current vehicle status data, the status of vehicle signals and operational controls, etc.).).
As per claim 5 Kobilarov discloses
wherein the at least one of the plurality of vehicle states is an initial vehicle state of the sequence of the plurality of vehicle states (see at least Kobilarov, Fig. 3A-C & para. [0060]: FIG. 3B depicts an example perturbed trajectory 310 for traversing the driving route, that has been perturbed relative to the baseline trajectory 306. As described above, the perturbed trajectory 310 may include a number of trajectory points (e.g., 310a-310g) determined based on a variable set provided by the optimization component 202 to the perturbed trajectory generator 204. The variable set may correspond to the set of relative vehicle state parameters in the perturbed parameter table 312. Each parameter in the parameter table 312 may define any a velocity difference or a lateral offset of the perturbed trajectory 310, relative to the baseline trajectory 306, at a particular trajectory point. The perturbed trajectory generator 204 also may construct a variable vector 314 including each of the relative vehicle state parameters from the parameter table 312.).
As per claim 6 Kobilarov discloses
wherein generating the second trajectory is based on the perturbed first vehicle state as an initial state of the second trajectory (see at least Kobilarov, Fig. 3C & para. [0061]: In this example, the perturbed trajectory 310 may be an infeasible perturbed trajectory 316 including a number of trajectory points (e.g., 316a-316m). In such cases, either within the perturbed trajectory generator 204, or within the active prediction model 206, the infeasible perturbed trajectory 316 may be transformed into a feasible perturbed trajectory 318 with modified trajectory points (not shown) that correspond to same time segments and/or trajectory length segments as the trajectory points of the perturbed trajectory 316. For example, the perturbed trajectory generator 204 may determine the feasible perturbed trajectory 318 as the closest approximate trajectory to the infeasible perturbed trajectory 316, that the autonomous vehicle 102 is kino-dynamically capable of performing.).
As per claim 9 Kobilarov discloses
wherein smoothening the second trajectory to correspond to the first trajectory comprises: applying a control loop with feedback to converge the second trajectory to the first trajectory (see at least Kobilarov, para. [0061]: For example, the perturbed trajectory generator 204 may determine the feasible perturbed trajectory 318 as the closest approximate trajectory to the infeasible perturbed trajectory 316, that the autonomous vehicle 102 is kino-dynamically capable of performing. Although not shown in this example, when the perturbed trajectory generator 204 modifies an infeasible perturbed trajectory 316 into a feasible perturbed trajectory 318, it also may update the variable vector 314 accordingly before providing it to the active prediction model 206. para. [0083]: At operation 714, the planning component 108 may determine whether the perturbed trajectory is to be selected as a potential control trajectory to be used by the autonomous vehicle 102 to traverse the driving route. With the optimization component 202 determines that the algorithm should continue and/or that the current perturbed trajectory is not an optimal solution (714:No), then process 700 may return to operation 704 to perturb and evaluate another potential solution selected in accordance with the optimization algorithm..).
As per claim 10 Kobilarov discloses
further comprising: deploying the trained machine learning model on one or more vehicles for generating planned trajectories that account for deviations in actual trajectories relative to training trajectories (see at least Kobilarov, Fig. 6 & para. [0073]: FIG. 6 illustrates an example system 600 including multiple computing devices (e.g., a CPU and a GPU) configured to predict driving scenes and compute costs associated with various perturbed trajectories for an autonomous vehicle. As described above, in some examples, stochastic optimization may scale well with processing via GPUs and/or other similar parallel compute architectures. Accordingly, as shown in this example, an optimization component 202 executing a stochastic optimization technique, and a perturbed trajectory generator 204 may be executed on the CPU, while the compute-heavy active prediction model 206 and cost evaluator 208 may be executed on a GPU.).
As per claim 11 Kobilarov discloses
A system, comprising: a memory storing instructions; and one or more processors communicably coupled to the memory and configured to execute the instructions to (see at least Kobilarov, para. [0112]: The methods described herein represent sequences of operations that may be implemented in hardware, software, or a combination thereof. In the context of software, the blocks represent computer-executable instructions stored on one or more computer-readable storage media that, when executed by one or more processors, perform the recited operations. Generally, computer-executable instructions include routines, programs, objects, components, data structures, and the like that perform particular functions or implement particular abstract data types):
obtain a training trajectory used to train a machine learning model, the training trajectory comprises a sequence of a plurality of vehicle states (see at least Kobilarov, para. [0059]: As discussed above, there are any number of possible trajectories that the autonomous vehicle 102 can take to traverse from the start state 302 to the end state 304, with each possible trajectory having a sequence of trajectory points including a number spatiotemporal states of the vehicle (e.g., x-position, y-position, yaw, yaw rate, steering angle, steering angle rate, velocity, acceleration, etc.). In this example, baseline trajectory 306 may represent a simplified and non-optimal trajectory including a number of trajectory points (e.g., 306a-306e, and also may include the start state 302 and/or the end state 304) that follows the center line and a constant speed within the driving lane…);
perturb at least one of the plurality of vehicle states (see at least Kobilarov, para. [0060]: FIG. 3B depicts an example perturbed trajectory 310 for traversing the driving route, that has been perturbed relative to the baseline trajectory 306. As described above, the perturbed trajectory 310 may include a number of trajectory points (e.g., 310a-310g) determined based on a variable set provided by the optimization component 202 to the perturbed trajectory generator 204. The variable set may correspond to the set of relative vehicle state parameters in the perturbed parameter table 312. Each parameter in the parameter table 312 may define any a velocity difference or a lateral offset of the perturbed trajectory 310, relative to the baseline trajectory 306, at a particular trajectory point. The perturbed trajectory generator 204 also may construct a variable vector 314 including each of the relative vehicle state parameters from the parameter table 312. As described above, the perturbed trajectory generator 204 may provide the perturbed trajectory in the form of a variable vector (e.g., vector 314) as an input to the active prediction model 206.);
generate a modified training trajectory based on the at least one perturbed vehicle state and convergence to the training trajectory (see at least Kobilarov, para. [0061]: In such cases, either within the perturbed trajectory generator 204, or within the active prediction model 206, the infeasible perturbed trajectory 316 may be transformed into a feasible perturbed trajectory 318 with modified trajectory points (not shown) that correspond to same time segments and/or trajectory length segments as the trajectory points of the perturbed trajectory 316. For example, the perturbed trajectory generator 204 may determine the feasible perturbed trajectory 318 as the closest approximate trajectory to the infeasible perturbed trajectory 316, that the autonomous vehicle 102 is kino-dynamically capable of performing. Although not shown in this example, when the perturbed trajectory generator 204 modifies an infeasible perturbed trajectory 316 into a feasible perturbed trajectory 318, it also may update the variable vector 314 accordingly before providing it to the active prediction model 206. para. [0081]: As discussed above, the active prediction model 206 may output a feasible trajectory for the autonomous vehicle in operation 708, that may or may not be the same as the perturbed trajectory provided as input to the active prediction model 206. For instance, if a perturbed trajectory is determined that is initially kino-dynamically infeasible for the autonomous vehicle 102 to perform, the perturbed trajectory generator 204 and/or the active prediction model 206 may be configured to smooth and/or modify the perturbed trajectory in a feasible trajectory. ); and
train the machine learning model using the training trajectory to produce a planned trajectory (see at least Kobilarov, para. [0080-0081]: As described above, the active prediction model 206 may include one or more ML models trained to output, based at least in part on the perturbed trajectory, predictions of future trajectories/states of the autonomous vehicle 102 and/or any additional agents in the driving environment. The active prediction model 206 may receive as input the perturbed trajectory (e.g., in the form of a variable vector) and/or a representation of the driving scene (e.g., a scene encoding) at an initial time point).
As per claim 13 Kobilarov discloses
wherein the plurality of vehicle states are based on vehicle data collected by a vehicle while performing a maneuver (see at least Kobilarov, para. [0035]: The planning component 108 may determine a route based at least in part on sensor data, map data, and/or based on an intended destination of a mission (e.g., received from a passenger, from a command center, etc.). As noted above, references to a “state” or “vehicle state” may include geometric state data, such as position (or location) and/or a pose (e.g., position and/or orientation/heading including yaw and steering angle) of a vehicle. Additionally, in some examples, a vehicle state may comprise any combination of a geometric state data for a vehicle, as well as temporal state data for the vehicle (e.g., a velocity, acceleration, yaw, yaw rate, steering angle, steering angle rate, etc.) and/or may include any other status data associated with the vehicle (e.g., current vehicle status data, the status of vehicle signals and operational controls, etc.).).
As per claim 14 Kobilarov discloses
wherein the at least one of the plurality of vehicle states is an initial vehicle state of the sequence of the plurality of vehicle states (see at least Kobilarov, Fig. 3A-C & para. [0060]: FIG. 3B depicts an example perturbed trajectory 310 for traversing the driving route, that has been perturbed relative to the baseline trajectory 306. As described above, the perturbed trajectory 310 may include a number of trajectory points (e.g., 310a-310g) determined based on a variable set provided by the optimization component 202 to the perturbed trajectory generator 204. The variable set may correspond to the set of relative vehicle state parameters in the perturbed parameter table 312. Each parameter in the parameter table 312 may define any a velocity difference or a lateral offset of the perturbed trajectory 310, relative to the baseline trajectory 306, at a particular trajectory point. The perturbed trajectory generator 204 also may construct a variable vector 314 including each of the relative vehicle state parameters from the parameter table 312.).
As per claim 16 Kobilarov discloses
wherein the one or more processors are further configured to execute the instructions to: smoothen the modified training trajectory to correspond to the training trajectory based on applying a control loop to converge the modified training trajectory to the training trajectory (see at least Kobilarov, para. [0061]: For example, the perturbed trajectory generator 204 may determine the feasible perturbed trajectory 318 as the closest approximate trajectory to the infeasible perturbed trajectory 316, that the autonomous vehicle 102 is kino-dynamically capable of performing. Although not shown in this example, when the perturbed trajectory generator 204 modifies an infeasible perturbed trajectory 316 into a feasible perturbed trajectory 318, it also may update the variable vector 314 accordingly before providing it to the active prediction model 206. para. [0083]: At operation 714, the planning component 108 may determine whether the perturbed trajectory is to be selected as a potential control trajectory to be used by the autonomous vehicle 102 to traverse the driving route. With the optimization component 202 determines that the algorithm should continue and/or that the current perturbed trajectory is not an optimal solution (714:No), then process 700 may return to operation 704 to perturb and evaluate another potential solution selected in accordance with the optimization algorithm..).
As per claim 17 Kobilarov discloses
wherein the one or more processors are further configured to execute the instructions to: deploy the trained machine learning model on one or more vehicles for generating planned trajectories that account for deviations in actual trajectories relative to training trajectories (see at least Kobilarov, Fig. 6 & para. [0073]: FIG. 6 illustrates an example system 600 including multiple computing devices (e.g., a CPU and a GPU) configured to predict driving scenes and compute costs associated with various perturbed trajectories for an autonomous vehicle. As described above, in some examples, stochastic optimization may scale well with processing via GPUs and/or other similar parallel compute architectures. Accordingly, as shown in this example, an optimization component 202 executing a stochastic optimization technique, and a perturbed trajectory generator 204 may be executed on the CPU, while the compute-heavy active prediction model 206 and cost evaluator 208 may be executed on a GPU.).
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.
This application currently names joint inventors. In considering patentability of the claims the examiner presumes that the subject matter of the various claims was commonly owned as of the effective filing date of the claimed invention(s) absent any evidence to the contrary. Applicant is advised of the obligation under 37 CFR 1.56 to point out the inventor and effective filing dates of each claim that was not commonly owned as of the effective filing date of the later invention in order for the examiner to consider the applicability of 35 U.S.C. 102(b)(2)(C) for any potential 35 U.S.C. 102(a)(2) prior art against the later invention.
The factual inquiries for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or nonobviousness.
Claim(s) 2 & 12 is/are rejected under 35 U.S.C. 103 as being unpatentable over Kobilarov, in view of US 2025/0115278A1 (“Pittaluga”).
As per claim 2 Kobilarov does not explicitly disclose
further comprising: introducing a collision loss function to the machine learning model based on the second trajectory; and
training the machine learning model to minimize the collision loss function.
Pittaluga teaches
further comprising: introducing a collision loss function to the machine learning model based on the second trajectory; and training the machine learning model to minimize the collision loss function (see at least Pittaluga, para. [0030]: To generate adversarial perturbations, the ground-truth past and future trajectories of all vehicles in the scene and a map of the scene are fed as input into a pretrained encoder neural network to generate a scene encoding, which is used to initialize a set of learnable parameters of the same shape. The learnable parameters are then optimized (perturbed) via standard learning algorithms, such as stochastic gradient descent, to minimize a combination of losses ALAN adversarial loss function, a traffic violation loss function, adversarial collision loss function, and a comfort loss function. To compute these losses, the learnable parameters are decoded by a pretrained decoder neural network into adversarial trajectories for the neighboring agents. The adversarial perturbed trajectories can be iteratively computed until a threshold has been met.).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified Kobilarov to incorporate the teaching of introduce a collision loss function to the machine learning model based on the modified training trajectory; and train the machine learning model to minimize the collision loss function of Pittaluga, with a reasonable expectation of success, in order to prevent future accidents and provide a more comfortable ride for their passengers (see at least Pittaluga, para. [0022]).
As per claim 12 Kobilarov does not explicitly disclose
wherein the one or more processors are further configured to execute the instructions to:
introduce a collision loss function to the machine learning model based on the modified training trajectory; and
train the machine learning model to minimize the collision loss function.
Pittaluga teaches
wherein the one or more processors are further configured to execute the instructions to:
introduce a collision loss function to the machine learning model based on the modified training trajectory; and train the machine learning model to minimize the collision loss function (see at least Pittaluga, para. [0030]: To generate adversarial perturbations, the ground-truth past and future trajectories of all vehicles in the scene and a map of the scene are fed as input into a pretrained encoder neural network to generate a scene encoding, which is used to initialize a set of learnable parameters of the same shape. The learnable parameters are then optimized (perturbed) via standard learning algorithms, such as stochastic gradient descent, to minimize a combination of losses ALAN adversarial loss function, a traffic violation loss function, adversarial collision loss function, and a comfort loss function. To compute these losses, the learnable parameters are decoded by a pretrained decoder neural network into adversarial trajectories for the neighboring agents. The adversarial perturbed trajectories can be iteratively computed until a threshold has been met.).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified Kobilarov to incorporate the teaching of introduce a collision loss function to the machine learning model based on the modified training trajectory; and train the machine learning model to minimize the collision loss function of Pittaluga, with a reasonable expectation of success, in order to prevent future accidents and provide a more comfortable ride for their passengers (see at least Pittaluga, para. [0022]).
Claim(s) 3 is/are rejected under 35 U.S.C. 103 as being unpatentable over Kobilarov, in view of Pittaluga, in view of US 2025/0026376A1 (“Schlacter”).
As per claim 3 Kobilarov does not explicitly disclose
wherein the collision loss function is based on detecting a collision of an ego vehicle and a road agent along the second trajectory and determining a magnitude of the collision, wherein minimizing the collision loss function is based on the magnitude of the collision
Schlacter teaches
wherein the collision loss function is based on detecting a collision of an ego vehicle and a road agent along the second trajectory and determining a magnitude of the collision, wherein minimizing the collision loss function is based on the magnitude of the collision (see at least Schlacter, para. [0062]: The object tracker 320 can associate the newly detected object with the generated tracking identifier if the Intersection Over Union (IOU) of the predicted bounding box and the actual bounding box is greater than a predetermined value. The object tracker 320 can calculate the IOU as the ratio of the area of the intersection of two bounding boxes to the area of their union. To calculate the IOU, the object tracker 320 can determine the coordinates of the top-left and bottom-right corners of the overlapping region between the two bounding boxes (e.g., by subtracting determined coordinates of each bounding box). Then, the object tracker 320 can calculate the width and height of the overlap and utilize the width and height to calculate the area of the overlap. The object tracker 320 can calculate the area of union as the sum of the areas of the two bounding boxes minus the area of their overlap, and then calculate the IOU as the ratio of the area of intersection to the area of the union. & para. [0068]: In some implementations, the object tracking and classification module 300 may include a cost analysis function module. The cost analysis function module may receive inputs from other components of object tracking and classification module 300 and generates a collision-aware cost function. The autonomy system may apply this collision-aware cost function in conjunction with other functions used in path planning. In an embodiment, the cost analysis function module provides a cost map that yields a path that has appropriate margins between the automated vehicle and surrounding target objects. & para. [0089]: The autonomy system generates the predicted trajectory track of the close vehicle up to the future time by modeling or otherwise determining a progression of projected or estimated vehicle positions of the close vehicle over time, from a current or initial time to the future time.).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified Kobilarov to incorporate the teaching of wherein the collision loss function is based on detecting a collision of an ego vehicle and a road agent along the second trajectory and determining a magnitude of the collision, wherein minimizing the collision loss function is based on the magnitude of the collision of Schlacter, with a reasonable expectation of success, in order to improve the accuracy of its predictions (see at least Schlacter, para. [0058]).
Claim(s) 7-8, & 15 is/are rejected under 35 U.S.C. 103 as being unpatentable over Kobilarov, in view of US 2024/0149918A1 (“Li”).
As per claim 7 Kobilarov does not explicitly disclose
wherein perturbing at least one of the plurality of vehicle states comprises: applying noise to the at least one of the plurality of vehicle states.
Li teaches
wherein perturbing at least one of the plurality of vehicle states comprises: applying noise to the at least one of the plurality of vehicle states (see at least Li, para. [0067]: Observation: it may be assumed that the physical states of the surrounding vehicles and pedestrians may be observable to the ego-agent, while the internal states may be not observable. The observation may be represented by o=[{circumflex over (x)}.sup.0, . . . , {circumflex over (x)}.sup.N+M], where {circumflex over (x)}.sup.i may be obtained by adding a little noise sampled from a zero-mean Gaussian distribution to the actual position and velocity to simulate sensor noise.).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified Kobilarov to incorporate the teaching of wherein perturbing at least one of the plurality of vehicle states comprises: applying noise to the at least one of the plurality of vehicle states of Li, with a reasonable expectation of success, in order to improve the decision making performance and enhance the explainability of navigation based on internal state inference and interactivity estimation (see at least Li, para. [0043]).
As per claim 8 Kobilarov does not explicitly disclose
wherein the noise comprises a zero mean Gaussian noise.
Li teaches
wherein the noise comprises a zero mean Gaussian noise (see at least Li, para. [0067]: Observation: it may be assumed that the physical states of the surrounding vehicles and pedestrians may be observable to the ego-agent, while the internal states may be not observable. The observation may be represented by o=[{circumflex over (x)}.sup.0, . . . , {circumflex over (x)}.sup.N+M], where {circumflex over (x)}.sup.i may be obtained by adding a little noise sampled from a zero-mean Gaussian distribution to the actual position and velocity to simulate sensor noise.).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified Kobilarov to incorporate the teaching of wherein the noise comprises a zero mean Gaussian noise of Li, with a reasonable expectation of success, in order to improve the decision making performance and enhance the explainability of navigation based on internal state inference and interactivity estimation (see at least Li, para. [0043]).
As per claim 15 Kobilarov does not explicitly disclose
wherein perturbing at least one of the plurality of vehicle states comprises: applying noise to the at least one of the plurality of vehicle states.
Li teaches
wherein perturbing at least one of the plurality of vehicle states comprises: applying noise to the at least one of the plurality of vehicle states (see at least Li, para. [0067]: Observation: it may be assumed that the physical states of the surrounding vehicles and pedestrians may be observable to the ego-agent, while the internal states may be not observable. The observation may be represented by o=[{circumflex over (x)}.sup.0, . . . , {circumflex over (x)}.sup.N+M], where {circumflex over (x)}.sup.i may be obtained by adding a little noise sampled from a zero-mean Gaussian distribution to the actual position and velocity to simulate sensor noise.).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified Kobilarov to incorporate the teaching of wherein perturbing at least one of the plurality of vehicle states comprises: applying noise to the at least one of the plurality of vehicle states of Li, with a reasonable expectation of success, in order to improve the decision making performance and enhance the explainability of navigation based on internal state inference and interactivity estimation (see at least Li, para. [0043]).
Claim(s) 18-20 is/are rejected under 35 U.S.C. 103 as being unpatentable over Kobilarov, in view of Li, in view of Pittaluga.
As per claim 18 Kobilarov discloses
A computer system, the computer system comprising: a memory storing instructions; and one or more processors communicably coupled to the memory and configured to execute the instructions to (see at least Kobilarov, para. [0112]: The methods described herein represent sequences of operations that may be implemented in hardware, software, or a combination thereof. In the context of software, the blocks represent computer-executable instructions stored on one or more computer-readable storage media that, when executed by one or more processors, perform the recited operations. Generally, computer-executable instructions include routines, programs, objects, components, data structures, and the like that perform particular functions or implement particular abstract data types):
generate second trajectory data based on applying perturbation to first trajectory data (see at least Kobilarov, para. [0061]: In such cases, either within the perturbed trajectory generator 204, or within the active prediction model 206, the infeasible perturbed trajectory 316 may be transformed into a feasible perturbed trajectory 318 with modified trajectory points (not shown) that correspond to same time segments and/or trajectory length segments as the trajectory points of the perturbed trajectory 316. For example, the perturbed trajectory generator 204 may determine the feasible perturbed trajectory 318 as the closest approximate trajectory to the infeasible perturbed trajectory 316, that the autonomous vehicle 102 is kino-dynamically capable of performing. Although not shown in this example, when the perturbed trajectory generator 204 modifies an infeasible perturbed trajectory 316 into a feasible perturbed trajectory 318, it also may update the variable vector 314 accordingly before providing it to the active prediction model 206. para. [0081]: As discussed above, the active prediction model 206 may output a feasible trajectory for the autonomous vehicle in operation 708, that may or may not be the same as the perturbed trajectory provided as input to the active prediction model 206. For instance, if a perturbed trajectory is determined that is initially kino-dynamically infeasible for the autonomous vehicle 102 to perform, the perturbed trajectory generator 204 and/or the active prediction model 206 may be configured to smooth and/or modify the perturbed trajectory in a feasible trajectory. );
create a collision function based on the second trajectory data (see at least Kobilarov, para. [0069]: In this example, the active prediction model 206 has determined that the autonomous vehicle 102 and the object 410 are likely to follow trajectory 434 and trajectory 436, respectively, in which the autonomous vehicle 102 aggressively merges into the path of the object 410 and a potential collision may result at an intersecting point 438 between the trajectories. Based on these predictions (and/or the various other predicted trajectories and states from the active prediction model 206), the cost evaluator 208 may compute costs associated with the second perturbed trajectory 428. In this example, the cost evaluator 208 may compute costs for the second perturbed trajectory 428 based at least in part on safety scores of the individual predicted trajectories 434 and 436, a passenger comfort score and route progression for the predicted trajectory 434, and/or based on the interaction between the predicted trajectories 434 and 436 (e.g., the likelihood, safety/risk level of the interaction, predicted impact speed, etc.).); and
train a machine learning model based on the second trajectory data and the collision function to generate planned trajectories for controlling a vehicle (see at least Kobilarov, para. [0080-0081]: As described above, the active prediction model 206 may include one or more ML models trained to output, based at least in part on the perturbed trajectory, predictions of future trajectories/states of the autonomous vehicle 102 and/or any additional agents in the driving environment. The active prediction model 206 may receive as input the perturbed trajectory (e.g., in the form of a variable vector) and/or a representation of the driving scene (e.g., a scene encoding) at an initial time point).
However Kobilarov does not explicitly disclose
generate second trajectory data based on applying noise to first trajectory data;
create a collision loss function based on the second trajectory data.
Li teaches
generate second trajectory data based on applying noise to first trajectory data (see at least Li, para. [0067]: Observation: it may be assumed that the physical states of the surrounding vehicles and pedestrians may be observable to the ego-agent, while the internal states may be not observable. The observation may be represented by o=[{circumflex over (x)}.sup.0, . . . , {circumflex over (x)}.sup.N+M], where {circumflex over (x)}.sup.i may be obtained by adding a little noise sampled from a zero-mean Gaussian distribution to the actual position and velocity to simulate sensor noise.).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified Kobilarov to incorporate the teaching of generate second trajectory data based on applying noise to first trajectory data of Li, with a reasonable expectation of success, in order to improve the decision making performance and enhance the explainability of navigation based on internal state inference and interactivity estimation (see at least Li, para. [0043]).
Pittaluga teaches
create a collision loss function based on the second trajectory data (see at least Pittaluga, para. [0030]: To generate adversarial perturbations, the ground-truth past and future trajectories of all vehicles in the scene and a map of the scene are fed as input into a pretrained encoder neural network to generate a scene encoding, which is used to initialize a set of learnable parameters of the same shape. The learnable parameters are then optimized (perturbed) via standard learning algorithms, such as stochastic gradient descent, to minimize a combination of losses ALAN adversarial loss function, a traffic violation loss function, adversarial collision loss function, and a comfort loss function. To compute these losses, the learnable parameters are decoded by a pretrained decoder neural network into adversarial trajectories for the neighboring agents. The adversarial perturbed trajectories can be iteratively computed until a threshold has been met.).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified Kobilarov to incorporate the teaching of create a collision loss function based on the second trajectory data of Pittaluga, with a reasonable expectation of success, in order to prevent future accidents and provide a more comfortable ride for their passengers (see at least Pittaluga, para. [0022]).
As per claim 19 Kobilarov does not explicitly disclose
wherein the noise comprises a zero mean Gaussian noise.
Li teaches
wherein the noise comprises a zero mean Gaussian noise (see at least Li, para. [0067]: Observation: it may be assumed that the physical states of the surrounding vehicles and pedestrians may be observable to the ego-agent, while the internal states may be not observable. The observation may be represented by o=[{circumflex over (x)}.sup.0, . . . , {circumflex over (x)}.sup.N+M], where {circumflex over (x)}.sup.i may be obtained by adding a little noise sampled from a zero-mean Gaussian distribution to the actual position and velocity to simulate sensor noise.).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified Kobilarov to incorporate the teaching of wherein the noise comprises a zero mean Gaussian noise of Li, with a reasonable expectation of success, in order to improve the decision making performance and enhance the explainability of navigation based on internal state inference and interactivity estimation (see at least Li, para. [0043]).
As per claim 20 Kobilarov discloses
wherein the one or more processors are further configured to execute the instructions to: deploy the trained machine learning model on one or more vehicles for generating planned trajectories that account for deviations in actual trajectories relative to first trajectory data (see at least Kobilarov, Fig. 6 & para. [0073]: FIG. 6 illustrates an example system 600 including multiple computing devices (e.g., a CPU and a GPU) configured to predict driving scenes and compute costs associated with various perturbed trajectories for an autonomous vehicle. As described above, in some examples, stochastic optimization may scale well with processing via GPUs and/or other similar parallel compute architectures. Accordingly, as shown in this example, an optimization component 202 executing a stochastic optimization technique, and a perturbed trajectory generator 204 may be executed on the CPU, while the compute-heavy active prediction model 206 and cost evaluator 208 may be executed on a GPU.).
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to MOHAMED ABDO ALGEHAIM whose telephone number is (571)272-3628. The examiner can normally be reached Monday-Friday 8-5PM EST.
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, Fadey Jabr can be reached at 571-272-1516. 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.
/MOHAMED ABDO ALGEHAIM/Primary Examiner, Art Unit 3668
Prosecution Insights