DETAILED ACTION
This is the second non-final Office action and is responsive to the papers filed 09/29/2025. The amendments filed on 09/29/2025 have been entered and considered by the examiner. Claims 1-19 are currently pending and examined below. Claims 1-2, 5-7, 9, 12-14, 16 and 19 have been amended.
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 .
Information Disclosure Statement
The information disclosure statement (IDS) submitted on 07/08/2025 is in compliance with the provisions of 37 CFR 1.97. Accordingly, the information disclosure statement has been considered by the examiner.
Response to Arguments
Applicant’s arguments, see page 10, filed 09/29/2025, with respect to claims 1-19 have been fully considered and are persuasive. The claim rejections under 35 U.S.C. 112(b) of claims 1-19 have been withdrawn.
Applicant’s arguments with respect to claim(s) 1-19 have been considered but are moot because the new ground of rejection does not rely on any reference applied in the prior rejection of record for any teaching or matter specifically challenged in the argument.
Claim Rejections - 35 USC § 103
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
Claims 1, 4-6, 9-13 and 16-19 are rejected under 35 U.S.C. 103 as being unpatentable over Pourkeshavarz et al. (US 20250115253 A1; hereinafter Pourkeshavarz) in view of Burlina et al. (US 20240353231 A1; hereinafter Burlina).
Regarding claim 1, Pourkeshavarz discloses:
A system (Fig. 1: computer system) comprising:
one or more processors (Fig. 1: processor 110); and
one or more non-transitory computer-readable media (Fig. 1: solid-state drive 120) storing instructions that, when executed, cause the system to perform operations ([0061] the solid-state drive 120 stores program instructions suitable for being loaded into the RAM 130 and executed by the processor 110 for performing the methods and function described herein) comprising:
receiving data associated with a vehicle operating within an environment ([0056] The computer system 10 comprises a computing unit 100 that may receive perception data 216 (see FIG. 2 ) representing a driving scene);
generating, based at least in part on the data, a graph comprising a plurality of nodes, a node of the plurality of nodes associated with one or more of the vehicle operating in the environment, a road feature, an additional vehicle, or a pedestrian ([0056] The computer system 10 is configured to generate a graph representation of the driving scene, to process the graph representation with the trajectory prediction model with additional processing of meta paths connecting a plurality of successive nodes in the graph representation and to generate predicted trajectories for agents in the driving scene, [0068] the moving surrounding objects can include, without limitation, vehicles, trains, cyclists, pedestrians or animals, object classes of the stationary objects can include, without limitation, trees, fire hydrants, road posts, streetlamps, traffic lights, and the like);
inputting the graph into a self-supervised machine learned model comprising an encoder ([0110] The systems and methods described herein provide for Heterogeneous Structural Learning (HSL) that models long-range connectivity within the map using structural graph characteristics, thus embedding existing constraints in the map…allowing for self-supervised learning…can be applied to any graph-based map encoder), wherein the machine learned model is trained to output a representation associated with the node ([0056] The computer system 10…is configured to generate a graph representation of the driving scene, to process the graph representation with the trajectory prediction model with additional processing of meta paths connecting a plurality of successive nodes in the graph representation and to generate predicted trajectories for agents in the driving scene);
receiving, from the self-supervised machine learned model, a representation associated with the node ([0056] The computer system 10…is configured to generate a graph representation of the driving scene, to process the graph representation with the trajectory prediction model with additional processing of meta paths connecting a plurality of successive nodes in the graph representation and to generate predicted trajectories for agents in the driving scene).
Pourkeshavarz does not specifically disclose:
transmitting the representation to a downstream machine learned model trained to output control data based at least in part on the representation, wherein the control data is configured to control the vehicle or another vehicle.
However, Burlina discloses:
transmitting the representation to a downstream machine learned model trained to output control data based at least in part on the representation, wherein the control data is configured to control the vehicle or another vehicle ([0060] training the transformer 234 may be self-supervised, [0024] transformer-based machine-learned model for determining various outputs that may be used by the vehicle to control operation of the vehicle).
Pourkeshavarz and Burlina are considered to be analogous to the claimed invention because they are in the same field of vehicle routing. Therefore, 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 Pourkeshavarz’s image learning to further incorporate Burlina’s image learning for the advantage of incorporating machine learned model which results in up-to-date map and improved accuracy in performing navigational tasks (Burlina’s [0014]).
Regarding claim 4, Pourkeshavarz does not specifically disclose:
wherein the operations further comprise:
receiving an input defining a task, wherein the downstream machine learned model is configured to perform the task; and
adapting the self-supervised machine learned model based on the task such that the representation is generated based at least in part on the task.
However, Burlina discloses:
wherein the operations further comprise:
receiving an input defining a task, wherein the downstream machine learned model is configured to perform the task ([0060] ground truth data associated with the task for which the transformer 234 is being trained); and
adapting the self-supervised machine learned model based on the task such that the representation is generated based at least in part on the task ([0060] training the transformer 234 may be self-supervised).
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 Pourkeshavarz’s image learning to further incorporate Burlina’s image learning for the advantage of incorporating machine learned model which results in up-to-date map and improved accuracy in performing navigational tasks (Burlina’s [0014]).
Regarding claim 5, Pourkeshavarz discloses:
wherein the graph further comprises a plurality of edges, such that there is at least one edge between the node and another node of the plurality of nodes, whereby the at least one edge is representative of a relationship between the at least one of the vehicle operating in the environment, road feature, additional vehicle, or pedestrian associated with the node and at least one other of a vehicle operating in the environment, a road feature, an additional vehicle, or a pedestrian associated with the another node ([0056] The computer system 10 is configured to generate a graph representation of the driving scene, to process the graph representation with the trajectory prediction model with additional processing of meta paths connecting a plurality of successive nodes in the graph representation and to generate predicted trajectories for agents in the driving scene, [0068] the moving surrounding objects can include, without limitation, vehicles, trains, cyclists, pedestrians or animals, object classes of the stationary objects can include, without limitation, trees, fire hydrants, road posts, streetlamps, traffic lights, and the like).
Regarding claim 6, Pourkeshavarz discloses:
A method ([0061] the solid-state drive 120 stores program instructions suitable for being loaded into the RAM 130 and executed by the processor 110 for performing the methods and function described herein) comprising:
receiving data associated with an environment ([0056] The computer system 10 comprises a computing unit 100 that may receive perception data 216 (see FIG. 2 ) representing a driving scene);
generating, based at least in part on the data, a graph representation of the environment comprising a plurality of nodes and a plurality of edges, a node of the plurality of nodes associated with a feature of the environment and an edge of the plurality of edges connecting two nodes ([0056] The computer system 10 is configured to generate a graph representation of the driving scene, to process the graph representation with the trajectory prediction model with additional processing of meta paths connecting a plurality of successive nodes in the graph representation and to generate predicted trajectories for agents in the driving scene, [0068] the moving surrounding objects can include, without limitation, vehicles, trains, cyclists, pedestrians or animals, object classes of the stationary objects can include, without limitation, trees, fire hydrants, road posts, streetlamps, traffic lights, and the like);
inputting the graph into a machine learned model ([0110] The systems and methods described herein provide for Heterogeneous Structural Learning (HSL) that models long-range connectivity within the map using structural graph characteristics, thus embedding existing constraints in the map…allowing for self-supervised learning…can be applied to any graph-based map encoder);
receiving, from the machine learned model, a node representation associated with the node of the graph ([0056] The computer system 10…is configured to generate a graph representation of the driving scene, to process the graph representation with the trajectory prediction model with additional processing of meta paths connecting a plurality of successive nodes in the graph representation and to generate predicted trajectories for agents in the driving scene).
Pourkeshavarz does not specifically disclose:
providing, to another machine learned model, the node representation for use in operating an autonomous vehicle in the environment in relation to or determining characteristics associated with the feature.
However, Burlina discloses:
providing, to another machine learned model, the node representation for use in operating an autonomous vehicle in the environment in relation to or determining characteristics associated with the feature ([0096] the transformer-based machine-learned model with input nodes, [0060] training the transformer 234 may be self-supervised, [0024] transformer-based machine-learned model for determining various outputs that may be used by the vehicle to control operation of the vehicle).
Pourkeshavarz and Burlina are considered to be analogous to the claimed invention because they are in the same field of vehicle routing. Therefore, 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 Pourkeshavarz’s image learning to further incorporate Burlina’s image learning for the advantage of incorporating machine learned model which results in up-to-date map and improved accuracy in performing navigational tasks (Burlina’s [0014]).
Regarding claim 9, Pourkeshavarz discloses:
wherein the graph further comprises a plurality of edges, such that there is at least one edge between the node and another node of the plurality of nodes, whereby the at least one edge is representative of a relationship between the feature associated with the node and at least one other feature of the environment associated with the another node ([0056] The computer system 10 is configured to generate a graph representation of the driving scene, to process the graph representation with the trajectory prediction model with additional processing of meta paths connecting a plurality of successive nodes in the graph representation and to generate predicted trajectories for agents in the driving scene, [0068] the moving surrounding objects can include, without limitation, vehicles, trains, cyclists, pedestrians or animals, object classes of the stationary objects can include, without limitation, trees, fire hydrants, road posts, streetlamps, traffic lights, and the like).
Regarding claim 10, Pourkeshavarz does not specifically disclose:
wherein the another machine learning model is an on-vehicle machine learning model executed on the autonomous vehicle and configured to control the autonomous vehicle based at least in part on the node representation.
However, Burlina discloses:
wherein the another machine learning model is an on-vehicle machine learning model executed on the autonomous vehicle and configured to control the autonomous vehicle based at least in part on the node representation ([0096] the transformer-based machine-learned model with input nodes, [0024] transformer-based machine-learned model for determining various outputs that may be used by the vehicle to control operation of the vehicle).
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 Pourkeshavarz’s image learning to further incorporate Burlina’s image learning for the advantage of incorporating machine learned model which results in up-to-date map and improved accuracy in performing navigational tasks (Burlina’s [0014]).
Regarding claim 11, Pourkeshavarz does not specifically disclose:
further comprising:
receiving an input defining a task, wherein the another machine learned model is configured to perform the task; and
adapting the machine learned model based on the task, such that the node representation is generated based at least in part on the task.
However, Burlina discloses:
further comprising:
receiving an input defining a task, wherein the another machine learned model is configured to perform the task ([0060] ground truth data associated with the task for which the transformer 234 is being trained); and
adapting the machine learned model based on the task, such that the node representation is generated based at least in part on the task ([0096] the transformer-based machine-learned model with input nodes, [0060] training the transformer 234 may be self-supervised).
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 Pourkeshavarz’s image learning to further incorporate Burlina’s image learning for the advantage of incorporating machine learned model which results in up-to-date map and improved accuracy in performing navigational tasks (Burlina’s [0014]).
Regarding claim 12, Pourkeshavarz discloses:
wherein the feature of the environment comprises one or more of:
a vehicle ([0068] vehicles);
a pedestrian ([0068] pedestrians); and
a road feature, wherein the road feature comprises at least one of:
a speed limit ([0068] road posts, [0082] speed limit);
curvature of the road;
a gradient of the road; and
a junction or intersection with another road.
Regarding claim 13, Pourkeshavarz discloses:
One or more non-transitory computer-readable media (Fig. 1: solid-state drive 120) storing instructions executable by one or more processors (Fig. 1: processor 110), wherein the instructions, when executed, cause the one or more processors to perform operations ([0061] the solid-state drive 120 stores program instructions suitable for being loaded into the RAM 130 and executed by the processor 110 for performing the methods and function described herein) comprising
receiving data associated with an environment ([0056] The computer system 10 comprises a computing unit 100 that may receive perception data 216 (see FIG. 2 ) representing a driving scene);
generating, based at least in part on the data, a graph representation of the environment comprising a plurality of nodes and a plurality of edges, a node of the plurality of nodes associated with a feature of the environment and an edge of the plurality of edges connecting two nodes ([0056] The computer system 10 is configured to generate a graph representation of the driving scene, to process the graph representation with the trajectory prediction model with additional processing of meta paths connecting a plurality of successive nodes in the graph representation and to generate predicted trajectories for agents in the driving scene, [0068] the moving surrounding objects can include, without limitation, vehicles, trains, cyclists, pedestrians or animals, object classes of the stationary objects can include, without limitation, trees, fire hydrants, road posts, streetlamps, traffic lights, and the like);
inputting the graph into a machine learned model ([0110] The systems and methods described herein provide for Heterogeneous Structural Learning (HSL) that models long-range connectivity within the map using structural graph characteristics, thus embedding existing constraints in the map…allowing for self-supervised learning…can be applied to any graph-based map encoder);
receiving, from the machine learned model, a node representation associated with the node of the graph ([0056] The computer system 10…is configured to generate a graph representation of the driving scene, to process the graph representation with the trajectory prediction model with additional processing of meta paths connecting a plurality of successive nodes in the graph representation and to generate predicted trajectories for agents in the driving scene).
Pourkeshavarz does not specifically disclose:
providing, to another machine learned model, the node representation for use in operating an autonomous vehicle in the environment in relation to or determining characteristics associated with the feature.
However, Burlina discloses:
providing, to another machine learned model, the node representation for use in operating an autonomous vehicle in the environment in relation to or determining characteristics associated with the feature ([0096] the transformer-based machine-learned model with input nodes, [0060] training the transformer 234 may be self-supervised, [0024] transformer-based machine-learned model for determining various outputs that may be used by the vehicle to control operation of the vehicle).
Pourkeshavarz and Burlina are considered to be analogous to the claimed invention because they are in the same field of vehicle routing. Therefore, 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 Pourkeshavarz’s image learning to further incorporate Burlina’s image learning for the advantage of incorporating machine learned model which results in up-to-date map and improved accuracy in performing navigational tasks (Burlina’s [0014]).
Regarding claim 16, Pourkeshavarz discloses:
wherein the graph further comprises a plurality of edges, such that there is at least one edge between the node and another node of the plurality of nodes, whereby the at least one edge is representative of a relationship between the feature associated with the node and at least one other feature of the environment associated with the another node ([0056] The computer system 10 is configured to generate a graph representation of the driving scene, to process the graph representation with the trajectory prediction model with additional processing of meta paths connecting a plurality of successive nodes in the graph representation and to generate predicted trajectories for agents in the driving scene, [0068] the moving surrounding objects can include, without limitation, vehicles, trains, cyclists, pedestrians or animals, object classes of the stationary objects can include, without limitation, trees, fire hydrants, road posts, streetlamps, traffic lights, and the like).
Regarding claim 17, Pourkeshavarz does not specifically disclose:
wherein the another machine learning model is an on-vehicle machine learning model executed on the autonomous vehicle and configured to control the autonomous vehicle based at least in part on the node representation.
However, Burlina discloses:
wherein the another machine learning model is an on-vehicle machine learning model executed on the autonomous vehicle and configured to control the autonomous vehicle based at least in part on the node representation ([0096] the transformer-based machine-learned model with input nodes, [0024] transformer-based machine-learned model for determining various outputs that may be used by the vehicle to control operation of the vehicle).
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 Pourkeshavarz’s image learning to further incorporate Burlina’s image learning for the advantage of incorporating machine learned model which results in up-to-date map and improved accuracy in performing navigational tasks (Burlina’s [0014]).
Regarding claim 18, Pourkeshavarz does not specifically disclose:
wherein the operations further comprise:
receiving an input defining a task, wherein the another machine learned model is configured to perform the task; and
adapting the machine learned model based on the task, such that the node representation is generated based at least in part on the task.
However, Burlina discloses:
wherein the operations further comprise:
receiving an input defining a task, wherein the another machine learned model is configured to perform the task ([0060] ground truth data associated with the task for which the transformer 234 is being trained); and
adapting the machine learned model based on the task, such that the node representation is generated based at least in part on the task ([0096] the transformer-based machine-learned model with input nodes, [0060] training the transformer 234 may be self-supervised).
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 Pourkeshavarz’s image learning to further incorporate Burlina’s image learning for the advantage of incorporating machine learned model which results in up-to-date map and improved accuracy in performing navigational tasks (Burlina’s [0014]).
Regarding claim 19, Pourkeshavarz discloses:
wherein the feature of the environment comprises one or more of:
a vehicle ([0068] vehicles);
a pedestrian ([0068] pedestrians); and
a road feature, wherein the road feature comprises at least one of:
a speed limit ([0068] road posts, [0082] speed limit);
curvature of the road;
a gradient of the road; and
a junction or intersection with another road.
Claims 2-3, 7-8 and 14-15 are rejected under 35 U.S.C. 103 as being unpatentable over Pourkeshavarz, in view of Burlina and in view of Zhao et al. (US 20250078532 A1; hereinafter Zhao).
Regarding claim 2, Pourkeshavarz as modified does not specifically disclose:
wherein the operations further comprise:
masking a portion of training data corresponding to a node of the plurality of nodes, thereby generating a masked portion of training data and an unmasked portion of training data;
inputting the masked portion and the unmasked portion of training data to the self-supervised machine learned model;
receiving a representation associated with the unmasked portion of training data and a proposed representation associated with the masked portion of training data;
determining a loss based at least in part on the masked portion of training data and the proposed representation; and
updating the self-supervised machine learned model based on the loss.
However, Zhao discloses:
wherein the operations further comprise:
masking a portion of training data corresponding to a node of the plurality of nodes, thereby generating a masked portion of training data ([0060] excludes from the mask unlabeled lane marking features that the generator model 120 is to ignore during training) and an unmasked portion of training data ([0060] training mask 522 may include within the mask the labeled lane marking features that the generator model 120 is to train on);
inputting the masked portion and the unmasked portion of training data to the self-supervised machine learned model ([0175] self-learning, [0060] training data preprocessor 520 may generate and apply a training mask 522 that is used with a training image used to train the heatmap generator model 120);
receiving a representation associated with the unmasked portion of training data and a proposed representation associated with the masked portion of training data (Fig. 3 – lane marking heatmap images 122);
determining a loss based at least in part on the masked portion of training data and the proposed representation (Fig. 5, [0057] a set of one or more loss functions may be computed by the loss optimizer 550); and
updating the self-supervised machine learned model based on the loss ([0057] the heatmap generator model 120 may be adjusted based on the loss feedback signal(s) to attempt to minimize the loss function(s)).
Zhao is analogous to the claimed invention because it pertains to the same field of image learning. Therefore, 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 Pourkeshavarz’s image learning as currently modified to further incorporate Zhao’s image learning for the advantage of omitting a portion of training image with challenging factors which results in accurate lane marking recognition (Zhao’s [0001]).
Regarding claim 3, Pourkeshavarz as currently modified does not specifically disclose:
wherein the training data comprises a set of data over a series of time steps and masking the portion of training data comprises one of:
temporal masking of a portion of the training data corresponding to the node associated with a time step of the series of time steps;
random masking of a random portion of the training data corresponding to the node; or
node masking of the training data corresponding to the node across the series of time steps.
However, Zhao discloses:
wherein the training data comprises a set of data over a series of time steps ([0001] rely on real-time or near real-time lane marking detection and recognition techniques to extract lane features and understand the structural features of lane markings that define lane boundaries) and masking the portion of training data comprises one of:
temporal masking of a portion of the training data corresponding to the node associated with a time step of the series of time steps;
random masking of a random portion of the training data corresponding to the node; or
node masking of the training data ([0060] excludes from the mask unlabeled lane marking features that the generator model 120 is to ignore during training) corresponding to the node across the series of time steps ([0001] rely on real-time or near real-time lane marking detection and recognition techniques to extract lane features and understand the structural features of lane markings that define lane boundaries).
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 Pourkeshavarz’s image learning as currently modified to further incorporate Zhao’s image learning for the advantage of omitting a portion of training image with challenging factors in real time lane marking detection which results in accurate lane marking recognition (Zhao’s [0001]).
Regarding claim 7, Pourkeshavarz does not specifically disclose:
wherein the machine learned model comprises an encoder and one or more reconstruction layers.
However, Burlina discloses:
wherein the machine learned model comprises an encoder ([0096] encoder) and one or more reconstruction layers ([0101] reconstruction).
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 Pourkeshavarz’s image learning to further incorporate Burlina’s image learning for the advantage of incorporating machine learned model including an encoder and training to reconstruct features which results in up-to-date map and improved accuracy in performing navigational tasks (Burlina’s [0014]).
Pourkeshavarz and Burlina do not specifically disclose:
wherein the method further comprises:
a training process comprising:
masking a portion of the data corresponding to a node of the plurality of nodes, thereby generating a masked portion of training data and an unmasked portion of training data;
inputting the masked portion and the unmasked portion of training data to the machine learned model;
receiving, from the machine learned model, a proposed node representation associated with the masked portion of training data;
determining a loss based at least in part on the proposed node representation and the masked portion of training data;
updating the machine learned model based on the loss; and
deploying the machine learned model to a vehicle computing system such that the machine learned model is configured to output the node representation for use by the another machine learned model.
However, Zhao discloses:
wherein the method further comprises:
a training process comprising:
masking a portion of the data corresponding to a node of the plurality of nodes, thereby generating a masked portion of training data ([0060] excludes from the mask unlabeled lane marking features that the generator model 120 is to ignore during training) and an unmasked portion of training data ([0060] training mask 522 may include within the mask the labeled lane marking features that the generator model 120 is to train on);
inputting the masked portion and the unmasked portion of training data to the machine learned model ([0060] training data preprocessor 520 may generate and apply a training mask 522 that is used with a training image used to train the heatmap generator model 120);
receiving, from the machine learned model, a proposed node representation associated with the masked portion of training data (Fig. 3 – lane marking heatmap images 122);
determining a loss based at least in part on the proposed node representation and the masked portion of training data (Fig. 5, [0057] a set of one or more loss functions may be computed by the loss optimizer 550);
updating the machine learned model based on the loss ([0057] the heatmap generator model 120 may be adjusted based on the loss feedback signal(s) to attempt to minimize the loss function(s)); and
deploying the machine learned model to a vehicle computing system such that the machine learned model is configured to output a node representation for use by the another machine learned model ([0055] The discriminator model 540 evaluates the one or more predicted heatmaps 520 against ground truth labeled training data 510 and attempts to predict which was generated by the heatmap generator model 120).
Zhao is analogous to the claimed invention because it pertains to the same field of image learning. Therefore, 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 Pourkeshavarz’s image learning as currently modified to further incorporate Zhao’s image learning for the advantage of omitting a portion of training image with challenging factors which results in accurate lane marking recognition (Zhao’s [0001]).
Regarding claim 8, Pourkeshavarz as currently modified does not specifically disclose:
wherein the data comprises a set of data over a series of time steps and masking a portion of the set of training log data comprises at least one of:
temporal masking of the data corresponding to the node at a time step of the series of time steps;
random masking of a random portion of the data corresponding to the node; or
node masking of the data corresponding to the node across the series of time steps.
However, Zhao discloses:
wherein the data comprises a set of data over a series of time steps ([0001] rely on real-time or near real-time lane marking detection and recognition techniques to extract lane features and understand the structural features of lane markings that define lane boundaries) and masking a portion of the set of training log data comprises at least one of:
temporal masking of the data corresponding to the node at a time step of the series of time steps;
random masking of a random portion of the data corresponding to the node; or
node masking of the data ([0060] excludes from the mask unlabeled lane marking features that the generator model 120 is to ignore during training) corresponding to the node across the series of time steps ([0001] rely on real-time or near real-time lane marking detection and recognition techniques to extract lane features and understand the structural features of lane markings that define lane boundaries).
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 Pourkeshavarz’s image learning as currently modified to further incorporate Zhao’s image learning for the advantage of omitting a portion of training image with challenging factors in real time lane marking detection which results in accurate lane marking recognition (Zhao’s [0001]).
Regarding claim 14, Pourkeshavarz as modified does not specifically disclose:
wherein the operations further comprise:
a training process comprising:
masking a portion of the data corresponding to a node of the plurality of nodes, thereby generating a masked portion of training data and an unmasked portion of training data;
inputting the masked portion and the unmasked portion of training data to the machine learned model;
receiving a proposed node representation associated with the masked portion of training data;
determining a loss based at least in part on the proposed node representation and the masked portion of training data;
updating the machine learned model based on the loss; and
deploying the machine learned model to a vehicle computing system such that the machine learned model is configured to output the node representation for use by the another machine learned model.
However, Zhao discloses:
wherein the operations further comprise:
a training process comprising:
masking a portion of the data corresponding to a node of the plurality of nodes, thereby generating a masked portion of training data ([0060] excludes from the mask unlabeled lane marking features that the generator model 120 is to ignore during training) and an unmasked portion of training data ([0060] training mask 522 may include within the mask the labeled lane marking features that the generator model 120 is to train on));
inputting the masked portion and the unmasked portion of training data to the machine learned model ([0060] training data preprocessor 520 may generate and apply a training mask 522 that is used with a training image used to train the heatmap generator model 120);
receiving a proposed node representation associated with the masked portion of training data (Fig. 3 – lane marking heatmap images 122);
determining a loss based at least in part on the proposed node representation and the masked portion of training data (Fig. 5, [0057] a set of one or more loss functions may be computed by the loss optimizer 550);
updating the machine learned model based on the loss ([0057] the heatmap generator model 120 may be adjusted based on the loss feedback signal(s) to attempt to minimize the loss function(s)); and
deploying the machine learned model to a vehicle computing system such that the machine learned model is configured to output the node representation for use by the another machine learned model ([0055] The discriminator model 540 evaluates the one or more predicted heatmaps 520 against ground truth labeled training data 510 and attempts to predict which was generated by the heatmap generator model 120).
Zhao is analogous to the claimed invention because it pertains to the same field of image learning. Therefore, 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 Pourkeshavarz’s image learning as currently modified to further incorporate Zhao’s image learning for the advantage of omitting a portion of training image with challenging factors which results in accurate lane marking recognition (Zhao’s [0001]).
Regarding claim 15, Pourkeshavarz as currently modified does not specifically disclose:
wherein the data comprises a set of data over a series of time steps and masking a portion of the set of training log data comprises at least one of:
temporal masking of the data corresponding to the node at a time step of the series of time steps;
random masking of a random portion of the data corresponding to the node; or
node masking of the data corresponding to the node across the series of time steps.
However, Zhao discloses:
wherein the data comprises a set of data over a series of time steps ([0001] rely on real-time or near real-time lane marking detection and recognition techniques to extract lane features and understand the structural features of lane markings that define lane boundaries) and masking a portion of the set of training log data comprises at least one of:
temporal masking of the data corresponding to the node at a time step of the series of time steps;
random masking of a random portion of the data corresponding to the node; or
node masking of the data ([0060] excludes from the mask unlabeled lane marking features that the generator model 120 is to ignore during training) corresponding to the node across the series of time steps ([0001] rely on real-time or near real-time lane marking detection and recognition techniques to extract lane features and understand the structural features of lane markings that define lane boundaries).
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 Pourkeshavarz’s image learning as currently modified to further incorporate Zhao’s image learning for the advantage of omitting a portion of training image with challenging factors in real time lane marking detection which results in accurate lane marking recognition (Zhao’s [0001]).
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to PAYSUN WU whose telephone number is (571)272-1528. The examiner can normally be reached Monday-Friday 8AM-5PM.
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, Hunter Lonsberry can be reached on (571)272-7298. 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.
/PAYSUN WU/Examiner, Art Unit 3665
/DONALD J WALLACE/Primary Examiner, Art Unit 3665