Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
DETAILED ACTION
This action is responsive to the Application filed on 11/03/2025
Claims 1-19 and 26 are pending in the case. Claims 1, 14 and 26 are independent claims. Claims 1-2, 14-15 and 26 have been currently amended. Claims 20-25 and 27 have been newly canceled.
Continued Examination Under 37 CFR 1.114
A request for continued examination under 37 CFR 1.114, including the fee set forth in 37 CFR 1.17(e), was filed in this application after final rejection. Since this application is eligible for continued examination under 37 CFR 1.114, and the fee set forth in 37 CFR 1.17(e) has been timely paid, the finality of the previous Office action has been withdrawn pursuant to 37 CFR 1.114. Applicant's submission filed on 11/03/2025 has been entered.
Claim Rejections - 35 USC § 103
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
Claims 1-9, 11-19 and 26 are rejected under 35 U.S.C. 103 as being unpatentable over Garcia et al. (Pub No.: 20210356294 A1), hereinafter referred to as Garcia and in view of Choi et al. (US Patent No.11,087,477 B2), hereinafter referred to as Choi and further in view of Ogale et al. (US Patent No.11,256,983 B2) hereinafter referred to as Ogale.
With respect to claim 1, Garcia disclose:
A method of predicting one or more road attributes corresponding to roads in a geographical area, the geographical area comprising road segments, the method comprising: providing of the geographical area, the trajectory data received as raw trace data recorded by one or more vehicles traversing at least a portion of the geographical area and including at least one of location, bearing and speed data (In Fig. 2 and paragraph [0055], Garcia disclose a digital representation of a road network through a digital road map. The map is organized into segment correspond to a specific section of the road network. Additionally, each segments contains multiple successive points that help define its geometry, including attributes like curvature, direction, and slope at those points. In paragraph [0057], Garcia discloses a technical system used to acquire geographic position data for vehicles on a road network. The acquisition method gathers location data such as measurements of geographic coordinates, specific position indicators (latitude, longitude, etc.) for each vehicle in the system.)
providing map data, wherein the map data comprises image data of the geographical area (In paragraph [0077], Garcia disclosed the image processing module comprising a digital road map.)
extracting trajectory features from the trajectory data (In paragraph [0057], Garcia disclose the acquisition module aimed at acquiring the geographic locations of various road vehicles (like cars, trucks, or motorcycle) on a road network. The acquisition module gathers multiple measurements of geographic coordinates (C.sub.1, C.sub.2, . . . , C.sub.i). These coordinates indicate the positions of each vehicle in real-time or over a period of time.)
extracting map features from the map data ( In paragraph [0077], Garcia disclose the image processing module incorporates a layer that visually represents statistical at certain points on the road map.)
With respect to claim 1, Garcia do not explicitly disclose:
using at least one processor[[ to]]for: predicting road attributes by inputting the trajectory features and the map features in a neural network, wherein the neural network is configured to generate an output of task- specific fused representations
classifying [[an ]]the output of the neural network into prediction probabilities of the road attributes, wherein the neural network comprises a first sub-neural network for the trajectory features and a second sub-neural network for the map features
However, it is known by Choi to disclose:
Using at least one processor[[ to]]for: predicting road attributes by inputting the trajectory features and the map features in a neural network, wherein the neural network is configured to generate an output of task- specific fused representations (In Col. 11-12, lines 47-3, Choi disclose map/scene features (e.g., LiDAR map feature extractor outputs) and then feeds past trajectory and map-derived features outputs into relation encoder -that’s a clear fusion stage producing a learned representation used to generated predicted trajectories.)
Garcia and Choi are analogous pieces of art because both references concern the method of predicting road attributes for a geographical area. Accordingly, it would have been obvious to a person of ordinary skill in the art, before the effective filing date of the claimed invention, to modify Garcia, predicting a map matching parameter that defines a difference between a measurement of geographic coordinates representative of the position of a road vehicle and a position as taught by Garcia, with generating a feature extractor result by feeding the LiDAR map through a feature extractor as taught by Choi. The motivation for doing so would have been to optimize the field of creating or updating a digital road map for a geographical area (See [0002] of Garcia.)
With respect to claim 1, Garcia in view of Choi do not disclose:
classifying [[an ]]the output of the neural network into prediction probabilities of the road attributes, wherein the neural network comprises a first sub-neural network for the trajectory features and a second sub-neural network for the map features
However, it is known by Ogale to disclose:
Classifying [[an ]]the output of the neural network into prediction probabilities of the road attributes, wherein the neural network comprises a first sub-neural network for the trajectory features and a second sub-neural network for the map features (In Col. 14, lines 8-42, Ogale discloses that the first neural network represents waypoint data for trajectories of vehicles that represent respective locations of a vehicle, e.g., waypoint data 108, and indicates a set of previous locations of a vehicle. Col. 3, lines 19-32 of Ogale, “The second neural network input can characterize multiple channels of environmental data. The multiple channels of environmental data can include …. light detection and ranging (LIDAR) data representing a LIDAR image of the vicinity of the vehicle, radio detection and ranging (RADAR) data representing a RADAR image of the vicinity of the vehicle, camera data representing an optical image of the vicinity of the vehicle…..” hence, the second neural network input is for the map features of the vehicle. The second neural network represents environmental data, e.g., environmental data 110, and navigation data, e.g., navigation data.) In Col. 18, lines 37-50, Ogale disclose the training target outputs 708 show what the trajectory planning neural network should produce after using the first and second training inputs 704, 706.For example, if the first input lists past locations of a vehicle at certain times, the training target output 708 will point to a specific location as the next planned spot (waypoint) for the vehicle. Sometimes, the training target output 708 is a list of scores for locations, where the target planned location has a score of 1 and all other locations have a score of 0.)
Garcia in view of Gao and Ogale are analogous pieces of art because both references concern the method of predicting road attributes for a geographical area. Accordingly, it would have been obvious to a person of ordinary skill in the art, before the effective filing date of the claimed invention, to modify Garcia, predicting a map matching parameter that defines a difference between a measurement of geographic coordinates representative of the position of a road vehicle and a position as taught by Garcia, with generating a feature extractor result by feeding the LiDAR map through a feature extractor as taught by Choi, with predicting locations for the trajectory that were predicted by the trajectory planning neural network as taught by Ogale . The motivation for doing so would have been to improve the efficacy of training a trajectory planning neural network system (See (Col.19, lines 19-20) of Ogale.)
Regarding claim 2, Garcia in view of Choi and Ogale, discloses the elements of claim 1. In addition, Ogale disclose:
The method of claim 1, wherein the neural network is configured to receive the trajectory features and the map features and wherein classifying is executed by a classifier, the classifier being configured to calculate one or more of the prediction probabilities based on the task-specific fused representations (In Col. 18, line 54-64, Ogale discloses trajectory-planning. The neural network uses the first and second training inputs (and maybe the third) from this data set to create predicted output scores. The neural network uses its current internal settings to process these inputs. The predicted output scores include a score for each possible waypoint location.)
Regarding claim 3, Garcia in view of Choi and Ogale, discloses the elements of claim 1. In addition, Ogale disclose:
The method of claim 1, wherein the trajectory features are processed by the first sub neural network into shared global trajectory features, wherein the first sub-neural network comprises one or more fully-connected layers (In the background, Col. 1, lines 29-34, Ogale discloses the architecture of a neural network and describes the layers in the network and their features, along with how the neurons in each layer are connected. In Col. 15, lines 7-24, they further disclose the first neural network: the trajectory-planning neural network creates scores for possible waypoint locations, and the waypoint selector picks one location as the waypoint for the current time step t.sub.3. This chosen waypoint is saved in memory and added to the list of waypoints that make up the vehicle's planned path.)
Regarding claim 4, Garcia in view of Choi and Ogale, discloses the elements of claim 2. In addition, Garcia disclose:
The method of claim 2, further comprising determining attention scores of pre-defined indicators corresponding to road attributes based on the trajectory data, wherein the pre-defined indicators are processed by a fully connected layer, and wherein the attention scores are determined based on activation functions (In paragraph [0070], Garcia discloses that the network has an output neuron that predicts a specific value called the map matching parameter. It uses an activation function, like the sigmoid type, to give a likelihood for each output neuron.)
Regarding claim 5, Garcia in view of Choi and Ogale, discloses the elements of claim 4. In addition, Garcia disclose:
The method of claim 4, wherein trajectory task-specific weighted representations are calculated based on the fusion of the attention scores with the shared global trajectory features of the first sub-neural network (In paragraph [0070], Garcia discloses that synaptic weights are determined by the supervised learning algorithm. There are a great many supervised learning algorithms, such as the backpropagation method. The principle of this algorithm consists, on the basis of a stimulus at the input of a neural network, in calculating the output of the neural network, comparing it with the expected output and backpropagating an error signal in the neural network, which modifies the synaptic weights via a gradient descent method.)
Regarding claim 6, Garcia in view of Choi and Ogale, discloses the elements of claim 1. In addition, Ogale disclose:
The method of claim 1, wherein the map features are processed by the second sub-neural network into shared global map features (("Based on examiners' broadest reasonable interpretation (BRI) and the lack of details in the specification, "global map features" are interpreted as sharing and/or exploring map data in "real-time", which Ogale discloses throughout the specification. In Col. 17, lines 11-33, Ogale discloses the second planned trajectory of the second neural network that may correspond in real-world times to a particular time step partway through the first planned trajectory.)
Regarding claim 7, Garcia in view of Choi and Ogale, discloses the elements of claim 6. In addition, Garcia disclose:
The method of claim 6, further comprising calculating second attention scores of pre-defined indicators based on the shared global map features, wherein the pre- defined indicators are processed by a second fully connected layer, and wherein the second attention scores are determined based on activation functions (In paragraph [0070], Garcia discloses that the network has an output neuron that predicts a specific value called the map matching parameter. It uses an activation function, like the sigmoid type, to give a likelihood for each output neuron.)
Regarding claim 8, Garcia in view of Choi and Ogale, discloses the elements of claim 7. In addition, Garcia disclose:
The method of claim 7, wherein map task-specific weighted representations are calculated based on the fusion of the second attention scores with the shared global map features of the second sub-neural network (In paragraph [0070], Garcia discloses that synaptic weights are determined by the supervised learning algorithm. There are a great many supervised learning algorithms, such as the backpropagation method. The principle of this algorithm consists, on the basis of a stimulus at the input of a neural network, in calculating the output of the neural network, comparing it with the expected output and backpropagating an error signal in the neural network, which modifies the synaptic weights via a gradient descent method.)
Regarding claim 9, Garcia in view of Choi and Ogale, discloses the elements of claim 5. In addition, Ogale disclose:
The method of claim 5, wherein the map features are processed by the second sub-neural network into shared global map features (In Col. 14, lines 53-58, Ogale discloses that a second neural network input represents environment and navigation data.)
the method further comprises calculating second attention scores of pre-defined indicators based on the shared global map features, wherein the pre-defined indicators are processed by a second fully connected layer (In Col. 15, lines 14-18, disclose the trajectory planning, the neural network 104 generates a set of scores for possible waypoint locations, and the waypoint selector 116 selects one of the locations as the waypoint for the current time step t.sub.2.)
the second attention scores are determined based on activation functions, wherein map task-specific weighted representations are calculated based on the fusion of the second attention scores with the shared global map features of the second sub-neural network (In Col. 14-15, lines 67-6, Ogale disclose that the selected waypoint is then stored in memory and added to a set of waypoints that define the planned trajectory of the vehicle. Image 206b shows the second waypoint of the planned trajectory for time step t.sub.2 as the second triangular dot that follows the trail of circular dots representing previously traveled locations of the vehicle.)
and task-specific fused representations are determined based on the map task-specific weighted representations and the trajectory task-specific weighted representations (In Col. 18, lines 54-64, Ogale discloses that the training system selects a first training data set from the set of training data sets. In substage 714, the trajectory-planning neural network system processes the first training input and the second training input (and, optionally, the third training input) from the training data set to generate a predicted set of output scores. The trajectory-planning neural network system processes the training inputs in accordance with current values of internal parameters of the network. The predicted set of output scores can include a respective score for each location in a set of all possible waypoint locations.)
Regarding claim 11, Garcia in view of Choi and Ogale, discloses the elements of claim 1. In addition, Ogale disclose:
The method of claim 1, wherein extracting trajectory features from the trajectory data comprises determining group of traces of the trajectory data that are associated with a road segment of the road segments (In Col. 21, lines 6-19, Ogale discloses a first group and a second group relating to trajectory data, such as environmental data.)
Regarding claim 12, Garcia in view of Choi and Ogale, discloses the elements of claim 11. In addition, Garcia disclose:
The method of claim 11, wherein extracting trajectory features from the trajectory data further comprises calculating respective distributions of one or more of location, bearing, and speed, and using the distributions as the trajectory features (In paragraph [0057], Garcia discloses a technical system used to acquire geographic position data for vehicles on a road network. The acquisition method gathers location data such as measurements of geographic coordinates, specific position indicators (latitude, longitude, etc.) for each vehicle in the system.)
Regarding claim 13, Garcia in view of Choi and Ogale, discloses the elements of claim 1. In addition, Garcia disclose:
The method of claim 1, wherein the trajectory data comprises a plurality of data points, each data point comprising latitude, longitude, bearing, and speed (In paragraph [0057], Garcia discloses a technical system used to acquire geographic position data for vehicles on a road network. The acquisition method gathers location data such as measurements of geographic coordinates, specific position indicators (latitude, longitude, etc.) for each vehicle in the system.)
With respect to claim 14, Garcia disclose:
A data processing system comprising one or more processors configured to carry out predicting road attributes corresponding to roads in a geographical area, comprising: a first memory configured to store trajectory data of the geographical area, the trajectory data received as raw trace data recorded by one or more vehicles traversing at least a portion of the geographical area and including at least one of location, bearing and speed data (In paragraph [0057], Garcia discloses a technical system used to acquire geographic position data for vehicles on a road network. The acquisition method gathers location data such as measurements of geographic coordinates, specific position indicators (latitude, longitude, etc.) for each vehicle in the system.)
a second memory configured to storing store map data, wherein the map data comprises image data of the geographical area (In paragraph [0077], Garcia disclosed the image processing module comprising a digital road map.)
a trajectory feature extractor configured to extract trajectory features from the trajectory data (In paragraph [0057], Garcia disclose the acquisition module aimed at acquiring the geographic locations of various road vehicles (like cars, trucks, or motorcycle) on a road network. The acquisition module gathers multiple measurements of geographic coordinates (C.sub.1, C.sub.2, . . . , C.sub.i). These coordinates indicate the positions of each vehicle in real-time or over a period of time.)
a map feature extractor configured to extract map features from the map data (In paragraph [0077], Garcia disclose the image processing module incorporates a layer that visually represents statistical at certain points on the road map.)
With respect to claim 14, Garcia do not explicitly disclose:
a neural network configured to predict road attributes by generating an output of task-specific fused representations based on the trajectory features and the map features
a classifier configured to classify [[an ]]the output of the neural network into prediction probabilities of the road attributes, wherein the neural network comprises a first sub-neural network for the trajectory features and a second sub-neural network for the map features
However, it is known by Choi to disclose:
A neural network configured to predict road attributes by generating an output of task-specific fused representations based on the trajectory features and the map features (In Col. 11-12, lines 47-3, Choi disclose map/scene features (e.g., LiDAR map feature extractor outputs) and then feeds past trajectory and map-derived features outputs into relation encoder -that’s a clear fusion stage producing a learned representation used to generated predicted trajectories.)
Garcia and Choi are analogous pieces of art because both references concern the method of predicting road attributes for a geographical area. Accordingly, it would have been obvious to a person of ordinary skill in the art, before the effective filing date of the claimed invention, to modify Garcia, predicting a map matching parameter that defines a difference between a measurement of geographic coordinates representative of the position of a road vehicle and a position as taught by Garcia, with generating a feature extractor result by feeding the LiDAR map through a feature extractor as taught by Choi. The motivation for doing so would have been to optimize the field of creating or updating a digital road map for a geographical area (See [0002] of Garcia.)
With respect to claim 14, Garcia in view of Choi do not disclose:
A classifier configured to classify [[an ]]the output of the neural network into prediction probabilities of the road attributes, wherein the neural network comprises a first sub-neural network for the trajectory features and a second sub-neural network for the map features (In Col. 14, lines 8-42, Ogale discloses that the first neural network represents waypoint data for trajectories of vehicles that represent respective locations of a vehicle, e.g., waypoint data 108, and indicates a set of previous locations of a vehicle. Col. 3, lines 19-32 of Ogale, “The second neural network input can characterize multiple channels of environmental data. The multiple channels of environmental data can include …. light detection and ranging (LIDAR) data representing a LIDAR image of the vicinity of the vehicle, radio detection and ranging (RADAR) data representing a RADAR image of the vicinity of the vehicle, camera data representing an optical image of the vicinity of the vehicle…..” hence, the second neural network input is for the map features of the vehicle. The second neural network represents environmental data, e.g., environmental data 110, and navigation data, e.g., navigation data.) In Col. 18, lines 37-50, Ogale disclose the training target outputs 708 show what the trajectory planning neural network should produce after using the first and second training inputs 704, 706.For example, if the first input lists past locations of a vehicle at certain times, the training target output 708 will point to a specific location as the next planned spot (waypoint) for the vehicle. Sometimes, the training target output 708 is a list of scores for locations, where the target planned location has a score of 1 and all other locations have a score of 0.)
Garcia in view of Choi and Ogale are analogous pieces of art because both references concern the method of predicting road attributes for a geographical area. Accordingly, it would have been obvious to a person of ordinary skill in the art, before the effective filing date of the claimed invention, to modify Garcia, predicting a map matching parameter that defines a difference between a measurement of geographic coordinates representative of the position of a road vehicle and a position as taught by Garcia, with generating a feature extractor result by feeding the LiDAR map through a feature extractor as taught by Choi, with predicting locations for the trajectory that were predicted by the trajectory planning neural network as taught by Ogale . The motivation for doing so would have been to improve the efficacy of training a trajectory planning neural network system (See (Col.19, lines 19-20) of Ogale.)
Regarding claim 15, Garcia in view of Choi and Ogale, discloses the elements of claim 14. In addition, Ogale disclose:
The data processing system of claim 14, wherein the neural network is configured to receive the trajectory features and the map features and to generate task-specific fused representations, and wherein the classifier is configured to calculate one or more of the prediction probabilities based on the task-specific fused representations (In Col. 18, line 54-64, Ogale discloses trajectory-planning. The neural network uses the first and second training inputs (and maybe the third) from this data set to create predicted output scores. The neural network uses its current internal settings to process these inputs. The predicted output scores include a score for each possible waypoint location.)
Regarding claim 16, Garcia in view of Choi and Ogale, discloses the elements of claim 15. In addition, Ogale disclose:
The data processing system of claim 15, wherein the first sub- neural network is configured to process the trajectory features into shared global trajectory features, wherein the first sub-neural network comprises one or more fully-connected layers (In the background, Col. 1, lines 29-34, Ogale discloses the architecture of a neural network and describes the layers in the network and their features, along with how the neurons in each layer are connected. In Col. 15, lines 7-24, they further disclose the first neural network: the trajectory-planning neural network creates scores for possible waypoint locations, and the waypoint selector picks one location as the waypoint for the current time step t.sub.3. This chosen waypoint is saved in memory and added to the list of waypoints that make up the vehicle's planned path.)
Regarding claim 17, Garcia in view of Choi and Ogale, discloses the elements of claim 15. In addition, Garcia disclose:
The data processing system of claim 15, wherein the neural network further comprises a fully connected layer and wherein the neural network is further configured to determine attention scores of pre-defined indicators corresponding to road attributes based on the trajectory data, wherein the pre-defined indicators are processed by the fully connected layer, and wherein the attention scores are determined based on activation functions (In paragraph [0070], Garcia discloses that the network has an output neuron that predicts a specific value called the map matching parameter. It uses an activation function, like the sigmoid type, to give a likelihood for each output neuron.)
Regarding claim 18, Garcia in view of Choi and Ogale, discloses the elements of claim 17. In addition, Garcia disclose:
The data processing system of claim 17, wherein the first sub- neural network is configured to process the trajectory features into shared global trajectory features, wherein the first sub-neural network comprises one or more fully-connected layers (In the background, Col. 1, lines 29-34, Ogale discloses the architecture of a neural network and describes the layers in the network and their features, along with how the neurons in each layer are connected. In Col. 15, lines 7-24, they further disclose the first neural network: the trajectory-planning neural network creates scores for possible waypoint locations, and the waypoint selector picks one location as the waypoint for the current time step t.sub.3. This chosen waypoint is saved in memory and added to the list of waypoints that make up the vehicle's planned path.)
Regarding claim 19, Garcia in view of Choi and Ogale, discloses the elements of claim 18. In addition, Ogale disclose:
The data processing system of claim 18, wherein the network is configured to fuse the attention scores with the shared global trajectory features of the first sub-neural network thereby generating trajectory task-specific weighted representations (In paragraph [0070], Garcia discloses that synaptic weights are determined by the supervised learning algorithm. There are a great many supervised learning algorithms, such as the backpropagation method. The principle of this algorithm consists, on the basis of a stimulus at the input of a neural network, in calculating the output of the neural network, comparing it with the expected output and backpropagating an error signal in the neural network, which modifies the synaptic weights via a gradient descent method.)
With respect to claim 26, Garcia disclose:
A method for training an automated predictor, the method comprising: performing forward propagation by inputting training data into the automated predictor to obtain an output result, for a plurality of road segments of a geographical area, wherein the training data comprises: trajectory features (In Fig. 2 and paragraph [0055], Garcia disclose a digital representation of a road network through a digital road map. The map is organized into segment correspond to a specific section of the road network. Additionally, each segments contains multiple successive points that help define its geometry, including attributes like curvature, direction, and slope at those points.
map features having an electronic image format (In paragraph [0077], Garcia disclose the image processing module incorporates a layer that visually represents statistical at certain points on the road map.)
performing back propagation according to a difference between the output result and an expected result to adjust weights of the automated predictor (In paragraph [0070], Garcia discloses a backpropagation method, wherein the basis of a stimulus at the input of a neural network, in calculating the output of the neural network, comparing it with the expected output and backpropagating an error signal in the neural network, which modifies the synaptic weights via a gradient descent method.)
With respect to claim 26, Garcia do not explicitly disclose:
repeating the above steps until a pre-determined convergence threshold is achieved, wherein the automated predictor comprises: a neural network configured to predict road attributes by generating an output of task-specific fused features using attention scores applied to based on trajectory features and map features
the trajectory features extracted from trajectory data received as raw trace data recorded by one or more vehicles traversing at least a portion of the geographical area and the map features extracted from map data
a classifier configured to classify an output of the neural network into prediction probabilities of the road attributes, wherein the neural network comprises a first sub-neural network for the trajectory features and a second sub-neural network for the map features
However, it is known by Choi to disclose:
Repeating the above steps until a pre-determined convergence threshold is achieved, wherein the automated predictor comprises: a neural network configured to predict road attributes by generating an output of task-specific fused features using attention scores applied to based on trajectory features and map features (I In Col. 11-12, lines 47-3, Choi disclose map/scene features (e.g., LiDAR map feature extractor outputs) and then feeds past trajectory and map-derived features outputs into relation encoder -that’s a clear fusion stage producing a learned representation used to generated predicted trajectories.)
The trajectory features extracted from trajectory data received as raw trace data recorded by one or more vehicles traversing at least a portion of the geographical area and the map features extracted from map data (In Col. 7, lines 25-31, Choi disclose a feature extractor based on the LiDAR map , the LiDAR map may be fed through the feature extractor 132 to generate the feature extractor result. The feature extractor 132 may include one or more 2D convolutional layers or convolutional layers
Garcia and Choi are analogous pieces of art because both references concern the method of predicting road attributes for a geographical area. Accordingly, it would have been obvious to a person of ordinary skill in the art, before the effective filing date of the claimed invention, to modify Garcia, predicting a map matching parameter that defines a difference between a measurement of geographic coordinates representative of the position of a road vehicle and a position as taught by Garcia, with generating a feature extractor result by feeding the LiDAR map through a feature extractor as taught by Choi. The motivation for doing so would have been to optimize the field of creating or updating a digital road map for a geographical area (See [0002] of Garcia.)
With respect to claim 26, Garcia in view of Choi do not disclose:
a classifier configured to classify an output of the neural network into prediction probabilities of the road attributes, wherein the neural network comprises a first sub-neural network for the trajectory features and a second sub-neural network for the map features
However, it is known by Ogale to disclose:
A classifier configured to classify an output of the neural network into prediction probabilities of the road attributes, wherein the neural network comprises a first sub-neural network for the trajectory features and a second sub-neural network for the map features (In Col. 14, lines 8-42, Ogale discloses that the first neural network represents waypoint data for trajectories of vehicles that represent respective locations of a vehicle, e.g., waypoint data 108, and indicates a set of previous locations of a vehicle. Col. 3, lines 19-32 of Ogale, “The second neural network input can characterize multiple channels of environmental data. The multiple channels of environmental data can include …. light detection and ranging (LIDAR) data representing a LIDAR image of the vicinity of the vehicle, radio detection and ranging (RADAR) data representing a RADAR image of the vicinity of the vehicle, camera data representing an optical image of the vicinity of the vehicle…..” hence, the second neural network input is for the map features of the vehicle. The second neural network represents environmental data, e.g., environmental data 110, and navigation data, e.g., navigation data.) In Col. 18, lines 37-50, Ogale disclose the training target outputs 708 show what the trajectory planning neural network should produce after using the first and second training inputs 704, 706.For example, if the first input lists past locations of a vehicle at certain times, the training target output 708 will point to a specific location as the next planned spot (waypoint) for the vehicle. Sometimes, the training target output 708 is a list of scores for locations, where the target planned location has a score of 1 and all other locations have a score of 0.)
Garcia in view of Choi and Ogale are analogous pieces of art because both references concern the method of predicting road attributes for a geographical area. Accordingly, it would have been obvious to a person of ordinary skill in the art, before the effective filing date of the claimed invention, to modify Garcia, predicting a map matching parameter that defines a difference between a measurement of geographic coordinates representative of the position of a road vehicle and a position as taught by Garcia, with generating a feature extractor result by feeding the LiDAR map through a feature extractor as taught by Choi, with predicting locations for the trajectory that were predicted by the trajectory planning neural network as taught by Ogale . The motivation for doing so would have been to improve the efficacy of training a trajectory planning neural network system (See (Col.19, lines 19-20) of Ogale.)
Claim 10 is rejected under 35 U.S.C. 103 as being unpatentable over Garcia in view of Choi, Ogale and further in view of KRUTSCH et al. (Pub No.: 20220402494 A1) hereinafter referred to as KRUTSCH.
Regarding claim 10, Garcia in view of Choi and Ogale, discloses the elements of claim 1. Garcia in view of Choi and Ogale does appear to explicitly disclose:
The method of claim 1, wherein extracting map features from the map data comprises generating cropped images by cropping images from the image data, wherein the cropped images are centered at a corresponding road segment of the road segments
However, KRUTSCH disclose the limitation (In paragraph [0111], KRUTSCH discloses the pre-processing, including cropping and/or down sampling. A respective feature map is generated from the pre-processed image and a feature map is generated from the additional information.)
Accordingly, it would have been obvious to a person having ordinary skills in the art before the effective filling date of the claimed invention, having the teaching of Garcia in view of Choi and Ogale before them to include KRUTSCH’s distance of vehicle to improve the accuracy of a correct identification of the road type as taught by KRUTSCH (see[0049])
Response to Arguments
The applicant's arguments filed 11/03/2025 have been fully considered, but in part are not persuasive.
Pertaining to the rejection under 101
Rejections for claims 1-19 and 26 are withdrawn under 35 USC § 101
Pertaining to the rejection under 103
Applicant’s arguments with respect to claim(s) 1, 19 and 26 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.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to EVEL HONORE whose telephone number is (703)756-1179. The examiner can normally be reached Monday-Friday 8 a.m. -5:30 p.m.
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, Mariela D Reyes can be reached at (571) 270-1006. 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.
EVEL HONORE
Examiner
Art Unit 2142
/HAIMEI JIANG/Primary Examiner, Art Unit 2142