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 .
Status of Claims
Claims 1-21 are pending.
Response to Arguments
Applicant’s arguments, see p.6-11, filed 03/17/2026, with respect to the rejections of Claims 1-21 under 35 U.S.C. 103 have been fully considered but are not persuasive. Applicant argues that the assertion that "map objects are produced including voxelized geometric maps and ground maps of the base map layer including basic road network data" mischaracterizes Ferguson because Ferguson more accurately describes "the generated mapping has various layers, such as a base map layer (SD map) (bottom or base layer), a geometric map layer, a semantic map layer, a map priors layer, and/or a real-time layer (top-most layer)." Furthermore, Applicant asserts that Ferguson is silent with respect to "a trajectory corresponding to locations of a base map, and, at best, Ferguson describes storing map objects in a geometric map and a ground map that "can be used to align the other layers of the map". Applicant additionally argues that Ferguson does not teach or suggest any limits on how the sensor data is obtained and that it fails to show that the sensor data of Ferguson is obtained "along a trajectory corresponding to locations of a base map". Examiner respectfully disagrees, and for further clarification, Ferguson, Paras. 119-121, teaches obtaining sensor data which is processed using particular algorithms such as SLAM techniques to build a 3D view of the geographical environment in which the output of the processed sensor data includes a 3D point cloud and particular trajectory that the mapping vehicle took wherein the output additionally includes map objects that are stored in the geometric map including voxelized map comprising data that represents a point in three-dimensional space which can be used to align the other layers of the map wherein the generated mapping has various layers such as a base map layer, geometric map layer, a semantic map layer, a map prior layer, and a real-time layer in which each of these layers can be aligned with each other and indexed which allows for parallel lookups of information both for the current location of the AV and also the local environment, i.e., sensor data is obtained along a particular trajectory that the mapping vehicle took which additionally includes mapped objects and their location in the environment and stored in a geometric map which is aligned and indexed with the base map layer indicating a correspondence between the sensor data along a trajectory and locations of a base map which includes the road network data and aligned and indexed map objects.
Furthermore, Applicant argues that Ferguson fails to teach that the inputs include the raw sensor data obtained from sensors. Examiner respectfully disagrees, and for further clarification, Ferguson, Paras. 38 and 150-152, teaches receiving an image or historical flight data and extracting one or more features from each of the one or more inputs wherein the UAVs comprise LIDAR, radar, and camera sensors and send sensor data to processing devices, i.e., extracting features from the input data comprising images which are received sensor data.
Additionally, Applicant argues that there is no proper motivation to combine Ferguson and Wei because the features of Ferguson are extracted for object detection purposes and the extracted features are mission/UAV attributes instead of geometric map elements. Furthermore, Applicant argues that the combination creates undue complexity. In response to applicant’s argument that there is no teaching, suggestion, or motivation to combine the references, the examiner recognizes that obviousness may be established by combining or modifying the teachings of the prior art to produce the claimed invention where there is some teaching, suggestion, or motivation to do so found either in the references themselves or in the knowledge generally available to one of ordinary skill in the art. See In re Fine, 837 F.2d 1071, 5 USPQ2d 1596 (Fed. Cir. 1988), In re Jones, 958 F.2d 347, 21 USPQ2d 1941 (Fed. Cir. 1992), and KSR International Co. v. Teleflex, Inc., 550 U.S. 398, 82 USPQ2d 1385 (2007). In this case, Ferguson, Paras. 62-63 and 152-154, teaches the use of a Convolutional Neural Network to recognize input images of a geographical area and detect objects in the input images wherein features are extracted from the inputs and used for training the machine learning model. Therefore, Ferguson teaches the extraction and inputting of features into a neural network in which the output is detected objects. Wei, Abstract, FIGs. 2, 3, and 5, and Section II-A, teaches utilizing a navigation map to guide the pe process along the road network and used aerial imagery and aggregated vehicle telemetry to extract lane level features at each step wherein a multi-task convolutional neural network is used to predict lane and road edges using aerial imagery in which predicted road features for each image are then stitched along a road segment to construct the road and lane edge polylines which are then used to predict lane marking and road edge types in a sliding window fashion along the road segment and wherein the decoder of the CNN at each branch specializes to learn desired feature maps from the embedding space which includes polylines, i.e., input features being the lane level features into a trained neural network that outputs overlapping feature maps being the stitched together features in a sliding window approach comprising polylines. Therefore, the references do not create undue complexity and have proper motivation for combination because both references teach the use of neural networks which receive features as input. One of ordinary skill in the art would be motivated to combine the sensor data and extracted features which are input to a neural network of Ferguson with the input of features into a neural network to output overlapping rich feature maps comprising polylines of Wei because it offers a flexible solution for HD maps for autonomous vehicles at scale (Wei, Abstract).
Lastly, Applicant argues that Zhang does not identify any raster image. Examiner respectfully disagrees because a raster image is simply an image comprising a matrix of pixels arranged in rows and columns wherein a depth image is also a two-dimensional image comprising pixels with a corresponding value. Therefore, the broadest reasonable interpretation of a raster image includes a depth image. Accordingly, this action is made FINAL.
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.
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.
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.
Claims 1, 4-8, 11, and 14-19 are rejected under 35 U.S.C. 103 as being unpatentable over Ferguson (US 20230020135 A1) in view of Wei et al. ("Creating Semantic HD Maps From Aerial Imagery and Aggregated Vehicle Telemetry for Autonomous Vehicles"), Zhang et al. (US 20220230338 A1), and Gao et al. (US 20210150350 A1).
Regarding Claim 1, Ferguson teaches "A method, comprising: obtaining, with at least one processor, sensor data along a trajectory corresponding to locations of a base map"; (Ferguson, Paras. 3 and 121, teaches using a processor to obtain raw sensor data processed to output a 3D point cloud and particular trajectory that the mapping vehicle took wherein map objects are produced including voxelized geometric maps and ground maps of the base map layer including basic road network data, i.e., obtaining sensor data along a trajectory corresponding to base map locations. For further clarification, Ferguson, Paras. 119-121, teaches obtaining sensor data which is processed using particular algorithms such as SLAM techniques to build a 3D view of the geographical environment in which the output of the processed sensor data includes a 3D point cloud and particular trajectory that the mapping vehicle took wherein the output additionally includes map objects that are stored in the geometric map including voxelized map comprising data that represents a point in three-dimensional space which can be used to align the other layers of the map wherein the generated mapping has various layers such as a base map layer, geometric map layer, a semantic map layer, a map prior layer, and a real-time layer in which each of these layers can be aligned with each other and indexed which allows for parallel lookups of information both for the current location of the AV and also the local environment, i.e., sensor data is obtained along a particular trajectory that the mapping vehicle took which additionally includes mapped objects and their location in the environment and stored in a geometric map which is aligned and indexed with the base map layer indicating a correspondence between the sensor data along a trajectory and locations of a base map which includes the road network data and aligned and indexed map objects);
"extracting, with the at least one processor, features from the sensor data"; (Ferguson, Para. 152, teaches extracting one or more features from each of the one or more inputs, i.e., sensor data. For further clarification, Ferguson, Paras. 38 and 150-152, teaches receiving an image or historical flight data and extracting one or more features from each of the one or more inputs wherein the UAVs comprise LIDAR, radar, and camera sensors and send sensor data to processing devices, i.e., extracting features from the input data comprising images which are received sensor data).
However, Ferguson does not explicitly teach "inputting, with the at least one processor, the features into a trained neural network that outputs overlapping rich feature maps comprising polylines; aggregating, with the at least one processor, the overlapping rich feature maps according to an aggregation function to obtain raster images; and applying vectorization, with the at least one processor, to the raster images to extract roadway geometry represented by globally consistent polylines".
In an analogous field of endeavor, Wei teaches "inputting, with the at least one processor, the features into a trained neural network that outputs overlapping rich feature maps comprising polylines"; (Wei, Abstract, FIGS. 2, 3, and5, and Section II-A, teaches utilizing a navigation map to guide the pe process along the road network and used aerial imagery and aggregated vehicle telemetry to extract lane level features at each step wherein a multi-task convolutional neural network is used to predict lane and road edges using aerial imagery in which predicted road features for each image are then stitched along a road segment to construct the road and lane edge polylines which are then used to predict lane marking and road edge types in a sliding window fashion along the road segment and wherein the decoder of the CNN at each branch specializes to learn desired feature maps from the embedding space which includes polylines, i.e., input features being the lane level features into a trained neural network that outputs overlapping feature maps being the stitched together features in a sliding window approach comprising polylines).
It would have been obvious to one having ordinary skill in the art before the effective filing date to modify the invention of Ferguson by including the input of features into a neural network to output overlapping feature maps comprising polylines taught by Wei. One of ordinary skill in the art would be motivated to combine the references since it is a solution to generate HD-Maps for autonomous vehicles at scale (Wei, Abstract, teaches the motivation of combination to offer a flexible solution for HD-Maps for autonomous vehicles at scale).
However, the combination of references of Ferguson in view of Wei does not explicitly teach “aggregating, with the at least one processor, the overlapping rich feature maps according to an aggregation function to obtain raster images; and applying vectorization, with the at least one processor, to the raster images to extract roadway geometry represented by globally consistent polylines".
In an analogous field of endeavor, Zhang teaches "aggregating, with the at least one processor, the overlapping rich feature maps according to an aggregation function to obtain raster images"; (Zhang, Abstract, teaches aggregating a plurality of feature maps to obtain an aggregated feature corresponding to each feature map set and performing fusion on the plurality of aggregated features to obtain a depth image, i.e., aggregating feature maps according to an aggregation function to obtain raster images).
It would have been obvious to one having ordinary skill in the art before the effective filing date to modify the invention of Ferguson and Wei wherein the feature maps are overlapping by including the aggregation of the feature maps according to an aggregation function to obtain raster images taught by Zhang. One of ordinary skill in the art would be motivated to combine the references since it enriches image content (Zhang, Abstract, teaches the motivation of combination to be to enrich information content of the acquired target images).
However, the combination of references of Ferguson in view of Wei and Zhang does not explicitly teach "and applying vectorization, with the at least one processor, to the raster images to extract roadway geometry represented by globally consistent polylines".
In an analogous field of endeavor, Gao teaches "and applying vectorization, with the at least one processor, to the raster images to extract roadway geometry represented by globally consistent polylines"; (Gao, Paras. 38 and 83, teaches generating a vectorized representation of the scene data, i.e., applying vectorization to the raster images, to approximate geographic entities using polylines and attributes of the polylines wherein the vectorized representation includes polylines representing crosswalks, lane boundaries, agent trajectory, road signs, stop lights, and sidewalks, i.e., extracting roadway geometry represented by globally consistent polylines).
It would have been obvious to one having ordinary skill in the art before the effective filing date to modify the invention of Ferguson, Wei, and Zhang by including the vectorization of raster images to extract road geometry comprising polylines taught by Gao. One of ordinary skill in the art would be motivated to combine the references since it accurately and reliably predicts trajectories (Gao, Para. 21, teaches the motivation of combination to be to accurately and reliably predict agent trajectory).
Thus, the claimed subject matter would have been obvious to a person having ordinary skill in the art before the effective filing date.
Regarding Claim 4, the combination of references of Ferguson in view of Wei, Zhang, and Gao further teaches "The method of claim 1, wherein the aggregation function is one of a maximum aggregation function, a minimum aggregation function, or a mean aggregation function"; (Gao, Para. 89, teaches an aggregation function as a max pooling operation or an average pooling operation, i.e., aggregation function is one of a maximum aggregation function or a mean aggregation function).
The proposed combination as well as the motivation for combining the Ferguson, Wei, Zhang, and Gao references presented in the rejection of Claim 1, applies to claim 4. Thus, the method recited in claim 4 is met by Ferguson in view of Wei, Zhang, and Gao.
Regarding Claim 5, the combination of references of Ferguson in view of Wei, Zhang, and Gao further teaches "The method of claim 1, wherein the trained neural network outputs rich feature maps in a floating point format"; (Ferguson, Para. 67, teaches the output of the feature map is a floating point value, i.e., neural network outputs rich feature maps in a floating point format).
Regarding Claim 6, the combination of references of Ferguson in view of Wei, Zhang, and Gao further teaches "The method of claim 1, wherein the sensor data comprises overlapping LiDAR scans"; (Ferguson, Para. 68, teaches a geographic terrain mapper which uses LIDAR sensors wherein a map of the geographical area is received from continuously streamed LIDAR sensor outputs, i.e., sensor data comprising overlapping LIDAR scans).
Regarding Claim 7, the combination of references of Ferguson in view of Wei, Zhang, and Gao further teaches "The method of claim 1, comprising storing the globally consistent polylines"; (Gao, Paras. 38 and 44, teaches polylines and attributes of the polylines to generate a respective predicted trajectory wherein the trained model parameter values are obtained from a trajectory prediction model parameters store, i.e., storing the globally consistent polylines);
"wherein the globally consistent polylines enable localization as a vehicle navigates locations corresponding to the base map"; (Wei, Abstract and Section I. Introduction, teaches HD-maps provide lane-level detailed information for precise localization and pose estimation, AV maneuver planning, and provide redundant information to the vehicle to compensate for the weakness of on-vehicle sensors wherein the HD-maps comprise road and lane edge polylines, i.e., polylines enable localization as a vehicle navigates locations corresponding to the map through the AV maneuver planning and localization).
The proposed combination as well as the motivation for combining the Ferguson, Wei, Zhang, and Gao references presented in the rejection of Claim 1, applies to claim 7. Thus, the method recited in claim 7 is met by Ferguson in view of Wei, Zhang, and Gao.
Regarding Claim 8, the combination of references of Ferguson in view of Wei, Zhang, and Gao further teaches "The method of claim 1, comprising storing the base map, globally consistent polylines, and polygons representing semantic objects as a high definition map"; (Ferguson, Para. 68, teaches the mapping including an HD map that includes a base map layer, a semantic map layer, and a geometric map layer. Gao, Paras. 51, 56, and 71, teaches the system rendering an HD map which comprises a respective polyline of each of the features of the map, i.e., globally consistent polylines, and road features represented as polygons such as crosswalks or stop signs, i.e., polygons representing semantic objects).
The proposed combination as well as the motivation for combining the Ferguson, Wei, Zhang, and Gao references presented in the rejection of Claim 1, applies to claim 8. Thus, the method recited in claim 8 is met by Ferguson in view of Wei, Zhang, and Gao.
Claim 11 recites a system with elements corresponding to the steps recited in Claim 1. Therefore, the recited elements of this claim are mapped to the proposed combination in the same manner as the corresponding steps in its corresponding method claim. Additionally, the rationale and motivation to combine the Ferguson, Wei, Zhang, and Gao references, presented in rejection of Claim 1, apply to this claim. Finally, the combination of the Ferguson, Wei, Zhang, and Gao references discloses a processor and a memory storing instructions (for example, see Ferguson, Paragraph 3).
Claim 14 recites a system with elements corresponding to the steps recited in Claim 4. Therefore, the recited elements of this claim are mapped to the proposed combination in the same manner as the corresponding steps in its corresponding method claim. Additionally, the rationale and motivation to combine the Ferguson, Wei, Zhang, and Gao references, presented in rejection of Claim 1, apply to this claim. Finally, the combination of the Ferguson, Wei, Zhang, and Gao references discloses a processor and a memory storing instructions (for example, see Ferguson, Paragraph 3).
Claim 15 recites a system with elements corresponding to the steps recited in Claim 5. Therefore, the recited elements of this claim are mapped to the proposed combination in the same manner as the corresponding steps in its corresponding method claim. Additionally, the rationale and motivation to combine the Ferguson, Wei, Zhang, and Gao references, presented in rejection of Claim 1, apply to this claim. Finally, the combination of the Ferguson, Wei, Zhang, and Gao references discloses a processor and a memory storing instructions (for example, see Ferguson, Paragraph 3).
Claim 16 recites a system with elements corresponding to the steps recited in Claim 6. Therefore, the recited elements of this claim are mapped to the proposed combination in the same manner as the corresponding steps in its corresponding method claim. Additionally, the rationale and motivation to combine the Ferguson, Wei, Zhang, and Gao references, presented in rejection of Claim 1, apply to this claim. Finally, the combination of the Ferguson, Wei, Zhang, and Gao references discloses a processor and a memory storing instructions (for example, see Ferguson, Paragraph 3).
Claim 17 recites a system with elements corresponding to the steps recited in Claim 7. Therefore, the recited elements of this claim are mapped to the proposed combination in the same manner as the corresponding steps in its corresponding method claim. Additionally, the rationale and motivation to combine the Ferguson, Wei, Zhang, and Gao references, presented in rejection of Claim 1, apply to this claim. Finally, the combination of the Ferguson, Wei, Zhang, and Gao references discloses a processor and a memory storing instructions (for example, see Ferguson, Paragraph 3).
Claim 18 recites a system with elements corresponding to the steps recited in Claim 8. Therefore, the recited elements of this claim are mapped to the proposed combination in the same manner as the corresponding steps in its corresponding method claim. Additionally, the rationale and motivation to combine the Ferguson, Wei, Zhang, and Gao references, presented in rejection of Claim 1, apply to this claim. Finally, the combination of the Ferguson, Wei, Zhang, and Gao references discloses a processor and a memory storing instructions (for example, see Ferguson, Paragraph 3).
Claim 19 recites a computer-readable storage medium storing a program with instructions corresponding to the steps recited in Claim 1. Therefore, the recited programming instructions of this claim are mapped to the proposed combination in the same manner as the corresponding steps in its corresponding method claim. Additionally, the rationale and motivation to combine the Ferguson, Wei, Zhang, and Gao references, presented in rejection of Claim 1, apply to this claim. Finally, the combination of the Ferguson, Wei, Zhang, and Gao references discloses a computer readable storage medium (for example, see Ferguson, Paragraph 31).
Claims 2-3, 12-13, and 20 are rejected under 35 U.S.C. 103 as being unpatentable over Ferguson in view of Wei, Zhang, Gao, and Jenkins et al. (US 20130321407 A1).
Regarding Claim 2, the combination of references of Ferguson in view of Wei, Zhang, and Gao does not explicitly teach "The method of claim 1, further comprising: determining intersecting points between a bounding polygon and at least one globally consistent polyline, and interior points of globally consistent polylines within the bounding polygon; wherein the bounding polygon intersects at least one globally consistent polyline; and constructing convex hulls using the intersecting points and the interior points to generate polygons representing semantic objects corresponding to locations of the base map".
In an analogous field of endeavor, Jenkins teaches "The method of claim 1, further comprising: determining intersecting points between a bounding polygon and at least one globally consistent polyline, and interior points of globally consistent polylines within the bounding polygon"; (Jenkins, Paras. 99-114, teaches the polygon crosses a cutting polyline and wherein an intersection between array of geometries and another geometry is constructed, i.e., intersecting points between the polygon and polyline are determined, and interior points for each polygon are calculated, i.e., determining interior points of the polylines within the polygon);
"wherein the bounding polygon intersects at least one globally consistent polyline"; (Jenkins, Paras. 99-114, teaches returning polygons at specified distances, areas, and perimeter lengths for the input geometry, i.e., drawing bounding polygons, wherein the polygon crosses a cutting polyline and wherein an intersection between array of geometries and another geometry is constructed, i.e., polygon intersects polylines);
"and constructing convex hulls using the intersecting points and the interior points to generate polygons representing semantic objects corresponding to locations of the base map"; (Jenkins, Paras. 68 and 99-114, teaches returning convex hulls of the input geometry from the polygons with calculated interior points wherein the polygons intersect with a cutting polyline and an intersection between an array of geometries and another geometry is constructed wherein the generated polygons are returned from input geometry comprising geological objects, i.e., constructing convex hulls from the intersecting and interior points for generating polygons of semantic objects).
It would have been obvious to one having ordinary skill in the art before the effective filing date to modify the invention of Ferguson, Wei, Zhang, and Gao wherein the polygons represent semantic objects corresponding to locations of the base map by including the construction of convex hulls using intersecting and interior points of polygons for semantic objects taught by Jenkins. One of ordinary skill in the art would be motivated to combine the references since it improves efficiency (Jenkins, Para. 34, teaches the motivation of combination to be to improve efficiency of the workflow).
Thus, the claimed subject matter would have been obvious to a person having ordinary skill in the art before the effective filing date.
Regarding Claim 3, the combination of references of Ferguson in view of Wei, Zhang, Gao, and Jenkins teaches "The method of claim 2, wherein the semantic objects represent road network connectivity properties, roadway physical properties, road features, or any combinations thereof"; (Ferguson, Para. 122, teaches semantic objects such as trees, telephone wires, buildings, lane boundaries, parking areas, crosswalks, traffic signs, lights, etc., i.e., road features).
Claim 12 recites a system with elements corresponding to the steps recited in Claim 2. Therefore, the recited elements of this claim are mapped to the proposed combination in the same manner as the corresponding steps in its corresponding method claim. Additionally, the rationale and motivation to combine the Ferguson, Wei, Zhang, Gao, and Jenkins references, presented in rejection of Claim 2, apply to this claim. Finally, the combination of the Ferguson, Wei, Zhang, Gao, and Jenkins references discloses a processor and a memory storing instructions (for example, see Ferguson, Paragraph 3).
Claim 13 recites a system with elements corresponding to the steps recited in Claim 3. Therefore, the recited elements of this claim are mapped to the proposed combination in the same manner as the corresponding steps in its corresponding method claim. Additionally, the rationale and motivation to combine the Ferguson, Wei, Zhang, Gao, and Jenkins references, presented in rejection of Claim 2, apply to this claim. Finally, the combination of the Ferguson, Wei, Zhang, Gao, and Jenkins references discloses a processor and a memory storing instructions (for example, see Ferguson, Paragraph 3).
Claim 20 recites a computer-readable storage medium storing a program with instructions corresponding to the steps recited in Claim 2. Therefore, the recited programming instructions of this claim are mapped to the proposed combination in the same manner as the corresponding steps in its corresponding method claim. Additionally, the rationale and motivation to combine the Ferguson, Wei, Zhang, Gao, and Jenkins references, presented in rejection of Claim 2, apply to this claim. Finally, the combination of the Ferguson, Wei, Zhang, Gao, and Jenkins references discloses a computer readable storage medium (for example, see Ferguson, Paragraph 31).
Claim 9 is rejected under 35 U.S.C. 103 as being unpatentable over Ferguson in view of Wei, Zhang, Gao, and Sajjan et al. (US 20230213945 A1).
Regarding Claim 9, the combination of references of Ferguson in view of Wei, Zhang, and Gao does not explicitly teach "The method of claim 1, wherein a human annotator draws a bounding polygon that intersects at least one globally consistent polyline to insert semantic objects into s semantic map layer corresponding to the base map".
In an analogous field of endeavor, Sajjan teaches "The method of claim 1, wherein a human annotator draws a bounding polygon that intersects at least one globally consistent polyline to insert semantic objects into s semantic map layer corresponding to the base map"; (Sajjan, Fig. 7 [700] and Paras. 32-33, teaches a human labeler drawing bounding polygons corresponding to objects with semantic information wherein the polygons intersect polylines that define paths, i.e., human annotator draws bounding polygon that intersects globally consistent polyline to insert semantic objects).
It would have been obvious to one having ordinary skill in the art before the effective filing date to modify the invention of Ferguson, Wei, Zhang, and Gao wherein the semantic objects are part of a semantic map layer corresponding to the base map by including the human annotation of bounding polygons intersection polylines for semantic objects taught by Sajjan. One of ordinary skill in the art would be motivated to combine the references since it increases accuracy of the assignments (Sajjan, Abstract, teaches the motivation of combination to be to increase accuracy of the obstacle to path assignments).
Thus, the claimed subject matter would have been obvious to a person having ordinary skill in the art before the effective filing date.
Claim 10 is rejected under 35 U.S.C. 103 as being unpatentable over Ferguson in view of Wei, Zhang, Gao, and Khadem et al. (US 20240125899 A1).
Regarding Claim 10, the combination of references of Ferguson in view of Wei, Zhang, and Gao does not explicitly teach "The method of claim 1, wherein the road geometry comprises lanes, lane dividers, intersections, and stop lines".
In an analogous field of endeavor, Khadem teaches "The method of claim 1, wherein the road geometry comprises lanes, lane dividers, intersections, and stop lines"; (Khadem, Para. 8, teaches road map elements including lane elements, lane divider elements, an intersection element, and stop line elements, i.e., road geometry comprises lanes, lane dividers, intersections, and stop lines).
It would have been obvious to one having ordinary skill in the art before the effective filing date to modify the invention of Ferguson, Wei, Zhang, and Gao by including the road geometry including lanes, dividers, intersections, and stop lines taught by Khadem. One of ordinary skill in the art would be motivated to combine the references since it enables automatic map creation and updates (Khadem, Para. 18, teaches the motivation of combination to be to enable automatic map creation and operation updates to significantly reduce processing and time required to maintain a road network map).
Thus, the claimed subject matter would have been obvious to a person having ordinary skill in the art before the effective filing date.
Claim 21 is rejected under 35 U.S.C. 103 as being unpatentable over Ferguson in view of Wei, Zhang, Gao, and Kwant et al. (US 9940729 B1).
Regarding Claim 21, the combination of references of Ferguson in view of Wei, Zhang, and Gao does not explicitly teach "The method of claim 1, wherein the overlapping rich feature maps correspond to the same locations at different timestamps".
In an analogous field of endeavor, Kwant teaches "The method of claim 1, wherein the overlapping rich feature maps correspond to the same locations at different timestamps"; (Kwant, Col. 14 lines 13-29, teaches two or more test images comprising at least two images that substantially overlap and that were taken at different times wherein the network analyzes the test images to identify features within the test images and generate a feature map comprising the identified features for each test image, i.e., overlapping feature maps corresponding to the same location at different timestamps).
It would have been obvious to one having ordinary skill in the art before the effective filing date to modify the invention of Ferguson, Wei, Zhang, and Gao by including the overlapping feature maps corresponding to the same locations at different timestamps taught by Kwant. One of ordinary skill in the art would be motivated to combine the references since it minimizes the loss function of the images (Kwant, Col. 14 lines 13-29, teaches the motivation of combination to be to determine if the feature maps corresponding to overlapping test images are sufficiently similar to minimize the loss function for the images).
Thus, the claimed subject matter would have been obvious to a person having ordinary skill in the art before the effective filing date.
Conclusion
THIS ACTION IS MADE FINAL. Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any extension fee pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the mailing date of this final action.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to ANDREW STEVEN BUDISALICH whose telephone number is (703)756-5568. The examiner can normally be reached Monday - Friday 8:30am-5:00pm 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, Amandeep Saini can be reached on (571) 272-3382. 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.
/ANDREW S BUDISALICH/Examiner, Art Unit 2662
/AMANDEEP SAINI/Supervisory Patent Examiner, Art Unit 2662