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 .
Response to Amendment
Applicant submitted amendments and remarks on April 28, 2026. Therein, Applicant submitted substantive arguments. Claims 1, 9, and 17 have been amended. Claims 21-23 were added. Claims 2, 10, and 18 were cancelled.
Applicant has made adequate amendments to claims 1, 9, and 17 in order to integrate the abstract idea of “generating” into a practical application. Therefore, the 35 U.S.C. 101 rejections for these claims are withdrawn.
The submitted claims are considered below.
Claim Rejections - 35 USC § 102
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
The following is a quotation of the appropriate paragraphs of 35 U.S.C. 102 that form the basis for the rejections under this section made in this Office action:
A person shall be entitled to a patent unless –
(a)(2) the claimed invention was described in a patent issued under section 151, or in an application for patent published or deemed published under section 122(b), in which the patent or application, as the case may be, names another inventor and was effectively filed before the effective filing date of the claimed invention.
Claims 1, 3-5, 7-9, 11-13, 15-17, and 19-20 are rejected under 35 U.S.C. 102(a)(2) as being anticipated by Yang, et al. (U.S. Patent No. 10545029).
Regarding claim 1, Yang, et al. teaches: A system comprising: (Fig. 1, Col. 5, lines 48-50: "The HD map system (100) includes an online HD map system (110) that interacts with a plurality of vehicles (150) [system].")
a processor; (Fig. 1, Col. 11, lines 65-67: "…the online HD map system (110) may be a distributed system comprising a plurality of processors [processor].")
a memory in communication with the processor, the memory includes instructions that, when executed by the processor, cause the processor to: (Fig. 44, Col. 46, lines 24-28: "The instructions (4424) (e.g., software) [instructions] may also reside, completely or at least partially, within the main memory (4404) [memory] or within the processor (4402) (e.g., within a processor's cache memory) during execution thereof by the computer system (4400) [communication with the processor]")
generate drivable surface polygons that represent a drivable surface of a road using key point detections and a vehicle trace; (Col. 29, lines 48-54: "…The identified 2D points with high enough center line probabilities are mapped to lane line points (2925) of a 3D voxel which exists in a 3D plane (2930). Lane lines (2935) are represented as continuous lines along a vehicle route, but can be broken down into lane line segments (2940) [point detections with respect to a vehicle trace]." ; Col. 32, lines 28-33: "FIG. 32E shows a visual representation of a lane line segment (2940) divided into several subclusters (3280) and their respective skeleton points (3282), according to an embodiment. In one embodiment, subclusters (3280) may be have a circular shape while in others they may be elliptically shaped or a polygon [creation of surface polygons]." ; Col. 37, lines 19-28: "…the HD map system (100) generates a lane element graph that represents a network of lanes to allow a vehicle to plan a legal path between a source and a destination. A lane element graph allows navigation of autonomous vehicles through a mapped area. […] A lane element graph represents the navigable road surface that is divided into lane elements, and includes connectivity among lane elements [representation of a drivable surface]")
generate an electronic map based on the drivable surface polygons (Col. 39, lines 51-54: "A high definition map [electronic map] of the local area can then be generated (3610) including the lane element graph for use in driving by one or more autonomous vehicles [based on drivable surface polygons].")
and control a vehicle to autonomously drive using the electronic map (Col. 7, lines 10-13: "The vehicle computing system (120) continuously provides control signals to the vehicle controls (130), thereby causing an autonomous vehicle to drive along a selected route [driving control of autonomous vehicle]." ; Col. 6, lines 27-33: "For example, if an autonomous vehicle needs to drive along a route, the vehicle computing system (120) of the autonomous vehicle provides information describing the route being traveled to the online HD map system (110). In response, the online HD map system (110) provides the required HD maps for driving along the route [maps provided by electronic map system to autonomously drive vehicle].").
Regarding claim 3, Yang, et al. teaches: The system of claim 1, wherein the memory further includes instructions that, when executed by the processor, cause the processor to: generate a first boundary line by connecting the key point detections of a first lane boundary; (Col. 38, lines 10-12: "The lane cut module (3510) generates lane cuts by analyzing lane lines and navigable boundaries. A lane line represents a boundary of a lane [boundary lane]" ; Col. 39, line 62 to Col. 40, lines 1-4: "The lane cut module (3510) casts (3702) a ray perpendicular to the line segment. The head or tail control points of each lane line will be referred to as the origin of the ray. The ray extends from the origin of the ray. The lane cut module (3510) computes (3704) the intersections of the ray to other nearby lane lines and navigable boundaries. The computation is done in a same direction that the ray extends [connections relating to detections of boundary]. In some embodiments, a ray can be cast in a first direction [first boundary line]")
and generate a second boundary line by connecting the key point detections of a second lane boundary (Col. 38, lines 10-12: "The lane cut module (3510) generates lane cuts by analyzing lane lines and navigable boundaries. A lane line represents a boundary of a lane [boundary lane]" ; Col. 39, line 62 to Col. 40, lines 1-4: "The lane cut module (3510) casts (3702) a ray perpendicular to the line segment. The head or tail control points of each lane line will be referred to as the origin of the ray. The ray extends from the origin of the ray. The lane cut module (3510) computes (3704) the intersections of the ray to other nearby lane lines and navigable boundaries. The computation is done in a same direction that the ray extends [connections relating to detections of boundary]. In some embodiments, […] a ray can be cast in a second direction [second boundary line]").
Regarding claim 4, Yang, et al. teaches: The system of claim 3, wherein the memory further includes instructions that, when executed by the processor, cause the processor to: segment the vehicle trace generated by a vehicle that collected sensor information used to generate the key point detections by a fixed length to generate segmented vehicle traces; (Col. 35, lines 50-56: "Specifically, to check endpoints for involvement in an existing connection, connections with a distance below the length of the lane line segment (2940) are analyzed. The system checks endpoints whose distances to one end of the connection are smaller than a threshold D. The threshold D is the maximum distance that the system considers [checking sensor data with respect to point detections at a fixed length]." ; Col. 41, lines 21-24: "In some embodiments, the lane elements are restricted to a maximum length. Breaking lane elements in to smaller lengths can make processing and usage of the lane element more efficient [fixed length - segmenting vehicle trace values].")
and generate, along each of the segmented vehicle traces, at least one of the drivable surface polygons that extend between the first boundary line and the second boundary line (Col. 34, lines 47-55: "Adjusting the endpoints of the polyline (3354) may be performed by identifying a first midpoint of the entire polyline and identifying any lane line points (2925) between the first midpoint and the first endpoint of the polyline that are a distance greater than the threshold distance from the polyline [generating segmented polygon from polylines with respect to segmented vehicle traces]. If no lane line point is identified, the first midpoint is set as a new endpoint and the above process is performed for a second midpoint that lies between the first midpoint and the second endpoint [extend between first and second boundary line].").
Regarding claim 5, Yang, et al. teaches: The system of claim 1, wherein the memory further includes instructions that, when executed by the processor, cause the processor to: segment the vehicle trace generated by a vehicle that collected sensor information used to generate the key point detections by a fixed length to generate segmented vehicle traces; (Col. 35, lines 50-56: "Specifically, to check endpoints for involvement in an existing connection, connections with a distance below the length of the lane line segment (2940) are analyzed. The system checks endpoints whose distances to one end of the connection are smaller than a threshold D. The threshold D is the maximum distance that the system considers [checking sensor data with respect to point detections at a fixed length]." ; Col. 41, lines 21-24: "In some embodiments, the lane elements are restricted to a maximum length. Breaking lane elements in to smaller lengths can make processing and usage of the lane element more efficient [fixed length - segmenting vehicle trace values].")
and in response to a determination that a second boundary line does not overlap a first boundary line, generate at least one of the drivable surface polygons that extend from at least one of the segmented vehicle traces to the first boundary line and from the at least one of the segmented vehicle traces in a direction that is opposite of the first boundary line (Col. 31, lines 39-43: "Using the identified skeleton points stored within the skeleton point store (3225), the fine clustering module (3230) distinguishes between intersecting lane lines (2935) [determination if second boundary line does not overlap first boundary line] moving in different directions [opposite direction]." ; Col. 33, lines 9-13: "The outlier analysis module (3320) identifies and analyzes outliers to determine if they represent a change in the direction of the lane line segment or merely a deviation from the polyline in the same direction [determination of segmented vehicle traces if direction is opposite first boundary line]." ; Col. 35, lines 1-6: "FIG. 34B shows the system architecture for the lane connection module (2940), according to an embodiment. The lane connection module (2940) connects individual lane line segments into complete representation of lane lines using the center-line polylines (3310) generated by the cluster center analysis module (2935) [creation of polygons based on segmented vehicle trace analysis].").
Regarding claim 7, Yang, et al. teaches: The system of claim 1, wherein the memory further includes instructions that, when executed by the processor, cause the processor to generate a three-dimensional mesh based on the drivable surface polygons (Col. 14, lines 9-18: "The occupancy map (530) comprises spatial 3-dimensional (3D) representation of the road and all physical objects around the road. […] The occupancy map (530) may be represented in a number of other ways. In one embodiment, the occupancy map (530) is represented as a 3D mesh geometry (collection of triangles) which covers the surfaces [3D mesh based on drivable surface polygons].").
Regarding claim 8, Yang, et al. teaches: The system of claim 7, wherein the memory further includes instructions that, when executed by the processor, cause the processor to generate a road graph for use in the electronic map based on the three-dimensional mesh (Col. 42, lines 11-16: "FIG. 41 illustrates generating a lane element graph from primary features and derived features. Primary features may include lane boundaries, navigable boundaries, lane cuts, lane connectors, and traffic sign, signal, bumps, etc [creation of road graph based on earlier determined 3D mesh].").
Regarding claim 9, Yang, et al. teaches: A method comprising: generating drivable surface polygons that represent a drivable surface of a road using key point detections and a vehicle trace; (Fig. 36, Step (3602), Col. 39, lines 3-7: "The lane element graph module (470) identifies (3602) lane cuts from lane lines and navigable boundaries. The lane cut lines and navigable boundaries are generated from a plurality of received image frames from an imaging system mounted on a vehicle [point detections with respect to a vehicle trace]." ; Col. 32, lines 28-33: "FIG. 32E shows a visual representation of a lane line segment (2940) divided into several subclusters (3280) and their respective skeleton points (3282), according to an embodiment. In one embodiment, subclusters (3280) may be have a circular shape while in others they may be elliptically shaped or a polygon [creation of surface polygons]." ; Col. 37, lines 19-28: "…the HD map system (100) generates a lane element graph that represents a network of lanes to allow a vehicle to plan a legal path between a source and a destination. A lane element graph allows navigation of autonomous vehicles through a mapped area. […] A lane element graph represents the navigable road surface that is divided into lane elements, and includes connectivity among lane elements [representation of a drivable surface]")
and generating an electronic map based on the drivable surface polygons (Fig. 36, Step (3610), Col. 39, lines 51-54: "A high definition map [electronic map] of the local area can then be generated (3610) including the lane element graph for use in driving by one or more autonomous vehicles [based on drivable surface polygons].")
and controlling a vehicle to autonomously drive using the electronic map (Fig. 36, Step (3610), Col. 39, lines 51-54: "A high definition map [electronic map] of the local area can then be generated (3610) including the lane element graph for use in driving by one or more autonomous vehicles [electronic map used to drive autonomous vehicle]." ; Col. 6, lines 27-33: "For example, if an autonomous vehicle needs to drive along a route, the vehicle computing system (120) of the autonomous vehicle provides information describing the route being traveled to the online HD map system (110). In response, the online HD map system (110) provides the required HD maps for driving along the route [maps provided by electronic map system to autonomously drive vehicle]." ; Col. 7, lines 10-13: "The vehicle computing system (120) continuously provides control signals to the vehicle controls (130), thereby causing an autonomous vehicle to drive along a selected route [driving control of autonomous vehicle].").
Regarding claim 11, Yang, et al. teaches: The method of claim 9, further comprising: generating a first boundary line by connecting the key point detections of a first lane boundary; (Col. 38, lines 10-12: "The lane cut module (3510) generates lane cuts by analyzing lane lines and navigable boundaries. A lane line represents a boundary of a lane [boundary lane]" ; Col. 39, line 62 to Col. 40, lines 1-4: "The lane cut module (3510) casts (3702) a ray perpendicular to the line segment. The head or tail control points of each lane line will be referred to as the origin of the ray. The ray extends from the origin of the ray. The lane cut module (3510) computes (3704) the intersections of the ray to other nearby lane lines and navigable boundaries. The computation is done in a same direction that the ray extends [connections relating to detections of boundary]. In some embodiments, a ray can be cast in a first direction [first boundary line]")
and generating a second boundary line by connecting the key point detections of a second lane boundary (Col. 38, lines 10-12: "The lane cut module (3510) generates lane cuts by analyzing lane lines and navigable boundaries. A lane line represents a boundary of a lane [boundary lane]" ; Col. 39, line 62 to Col. 40, lines 1-4: ""The lane cut module (3510) casts (3702) a ray perpendicular to the line segment. The head or tail control points of each lane line will be referred to as the origin of the ray. The ray extends from the origin of the ray. The lane cut module (3510) computes (3704) the intersections of the ray to other nearby lane lines and navigable boundaries. The computation is done in a same direction that the ray extends [connections relating to detections of boundary]. In some embodiments, […] a ray can be cast in a second direction [second boundary line]").
Regarding claim 12, Yang, et al. teaches: The method of claim 11, further comprising: segmenting the vehicle trace generated by a vehicle that collected sensor information used to generate the key point detections by a fixed length to generate segmented vehicle traces; (Col. 35, lines 50-56: "Specifically, to check endpoints for involvement in an existing connection, connections with a distance below the length of the lane line segment (2940) are analyzed. The system checks endpoints whose distances to one end of the connection are smaller than a threshold D. The threshold D is the maximum distance that the system considers [checking sensor data with respect to point detections at a fixed length]." ; Col. 41, lines 21-24: "In some embodiments, the lane elements are restricted to a maximum length. Breaking lane elements in to smaller lengths can make processing and usage of the lane element more efficient [fixed length - segmenting vehicle trace values].")
and generating, along each of the segmented vehicle traces, at least one of the drivable surface polygons that extend between the first boundary line and the second boundary line (Col. 34, lines 47-55: "Adjusting the endpoints of the polyline (3354) may be performed by identifying a first midpoint of the entire polyline and identifying any lane line points (2925) between the first midpoint and the first endpoint of the polyline that are a distance greater than the threshold distance from the polyline [generating segmented polygon from polylines with respect to segmented vehicle traces]. If no lane line point is identified, the first midpoint is set as a new endpoint and the above process is performed for a second midpoint that lies between the first midpoint and the second endpoint [extend between first and second boundary line].").
Regarding claim 13, Yang, et al. teaches: The method of claim 9, further comprising: segmenting the vehicle trace generated by a vehicle that collected sensor information used to generate the key point detections by a fixed length to generate segmented vehicle traces; (Col. 35, lines 50-56: "Specifically, to check endpoints for involvement in an existing connection, connections with a distance below the length of the lane line segment (2940) are analyzed. The system checks endpoints whose distances to one end of the connection are smaller than a threshold D. The threshold D is the maximum distance that the system considers [checking sensor data with respect to point detections at a fixed length]." ; Col. 41, lines 21-24: "In some embodiments, the lane elements are restricted to a maximum length. Breaking lane elements in to smaller lengths can make processing and usage of the lane element more efficient [fixed length - segmenting vehicle trace values].")
and in response to a determination that a second boundary line does not overlap a first boundary line, generating at least one of the drivable surface polygons that extend from at least one of the segmented vehicle traces to the first boundary line and from the at least one of the segmented vehicle traces in a direction that is opposite of the first boundary line (Col. 31, lines 39-43: "Using the identified skeleton points stored within the skeleton point store (3225), the fine clustering module (3230) distinguishes between intersecting lane lines (2935) [determination if second boundary line does not overlap first boundary line] moving in different directions [opposite direction]." ; Col. 33, lines 9-13: "The outlier analysis module (3320) identifies and analyzes outliers to determine if they represent a change in the direction of the lane line segment or merely a deviation from the polyline in the same direction [determination of segmented vehicle traces if direction is opposite first boundary line]." ; Col. 35, lines 1-6: "FIG. 34B shows the system architecture for the lane connection module (2940), according to an embodiment. The lane connection module (2940) connects individual lane line segments into complete representation of lane lines using the center-line polylines (3310) generated by the cluster center analysis module (2935) [creation of polygons based on segmented vehicle trace analysis].").
Regarding claim 15, Yang, et al. teaches: The method of claim 9, further comprising generating a three-dimensional mesh based on the drivable surface polygons (Col. 14, lines 9-18: "The occupancy map (530) comprises spatial 3-dimensional (3D) representation of the road and all physical objects around the road. […] The occupancy map (530) may be represented in a number of other ways. In one embodiment, the occupancy map (530) is represented as a 3D mesh geometry (collection of triangles) which covers the surfaces [3D mesh based on drivable surface polygons].").
Regarding claim 16, Yang, et al. teaches: The method of claim 15, further comprising generating a road graph for use in the electronic map based on the three-dimensional mesh (Col. 42, lines 11-16: "FIG. 41 illustrates generating a lane element graph from primary features and derived features. Primary features may include lane boundaries, navigable boundaries, lane cuts, lane connectors, and traffic sign, signal, bumps, etc [creation of road graph based on earlier determined 3D mesh].").
Regarding claim 17, Yang, et al. teaches: A non-transitory computer-readable medium storing instructions that, when executed by a processor, cause the processor to: ("The instructions (4424) (e.g., software) [instructions] may also reside, completely or at least partially, within the main memory (4404) or within the processor (4402) (e.g., within a processor's cache memory) during execution thereof by the computer system (4400) [communication with the processor] the main memory (4404) and the processor (4402) also constituting machine-readable media [non-transitory computer-readable medium].")
generate drivable surface polygons that represents a drivable surface of a road using key point detections and a vehicle trace; (Col. 29, lines 48-54: "…The identified 2D points with high enough center line probabilities are mapped to lane line points (2925) of a 3D voxel which exists in a 3D plane (2930). Lane lines (2935) are represented as continuous lines along a vehicle route, but can be broken down into lane line segments (2940) [point detections with respect to a vehicle trace]." ; Col. 32, lines 28-33: "FIG. 32E shows a visual representation of a lane line segment (2940) divided into several subclusters (3280) and their respective skeleton points (3282), according to an embodiment. In one embodiment, subclusters (3280) may be have a circular shape while in others they may be elliptically shaped or a polygon [creation of surface polygons]." ; Col. 37, lines 19-28: "In some embodiments, the HD map system (100) generates a lane element graph that represents a network of lanes to allow a vehicle to plan a legal path between a source and a destination. A lane element graph allows navigation of autonomous vehicles through a mapped area. […] A lane element graph represents the navigable road surface that is divided into lane elements, and includes connectivity among lane elements [representation of a drivable surface]")
and generate an electronic map based on the drivable surface polygons (Col. 39, lines 51-54: "A high definition map [electronic map] of the local area can then be generated (3610) including the lane element graph for use in driving by one or more autonomous vehicles [based on drivable surface polygons].")
and control a vehicle to autonomously drive using the electronic map (Col. 7, lines 10-13: "The vehicle computing system (120) continuously provides control signals to the vehicle controls (130), thereby causing an autonomous vehicle to drive along a selected route [driving control of autonomous vehicle]." ; Col. 6, lines 27-33: "For example, if an autonomous vehicle needs to drive along a route, the vehicle computing system (120) of the autonomous vehicle provides information describing the route being traveled to the online HD map system (110). In response, the online HD map system (110) provides the required HD maps for driving along the route [maps provided by electronic map system to autonomously drive vehicle].").
Regarding claim 19, Yang, et al. teaches: The non-transitory computer-readable medium of claim 17, further comprising instructions that, when executed by the processor, cause the processor to: generate a first boundary line by connecting the key point detections of a first lane boundary; (Col. 38, lines 10-12: "The lane cut module (3510) generates lane cuts by analyzing lane lines and navigable boundaries. A lane line represents a boundary of a lane [boundary lane]" ; Col. 39, line 62 to Col. 40, lines 1-4: "The lane cut module (3510) casts (3702) a ray perpendicular to the line segment. The head or tail control points of each lane line will be referred to as the origin of the ray. The ray extends from the origin of the ray. The lane cut module (3510) computes (3704) the intersections of the ray to other nearby lane lines and navigable boundaries. The computation is done in a same direction that the ray extends [connections relating to detections of boundary]. In some embodiments, a ray can be cast in a first direction [first boundary line]")
and generate a second boundary line by connecting the key point detections of a second lane boundary (Col. 38, lines 10-12: "The lane cut module (3510) generates lane cuts by analyzing lane lines and navigable boundaries. A lane line represents a boundary of a lane [boundary lane]" ; Col. 39, line 62 to Col. 40, lines 1-4: "The lane cut module (3510) casts (3702) a ray perpendicular to the line segment. The head or tail control points of each lane line will be referred to as the origin of the ray. The ray extends from the origin of the ray. The lane cut module (3510) computes (3704) the intersections of the ray to other nearby lane lines and navigable boundaries. The computation is done in a same direction that the ray extends [connections relating to detections of boundary]. In some embodiments, […] a ray can be cast in a second direction [second boundary line]").
Regarding claim 20, Yang, et al. teaches: The non-transitory computer-readable medium of claim 19, further comprising instructions that, when executed by the processor, cause the processor to: segment the vehicle trace generated by a vehicle that collected sensor information used to generate the key point detections by a fixed length to generate segmented vehicle traces; (Col. 35, lines 50-56: "Specifically, to check endpoints for involvement in an existing connection, connections with a distance below the length of the lane line segment (2940) are analyzed. The system checks endpoints whose distances to one end of the connection are smaller than a threshold D. The threshold D is the maximum distance that the system considers [checking sensor data with respect to point detections at a fixed length]." ; Col. 41, lines 21-24: "In some embodiments, the lane elements are restricted to a maximum length. Breaking lane elements in to smaller lengths can make processing and usage of the lane element more efficient [fixed length - segmenting vehicle trace values].")
and generate, along each of the segmented vehicle traces, at least one of the drivable surface polygons that extend between the first boundary line and the second boundary line (Col. 34, lines 47-55: "Adjusting the endpoints of the polyline (3354) may be performed by identifying a first midpoint of the entire polyline and identifying any lane line points (2925) between the first midpoint and the first endpoint of the polyline that are a distance greater than the threshold distance from the polyline [generating segmented polygon from polylines with respect to segmented vehicle traces]. If no lane line point is identified, the first midpoint is set as a new endpoint and the above process is performed for a second midpoint that lies between the first midpoint and the second endpoint [extend between first and second boundary line].").
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 (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
The following is a quotation of 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.
Claims 6 and 14 are rejected under 35 U.S.C. 103 as being unpatentable over Yang, et al. (U.S. Patent No. 10545029) in view of Fujita, et al. (U.S. Patent No. 10384679).
Regarding claim 6, Yang, et al. does not teach the system of claim 5, wherein a length of the direction that is opposite of the first boundary line is one of: half a width of the vehicle that collected sensor information used to generate the key point detections; and a maximum sensing distance of a sensor of the vehicle that collected sensor information used to generate the first boundary line.
In a similar field of endeavor (lane boundary line detection), Fujita, et al. teaches: The system of claim 5, wherein a length of the direction that is opposite of the first boundary line is one of: half a width of the vehicle that collected sensor information used to generate the key point detections; and a maximum sensing distance of a sensor of the vehicle that collected sensor information used to generate the first boundary line (Col. 6, lines 10-15: "The control device (160) uses the boundary line integration function to integrate the map boundary lines detected using the map boundary line detection function and the sensor boundary lines detected using the sensor boundary line detection function to generate lane boundary lines of lanes including the lane in which the subject vehicle travels [integration of boundary lines into maps]." ; Col. 9, lines 15-19: "…the range in which the ambient detection sensor (110) can detect the sensor boundary lines is a range of a certain distance (e.g. several tens of meters) from the subject vehicle, that is, a range around the subject vehicle [maximum vehicle sensing distance]." ; Col. 14, lines 17-25: "Then, as the degree of reliability of the sensor boundary lines increases, the range of the sensor boundary lines to be integrated with the map boundary lines is expanded toward the traveling direction of the subject vehicle, while as the degree of reliability of the sensor boundary lines decreases, the range of the sensor boundary lines to be integrated with the map boundary lines is contracted toward the direction opposite to the traveling direction of the subject vehicle [relationship - length of direction opposite first boundary line with respect to sensor information].").
Therefore, it would have been obvious to one of the ordinary skill of the art before the effective filing date of the claimed invention to modify Yang, et al. to include the teaching of Fujita, et al. based on a reasonable expectation of success and motivation to improve the proper detection of a lane boundary line around a subject vehicle in an actual environment (Fujita, et al. Col. 1, lines 35-44).
Regarding claim 14, Yang, et al. does not teach the method of claim 13, wherein a length of the direction that is opposite of the first boundary line is one of: half a width of the vehicle that collected sensor information used to generate the key point detections; and a maximum sensing distance of a sensor of the vehicle that collected sensor information used to generate the first boundary line.
In a similar field of endeavor (lane boundary line detection), Fujita, et al. teaches: The method of claim 13, wherein a length of the direction that is opposite of the first boundary line is one of: half a width of the vehicle that collected sensor information used to generate the key point detections; and a maximum sensing distance of a sensor of the vehicle that collected sensor information used to generate the first boundary line (Col. 6, lines 10-15: "The control device (160) uses the boundary line integration function to integrate the map boundary lines detected using the map boundary line detection function and the sensor boundary lines detected using the sensor boundary line detection function to generate lane boundary lines of lanes including the lane in which the subject vehicle travels [integration of boundary lines into maps]." ; Col. 9, lines 15-19: "…the range in which the ambient detection sensor (110) can detect the sensor boundary lines is a range of a certain distance (e.g. several tens of meters) from the subject vehicle, that is, a range around the subject vehicle [maximum vehicle sensing distance]." ; Col. 14, lines 17-25: "Then, as the degree of reliability of the sensor boundary lines increases, the range of the sensor boundary lines to be integrated with the map boundary lines is expanded toward the traveling direction of the subject vehicle, while as the degree of reliability of the sensor boundary lines decreases, the range of the sensor boundary lines to be integrated with the map boundary lines is contracted toward the direction opposite to the traveling direction of the subject vehicle [relationship - length of direction opposite first boundary line with respect to sensor information].").
Therefore, it would have been obvious to one of the ordinary skill of the art before the effective filing date of the claimed invention to modify Yang, et al. to include the teaching of Fujita, et al. based on a reasonable expectation of success and motivation to improve the proper detection of a lane boundary line around a subject vehicle in an actual environment (Fujita, et al. Col. 1, lines 35-44).
Claims 21-23 are rejected under 35 U.S.C. 103 as being unpatentable over Yang, et al. (U.S. Patent No. 10545029) in view of Thibaux, et al. (U.S. Patent Application Publication No. 20230099772).
Regarding claim 21, Yang, et al. does not teach the system of claim 1, wherein the electronic map is generated from the drivable surface polygons using a connection graph and a separation graph derived from the drivable surface polygons, the connection graph indicating which overlapping polygons represent road surfaces that are directly accessible to each other and the separation graph indicating which overlapping polygons represent road surfaces that are not directly accessible to each other.
In a similar field of endeavor (lane graph topology), Thibaux, et al. teaches: The system of claim 1, wherein the electronic map is generated from the drivable surface polygons using a connection graph and a separation graph derived from the drivable surface polygons, (Paragraph [0042]: "Rather, the cells can be defined solely by information representing how cells are connected by edges [connection relationship]. […] a cell having an edge represents that a vehicle can travel from a region represented by the cell to a second region. The second region might be represented by another cell or might be considered a drivable region outside the region of interest, in which case no cell would be included. Thus, two cells sharing an edge between them represents two drivable areas that are physically contiguous in reality [electronic map generated from polygons using connection graph]." ; Paragraph [0051]: "FIG. (1a) illustrates a lane (102a) that splits into two lanes (104a) and (104b) at split point (106a). The two lanes (104a), (104b) travel to the left and right, respectively, of an obstacle (108d). FIG. 1B similarly illustrates a lane (102b) that splits into two lanes (104c) and (104d) at split point (106b) that exists at a different geometric location. The two lanes (104c), (104d) travel to the left and right, respectively, of an obstacle (108d) [separation graph - example]. However, while the lanes illustrated in FIGS. (1a) and (1b) are geometrically different, they are topologically identical because they enter the same cells through the same edges, and can therefore be continuously deformed from the geometry of FIG. (1a) to that of FIG. (1B) and vice versa [electronic map derived from drivable surface polygons using separation graph].")
the connection graph indicating which overlapping polygons represent road surfaces that are directly accessible to each other (Paragraph [0042]: "Rather, the cells can be defined solely by information representing how cells are connected by edges [connection graph]. In this specification, a cell having an edge represents that a vehicle can travel from a region represented by the cell to a second region. The second region might be represented by another cell or might be considered a drivable region outside the region of interest, in which case no cell would be included. Thus, two cells sharing an edge between them represents two drivable areas that are physically contiguous in reality. Edges on the border of a region of interest can be referred to as entrance edges or exit edges depending on the direction of travel. Entrance edges and exit edges thus connect a cell within the region of interest to a drivable area that is outside the region of interest [overlapping polygons represent road surfaces directly accessible to each other].")
and the separation graph indicating which overlapping polygons represent road surfaces that are not directly accessible to each other (Paragraph [0143]: "…when there is a split point in the lane graph topology (for example as illustrated by split point (106a) in FIG. (1A), split point (106b) in FIG. (1B), and as two lanes (102d), (102e) in FIG. (1C)), the system can treat the split as two lanes (as shown by (102d) and (102e) in FIG. (1C) traversing the same path, with each lane represented by a polyline [separation graph structure - example]. […] If the vertices of the two poly lines coincide along a portion of the path, the two lanes can be considered to be the same lane until their final coinciding vertex, which can be considered the split point between the two lanes. If the polylines are separated, the lanes can be considered separate neighboring lanes that eventually diverge [separation graph - overlapping polygons represent road surfaces not directly accessible to each other]").
Therefore, it would have been obvious to one of the ordinary skill of the art before the effective filing date of the claimed invention to modify Yang, et al. to include the teaching of Thibaux, et al. based on a reasonable expectation of success and motivation to improve the mapping of lane graph geometries on a road surface from lane graph topologies on a road surface (Thibaux, et al. Paragraph [0004]).
Regarding claim 22, Yang, et al. does not teach the method of claim 9, wherein the electronic map is generated from the drivable surface polygons using a connection graph and a separation graph derived from the drivable surface polygons, the connection graph indicating which overlapping polygons represent road surfaces that are directly accessible to each other and the separation graph indicating which overlapping polygons represent road surfaces that are not directly accessible to each other.
In a similar field of endeavor (lane graph topology), Thibaux, et al. teaches: The method of claim 9, wherein the electronic map is generated from the drivable surface polygons using a connection graph and a separation graph derived from the drivable surface polygons, (Step (720), Paragraph [0123]: "In operation (720), the system receives a request to generate lane graph topologies [Method - creating electronic map]." ; Paragraph [0042]: "Rather, the cells can be defined solely by information representing how cells are connected by edges [connection relationship]. […] a cell having an edge represents that a vehicle can travel from a region represented by the cell to a second region. The second region might be represented by another cell or might be considered a drivable region outside the region of interest, in which case no cell would be included. Thus, two cells sharing an edge between them represents two drivable areas that are physically contiguous in reality [electronic map generated from polygons using connection graph]." ; Paragraph [0051]: "FIG. (1a) illustrates a lane (102a) that splits into two lanes (104a) and (104b) at split point (106a). The two lanes (104a), (104b) travel to the left and right, respectively, of an obstacle (108d). FIG. 1B similarly illustrates a lane (102b) that splits into two lanes (104c) and (104d) at split point (106b) that exists at a different geometric location. The two lanes (104c), (104d) travel to the left and right, respectively, of an obstacle (108d) [separation graph - example]. However, while the lanes illustrated in FIGS. (1a) and (1b) are geometrically different, they are topologically identical because they enter the same cells through the same edges, and can therefore be continuously deformed from the geometry of FIG. (1a) to that of FIG. (1B) and vice versa [electronic map derived from drivable surface polygons using separation graph].")
the connection graph indicating which overlapping polygons represent road surfaces that are directly accessible to each other (Paragraph [0042]: "Rather, the cells can be defined solely by information representing how cells are connected by edges [connection graph]. In this specification, a cell having an edge represents that a vehicle can travel from a region represented by the cell to a second region. The second region might be represented by another cell or might be considered a drivable region outside the region of interest, in which case no cell would be included. Thus, two cells sharing an edge between them represents two drivable areas that are physically contiguous in reality. Edges on the border of a region of interest can be referred to as entrance edges or exit edges depending on the direction of travel. Entrance edges and exit edges thus connect a cell within the region of interest to a drivable area that is outside the region of interest [overlapping polygons represent road surfaces directly accessible to each other].")
and the separation graph indicating which overlapping polygons represent road surfaces that are not directly accessible to each other (Paragraph [0143]: "In addition, when there is a split point in the lane graph topology (for example as illustrated by split point (106a) in FIG. (1A), split point (106b) in FIG. (1B), and as two lanes (102d), (102e) in FIG. (1C)), the system can treat the split as two lanes (as shown by (102d) and (102e) in FIG. (1C) traversing the same path, with each lane represented by a polyline [separation graph structure - example]. […] If the vertices of the two poly lines coincide along a portion of the path, the two lanes can be considered to be the same lane until their final coinciding vertex, which can be considered the split point between the two lanes. If the polylines are separated, the lanes can be considered separate neighboring lanes that eventually diverge [separation graph - overlapping polygons represent road surfaces not directly accessible to each other]").
Therefore, it would have been obvious to one of the ordinary skill of the art before the effective filing date of the claimed invention to modify Yang, et al. to include the teaching of Thibaux, et al. based on a reasonable expectation of success and motivation to improve the mapping of lane graph geometries on a road surface from lane graph topologies on a road surface (Thibaux, et al. Paragraph [0004]).
Regarding claim 23, Yang, et al. does not teach the non-transitory computer-readable medium of claim 17, wherein the electronic map is generated from the drivable surface polygons using a connection graph and a separation graph derived from the drivable surface polygons, the connection graph indicating which overlapping polygons represent road surfaces that are directly accessible to each other and the separation graph indicating which overlapping polygons represent road surfaces that are not directly accessible to each other.
In a similar field of endeavor (lane graph topology), Thibaux, et al. teaches: The non-transitory computer-readable medium of claim 17, wherein the electronic map is generated from the drivable surface polygons using a connection graph and a separation graph derived from the drivable surface polygons, (Paragraph [0042]: "Rather, the cells can be defined solely by information representing how cells are connected by edges [connection relationship]. […] a cell having an edge represents that a vehicle can travel from a region represented by the cell to a second region. The second region might be represented by another cell or might be considered a drivable region outside the region of interest, in which case no cell would be included. Thus, two cells sharing an edge between them represents two drivable areas that are physically contiguous in reality [electronic map generated from polygons using connection graph]." ; Paragraph [0051]: "FIG. (1a) illustrates a lane (102a) that splits into two lanes (104a) and (104b) at split point (106a). The two lanes (104a), (104b) travel to the left and right, respectively, of an obstacle (108d). FIG. 1B similarly illustrates a lane (102b) that splits into two lanes (104c) and (104d) at split point (106b) that exists at a different geometric location. The two lanes (104c), (104d) travel to the left and right, respectively, of an obstacle (108d) [separation graph - example]. However, while the lanes illustrated in FIGS. (1a) and (1b) are geometrically different, they are topologically identical because they enter the same cells through the same edges, and can therefore be continuously deformed from the geometry of FIG. (1a) to that of FIG. (1B) and vice versa [electronic map derived from drivable surface polygons using separation graph].")
the connection graph indicating which overlapping polygons represent road surfaces that are directly accessible to each other (Paragraph [0042]: "Rather, the cells can be defined solely by information representing how cells are connected by edges [connection graph]. In this specification, a cell having an edge represents that a vehicle can travel from a region represented by the cell to a second region. The second region might be represented by another cell or might be considered a drivable region outside the region of interest, in which case no cell would be included. Thus, two cells sharing an edge between them represents two drivable areas that are physically contiguous in reality. Edges on the border of a region of interest can be referred to as entrance edges or exit edges depending on the direction of travel. Entrance edges and exit edges thus connect a cell within the region of interest to a drivable area that is outside the region of interest [overlapping polygons represent road surfaces directly accessible to each other].")
and the separation graph indicating which overlapping polygons represent road surfaces that are not directly accessible to each other (Paragraph [0143]: "…when there is a split point in the lane graph topology (for example as illustrated by split point (106a) in FIG. (1A), split point (106b) in FIG. (1B), and as two lanes (102d), (102e) in FIG. (1C)), the system can treat the split as two lanes (as shown by (102d) and (102e) in FIG. (1C) traversing the same path, with each lane represented by a polyline [separation graph structure - example]. […] If the vertices of the two poly lines coincide along a portion of the path, the two lanes can be considered to be the same lane until their final coinciding vertex, which can be considered the split point between the two lanes. If the polylines are separated, the lanes can be considered separate neighboring lanes that eventually diverge [separation graph - overlapping polygons represent road surfaces not directly accessible to each other]").
Therefore, it would have been obvious to one of the ordinary skill of the art before the effective filing date of the claimed invention to modify Yang, et al. to include the teaching of Thibaux, et al. based on a reasonable expectation of success and motivation to improve the mapping of lane graph geometries on a road surface from lane graph topologies on a road surface (Thibaux, et al. Paragraph [0004]).
Response to Arguments
Applicant asserted that amended claims 1, 9, and 17 were patentable over Yang, et al. (U.S. Patent No. 10545029) because Yang, et al. did disclose the claimed drivable surface polygons. The examiner disagrees. In Yang, et al. the use of drivable lane line segments have the ability to be represented as subclusters which can be “…a circular shape while in others they may be elliptically shaped or a polygon” (Col. 32, lines 28-33) which can be illustrated on a lane element graph, which consists of “…the navigable road surface that is divided into lane elements, and includes connectivity among lane elements” (Col. 37, lines 19-28). Subsequently, it would have been obvious to combine Yang, et al. with Fujita, et al. because Fujita, et al. teaches a length of a direction that is opposite a first boundary line is the maximum sensing distance of a vehicle sensor that is used to generate a first boundary line (Col. 6, lines 10-15, Col. 9, lines 15-19, Col. 14, lines 17-25).
Applicant asserted that amended claims 1, 9, and 17 were patentable over Yang, et al. (U.S. Patent No. 10545029) because Yang, et al. did disclose using key point detections and a vehicle trace to generate the polygons. The examiner disagrees. In Yang, et al., a camera is used in order to generate an image and detect 2D points stemming from an image into a 2D plane which are then used to map lane line points in a 3D voxel in a 3D plane (Col. 29, lines 48-52). Subsequently, the generated lane line points can be converted into lane line segments along a vehicle route, or vehicle trace (Col. 29, lines 52-54) and the lane line segments can be broken into subclusters which can encompass polygonal arrangements (Col. 32, lines 28-33). Subsequently, it would have been obvious to combine Yang, et al. with Fujita, et al. because Fujita, et al. teaches a length of a direction that is opposite a first boundary line is the maximum sensing distance of a vehicle sensor that is used to generate a first boundary line (Col. 6, lines 10-15, Col. 9, lines 15-19, Col. 14, lines 17-25).
Applicant asserted that amended claims 1, 9, and 17 were patentable over Yang, et al. (U.S. Patent No. 10545029) because Yang, et al. did disclose generating an electronic map based on the claimed polygons. The examiner disagrees. In Yang, et al., the results of the creation of the lane element graph, which consists of drivable lane line segments in polygon form (Col. 32, lines 28-33) are used to create “a high definition map of the local area”, which includes the lane element graph, “…for use in driving by one more autonomous vehicles” (Col. 39, lines 51-54). Subsequently, it would have been obvious to combine Yang, et al. with Fujita, et al. because Fujita, et al. teaches a length of a direction that is opposite a first boundary line is the maximum sensing distance of a vehicle sensor that is used to generate a first boundary line (Col. 6, lines 10-15, Col. 9, lines 15-19, Col. 14, lines 17-25).
Therefore, it can be concluded that since Yang, et al. reads on the claim limitations of disclosing the claimed drivable surface polygons, disclosing using key point detections and a vehicle trace to generate the polygons, and generating an electronic map based on the claimed polygons in claims 1, 9, and 17, and since it would have obvious to combine Yang, et al. with Fujita, et al., the arguments presented by the Applicant are not persuasive, and the rejection is maintained.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
Jeong, et al. (U.S. Patent Application Publication No. 20250297866) teaches a process of determining a first polygon representing a first traversable surface and a second polygon representing a second traversable surface and deciding whether to update a map based on the merged regions between the two polygons.
Applicant is considered to have implicit knowledge of the entire disclosure once a reference has been cited. Therefore, any previously cited figures, columns and lines should not be considered to limit the references in any way. The entire reference must be taken as a whole; accordingly, the Examiner contends that the art supports the rejection of the claims and the rejection is maintained.
THIS ACTION IS MADE FINAL. Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any nonprovisional extension fee (37 CFR 1.17(a)) pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the mailing date of this final action.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to TORRENCE S MARUNDA II whose telephone number is (571)272-5172. The examiner can normally be reached Monday-Friday 8:00-5:30.
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, ANGELA Y ORTIZ can be reached at 571-272-1206. 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.
/TORRENCE S MARUNDA II/Examiner, Art Unit 3663
/ANGELA Y ORTIZ/Supervisory Patent Examiner, Art Unit 3663
Prosecution Insights