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
This Office Action is in response to the application filed on December 20, 2024. Claims 1-19 are presently pending and are presented for examination.
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 is incorrect, any correction of the statutory basis for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
The factual inquiries set forth in Graham v. John Deere Co., 383 U.S. 1, 148 USPQ 459 (1966), that are applied for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows:
Determining the scope and contents of the prior art.
Ascertaining the differences between the prior art and the claims at issue.
Resolving the level of ordinary skill in the pertinent art.
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, 9, and 17-19 are rejected under 35 U.S.C. 103 as being unpatentable over U.S. Pub. No. 2020/0183011 (hereinafter, "Lin") in view of U.S. Pub. No. 2021/0356972 (hereinafter, "Kwon").
Regarding claim 1, Lin discloses a grid map construction method, comprising:
acquiring a point cloud of a target scene under a current field of view (“capture a laser point cloud as the environment perception information” (para 0090));
constructing an occupancy grid map and … under the current field of view according to the point cloud under the current field of view (“an initial occupancy grid map is created based on the location of the vehicle each time the location of the vehicle is received” (para 0032)), wherein the occupancy grid map comprises a point cloud occupancy probability value of each grid (“a current probability that each grid in the current occupancy grid map belongs to each of occupancy categories is determined based on last environment perception information received from the sensors” (para 0030)),…;
updating a target grid map of the target scene according to point cloud occupancy probability values in the occupancy grid map … (“each grid in the current occupancy grid map belongs is updated based on the current probability that the grid belongs to each of the occupancy categories” (para 0030) and “the current probability that the grid belongs to each of the occupancy categories is calculated based on the current observed probability …, the current probability that the grid is occupied and a time interval between a previous observation and a current observation” (para 0082));
However, Lin does not explicitly teach
constructing … a height grid map under the current field of view according to the point cloud under the current field of view,
…the height grid map comprises a point cloud height value of each grid, and the occupancy grid map corresponds to the height grid map;
updating a target grid map of the target scene according to … height values in the height grid map.
Kwon, in the same field of endeavor, teaches
constructing … a height grid map under the current field of view according to the point cloud under the current field of view (“The height map 910-2 may include a plurality of cells corresponding to the position (or area) of the actual space, and the height information indicating the height of an object present in the corresponding cell may be mapped to each of the plurality of cells” (para 0149) and “The height information can be calculated based on the sensing data obtained by at least one sensor provided in the external device 300. Here, the sensor may include a distance sensor (e.g., a RADAR, LiDAR, an ultrasound sensor, or the like)” (para 0097)),
…the height grid map comprises a point cloud height value of each grid (“The height information mapped to the cell may represent the height of the space occupied by the object (e.g., the height on the z-axis), and the location of the cell can represent the location of the space occupied by the object (e.g., the position on the xy plane)” (para 0154)); and the occupancy grid map corresponds to the height grid map (“the processor 130 can determine whether the robot 200 is traversable in each cell by combining the occupancy map 910-1 and the height map 910-2” (para 0152)),
updating a target grid map of the target scene according to … height values in the height grid map (“update the generated map by updating at least one of height information and probability information mapped to at least one cell among a plurality of cells of the generated map based on subsequent sensing data” (para 0012)).
One of ordinary skill in the art, before the time of filing, would have been motivated to modify the disclosure of Lin with the teachings of Kwon in order to determine whether the robot is traversal or not in each of the plurality of cells based on the information mapped to each of the plurality of cells included in the height map; see Kwon at least at [0108].
Regarding claim 9, Lin discloses a grid map construction apparatus, comprising:
a point cloud acquisition module (“a laser radar configured to capture a laser point cloud” (para 0090)), a map construction module (“a map generation module 31” (para 0123)), and a map update module (“a map updating module 32” (para 0124)); wherein
the point cloud acquisition module is configured to acquire a point cloud of a target scene under a current field of view (“capture a laser point cloud as the environment perception information” (para 0090)); the map construction module is configured to construct an occupancy grid map and … under the current field of view according to the point cloud under the current field of view (“an initial occupancy grid map is created based on the location of the vehicle each time the location of the vehicle is received” (para 0032)), wherein the occupancy grid map comprises a point cloud occupancy probability value of each grid (“a current probability that each grid in the current occupancy grid map belongs to each of occupancy categories is determined based on last environment perception information received from the sensors” (para 0030)), and …;
the map update module is configured to update a target grid map of the target scene according to point cloud occupancy probability values in the occupancy grid map (“each grid in the current occupancy grid map belongs is updated based on the current probability that the grid belongs to each of the occupancy categories” (para 0030) and “the current probability that the grid belongs to each of the occupancy categories is calculated based on the current observed probability …, the current probability that the grid is occupied and a time interval between a previous observation and a current observation” (para 0082)) …;
However, Lin does not explicitly teach
the map construction module is configured to construct … a height grid map under the current field of view according to the point cloud under the current field of view;
…the height grid map comprises a point cloud height value of each grid, and the occupancy grid map corresponds to the height grid map;
the map update module is configured to update a target grid map of the target scene according to … point cloud height values in the height grid map.
Kwon, in the same field of endeavor, teaches
the map construction module is configured to construct … a height grid map under the current field of view according to the point cloud under the current field of view (“The height map 910-2 may include a plurality of cells corresponding to the position (or area) of the actual space, and the height information indicating the height of an object present in the corresponding cell may be mapped to each of the plurality of cells” (para 0149) and “The height information can be calculated based on the sensing data obtained by at least one sensor provided in the external device 300. Here, the sensor may include a distance sensor (e.g., a RADAR, LiDAR, an ultrasound sensor, or the like)” (para 0097));
…the height grid map comprises a point cloud height value of each grid (“The height information mapped to the cell may represent the height of the space occupied by the object (e.g., the height on the z-axis), and the location of the cell can represent the location of the space occupied by the object (e.g., the position on the xy plane)” (para 0154)), and the occupancy grid map corresponds to the height grid map (“the processor 130 can determine whether the robot 200 is traversable in each cell by combining the occupancy map 910-1 and the height map 910-2” (para 0152));
the map update module is configured to update a target grid map of the target scene according to … point cloud height values in the height grid map (“update the generated map by updating at least one of height information and probability information mapped to at least one cell among a plurality of cells of the generated map based on subsequent sensing data” (para 0012)).
One of ordinary skill in the art, before the time of filing, would have been motivated to modify the disclosure of Lin with the teachings of Kwon in order to determine whether the robot is traversal or not in each of the plurality of cells based on the information mapped to each of the plurality of cells included in the height map; see Kwon at least at [0108].
Regarding claim 17, Lin discloses and Kwon teaches the method of claim 1. Additionally, Lin discloses a robot (“Occupancy grid map is the most commonly used map creation method in the field of artificial intelligence (e.g., self-driving vehicles, robotics or the like)” (para 0003)), comprising a processor and a memory storing a computer program, wherein when executing the computer program, the processor is configured to implement the method of claim 1 (“The processing apparatus includes a memory and one or more processors communicatively connected to the memory, the instructions, when executed by the one or more processors, cause the one or more processors to perform the above method for creating an occupancy grid map” (para 0008)).
Regarding claim 18, Lin discloses and Kwon teaches the method of claim 1. Additionally, Lin discloses a computer-readable storage medium, on which a computer program is stored, wherein the computer program, when executed by a processor, causes the processor to implement the method of claim 1 (“The program can be stored in a computer readable storage medium” (para 0140)).
Regarding claim 19, Lin discloses and Kwon teaches the method of claim 1. Additionally, Lin discloses a computer program product , comprising a computer program (“a computer readable storage medium” (para 0140)), wherein the computer program, when executed by a processor, causes the processor to implement the method of claim 1 (“an embedded processor or a processor of any other programmable data processing device to constitute a machine, such that the instructions executed by a processor of a computer or any other programmable data processing device can constitute means for implementing the functions specified by one or more processes in the flowcharts and/or one or more blocks in the block diagrams” (para 0143)).
Claims 2-7 and 10-15 are rejected under 35 U.S.C. 103 as being unpatentable over U.S. Pub. No. 2020/0183011 (hereinafter, "Lin"), in view of U.S. Pub. No. 2021/0356972 (hereinafter, "Kwon"), as applied to claims 1 and 9 above, and in further view of U.S. Pub. No. 2018/0216942 (hereinafter, "Wang").
Regarding claim 2, Lin discloses and Kwon teaches the method according to claim 1. Additionally, Lin discloses wherein the constructing the occupancy grid map and the height grid map under the current field of view according to the point cloud under the current field of view comprises:
determining the occupancy grid map under the current field of view according to distribution information of a point cloud in the reference grid map under the current field of view (“Obtain the current occupancy grid map” (para 0094), “A ratio of the number of laser points of the ground type to the total number of laser points corresponding to the grid is calculated” (para 0097) and “when the observed type of the current observation for the grid is ground, setting a current probability that the grid belongs to the ground category to 1 and a current probability that the grid belongs to each of the other occupancy categories to 0” (para 0099));
However, Lin does not explicitly teach
mapping the point cloud under the current field of view to a blank grid map, and obtaining a reference grid map under the current field of view;
determining the height grid map under the current field of view according to height information of the point cloud in the reference grid map under the current field of view and a height grid map under a previous field of view.
Wang, in the same field of endeavor, teaches
mapping the point cloud under the current field of view to a blank grid map (“a system of an ADV collects localization data, e.g., 3D point cloud of a LIDAR scanner, … the first localization map may be a blank map. The second localization map represents an updated version of the first localization map” (para 0021)), and obtaining a reference grid map under the current field of view (“applies a subset of the collected localization data onto the first localization map based on the selected candidate pose to generate a second localization map, such that the second localization map is utilized to subsequently determine a location of the ADV” (para 0021)).
One of ordinary skill in the art, before the time of filing, would have been motivated to modify the disclosure of Lin with the teachings of Wang in order to apply to a self-contained self-evolving localization map; see Wang at least at [0016];
Kwon, in the same field of endeavor, teaches
determining the height grid map under the current field of view (“updating the generated map by updating at least one of height information and probability information mapped to at least one cell among a plurality of cells of the generated map based on the subsequent sensing data” (para 0021)) according to height information of the point cloud in the reference grid map under the current field of view and a height grid map under a previous field of view (“the subsequent sensing data can represent sensing data received (or sensed) after the previously received (or sensed) sensing data” (para 0217)).
One of ordinary skill in the art, before the time of filing, would have been motivated to modify the disclosure of Lin with the teachings of Kwon in order to continuously change (i.e., update) the traversability map; see Kwon at least at [0173].
Regarding claim 3, Lin discloses and Kwon teaches the method according to claim 2. However, Lin does not explicitly teach wherein the determining the occupancy grid map under the current field of view according to the distribution information of the point cloud in the reference grid map under the current field of view comprises:
when a grid in the reference grid map under the current field of view excludes a point cloud, determining a point cloud occupancy probability value of the grid as a first probability value;
when a grid in the reference grid map under the current field of view includes a point cloud, determining a point cloud occupancy probability value of the grid as a second probability value, wherein the second probability value is greater than the first probability value;
determining the occupancy grid map under the current field of view according to a point cloud occupancy probability value of each grid in the reference grid map under the current field of view.
Kwon, in the same field of endeavor, teaches
when a grid in the reference grid map under the current field of view excludes a point cloud, determining a point cloud occupancy probability value of the grid as a first probability value (“the occupancy map 10-1, is changed (i.e., updated), considering a dynamic environment” (para 0173) and “ The probability information may represent a probability value (e.g., between a value between 0 and 1 or a value between 0 and 100%) that an object may exist (or may occupy) in the position corresponding to each cell (area on the real space)” (para 0089));
when a grid in the reference grid map under the current field of view includes a point cloud, determining a point cloud occupancy probability value of the grid as a second probability value, wherein the second probability value is greater than the first probability value (“even though the first object is not present in a first cell 1211 of t−1 occupancy map 1210, the object is present in the first cell 1221 of the t occupancy map 1220 and thus, the occupancy state of the object is changed, and that the second object is present in a second cell 1212 of the t−1 occupancy map 1210, the object is not present in the second cell 1222 of the t occupancy map 1220 so that the occupancy state of the object is changed” (para 0181));
determining the occupancy grid map under the current field of view according to a point cloud occupancy probability value of each grid in the reference grid map under the current field of view (“The processor 130 may update information mapped to at least one cell among a plurality of cells of the pre-generated map 10 based on the subsequent sensing data to update the pre-generated map 10, the updated information may be information about a probability information for the occupancy map 10-1” (para 0175)).
One of ordinary skill in the art, before the time of filing, would have been motivated to modify the disclosure of Lin with the teachings of Kwon in order to update the pre-generated map based on probability information; see Kwon at least at [0175].
Regarding claim 4, Lin discloses and Kwon teaches the method according to claim 2. Additionally, Lin discloses wherein the determining the height grid map under the current field of view according to the height information of the point cloud in the reference grid map under the current field of view and the height grid map under the previous field of view comprises:
determining… height value in each grid according to the height information of the point cloud in the reference grid map under the current field of view, as the point cloud height value of each grid (“creating a first occupancy grid map in a vehicle body coordinate system based on the location of the vehicle; assigning an initial height value to each grid in the first occupancy grid map based on a height of an origin of the vehicle body coordinate system with respect to a ground; and obtaining the initial occupancy grid map by modifying the initial height value of each grid in the first occupancy grid map based on a predetermined terrain map” (para 0129));
However, Lin does not explicitly teach
determining a maximum point cloud height value in each grid …;
forming the height grid map under the current field of view according to the point cloud height value of each grid and the height grid map under the previous field of view, wherein a point cloud acquisition moment corresponding to the current field of view is adjacent to a point cloud acquisition moment corresponding to the previous field of view.
Kwon, in the same field of endeavor, teaches
determining a maximum point cloud height value in each grid … (“a second map 10-2 including a plurality of cells mapped with each of height information indicating the height (that is, the height of z axis) of the object” (para 0088) and “the height information can include a minimum height and a maximum height of an area where an object is present (or occupied)” (para 0150));
forming the height grid map under the current field of view according to the point cloud height value of each grid and the height grid map (“A second map 10-2 may include a plurality of cells mapped with each of height information indicating a height of an object. This may be referred to as the height map 10-2. The height information may indicate the height of an object present in the corresponding cell” (para 0096)) under the previous field of view (“the subsequent sensing data can represent sensing data received (or sensed) after the previously received (or sensed) sensing data” (para 0217) and “ based on the subsequent sensing data, by updating the height information mapped to at least one of the plurality of cells of the previously generated map, the previously generated map can be updated. Here, the previously generated map and the updated map indicate a temporal relationship over time” (para 0218)), wherein a point cloud acquisition moment corresponding to the current field of view is adjacent to a point cloud acquisition moment corresponding to the previous field of view (“the subsequent sensing data can represent sensing data received (or sensed) after the previously received (or sensed) sensing data” (para 0217)).
One of ordinary skill in the art, before the time of filing, would have been motivated to modify the disclosure of Lin with the teachings of Kwon in order to determine whether the robot is traversable in each cell by combining the occupancy map and the height map; see Kwon at least at [0152].
Regarding claim 5, Lin discloses and Kwon teaches the method according to claim 4. Additionally, Lin discloses wherein the forming the height grid map under the current field of view according to the point cloud height value of each grid and the height grid map under the previous field of view comprises:
comparing a point cloud height value of a grid at a corresponding position under the previous field of view to the point cloud height value of the grid under the current field of view (“determining the current probability that the grid belongs to each of the occupancy categories based on a previous probability that the grid belongs to the occupancy category and the current observed probability that the grid belongs to the occupancy category” (para 0128) and “Assigning an initial height value to each grid in the first occupancy grid map based on a height of an origin of the vehicle body coordinate system with respect to a ground” (para 0129));
However, Lin does not explicitly teach
determining a maximum point cloud height value as the point cloud height value of the grid at the corresponding position, and forming the height grid map under the current field of view.
Kwon, in the same field of endeavor, teaches
determining a maximum point cloud height value as the point cloud height value of the grid at the corresponding position (“updating the generated map by updating at least one of height information and probability information mapped to at least one cell among a plurality of cells of the generated map based on the subsequent sensing data” (para 0021) and “the height information can include a minimum height and a maximum height of an area where an object is present (or occupied)” (para 0150)), and forming the height grid map under the current field of view (“A second map 10-2 may include a plurality of cells mapped with each of height information indicating a height of an object. This may be referred to as the height map 10-2. The height information may indicate the height of an object present in the corresponding cell” (para 0096) and “The height information can be calculated based on the sensing data obtained by at least one sensor provided in the external device 300. Here, the sensor may include a distance sensor (e.g., a RADAR, LiDAR, an ultrasound sensor, or the like)” (para 0097)).
One of ordinary skill in the art, before the time of filing, would have been motivated to modify the disclosure of Lin with the teachings of Kwon in order to continuously change (i.e., update) the traversability map; see Kwon at least at [0173].
Regarding claim 6, Lin discloses and Kwon teaches the method according to claim 1. However, Lin does not explicitly teach wherein the updating the target grid map of the target scene according to the point cloud occupancy probability values in the occupancy grid map and the point cloud height values in the height grid map comprises:
determining a visible height value in each grid according to the point cloud height values in the height grid map;
determining a point cloud occupancy probability value and a point cloud height value of a grid at a corresponding position in the occupancy grid map and the height grid map;
updating the point cloud occupancy probability value in the target grid map of the target scene according to the visible height value, the point cloud occupancy probability value, and the point cloud height value of the grid at the corresponding position;
wherein the target grid map is a blank grid map when the current field of view corresponds to a first acquisition of the point cloud, and the target grid map is determined under a previous field of view when the current field of view corresponds to a non-first acquisition of the point cloud.
Kwon, in the same field of endeavor, teaches
determining a visible height value in each grid according to the point cloud height values in the height grid map (“A second map 10-2 may include a plurality of cells mapped with each of height information indicating a height of an object. This may be referred to as the height map 10-2. The height information may indicate the height of an object present in the corresponding cell” (para 0096) and “the height information can include a minimum height and a maximum height of an area where an object is present (or occupied)” (para 0150));
determining a point cloud occupancy probability value (“The first map 10-1 may include a plurality of cells mapped with each of the probability information in which the object is present. This may be referred to as occupancy map 10-1” (para 0089)) and a point cloud height value of a grid at a corresponding position in the occupancy grid map and the height grid map (“The probability information may represent a probability value that an object may exist (or may occupy) in the position corresponding to each cell (area on the real space). The occupancy map 10-1 may be composed of a two-dimensional map (i.e., a map representing the position on the xy plane) for a specific height (i.e., the height on the z axis)” (para 0089));
updating the point cloud occupancy probability value in the target grid map of the target scene according to the visible height value (“the occupancy map 10-1, is changed (i.e., updated), considering a dynamic environment” (para 0173) and “identify the location of the object and the height of the object based on the height information mapped to the cell included in the height map 910-2” (para 0154), and “the height information can include a minimum height and a maximum height of an area where an object is present (or occupied)” (para 0150)), the point cloud occupancy probability value (“generate (or update) the traversability map 20 of the robot 200 based on the information mapped to each of the plurality of cells included in the occupancy map” (para 0126) “the processor 130 according to one embodiment can calculate a score for each of a plurality of cells based on the probability information mapped to each of the plurality of cells included in an occupancy map” (para 0128)), and the point cloud height value of the grid at the corresponding position (“generate a first final score map 920-1 based on the occupancy map corresponding to the height” (para 0156));
One of ordinary skill in the art, before the time of filing, would have been motivated to modify the disclosure of Lin with the teachings of Kwon in order to update the generated map by updating at least one of height information and probability information mapped to at least one cell among a plurality of cells; see Kwon at least at [0012];
Wang, in the same field of endeavor, teaches
wherein the target grid map is a blank grid map when the current field of view corresponds to a first acquisition of the point cloud (“Collect module 301D periodically collects 3D point cloud from the sensors of perception module 302. 3D point cloud represents sensor data surrounding the ADV” (para 0045) and “a system of an ADV collects localization data, e.g., 3D point cloud of a LIDAR scanner, … the first localization map may be a blank map. The second localization map represents an updated version of the first localization map” (para 0021)), and the target grid map is determined under a previous field of view when the current field of view corresponds to a non-first acquisition of the point cloud (“the first localization map may be a blank map. The second localization map represents an updated version of the first localization map” (para 0021) and “ADV 503 may have a blank initial version of a localization map” (para 0072)).
One of ordinary skill in the art, before the time of filing, would have been motivated to modify the disclosure of Lin with the teachings of Wang in order to apply to a self-contained self-evolving localization map; see Wang at least at [0016].
Regarding claim 7, Lin discloses and Kwon teaches the method according to claim 6. However, Lin does not explicitly teach wherein the updating the point cloud occupancy probability value in the target grid map of the target scene according to the visible height value, the point cloud occupancy probability value, and the point cloud height value of the grid at the corresponding position comprises:
increasing the point cloud occupancy probability value of the grid at the corresponding position in the target grid map according to a preset increase parameter when the point cloud occupancy probability value of the grid at the corresponding position indicates that the grid at the corresponding position is occupied;
updating the point cloud occupancy probability value of the grid at the corresponding position in the target grid map according to the point cloud height value and the visible height of the grid at the corresponding position when the point cloud occupancy probability value of the grid at the corresponding position indicates that the grid at the corresponding position is not occupied.
Kwon, in the same field of endeavor, teaches
increasing the point cloud occupancy probability value of the grid at the corresponding position in the target grid map (“The probability information may represent a probability value (e.g., between a value between 0 and 1 or a value between 0 and 100%) that an object may exist (or may occupy) in the position corresponding to each cell (area on the real space)” (0089) and “calculate a score for each of a plurality of cells based on the probability information mapped to each of the plurality of cells included in an occupancy map” (para 0128)) according to a preset increase parameter (“map a probability value of a first predetermined value (e.g., 0, 0.3, etc.) to a cell having a distance less than the measured distance among the cells present in the direction in which the radio waves are transmitted at the location of the external device 300 based on the sensing data received” (para 0092)) when the point cloud occupancy probability value of the grid at the corresponding position indicates that the grid at the corresponding position is occupied (“updating at least one of height information and probability information mapped to at least one cell among a plurality of cells of the generated map based on the subsequent sensing data” (para 0021));
updating the point cloud occupancy probability value of the grid at the corresponding position in the target grid map according to the point cloud height value (“the occupancy map 10-1, is changed (i.e., updated), considering a dynamic environment” (para 0173) and “the updated information may be information about a probability information for the occupancy map 10-1, height information for the height map 10-2” (para 0175)) and the visible height of the grid at the corresponding position when the point cloud occupancy probability value of the grid at the corresponding position indicates that the grid at the corresponding position is not occupied (“the updated information may be information about a probability information for the occupancy map 10-1, height information for the height map 10-2” (para 0175) and “the height information can include a minimum height and a maximum height of an area where an object is present (or occupied)” (para 0150)).
One of ordinary skill in the art, before the time of filing, would have been motivated to modify the disclosure of Lin with the teachings of Kwon in order to update a probability information for the occupancy map based on height information; see Kwon at least at [0175].
Regarding claim 10, Lin discloses and Kwon teaches the apparatus according to claim 9. Additionally, Lin discloses wherein the map construction module is further configured to:
determine the occupancy grid map under the current field of view according to distribution information of a point cloud in the reference grid map under the current field of view (“Obtain the current occupancy grid map” (para 0094), “The observed type of the current observation for the grid is determined as ground when the ratio is larger than or equal to a predetermined ratio threshold, or the observed type of the current observation for the grid is determined as non-ground when the ratio is smaller than the predetermined ratio threshold” (para 0097), and “when the observed type of the current observation for the grid is ground, setting a current probability that the grid belongs to the ground category to 1 and a current probability that the grid belongs to each of the other occupancy categories to 0” (para 0099));
However, Lin does not explicitly teach
map the point cloud under the current field of view to a blank grid map, and obtain a reference grid map under the current field of view;
determine the height grid map under the current field of view according to height information of the point cloud in the reference grid map under the current field of view and a height grid map under a previous field of view.
Wang, in the same field of endeavor, teaches
map the point cloud under the current field of view to a blank grid map (“a system of an ADV collects localization data, e.g., 3D point cloud of a LIDAR scanner, … the first localization map may be a blank map. The second localization map represents an updated version of the first localization map” (para 0021)), and obtain a reference grid map under the current field of view (“applies a subset of the collected localization data onto the first localization map based on the selected candidate pose to generate a second localization map, such that the second localization map is utilized to subsequently determine a location of the ADV” (para 0021)).
One of ordinary skill in the art, before the time of filing, would have been motivated to modify the disclosure of Lin with the teachings of Wang in order to apply to a self-contained self-evolving localization map; see Wang at least at [0016];
Kwon, in the same field of endeavor, teaches
determine the height grid map under the current field of view (“updating the generated map by updating at least one of height information and probability information mapped to at least one cell among a plurality of cells of the generated map based on the subsequent sensing data” (para 0021)) according to height information of the point cloud in the reference grid map under the current field of view and a height grid map under a previous field of view (“the subsequent sensing data can represent sensing data received (or sensed) after the previously received (or sensed) sensing data” (para 0217)).
One of ordinary skill in the art, before the time of filing, would have been motivated to modify the disclosure of Lin with the teachings of Kwon in order to continuously change (i.e., update) the traversability map; see Kwon at least at [0173].
Regarding claim 11, Lin discloses and Kwon teaches the apparatus according to claim 10. However, Lin does not explicitly teach wherein the map construction module is further configured to:
when a grid in the reference grid map under the current field of view excludes a point cloud, determine a point cloud occupancy probability value of the grid as a first probability value;
when a grid in the reference grid map under the current field of view includes a point cloud, determine a point cloud occupancy probability value of the grid as a second probability value, wherein the second probability value is greater than the first probability value;
determine the occupancy grid map under the current field of view according to the point cloud occupancy probability value of each grid in the reference grid map under the current field of view.
Kwon, in the same field of endeavor, teaches
when a grid in the reference grid map under the current field of view excludes a point cloud, determine a point cloud occupancy probability value of the grid as a first probability value (“the occupancy map 10-1, is changed (i.e., updated), considering a dynamic environment” (para 0173) and “ The probability information may represent a probability value (e.g., between a value between 0 and 1 or a value between 0 and 100%) that an object may exist (or may occupy) in the position corresponding to each cell (area on the real space)” (para 0089));
when a grid in the reference grid map under the current field of view includes a point cloud, determine a point cloud occupancy probability value of the grid as a second probability value, wherein the second probability value is greater than the first probability value (“This may represent that, even though the first object is not present in a first cell 1211 of t−1 occupancy map 1210, the object is present in the first cell 1221 of the t occupancy map 1220 and thus, the occupancy state of the object is changed, and that the second object is present in a second cell 1212 of the t−1 occupancy map 1210, the object is not present in the second cell 1222 of the t occupancy map 1220 so that the occupancy state of the object is changed” (para 0181));
determine the occupancy grid map under the current field of view according to the point cloud occupancy probability value of each grid in the reference grid map under the current field of view (“The processor 130 may update information mapped to at least one cell among a plurality of cells of the pre-generated map 10 based on the subsequent sensing data to update the pre-generated map 10, the updated information may be information about a probability information for the occupancy map 10-1” (para 0175)).
One of ordinary skill in the art, before the time of filing, would have been motivated to modify the disclosure of Lin with the teachings of Kwon in order to update the pre-generated map based on probability information; see Kwon at least at [0175].
Regarding claim 12, Lin discloses and Kwon teaches the apparatus according to claim 10. Additionally, Lin discloses wherein the map construction module is configured to:
determine … height in each grid according to the height information of the point cloud in the reference grid map under the current field of view, as the point cloud height value of each grid (“creating the initial occupancy grid map based on the location of the vehicle may include: creating a first occupancy grid map in a vehicle body coordinate system based on the location of the vehicle; assigning an initial height value to each grid in the first occupancy grid map based on a height of an origin of the vehicle body coordinate system with respect to a ground; and obtaining the initial occupancy grid map by modifying the initial height value of each grid in the first occupancy grid map based on a predetermined terrain map” (para 0129));
However, Lin does not explicitly teach
determine a maximum point cloud height in each grid …
form the height grid map under the current field of view according to the point cloud height value of each grid and the height grid map under the previous field of view, wherein a point cloud acquisition moment corresponding to the current field of view is adjacent to a point cloud acquisition moment corresponding to the previous field of view.
Kwon, in the same field of endeavor, teaches
determine a maximum point cloud height in each grid …(“a second map 10-2 including a plurality of cells mapped with each of height information indicating the height (that is, the height of z axis) of the object” (para 0088) and “the height information can include a minimum height and a maximum height of an area where an object is present (or occupied)” (para 0150));
form the height grid map under the current field of view according to the point cloud height value of each grid and the height grid map (“A second map 10-2 may include a plurality of cells mapped with each of height information indicating a height of an object. This may be referred to as the height map 10-2. The height information may indicate the height of an object present in the corresponding cell” (para 0096)) under the previous field of view (“the subsequent sensing data can represent sensing data received (or sensed) after the previously received (or sensed) sensing data” (para 0217) and “ based on the subsequent sensing data, by updating the height information mapped to at least one of the plurality of cells of the previously generated map, the previously generated map can be updated. Here, the previously generated map and the updated map indicate a temporal relationship over time” (para 0218)), wherein a point cloud acquisition moment corresponding to the current field of view is adjacent to a point cloud acquisition moment corresponding to the previous field of view (“the subsequent sensing data can represent sensing data received (or sensed) after the previously received (or sensed) sensing data” (para 0217)).
One of ordinary skill in the art, before the time of filing, would have been motivated to modify the disclosure of Lin with the teachings of Kwon in order to continuously change (i.e., update) the traversability map; see Kwon at least at [0173].
Regarding claim 13, Lin discloses and Kwon teaches the apparatus according to claim 12. Additionally, Lin discloses wherein the map construction module is further configured to:
compare the point cloud height value of the grid at the corresponding position under the previous field of view to the point cloud height value of the grid under the current field of view (“determining the current probability that the grid belongs to each of the occupancy categories based on a previous probability that the grid belongs to the occupancy category and the current observed probability that the grid belongs to the occupancy category” (para 0128), “Assigning an initial height value to each grid in the first occupancy grid map based on a height of an origin of the vehicle body coordinate system with respect to a ground”, and “the occupancy category and a weight for the current observed probability that the grid belongs to the occupancy category are determined based on the previous probability that the grid belongs to the occupancy category, the current observed probability that the grid belongs to the occupancy category and a time interval between a previous observation and a current observation of the current occupancy grid map” (para 0070));
However, Lin does not explicitly teach
determine a maximum point cloud height value as the point cloud height value of the grid at the corresponding position, and form the height grid map under the current field of view.
Kwon, in the same field of endeavor, teaches
determine a maximum point cloud height value as the point cloud height value of the grid at the corresponding position (“updating the generated map by updating at least one of height information and probability information mapped to at least one cell among a plurality of cells of the generated map based on the subsequent sensing data” (para 0021) and “ the height information can include a minimum height and a maximum height of an area where an object is present (or occupied)” (para 0150)), and form the height grid map under the current field of view (“A second map 10-2 may include a plurality of cells mapped with each of height information indicating a height of an object. This may be referred to as the height map 10-2. The height information may indicate the height of an object present in the corresponding cell” (para 0096) and “The height information can be calculated based on the sensing data obtained by at least one sensor provided in the external device 300. Here, the sensor may include a distance sensor (e.g., a RADAR, LiDAR, an ultrasound sensor, or the like)” (para 0097).
One of ordinary skill in the art, before the time of filing, would have been motivated to modify the disclosure of Lin with the teachings of Kwon in order to continuously change (i.e., update) the traversability map; see Kwon at least at [0173].
Regarding claim 14, Lin discloses and Kwon teaches the apparatus according to claim 9. However, Lin does not explicitly teach wherein the map update module is further configured to:
determine a visible height value in each grid according to the point cloud height values in the height grid map;
determine the point cloud occupancy probability value and the point cloud height value of the grid at the corresponding position in the occupancy grid map and the height grid map;
update the point cloud occupancy probability value in the target grid map of the target scene according to the visible height value, the point cloud occupancy probability value, and the point cloud height value of the grid at the corresponding position;
wherein the target grid map is a blank grid map when the current field of view corresponds to a first acquisition of the point cloud, and the target grid map is determined under the previous field of view when the current field of view corresponds to a non-first acquisition of the point cloud.
Kwon, in the same field of endeavor, teaches
determine a visible height value in each grid according to the point cloud height values in the height grid map (“A second map 10-2 may include a plurality of cells mapped with each of height information indicating a height of an object. This may be referred to as the height map 10-2. The height information may indicate the height of an object present in the corresponding cell” (para 0096) and “the height information can include a minimum height and a maximum height of an area where an object is present (or occupied)” (para 0150));
determine the point cloud occupancy probability value (“The first map 10-1 may include a plurality of cells mapped with each of the probability information in which the object is present. This may be referred to as occupancy map 10-1” (para 0089)) and the point cloud height value of the grid at the corresponding position in the occupancy grid map and the height grid map (“The probability information may represent a probability value that an object may exist (or may occupy) in the position corresponding to each cell (area on the real space). The occupancy map 10-1 may be composed of a two-dimensional map (i.e., a map representing the position on the xy plane) for a specific height (i.e., the height on the z axis)” (para 0089));
update the point cloud occupancy probability value in the target grid map of the target scene according to the visible height value (“the occupancy map 10-1, is changed (i.e., updated), considering a dynamic environment” (para 0173) and “identify the location of the object and the height of the object based on the height information mapped to the cell included in the height map 910-2” (para 0154), and “the height information can include a minimum height and a maximum height of an area where an object is present (or occupied)” (para 0150)), the point cloud occupancy probability value (“generate (or update) the traversability map 20 of the robot 200 based on the information mapped to each of the plurality of cells included in the occupancy map” (para 0126) “the processor 130 according to one embodiment can calculate a score for each of a plurality of cells based on the probability information mapped to each of the plurality of cells included in an occupancy map” (para 0128)), and the point cloud height value of the grid at the corresponding position (“generate a first final score map 920-1 based on the occupancy map corresponding to the height” (para 0156));
One of ordinary skill in the art, before the time of filing, would have been motivated to modify the disclosure of Lin with the teachings of Kwon in order to update the generated map by updating at least one of height information and probability information mapped to at least one cell among a plurality of cells; see Kwon at least at [0012];
Wang, in the same field of endeavor, teaches
wherein the target grid map is a blank grid map when the current field of view corresponds to a first acquisition of the point cloud (“a system of an ADV collects localization data, e.g., 3D point cloud of a LIDAR scanner, … the first localization map may be a blank map. The second localization map represents an updated version of the first localization map” (para 0021) and “Collect module 301D periodically collects 3D point cloud and pose data from the sensors of perception module 302. 3D point cloud represents sensor data surrounding the ADV” (para 0045)), and the target grid map is determined under the previous field of view when the current field of view corresponds to a non-first acquisition of the point cloud (“the first localization map may be a blank map. The second localization map represents an updated version of the first localization map” (para 0021) and “ADV 503 may have a blank initial version of a localization map” (para 0072)).
One of ordinary skill in the art, before the time of filing, would have been motivated to modify the disclosure of Lin with the teachings of Wang in order to apply to a self-contained self-evolving localization map; see Wang at least at [0016].
Regarding claim 15, Lin discloses and Kwon teaches the apparatus according to claim 14. However, Lin does not explicitly teach wherein the map update module is further configured to:
increase the point cloud occupancy probability value of the grid at the corresponding position in the target grid map according to a preset increase parameter when the point cloud occupancy probability value of the grid at the corresponding position indicates that the grid at the corresponding position is occupied;
update the point cloud occupancy probability value of the grid at the corresponding position in the target grid map according to the point cloud height value and the visible height of the grid at the corresponding position when the point cloud occupancy probability value of the grid at the corresponding position indicates that the grid at the corresponding position is not occupied.
Kwon, in the same field of endeavor, teaches
increase the point cloud occupancy probability value of the grid at the corresponding position in the target grid map (“The probability information may represent a probability value (e.g., between a value between 0 and 1 or a value between 0 and 100%) that an object may exist (or may occupy) in the position corresponding to each cell (area on the real space)” (0089) and “calculate a score for each of a plurality of cells based on the probability information mapped to each of the plurality of cells included in an occupancy map” (para 0128)) according to a preset increase parameter (“map a probability value of a first predetermined value (e.g., 0, 0.3, etc.) to a cell having a distance less than the measured distance among the cells present in the direction in which the radio waves are transmitted at the location of the external device 300 based on the sensing data received” (para 0092)) when the point cloud occupancy probability value of the grid at the corresponding position indicates that the grid at the corresponding position is occupied (“updating at least one of height information and probability information mapped to at least one cell among a plurality of cells of the generated map based on the subsequent sensing data” (para 0021));
update the point cloud occupancy probability value of the grid at the corresponding position in the target grid map according to the point cloud height value (“the occupancy map 10-1, is changed (i.e., updated), considering a dynamic environment” (para 0173) and “the updated information may be information about a probability information for the occupancy map 10-1, height information for the height map 10-2” (para 0175)) and the visible height of the grid at the corresponding position when the point cloud occupancy probability value of the grid at the corresponding position indicates that the grid at the corresponding position is not occupied (“the updated information may be information about a probability information for the occupancy map 10-1, height information for the height map 10-2” (para 0175) and “the height information can include a minimum height and a maximum height of an area where an object is present (or occupied)” (para 0150)).
One of ordinary skill in the art, before the time of filing, would have been motivated to modify the disclosure of Lin with the teachings of Kwon in order to update a probability information for the occupancy map based on height information; see Kwon at least at [0175].
Allowable Subject Matter
Claims 8 and 16 are objected to as depending on a rejected claim but may be found allowable if re-written in independent form including all intervening claims. Reasons for indicating allowable subject matter will be provided once one or more claims is in a state of allowance.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to ADAM ALHARBI whose telephone number is (313)446-6621. The examiner can normally be reached on M-F 11:00AM – 7:30PM 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, Abby Flynn can be reached on (571) 272-9855. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of an application may be obtained from the Patent Application Information Retrieval (PAIR) system. Status information for published applications may be obtained from either Private PAIR or Public PAIR. Status information for unpublished applications is available through Private PAIR only. For more information about the PAIR system, see https://ppair-my.uspto.gov/pair/PrivatePair. Should you have questions on access to the Private PAIR system, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative or access to the automated information system, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/ADAM M ALHARBI/Primary Examiner, Art Unit 3663
Prosecution Insights