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 .
Claim Rejections - 35 USC § 103
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
Claims 1, 3, 5-6, 10-13 are rejected under 35 U.S.C. 103 as being unpatentable over Douillard in view of Bell (US 20150262421).
Regarding claim 1, Douillard teaches:
A method for reconstructing the surface topology of a ground surface in an environment of a motor vehicle, wherein the reconstruction is based on scan data of at least one LIDAR sensor, and wherein the scan data describe measurement points of the environment (Paragraph 14, This disclosure describes methods, apparatuses, and systems for performing segmentation on three-dimensional data represented in a voxel space to determine a ground plane, static objects, and dynamic objects in an environment. For example, a three-dimensional dataset may include data captured by a LIDAR system for use in conjunction with a perception system for an autonomous vehicle), and wherein the method comprises by a processing unit:
In each grid cell, defining a local tile as a function of coordinates of those measurement points that are contained in the respective grid cell using a predefined tile fitting method (Paragraph 47, The ground determination module 214 may include functionality to parse through individual voxels of the voxel space to determine a ground associated with the environment in the voxel space);
For at least some of the grid cells, classifying the respective local tile of those individual grid cells as belonging to the ground surface based on predefined region growing method that is started based on reference surface data that identifies the respective local tile of at least one grid cell as a ground surface tile belonging to the ground surface and that identifies at least one further local tile as a ground surface tile (Paragraph 16, After locally flat voxels are determined, clustering techniques such as region growing can be used to identify ground voxels or a ground plane representing a flat or drivable surface); and
For one or some or each of the grid cells, re-calculating a respective height value of the measurement points in the respective grid cell as being the vertical distance of the respective measurement point above the ground surface as it is defined by the identified ground surface tiles (Paragraph 63, the reference direction 322 may comprise a unit vector along a height direction of the autonomous vehicle 324. Thus, as the autonomous vehicle 324 travels on a variety of surfaces (flat surfaces, up/down hills, on side slopes, etc.) the reference direction 322 may vary; Paragraph 72, the height of cells in a ground cluster can be used to identify objects of interest to further identify static objects and dynamic objects).
While Douillard fails to disclose the following, Bell teaches:
Defining a virtual horizontal grid in an x-y plane (Paragraph 39, a 3D model can be partitioned by employing a 2D grid in an X-Y plane (e.g., a horizontal plane));
Dividing the environment into distinct grid cells corresponding to the virtual horizontal grid (Paragraph 39, volume encompassed by a data chunk can be a rectangular prism of infinite height);
Bell and Douillard are both considered to be analogous to the claimed invention because they are in the same field of analyzing and mapping an environment using sensors. Therefore, it would have been obvious to a person of ordinary skill in the art before the effective filing date of the claimed invention to have modified Douillard to incorporate the teachings of Bell and use a horizontal grid with columns of infinite height. Doing so would allow for assigning geometry information to the data chunks for further processing (Bell, Paragraph 39).
Regarding claim 3, the combination of Douillard and Bell teaches the method of claim 1, wherein the reference surface data identifies the local tile that the vehicle is standing on as a ground surface tile (Douillard, Paragraph 16, processing can include determining voxels that are associated with a ground plane (e.g., a drivable surface for an autonomous vehicle), which may include determining locally flat voxels); and/or
The reference surface data identifies the local tile that is positioned immediately in front of the vehicle as a ground surface tile (Douillard, Paragraph 16, After locally flat voxels are determined, clustering techniques such as region growing can be used to identify ground voxels or a ground plane representing a flat or drivable surface; Paragraph 66, the operation 332 may determine that a cluster proximate to the autonomous vehicle 324′ is to be considered to be a primary ground cluster).
Regarding claim 5, the combination of Douillard and Bell teaches the method of claim 1, wherein the predefined growing method comprises a directional criterion that states that a local tile that is a neighbor of a ground surface tile or that is a next-to-neighbor of a ground surface tile is also a ground surface tile, if an angle difference of the normal vector of the local tile and the ground surface tile is less than a predefined angle threshold value (Douillard, Paragraph 64, the surface normal vector 316 is compared to the reference direction 322 by taking an inner product between the surface normal vector 316 and the reference direction 322, with the two vectors forming an angle θ. In some instances, the threshold may be set to any angle, such as 15 degrees, such that if θ is greater than 15 degrees, the voxel is determined not to correspond to a locally flat voxel; Paragraph 66, a cluster may be grown by determining locally flat voxels that are adjacent to one another, or that are within a threshold distance to another locally flat voxel).
Regarding claim 6, the combination of Douillard and Bell teaches the method of claim 1, further comprising: based on the region grown area that has been determined by the region growing method and based on a predefined interpolation method, in those grid cells which are outside the region grown area and which have two or three or four cells of the region grown area as neighbors, interpolating a respective new local tile as a ground surface tile (Douillard, Paragraph 66, Using region growing techniques, the operation 332 may grow clusters to include LIDAR data 338 and 340 associated with locally flat voxels. In some instances, a cluster may be grown by determining locally flat voxels that are adjacent to one another, or that are within a threshold distance to another locally flat voxel, to generate a first cluster 342 and a second cluster 344).
Regarding claim 10, the combination of Douillard and Bell teaches the method of claim 1, further comprising: planning a driving trajectory of the motor vehicle, wherein the driving trajectory is positioned exclusively on ground surface tiles, and causing the motor vehicle to be driven according to the trajectory by an autonomous driving function (Douillard, Paragraph 54, the planning module 228 may receive segmentation information identifying the ground plane and may generate a trajectory for the autonomous vehicle to follow).
Regarding claim 11, Douillard teaches a processing unit for a vehicle, wherein the processing unit comprises:
At least one processor (Paragraph 106, one or more processor(s)); and
A data storage that is coupled to the at least one processor, wherein the data storage comprises computer readable processing instructions that are designed to cause the at least one processor to perform a method (Paragraph 77, the operations represent computer-executable instructions stored on one or more computer-readable storage media that, when executed by one or more processors, perform the recited operations).
The combination of Douillard and Bell teaches the method according to claim 1.
Regarding claim 12, Douillard teaches a motor vehicle comprising:
At least one LIDAR sensor (Paragraph 160, using at least one LIDAR sensor); and
A processing unit comprising:
At least one processor (Paragraph 106, one or more processor(s)), and
A data storage that is coupled to the at least one processor, wherein the data storage comprises computer readable processing instructions that are designed to cause any of the at least one processor to perform a method (Paragraph 77, the operations represent computer-executable instructions stored on one or more computer-readable storage media that, when executed by one or more processors, perform the recited operations).
Wherein the processing unit is coupled to the at least one LIDAR sensor for receiving scan data describing measurement points from the at least one LIDAR sensor (Paragraph 148, wherein the instructions are further executable by the one or more processors to: determine, as a first height, an average height of LIDAR data).
The combination of Douillard and Bell teaches the method according to claim 1.
Regarding claim 13, the combination of Douillard and Bell teaches the method of claim 1, wherein the distinct grid cells do not have a defined height limitation in a z-direction (Bell, Paragraph 39, volume encompassed by a data chunk can be a rectangular prism of infinite height).
Bell and Douillard are both considered to be analogous to the claimed invention because they are in the same field of analyzing and mapping an environment using sensors. Therefore, it would have been obvious to a person of ordinary skill in the art before the effective filing date of the claimed invention to have modified Douillard to incorporate the teachings of Bell and use a horizontal grid with columns of infinite height. Doing so would allow for assigning geometry information to the data chunks for further processing (Bell, Paragraph 39).
Claim 2 is rejected under 35 U.S.C. 103 as being unpatentable over Douillard in view of Bell as applied to claims 1, 3, 5-6, 10-13 and further in view of Hu (CN 110285754).
Regarding claim 2, the combination of Douillard and Bell teaches the method according to claim 1. While the combination fails to disclose the following, Hu teaches:
The predefined tile fitting method is based on a Least-Mean-Square-Fitting of the z-values of the measurement points contained in the grid cell (Page 7, Paragraph 6, also capable of performing plane fitting by least squares. least square means square fitting by the optimal function matching and searching the data), and/or the predefined tile fitting method is based on a RANSAC-algorithm (Page 7, Paragraph 6, Specifically, can determine a plane through at least three point cloud data, determining algorithm of the plane using random sampling consistency algorithm (Random Sample Consensus, Ransac) fitting a plurality of planes, and using equations to calculate the equation of each plane).
Hu and the combination of Douillard and Bell are both considered to be analogous to the claimed invention because they are in the same field of analyzing and mapping an environment using sensors. Therefore, it would have been obvious to a person of ordinary skill in the art before the effective filing date of the claimed invention to have modified the combination of Douillard and Bell to incorporate the teachings of Hu and use Least-Mean-Square-Fitting or RANSAC to perform tile fitting. Doing so would allow for an efficient method to identify and classify surrounding tiles.
Claims 4 and 7-9 are rejected under 35 U.S.C. 103 as being unpatentable over Douillard in view of Bell as applied to claims 1, 3, 5-6, 10-13 and further in view of Chen (US 20170039436).
Regarding claim 4, the combination of Douillard and Bell teaches the method of claim 1, wherein the predefined region growing method comprises a height criterion that states that a local tile that is a neighbor of a ground surface tile or that is a next-to-neighbor of a ground surface tile is also a surface tile (Douillard, Paragraph 16, After locally flat voxels are determined, clustering techniques such as region growing can be used to identify ground voxels or a ground plane representing a flat or drivable surface)
While the combination fails to disclose the following, Chen teaches:
When a difference of the height of the local tile and the ground surface tile is less than a predefined height threshold value (Paragraph 24, the ground plane is segmented from the point cloud data by the server 125. The ground plane may be segmented by thresholding based on height. A threshold value may be selected. One non-limiting example of a threshold value may be one meter).
Chen and the combination of Douillard and Bell are both considered to be analogous to the claimed invention because they are in the same field of analyzing and mapping an environment using sensors. Therefore, it would have been obvious to a person of ordinary skill in the art before the effective filing date of the claimed invention to have modified the combination of Douillard and Bell to incorporate the teachings of Chen and use a predefined height threshold to identify ground tiles. Doing so would allow for providing a quick and efficient method of estimating the height of the ground plane.
Regarding claim 7, the combination of Douillard and Bell teaches the method according to claim 6. While the combination fails to disclose the following, Chen teaches:
Wherein the interpolation method comprises setting a height value of the new local tile to the minimum z-coordinate of the measurement points of the respective grid cell (Paragraph 24, The ground point is determined from the vehicle trajectory as the minimum value on the z axis of the point cloud data sensor. All three-dimensional point cloud data points that are within the threshold distance from the minimum value on the z axis are selected, and all coordinates outside the threshold are removed). Note: Chen teaches modifying the point cloud coordinates after identifying the minimum z-coordinates and the ground plane. This could be easily translated to replace identified ground plane z-values with the minimum identified z-value.
Chen and the combination of Douillard and Bell are both considered to be analogous to the claimed invention because they are in the same field of analyzing and mapping an environment using sensors. Therefore, it would have been obvious to a person of ordinary skill in the art before the effective filing date of the claimed invention to have modified the combination of Douillard and Bell to incorporate the teachings of Chen and replace identified ground plane z-values with the minimum identified z-value. Doing so would allow for easily identifying ground tiles after determining them from the initial calculation.
Regarding claim 8, the combination of Douillard and Bell teaches the method of claim 1. While the combination fails to disclose the following, Chen teaches:
For some of each of the measurement points, performing a classification, where the respective measurement point is classified as being a ground surface point when its height value is smaller than a predefined maximum height-above-ground-value (Paragraph 24, The ground plane may be segmented by thresholding based on height. A threshold value may be selected. One non-limiting example of a threshold value may be one meter).
Chen and the combination of Douillard and Bell are both considered to be analogous to the claimed invention because they are in the same field of analyzing and mapping an environment using sensors. Therefore, it would have been obvious to a person of ordinary skill in the art before the effective filing date of the claimed invention to have modified the combination of Douillard and Bell to incorporate the teachings of Chen and use a predefined height threshold to identify ground tiles. Doing so would allow for providing a quick and efficient method of estimating the height of the ground plane.
Regarding claim 9, the combination of Douillard, Bell, and Chen teach the method according to claim 8, wherein at least one other measurement point that is not classified as a ground surface point is instead classified as an object point that indicates a position of an object in the environment (Douillard, Paragraph 32, receiving an indication of the ground, the ground plane, and/or voxels that correspond to a ground, and removing the subset of voxels associated with the ground. Following this removing operation, voxels that remain in the voxel space may represent objects).
Response to Amendment
Applicant’s arguments with respect to claim 1 have been considered but are moot because the new ground of rejection does not rely on any reference applied in the prior rejection of record for any teaching or matter specifically challenged in the argument. Bell teaches a horizontal grid with cells of unlimited height as required by the amended claims. Douillard teaches identifying the height of cells to identify objects or the height of the ground as the claim requires.
Applicant’s arguments with respect to claim 5 have been considered but are not persuasive. Douillard teaches using the angle with respect to the surface normal to determine locally flat voxels, and using that information to determine if neighboring tiles are also locally flat. It would have been obvious to a person of ordinary skill in the art to determine that if a tile is locally flat using an angle threshold, and its neighbor is also locally flat using the angle threshold, then the neighbor is also a ground surface tile.
Conclusion
THIS ACTION IS MADE FINAL. Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any 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 SNIGDHA SINHA whose telephone number is (571)272-6618. The examiner can normally be reached Mon-Fri. 12pm-8pm.
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, Jason Chan can be reached at 571-272-3022. 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.
/SNIGDHA SINHA/ Examiner, Art Unit 2619
/JASON CHAN/ Supervisory Patent Examiner, Art Unit 2619