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 .
Priority
Receipt is acknowledged of certified copies of papers required by 37 CFR 1.55.
Status of Claims
Claims 1-3 and 5-10 are pending in this application.
Claims 4 are cancelled.
Claims 1, 3, and 7-10 are amended.
Claims 1-3 and 5-10 are presented for examination.
Response to Amendments
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 text of those sections of Title 35, U.S. Code not included in this action can be found in a prior Office action.
The factual inquiries for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or nonobviousness.
This application currently names joint inventors. In considering patentability of the claims the examiner presumes that the subject matter of the various claims was commonly owned as of the effective filing date of the claimed invention(s) absent any evidence to the contrary. Applicant is advised of the obligation under 37 CFR 1.56 to point out the inventor and effective filing dates of each claim that was not commonly owned as of the effective filing date of the later invention in order for the examiner to consider the applicability of 35 U.S.C. 102(b)(2)(C) for any potential 35 U.S.C. 102(a)(2) prior art against the later invention.
Claims 1-3 and 5-10 are rejected under 35 U.S.C. 103 as being unpatentable over Demir et al. (US Publication 2021/0010814 A1) in view of Zhang et al. (Foreign Reference CN110687549A) and in further view of Park et al. (US Publication 2024/0249531 A1).
Regarding claim 1, Demir teaches a calibration method comprising the steps of: acquiring, by a data creation device, first point cloud data …....... in order to create a reference map (Demir: Para. 41; map tile point cloud data may be indicative of transformed point cloud data associated with a coarse vehicle location and be built using a reference set of sensors), a plurality of second point cloud data acquired from a plurality of second LIDARs mounted on a vehicle traveling on a path on the reference map and specification values for the first LIDAR and the plurality of second LIDARs (Demir: Para. 38-39; LiDAR; generate a sensor scan point cloud output by transforming the set of sensor data from each sensor frame to a corresponding vehicle frame); performing, by the data creation device, preprocessing on the first point cloud data and the plurality of second point cloud data (Demir: Para. 39, 41; scan accumulator may transform each sensor data to a common coordinate frame; point cloud data from the map tile server (e.g., map tile point cloud data) may be represented in a local coordinate frame).
Demir doesn’t explicitly teach from a first LIDAR.
However Zhang, in the same field of endeavor, teaches from a first LIDAR (Zhang: Pg. 6 Lines 7-11; obtains the first point cloud data collected by the first on-board lidar and the second point cloud data collected by the second on-board lidar).
It would have been obvious to one having ordinary skill in the art to modify the LIDAR calibration (Demir: Para. 41, 53) with the ground point matching (Zhang: Pg. 6 Lines 32-40) with a reasonable expectation of success because using the ground points from a first LIDAR’s point cloud with the ground point filtered reducing the false detection rate of ground points being misjudged as obstacle points, and improving detection accuracy (Zhang: Pg. 5 Lines 52-55).
Demir and Zhang don’t explicitly teach performing, by the data creation device, calibration on the preprocessed first point cloud data and plurality of second point cloud data, wherein the performing of the preprocessing includes detecting a ground from the plurality of second point cloud data as a ground point cloud, approximating the ground point cloud to a plane, and then interpolating additional points between points of the ground point cloud to increase a density of the ground point cloud.
However Park, in the same field of endeavor, teaches performing, by the data creation device, calibration on the preprocessed first point cloud data and plurality of second point cloud data, wherein the performing of the preprocessing includes detecting a ground from the plurality of second point cloud data as a ground point cloud, approximating the ground point cloud to a plane, and then interpolating additional points between points of the ground point cloud to increase a density of the ground point cloud (Park: Para. 54; pre-training; pixels that have valid ground-truth depth from the sparse Lidar point clouds are projected onto the camera plane; D, is the predicted depth map from the I-th level in FPN (i.e., interpolated z.sub.p), and M is the binary indicator for valid pixels).
It would have been obvious to one having ordinary skill in the art to modify the LIDAR calibration (Demir: Para. 41, 53) with the ground point matching (Zhang: Pg. 6 Lines 32-40) and the pre-training interpolation of the ground-truth (Park: Para. 54) with a reasonable expectation of success because interpolating the ground-truth point cloud allowing for training with lower resolution data creating more stable model training (Park: Para. 54).
Regarding claim 2, Demir teaches the calibration method according to claim 1, wherein the step of performing the preprocessing includes voxelizing the first point cloud data and the plurality of second point cloud data (Demir: Para. 42-43; map tile point cloud data may be represented as a voxel; determine a match based on the sensor scan point cloud output (e.g., sensor point cloud) and the map tile point cloud data (e.g., the reference point cloud)).
Regarding claim 3, Demir teaches the calibration method according to claim 1, wherein the step of performing the preprocessing includes identifying and removing an object having a height of a preset value on a basis of the ground point cloud as a noise object (Demir: Para. 41, 46, 55; effect of non-mapped objects in the fitness score calculation may be minimized by treating points in the scan as outliers if the distance to the corresponding closest point in the map is greater than a threshold).
Regarding claim 4, Demir teaches the calibration method according to claim 1, wherein the step of performing the preprocessing includes detecting the ground from the plurality of second point cloud data, approximating the point cloud detected as the ground to a plane (Demir: Para. 60; fusion of different sensors may be performed by the location fuser, including fusion of features, such as LiDAR, wheel odometry, CAN data, IMU data, GPS data, ground reflectivity, vertical features, roach marker features).
Demir doesn’t explicitly teach then interpolating additional points between the point clouds detected as the ground.
However Zhang, in the same field of endeavor, teaches then interpolating additional points between the point clouds detected as the ground (Zhang: Para. Pg. 5 Lines 52-56, Pg. 6 Lines 32-40; estimate the ground based on the point cloud data collected by the first vehicle lidar LiDAR1, and then filter the ground points based on the estimated ground to the point cloud data collected by the second vehicle lidar LiDAR2 at the same geographic location, and then Based on the second vehicle-mounted lidar LiDAR2, the other point clouds after filtering out the ground points are clustered and matched).
It would have been obvious to one having ordinary skill in the art to modify the LIDAR calibration (Demir: Para. 41, 53) with the ground point matching (Zhang: Pg. 6 Lines 32-40) with a reasonable expectation of success because using the ground points from a first LIDAR’s point cloud with the ground point filtered reducing the false detection rate of ground points being misjudged as obstacle points, and improving detection accuracy (Zhang: Pg. 5 Lines 52-55).
Regarding claim 5, Demir teaches the calibration method according to claim 1, wherein the step of performing the calibration includes performing a normal distribution transform (NDT) matching on each of the first point cloud data and the plurality of second point cloud data (Demir: Para. 43; determine the match between the sensor scan point cloud output and the map tile point cloud data based on a normal distribution transform (NDT)), and simultaneously performing calibration on the plurality of second LIDARs through multi-threading (Demir: 60, 63; LiDAR; enable multi-threading, this data structure (e.g., concurrent object buffer) may be implemented; concurrent object buffer may include two thread-safe scan queues: a scan pool and a scan buffer).
Regarding claim 6, Demir teaches the calibration method according to claim 5, wherein the step of performing the calibration includes performing the calibration by designating the specification value of each of the first LIDAR and the plurality of second LIDARs as initial pose (Demir: Para. 51; initialization procedure aims to find a good initial pose estimate that is close enough for the scan matcher to converge).
Regarding claim 7, Demir teaches the calibration method according to claim 6, wherein the step of performing the calibration includes determining a matching between the first point cloud data and the plurality of second point cloud data using a fitness score that is a sum of average and covariance between voxels during a process of the NDT matching (Demir: Para. 42, 43; scan matcher may determine the match between the sensor scan point cloud output and the map tile point cloud data based on a normal distribution transform (NDT); map tile point cloud data may be represented as a voxel associated with a mean and a covariance).
Regarding claim 8, Demir teaches the calibration method according to claim 1, wherein the step of performing the calibration includes performing an NDT matching with the first point cloud data by designating a region of interest (ROI) to each of the plurality of second point cloud data (Demir: Para. 42-43; map tiles may be ‘tiles’ around the vehicle which may be loaded at runtime e.g., as the vehicle is passing through the operating environment; stored and loaded in a NDT compatible format; determine a match based on the sensor scan point cloud output (e.g., sensor point cloud) and the map tile point cloud data (e.g., the reference point cloud)).
Regarding claim 9, Demir teaches the calibration method according to claim 8, wherein the step of performing the calibration includes designating the region of interest to each of the plurality of second point cloud data on a basis of a coordinate system of the first point cloud data (Demir: Para. 41, 52; map tile point cloud data may include static features, ground surfaces, features of the environment, layout of the environment; an initialization pattern to pick from initial pose candidates in an order and check if any of those candidates makes the scan matcher to converge and achieve high localization confidence).
Demir doesn’t explicitly teach wherein the region of interest is designated after aligning the coordinate system of the first point cloud data and the plurality of second LIDARs using specification value of each of the plurality of second LIDARs.
However Zhang, in the same field of endeavor, teaches wherein the region of interest is designated after aligning the coordinate system of the first point cloud data and the plurality of second LIDARs using specification value of each of the plurality of second LIDARs (Zhang: Pg. 5 Lines 52-56, Pg. 6 Lines 32-40; estimate the ground based on the point cloud data collected by the first vehicle lidar LiDAR1, and then filter the ground points based on the estimated ground to the point cloud data collected by the second vehicle lidar LiDAR2 at the same geographic location, and then Based on the second vehicle-mounted lidar LiDAR2, the other point clouds after filtering out the ground points are clustered and matched).
It would have been obvious to one having ordinary skill in the art to modify the LIDAR calibration (Demir: Para. 41, 53) with the ground point matching (Zhang: Pg. 6 Lines 32-40) with a reasonable expectation of success because using the ground points from a first LIDAR’s point cloud with the ground point filtered reducing the false detection rate of ground points being misjudged as obstacle points, and improving detection accuracy (Zhang: Pg. 5 Lines 52-55).
Regarding claim 10, Demir teaches a computer program recorded on a recording medium being combined with a computing device including a memory, a transceiver and a processor for processing instructions loaded in the memory, wherein the computer program causes the processor to execute steps of: acquiring first point cloud data …..... in order to create a reference map (Demir: Para. 41; map tile point cloud data may be indicative of transformed point cloud data associated with a coarse vehicle location and be built using a reference set of sensors), a plurality of second point cloud data acquired from a plurality of second LIDARs mounted on a vehicle traveling on a path on the reference map and specification values for the first LIDAR and the plurality of second LIDARs (Demir: Para. 38-39; LiDAR; generate a sensor scan point cloud output by transforming the set of sensor data from each sensor frame to a corresponding vehicle frame); performing preprocessing on the first point cloud data and the plurality of second point cloud data (Demir: Para. 39, 41; scan accumulator may transform each sensor data to a common coordinate frame; point cloud data from the map tile server (e.g., map tile point cloud data) may be represented in a local coordinate frame).
Demir doesn’t explicitly teach from a first LIDAR.
However Zhang, in the same field of endeavor, teaches from a first LIDAR (Zhang: Pg. 6 Lines 7-11; obtains the first point cloud data collected by the first on-board lidar and the second point cloud data collected by the second on-board lidar).
It would have been obvious to one having ordinary skill in the art to modify the LIDAR calibration (Demir: Para. 41, 53) with the ground point matching (Zhang: Pg. 6 Lines 32-40) with a reasonable expectation of success because using the ground points from a first LIDAR’s point cloud with the ground point filtered reducing the false detection rate of ground points being misjudged as obstacle points, and improving detection accuracy (Zhang: Pg. 5 Lines 52-55).
Demir and Zhang don’t explicitly teach performing calibration on the preprocessed first point cloud data and plurality of second point cloud data, wherein the performing of the preprocessing includes detecting a ground from the plurality of second point cloud data as a ground point cloud, approximating the ground point cloud to a plane, and then interpolating additional points between points of the ground point cloud to increase a density of the ground point cloud.
However Park, in the same field of endeavor, teaches performing calibration on the preprocessed first point cloud data and plurality of second point cloud data, wherein the performing of the preprocessing includes detecting a ground from the plurality of second point cloud data as a ground point cloud, approximating the ground point cloud to a plane, and then interpolating additional points between points of the ground point cloud to increase a density of the ground point cloud (Park: Para. 54; pre-training; pixels that have valid ground-truth depth from the sparse Lidar point clouds are projected onto the camera plane; D, is the predicted depth map from the I-th level in FPN (i.e., interpolated z.sub.p), and M is the binary indicator for valid pixels).
It would have been obvious to one having ordinary skill in the art to modify the LIDAR calibration (Demir: Para. 41, 53) with the ground point matching (Zhang: Pg. 6 Lines 32-40) and the pre-training interpolation of the ground-truth (Park: Para. 54) with a reasonable expectation of success because interpolating the ground-truth point cloud allowing for training with lower resolution data creating more stable model training (Park: Para. 54).
Response to Arguments
Applicant’s arguments, filed on 13 July 2026, with respect to the rejection of claims 1-10 under 35 U.S.C. 103 have been fully considered, but they are not persuasive.
The applicant’s attorney argues the combined references of Demir and Zhang fail to teach or suggest at least the feature of "wherein the performing of the preprocessing includes detecting a ground from the plurality of second point cloud data as a ground point cloud, approximating the ground point cloud to a plane, and then interpolating additional points between points of the ground point cloud to increase a density of the ground point cloud" in claim 1
In response to the argument above, the argument is moot because it doesn’t apply to the prior art in this rejection.
The applicant next argues that there is no motivation to combine the teachings of Demir and Zhang in the manner claimed.
In response to applicant’s argument above that there is no teaching, suggestion, or motivation to combine the references, the examiner recognizes that obviousness may be established by combining or modifying the teachings of the prior art to produce the claimed invention where there is some teaching, suggestion, or motivation to do so found either in the references themselves or in the knowledge generally available to one of ordinary skill in the art. See In re Fine, 837 F.2d 1071, 5 USPQ2d 1596 (Fed. Cir. 1988), In re Jones, 958 F.2d 347, 21 USPQ2d 1941 (Fed. Cir. 1992), and KSR International Co. v. Teleflex, Inc., 550 U.S. 398, 82 USPQ2d 1385 (2007). In this case, Demir teaches a point cloud data in a map tile format in order to localize a vehicle and help it navigate the real-world environment (Demir: Para. 41). Zhang teaches a vehicle with a two LIDAR system to reduce the false detection rate of ground points being misjudged as obstacle points, and improve detection accuracy (Zhang: Pg. 5 Lines 52-56, Pg. 6 Lines 7-11, Lines 32-40). Both prior arts are in the field of vehicle location and navigation using vehicle mounted LIDAR point cloud data. It would be obvious to one of ordinary skill to use various vehicle navigation and point cloud analysis techniques.
The applicant next argues that dependent claims 2-3 and 5-9 are allowable at least based on their dependencies on claim 1.
In response to the applicant’s argument above, claim 1 is rejected. Claims 203 and 5-9 are rejected at least based on their dependencies.
The applicant next argues that dependent claims 2-3 and 5-9 recite additional narrow, non-obvious features at in the following: claim 2 recites voxelizing the first point cloud data and the plurality of second point cloud data, which optimizes data structure and processing efficiency specifically for multi-LiDAR calibration; claim 3 recites identifying and removing objects of a preset height on the basis of the detected ground as noise, ensuring that non-ground obstacles do not distort the approximated ground plane used for interpolation; claims 5-7 recite performing NDT matching on each of the point cloud data and simultaneously performing calibration through multi-threading, and using a fitness score that is a sum of average and covariance between voxels. This provides highly parallelized and mathematically robust optimization that is unique to the claimed calibration framework; Claims 8-9 recite designating a region of interest (ROI) to each of the plurality of second point cloud data on the basis of the coordinate system of the first point cloud data, after aligning the coordinate systems using specification values as an initial pose. This targeted matching prevents irrelevant environmental points from introducing errors into the extrinsic calibration process, ensuring fast and reliable convergence. These features make the dependent claims allowable.
In response to the applicant’s argument above, Applicant's arguments fail to comply with 37 CFR 1.111(b) because they amount to a general allegation that the claims define a patentable invention without specifically pointing out how the language of the claims patentably distinguishes them from the references.
The applicant next argues that claim 10 is amended similarly to claim 1 and therefore allowable for the same reasons.
In response to the applicant’s argument above, claim 1 is rejected. The examiner has answered claim 1’s arguments above. Those replies would similarly apply to claim 10.
The applicant’s arguments have failed to point out the distinguishing characteristics of the amended claim language over the prior art. For the above reasons, Demir’s LIDAR map tile point cloud in view of Zhang’s two LIDAR system and Park’s preprocessing the ground-truth reads on applicant’s method for calibration of multiple LIDARs. The rejection is maintained.
Conclusion
Applicant's amendment necessitated the new ground(s) of rejection presented in this Office action. Accordingly, THIS ACTION IS MADE FINAL. See MPEP § 706.07(a). Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any extension fee pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the date of this final action.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to LAURA E LINHARDT whose telephone number is (571)272-8325. The examiner can normally be reached on M-TR, M-F: 8am-4pm.
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 Ortiz can be reached on (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 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 http://pair-direct.uspto.gov. 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.
/L.E.L./Examiner, Art Unit 3663
/ADAM D TISSOT/Primary Examiner, Art Unit 3663
