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 Status
Applicant’s amendments filed on 05/04/2026 have been received and considered. Claims 1-20 are pending. No claims have been amended.
Response to Arguments
Applicant's arguments filed 05/04/2026 have been fully considered but they are not persuasive.
Applicant argues (Remarks pg. 9 Par 1) that the proposed combination of references does not teach or suggest the reconstruction architecture that includes a first optimization in which the mesh of the three-dimensional space is dynamic while the object poses are fixed, followed by a second optimization in which the mesh is fixed while the object poses are dynamic, with those two different optimizations repeated until convergence. Examiner responds that the claim language as presented does not require that the second optimization follow the first, and that the proposed combination of references does teach two optimization steps repeated until convergence, the first in [0029] of Kulkarni, which recites “ICP can be used as an algorithm for interpreting LiDAR collected data points in autonomous vehicles to provide, for example, localization, mapping, trajectory estimation and calculation, dynamic object detection, and free space detection. Trajectory calculations can use relative motion identified, as an object, such as a vehicle, moves from an identified data point plane to another plane. For example, ICP produces the transforms between two point clouds, which when inversed, generates the trajectory that the vehicle travelled.”, and the second in [0026] of Kulkarni, which recites “The ICP algorithm can be used to roughly align the data points in the two point clouds so the system can identify the same objects in both point clouds. The system can calculate the distance between matched points; matched points are corresponding points that exist in the first and second point clouds. The system can then calculate if that other object is moving, how fast, and in which direction.” FIG. 7 of Kulkarni provides further clarification that there are two stages, a calculation of geometric space parameters, and a calculation of moving object parameters, and [0070] states “The outlier data point can be removed from the planar analysis. The removed data point can be analyzed separately, apart from the other data points”, where dynamic objects are identified using outlier data points. Applicant further argues that the present application describes that architecture expressly as an alternating coordinate-descent framework. The specification explains that the disclosed methodology decomposes optimization into alternating steps of estimating rigid- body motion parameters and estimating geometry, including "alternating steps" of motion and geometry optimization. Examiner responds that these features are not disclosed in or required by the claims as presented, but rather that the claims as presented specify only two distinct optimization steps, not that the second must follow the first, or that the steps must alternate.
In response to applicant's argument that the references fail to show certain features of the invention, it is noted that the features upon which applicant relies (i.e., "alternating steps" of motion and geometry optimization, "coordinate descent alternating between fixing the poses to optimize the meshes then fixing the meshes to update the poses") are not recited in the rejected claims. Although the claims are interpreted in light of the specification, limitations from the specification are not read into the claims. See In re Van Geuns, 988 F.2d 1181, 26 USPQ2d 1057 (Fed. Cir. 1993).
PNG
media_image1.png
465
485
media_image1.png
Greyscale
Applicant argues (Remarks pg. 9 Par 2 – pg. 10 Par 1) that Kulkarni in view of Mitrokhin does not teach the recited alternating mesh/pose optimization, and that the Office Action instead treats the fact that ICP is iterative as if it disclosed the claimed repetition of two distinct optimization stages, but iteration alone is not enough. Applicant further argues that nothing in Kulkarni teaches or suggests optimizing a scene mesh while holding object poses fixed, then optimizing object poses while holding the mesh fixed. Examiner responds that the claims as presented provide no requirement of alternating between a first and second optimization, and that the office action cited two ICP calculations of Kulkarni, constituting two optimization stages. FIG. 7 of Kulkarni provides further clarification that there are two stages, a calculation of geometric space parameters, and a calculation of moving object parameters and trajectory equations, and [0070] states “The outlier data point can be removed from the planar analysis. The removed data point can be analyzed separately, apart from the other data points”, where dynamic objects are identified using outlier data points, showing that analysis for dynamic objects is handled separately from analysis of 3D space. The claim language as presented does not provide a sequence or order that the optimization stages must be performed in. [0029] of Kulkarni teaches an optimization where 3D space is dynamic, and the position of objects is fixed (“Thus, ICP can be used as a process to analyze point cloud data and solving for the above described pose-differences between clouds of points. ICP can be used as an algorithm for interpreting LiDAR collected data points in autonomous vehicles to provide, for example, localization, mapping, trajectory estimation and calculation, dynamic object detection, and free space detection”), while [0026] teaches an optimization where the position of objects is dynamic, and 3D space is fixed (“The ICP algorithm can be used to roughly align the data points in the two point clouds so the system can identify the same objects in both point clouds. The system can calculate the distance between matched points; matched points are corresponding points that exist in the first and second point clouds. The system can then calculate if that other object is moving, how fast, and in which direction. From that information, the vehicle can determine what next steps and actions to process.”).
Applicant argues (Remarks pg. 10 Par 2 – pg. 11 Par 1) that nothing in [0026] of Kulkarni teaches that the mesh of a 3D space is fixed while respective positions and orientations of one or more objects are dynamic, and that nothing in [0026] of Kulkarni makes any distinction between one or more objects (or poses thereof) and a mesh of a 3D space that are handled separately from one another. Examiner responds that [0026] of Kulkarni teaches an optimization where the mesh of 3D space is fixed and the pose of one or more objects is dynamic (“The ICP algorithm can be used to roughly align the data points in the two point clouds so the system can identify the same objects in both point clouds. The system can calculate the distance between matched points; matched points are corresponding points that exist in the first and second point clouds. The system can then calculate if that other object is moving, how fast, and in which direction. From that information, the vehicle can determine what next steps and actions to process.”). [0040] of Kulkarni offers more clarification to this step, and states “a moving object, depending on the object's motion vector compared to the vector of the vehicle, can be identified, along with the moving object's trajectory. An object can be detected in 2 different slices, either slices that are positionally different, or slices of the same geometric space that are collected during different rotations of the LiDAR system. By comparing the object's position relative to the vehicle, and factoring in the vehicle's own movement, the movement of the object can be detected” (Emphasis added).
Applicant argues (Remarks pg. 11 Par 2 – pg. 12 Par 1) that nothing in [0029] of Kulkarni provides any teaching or suggestion of an optimization (or portion thereof) where a mesh of a 3D space is dynamic and respective positions and orientations of one or more objects are fixed, and fails to teach or suggest any distinction between a mesh of 3D space and positions and orientations of one or more objects. Examiner responds that [0029] does teach an optimization where 3D space is dynamic and object poses are fixed. [0029] states in part “Thus, ICP can be used as a process to analyze point cloud data and solving for the above described pose-differences between clouds of points. ICP can be used as an algorithm for interpreting LiDAR collected data points in autonomous vehicles to provide, for example, localization, mapping, trajectory estimation and calculation, dynamic object detection, and free space detection”. [0030] and [0070] of Kulkarni offer more clarification to this process, and [0030] states “identifying potential dynamic objects using outlier data points from the trajectory equations”, and [0070] further describes that “depth information can be used to remove data points, which can be within the window or grid, and at a significant enough of a depth difference from the other data points. For example, a data point can be from an object that is at a significantly different depth than an object represented by the remaining data points in the window or grid. The outlier data point can be removed from the planar analysis. The removed data point can be analyzed separately, apart from the other data points.” In other words, dynamic objects are analyzed separately and removed from planar analysis, being effectively ‘fixed’ during the solving of pose-differences between clouds of points.
Applicant argues that neither Kulkarni nor Mitrokhin teaches or suggests the claimed first and second optimizations, so a case of obviousness cannot be established, and further argues that because the combined rationale does not explain why a person of ordinary skill would have modified the cited references to implement the first and second optimizations recited in the independent claims, the rejection lacks the articulated reasoning with rational underpinning necessary to arrive at the combination of features recited in the independent claims. Examiner responds that, as explained above, the primary reference of Kulkarni teaches a first optimization to a mesh of the 3D space, and a second optimization to the respective positions and orientations of the one or more objects, without requiring modification.
Claim Rejections - 35 USC § 103
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
The factual inquiries for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or nonobviousness.
Claims 1-7, 9-16, and 18-20 are rejected under 35 U.S.C. 103 as being unpatentable
over US 20190266779 A1 (Kulkarni et al, hereinafter Kulkarni) in view of US 20240353234 A1
(Mitrokhin et al, hereinafter Mitrokhin).
Regarding claim 1, Kulkarni teaches a method for reconstructing a dynamic scene using
LIDAR (Light Detection and Ranging) data, the method comprising: (Par 17 "Various types of
data collection technologies or systems can be used, in different combinations, to periodically
collect data in a 3D space. For example, LiDAR (light detection and ranging) and RADAR (radio
detection and ranging) systems are commonly used to generate point cloud data for 3D space") generating, using a LIDAR system implemented on a vehicle point cloud data for an
environment including a plurality of objects including static and dynamic objects, wherein the
point cloud data comprises a plurality of points in a three-dimensional space; (Par 26 "For
example, the LiDAR system can collect two different point clouds at 0.6 seconds apart. The
vehicle can be traveling at some speed on a road. Because the vehicle is moving, the two sets of
point cloud data may not align. The system needs to know if the system is viewing a new object or the same object that has moved a little, relative to the vehicle. The ICP algorithm can be
used to roughly align the data points in the two point clouds so the system can identify the
same objects in both point clouds", Par 27 "The above mentioned calculation on how the other
object is moving can be relative to how the vehicle with the LiDAR system is moving.") estimating a position and orientation for one or more objects of the plurality of objects within each of the first and second annotated frames (Par 26 "The ICP algorithm can be used to roughly align the data points in the two point clouds so the system can identify the same objects in both point clouds. The system can calculate the distance between matched points; matched points are corresponding points that exist in the first and second point clouds. The system can then calculate if that other object is moving, how fast, and in which direction. From that information, the vehicle can determine what next steps and actions to process.")
transforming global-referenced coordinates to vehicle-referenced coordinates for each
of the one or more objects (Par 41 "Rather than mapping directly from point cloud data to a 2D
depth map, point cloud data, i.e., 3D coordinates (x, y, z), are being mapped to a 3D polar depth
map, i.e., polar coordinates (r, Θ, Ф). The collected 3D data points, collected by a detection and
ranging sensor, such as a LiDAR or RADAR system, can be stored as the 3D polar depth map.
These coordinates, for a LiDAR system, are defined as: [0042] X is to the left of the
forward/origin position of the LiDAR system [0043] y is the forward depth as compared to the
origin at the LiDAR system [0044] Z is the upward position as compared to the origin at
the LiDAR system [0045] r is the radial line [0046] Θ is the azimuth as measured from the plane
containing the X and y directions of the LiDAR system and rotates in a clockwise motion [0047]
Ф is the polar angle as measured from the forward position of the LiDAR system.")
transforming, for each of the one or more objects and using the plurality of
intermediate frames, respective object-referenced coordinates to vehicle-referenced
coordinates (Par 57 "When mapping point cloud data into a 2D depth map, the point cloud
data is transformed. Rather than precise coordinates for objects 412 and 414, the depth map
translates object location information to corresponding data points in the 2D depth map.")
performing a first optimization to a mesh of the three-dimensional space, wherein, during the first optimization, the mesh of the three-dimensional space is dynamic and respective positions and orientations of the one or more objects are fixed; (Par 29 "Trajectory calculations can use relative motion identified, as an object, such as a vehicle, moves from an
identified data point plane to another plane. For example, ICP produces the transforms between two point clouds, which when inversed, generates the trajectory that the vehicle travelled.")
performing a second optimization to the respective positions and orientations of the
one or more objects, wherein, during the second optimization, the mesh of the three-
dimensional space is fixed and the respective positions of the one or more objects are
dynamic (Par 26 "The ICP algorithm can be used to roughly align the data points in the
two point clouds so the system can identify the same objects in both point clouds. The system
can calculate the distance between matched points; matched points are corresponding points
that exist in the first and second point clouds. The system can then calculate if that other object
is moving, how fast, and in which direction.")
reconstructing the dynamic scene by performing the first and second optimizations until convergence (Par 26 "The ICP algorithm can be used to roughly align the data points in the two point clouds so the system can identify the same objects in both point clouds." where ICP
(iterative closest point) is an algorithm repeated until a condition is met, in this case aligning
the data points.)
Regarding claim 1, Kulkarni fails to explicitly teach annotating a plurality of frames based on the point cloud data, wherein the annotated frames include a first annotated frame and a second annotated frame, wherein the first and second annotated frames correspond to point cloud data generated at first and second instances of time, respectively. In related endeavor, Mitrokhin teaches annotating a plurality of frames based on the point cloud data, wherein the annotated frames include a first annotated frame and a second annotated frame, wherein the first and second annotated frames correspond to point cloud data generated at first and second instances of time, respectively (Par 58 "For example, a first point cloud represented by the first sensor data 102 (e.g., a first instance of the first sensor data 102) may represent the dynamic object at a first location at a first time, a second point cloud represented by the first sensor data 102 (e.g., a second instance of the first sensor data 102) may represent the dynamic object at a second location at a second time, a third point cloud represented by the first sensor data 102 (e.g., a third instance of the first sensor data 102) may represent the dynamic object at a third location at a third time, and/or so forth. As such, the tracking component 122 may use the annotations associated with the point clouds of the first sensor data 102 to identify the points from the point clouds that are associated with the dynamic object. The tracking component 122 may then use the points from the point clouds to generate a track for the dynamic object over the period of time")
It would have been obvious to a person of ordinary skill in the art prior to the effective filing date of the claimed invention to have modified Kulkarni to include annotating a plurality
of frames based on the point cloud data, wherein the annotated frames include a first
annotated frame and a second annotated frame, wherein the first and second annotated
frames correspond to point cloud data generated at first and second instances of time,
respectively, as taught by Mitrokhin. Doing so would allow an object to be tracked across point
clouds (Par 58 "use the annotations associated with the point clouds of the first sensor
data 102 to identify the points from the point clouds that are associated with
the dynamic object").
Regarding claim 1, Kulkarni fails to explicitly teach generating, using the first and
second annotated frames, a plurality of intermediate frames indicative of respective positions
and orientations of the one or more objects between first and second instances of time. In
related endeavor, Mitrokhin teaches generating, using the first and second annotated frames, a
plurality of intermediate frames indicative of respective positions and orientations of the one or
more objects between first and second instances of time (Par 61 "the mapping component 120 may use interpolation to determine one or more of the locations 502(1)-(4) associated with the dynamic object 208(4). For example, the mapping component 120 may process a first point cloud to determine the second location 502(2) of the dynamic object 208(4) and a second point
cloud to determine the fourth location 502(4) of the dynamic object 208(4). The mapping component 120 may then perform interpolation to determine the third location 502(3) of the dynamic object 208(4) using the second location 502(2) and the fourth location 502(4)", Par 62 "The mapping component 120 may then perform similar processes to track one or more other dynamic objects")
It would have been obvious to a person of ordinary skill in the art prior to the effective
filing date of the claimed invention to have modified Kulkarni to include generating, using the
first and second annotated frames, a plurality of intermediate frames indicative of respective
positions and orientations of the one or more objects between first and second instances of
time as taught by Mitrokhin. Doing so would allow objects to be tracked as they move
throughout the environment (Par 62 "the tracking component 122 may perform similar
processes to track the dynamic object 208(5) as the dynamic object 208(5) moves throughout
the environment").
Regarding claim 2, Kulkarni as modified by Mitrokhin teaches the method of claim 1.
Kulkarni further teaches wherein the LIDAR system comprises a rotating LIDAR sensor (Par 39
"Each rotation of the LiDAR sensor, in conjunction with motion, i.e., trajectory between two
time points, can create an overlap of point cloud data points, which in turn can indicate
movement of the vehicle or of an external object.")
Regarding claim 3, Kulkarni as modified by Mitrokhin teaches the method of claim 2
Kulkarni fails to explicitly teach wherein the first annotated frame comprises point cloud data
generated by the LIDAR sensor when pointing in a particular direction at the first instance of
time, and wherein the second annotated frame comprises point cloud data generated by the
LIDAR sensor when pointing in the particular direction at the second instance of time,
wherein the second instance of time is subsequent to the first instance of time. In related
endeavor, Mitrokhin teaches wherein the first annotated frame comprises point cloud data generated by the LIDAR sensor when pointing in a particular direction at the first instance of
time, and wherein the second annotated frame comprises point cloud data generated by the
LIDAR sensor when pointing in the particular direction at the second instance of time, wherein
the second instance of time is subsequent to the first instance of time. (Par 45 "since the
first sensor(s) is rotating when generating the first sensor data, the points associated with the
environment 204 may also be associated with timestamps indicating when the points were
generated. For example, the first point(s) associated with the static object 208(1) may be
associated with a first timestamp(s) indicating a first time(s) that the first point(s) was
generated, the second point(s) associated with the static object 208(2) may be associated with
a second timestamp(s) indicating a second time(s) that the second point(s) was generated")
It would have been obvious to a person of ordinary skill in the art prior to the effective
filing date of the claimed invention to have modified Kulkarni to include wherein the first
annotated frame comprises point cloud data generated by the LIDAR sensor when pointing in a
particular direction at the first instance of time, and wherein the second annotated frame
comprises point cloud data generated by the LIDAR sensor when pointing in the particular
direction at the second instance of time, wherein the second instance of time is subsequent to
the first instance of time as taught by Mitrokhin. Doing so would allow the time between
frames depicting the same direction to be indicated (Par 45 "the points associated with the
environment 204 may also be associated with timestamps indicating when the points were
generated")
Regarding claim 4, Kulkarni as modified by Mitrokhin teaches the method of claim 3.
Kulkarni fails to explicitly teach wherein each of the plurality of intermediate frames represent
estimated positions and orientations of the one or more objects between the first and second
instances of time, when the LIDAR sensor is not pointing in the particular direction. In related
field of endeavor, Mitrokhin teaches wherein each of the plurality of intermediate frames
represent estimated positions and orientations of the one or more objects between the first
and second instances of time, when the LIDAR sensor is not pointing in the particular direction
(Par 61 "Additionally, or alternatively, in some examples, the mapping component 120 may
use interpolation to determine one or more of the locations 502(1)-(4) associated with
the dynamic object 208(4). For example, the mapping component 120 may process a first point
cloud to determine the second location 502(2) of the dynamic object 208(4) and a second point
cloud to determine the fourth location 502(4) of the dynamic object 208(4). The mapping
component 120 may then perform interpolation to determine the third location 502(3) of
the dynamic object 208(4) using the second location 502(2) and the fourth location 502(4).")
It would have been obvious to a person of ordinary skill in the art prior to the effective
filing date of the claimed invention to have modified Kulkarni to include wherein each of the
plurality of intermediate frames represent estimated positions and orientations of the one or
more objects between the first and second instances of time, when the LIDAR sensor is not
pointing in the particular direction as taught by Mitrokhin. Doing so would allow dynamic
objects to be tracked as they move through the environment (Par 62 may perform similar
processes to track the dynamic object 208(5) as the dynamic object 208(5) moves throughout
the environment")
Regarding claim 5, Kulkarni as modified by Mitrokhin teaches the method of claim 1.
Kulkarni further teaches further comprising generating meshes for one or more moving
objects and generating meshes for one or more non-moving objects (Par 50 "The point cloud
data can include data points representing different features and artifacts in the geometric
space around the vehicle. In this example, a landmark detection is represented by a road
sign 128, a freespace detection is represented by open space 124, and an object detection is
represented by a second vehicle 126. These elements, 124, 126, and 128, are collectively
referred to as the geometric space parameters. Building 122 can also be part of the geometric
space parameters. In addition, the geometric space parameters include object trajectories and
moving objects. These are the parameters of areas and objects around, or partially around,
the LiDAR system 105a and are used in further processing systems.")
Regarding claim 6, Kulkarni as modified by Mitrokhin teaches the method of claim 5.
Kulkarni further teaches further comprising generating the meshes for the one or more
moving objects based on a constant velocity of the moving objects. (Par 50 "The point cloud
data can include data points representing different features and artifacts in the geometric
space around the vehicle. In this example, a landmark detection is represented by a road sign
128, a freespace detection is represented by open space 124, and an object detection is
represented by a second vehicle 126. These elements, 124, 126, and 128, are collectively
referred to as the geometric space parameters. Building 122 can also be part of the geometric
space parameters. In addition, the geometric space parameters include object trajectories and moving objects. These are the parameters of areas and objects around, or partially around, the
LiDAR system 105a and are used in further processing systems.")
Regarding claim 7, Kulkarni as modified by Mitrokhin teaches the method of claim 5.
Kulkarni further teaches further comprising determining point-to-mesh registration for the
plurality of points using an iterative closest point method to minimize a difference between
two different point clouds of the point cloud data (Par 26 "As noted above, another algorithm
that can be used to process point cloud data is the ICP. This algorithm can be used to roughly
align two point clouds. For example, the LiDAR system can collect two different point clouds at
0.6 seconds apart. The vehicle can be traveling at some speed on a road. Because the vehicle is
moving, the two sets of point cloud data may not align. The system needs to know if the system
is viewing a new object or the same object that has moved a little, relative to the vehicle.
The ICP algorithm can be used to roughly align the data points in the two point clouds so the
system can identify the same objects in both point clouds. The system can calculate the
distance between matched points; matched points are corresponding points that exist in the
first and second point clouds. The system can then calculate if that other object is moving, how
fast, and in which direction. From that information, the vehicle can determine what next steps
and actions to process.").
Regarding claim 9, Kulkarni as modified by Mitrokhin teaches the method of claim 1.
Kulkarni further teaches wherein repeating performing the first and second optimizations
until convergence comprises performing the first and second optimizations until an error metric is less than an error threshold (Par 67 "The resulting output of the ICP algorithm is a six
degree of freedom transform M that transforms the source points such that the point-plane
error between their corresponding target points is a minimum, i.e., the sum of the squared
distance between each source point and the tangent plane at its corresponding destination
point is a minimum").
Regarding claim 10, the system claim 10 is similar in scope to the method claim 1, and is
rejected under similar rationale.
Regarding claim 11, the system claim 11 is similar in scope to the method claim 2, and is
rejected under similar rationale.
Regarding claim 12, the system claim 12 is similar in scope to the method claim 3, and is
rejected under similar rationale.
Regarding claim 13, the system claim 13 is similar in scope to the method claim 4, and is
rejected under similar rationale.
Regarding claim 14, the system claim 14 is similar in scope to the method claim 5, and is
rejected under similar rationale.
Regarding claim 15, the system claim 15 is similar in scope to the method claim 6, and is
rejected under similar rationale.
Regarding claim 16, the system claim 16 is similar in scope to the method claim 7, and is
rejected under similar rationale.
Regarding claim 18, the non-transitory computer readable medium claim 18 is similar in
scope to the method claim 1 and is rejected under similar rationale.
Regarding claim 19, the non-transitory computer readable medium claim 19 is similar in
scope to the method claim 4 and is rejected under similar rationale.
Regarding claim 20, Kulkarni as modified by Mitrokhin teaches the computer readable
medium of claim 18. Kulkarni further teaches generate meshes for one or more moving
objects and generating meshes for one or more non-moving objects, wherein generating the
meshes for the one or more moving objects is based on a constant velocity of the moving
objects (Par 50 "The point cloud data can include data points representing different features
and artifacts in the geometric space around the vehicle. In this example, a landmark detection
is represented by a road sign 128, a freespace detection is represented by open space 124, and
an object detection is represented by a second vehicle 126. These elements, 124, 126, and 128,
are collectively referred to as the geometric space parameters. Building 122 can also be part of
the geometric space parameters. In addition, the geometric space parameters include object
trajectories and moving objects. These are the parameters of areas and objects around, or
partially around, the LiDAR system 105a and are used in further processing systems.")
and determine point-to-mesh registration for the plurality of points using an iterative
closest point method to minimize a difference between two different point clouds of the
point cloud data (Par 26 "As noted above, another algorithm that can be used to
process point cloud data is the ICP. This algorithm can be used to roughly align two point
clouds. For example, the LiDAR system can collect two different point clouds at 0.6 seconds
apart. The vehicle can be traveling at some speed on a road. Because the vehicle is moving, the
two sets of point cloud data may not align. The system needs to know if the system is viewing a new object or the same object that has moved a little, relative to the vehicle. The ICP algorithm
can be used to roughly align the data points in the two point clouds so the system can identify
the same objects in both point clouds. The system can calculate the distance between matched
points; matched points are corresponding points that exist in the first and second point clouds.
The system can then calculate if that other object is moving, how fast, and in which direction.
From that information, the vehicle can determine what next steps and actions to process.").
Claims 8 and 17 are rejected under 35 U.S.C. 103 as being unpatentable over Kulkarni in
view of Mitrokhin as applied to claim 1 above, and further in view of LIDAR Data Registration
for Unmanned Ground Vehicle Based on Improved ICP Algorithm (Zhongyang Zheng, Yan Li,
hereinafter Zheng).
Regarding claim 8, Kulkarni as modified by Mitrokhin fail to explicitly teach wherein
repeating performing the first and second optimizations until convergence comprises
repeating the first and second optimizations for a predetermined number of iterations. In
related field of endeavor, Zheng teaches limiting the number of iterations of a convergence
optimization to a predetermined number (Sect III, Par 3 "The second experiment is under the
condition of not limiting the convergence value and limiting the iteration numbers in 30
times.")
It would have been obvious to a person of ordinary skill in the art prior to the effective
filing date of the claimed invention to further modify Kulkarni in view of Mitrokhin to include
limiting the number of iterations of a convergence optimization to a predetermined number.
Doing so would limit the amount of time the convergence optimizations can take.
Furthermore, MPEP 2144.05 Section II.A. states "[W]here the general conditions of a
claim are disclosed in the prior art, it is not inventive to discover the optimum or workable
ranges by routine experimentation." An optimal number of iterations for an optimization could
be discovered through routine experimentation, and applied as the predetermined number of
iterations described in claim 8.
Regarding claim 17, the system claim 17 is similar in scope to the method claim 8 and is
rejected under similar rationale.
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 JOHN PATRICK GOCO whose telephone number is (571)272-5872. The examiner can normally be reached M-Th, 7:00 am - 5:00 pm.
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, Kee Tung can be reached at (571)272-7794. 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.
/J.P.G./Examiner, Art Unit 2611
/KEE M TUNG/Supervisory Patent Examiner, Art Unit 2611
Prosecution Insights