DETAILED ACTION
Notice of Pre-AIA or AIA Status
1. The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA . It is responsive to the submission dated 03/11/2025. Claims 1-20 are presented for examination. Claims 1, 10 and 17 are independent claims.
Information Disclosure Statement
2. The information disclosure statements (IDSs) submitted on 03/11/2025 AND 06/16/2026 are in compliance with the provisions of 37 CFR 1.97 and are being considered by the Examiner.
Claim Objections
3. Claim 17 is objected to because of the following informalities: the preamble of the claim appears to be broadly vague, as the body of the claim lacks the necessary structures for performing the associating step, the determining steps and the controlling step, as claimed. To make clear the claimed invention, the Examiner suggests amending the preamble to recite:
-A computer-implemented method for controlling a vehicle within an environment-. Appropriate correction is required.
Claim Rejections - 35 USC § 102
4. The following is a quotation of the appropriate paragraphs of 35 U.S.C. 102 that form the basis for the rejections under this section made in this Office action:
A person shall be entitled to a patent unless –
(a)(1) the claimed invention was patented, described in a printed publication, or in public use, on sale, or otherwise available to the public before the effective filing date of the claimed invention.
5. Claims 1-4, 6, 8-13, and 16-20 are rejected under 35 U.S.C. 102(a)(a1) as being anticipated by Maher et al. (US 20190272665).
Considering claim 1, Maher discloses a system (see fig. 3) comprising: one or more processors (320); and one or more non-transitory computer readable media (330, 340) storing instructions executable by the one or more processors, wherein the instructions, when executed, cause the system to perform operations (see paras. 31-37) comprising:
receiving sensor data from a sensor associated with a vehicle (e.g., Maher discloses a LIDAR device might provide map data that defines objects in a 3D space using points. See para. 12. Maher further describes the system to include a User device 210 capable of receiving, generating, storing, processing, and/or providing information associated with 3D voxels. The user device can be included in and/or attached to a variety of other types of devices that might make use of 3D voxels. Examples include aircraft (including manned and unmanned aircraft) computing devices, such as a flight controller and/or navigation component; ground-based vehicle (including autonomous vehicles or user-operated vehicles) computing devices, such as a collision avoidance system and/or navigation component. See para. 24);
associating a first portion of the sensor data with a first voxel of a first voxel space (e.g., Maher discloses a LIDAR device might provide map data that defines objects in a 3D space using points… The map data may include data points specifying a 3D space for which voxels are to be generated and indexed (e.g., map data may indicate that voxels should be generated…..the map data may be normalized (e.g., data points or other information included in the map data converted to a particular format) by the map data provider(s) prior to the map data being provided to the voxel mapping device. …. For example, the voxel data can include a 3D grid of voxels for a 3D space, and each voxel can represent a portion of the 3D space in the 3D grid. See paras. 12-13. In addition, Maher discloses "different sets of voxel data can include different map data. See para. 15; "the first set of voxels might include data relevant to an autonomous vehicle; see para. 67, wherein each of the first and second voxel data sets correspond to a first and second voxel space, respectively and the first voxel data set encompasses a first and a second voxel);
determining, based on the first portion, a covariance associated with the first voxel (e.g., Maher discloses: the voxel mapping device can generate a voxel grid for a city using map data provided by various map data providers…. For example, a voxel that includes a portion of the city might include multiple 3D points associated with one or more street names, street addresses, building descriptions, temperature measurement, zoning information, regulatory information, and/or the like. See para. 14. Maher further describes that voxel data for one portion of a relatively large space, such as a portion of a large voxel, may be managed by one voxel mapping device 230, while another portion of the relatively large space, such as another portion of the large voxel, may be managed by another voxel mapping device 230. See para. 27. See also para. 56);
determining, based on the covariance, a voxel correspondence between the first voxel and a reference voxel of a reference voxel space (e.g., Maher discloses: In some implementations, voxel mapping device 230 can index the first set of voxels prior to the receipt of map data, or prior to receipt of map data that is to be included in the voxels. For example, in preparation for the receipt of map data, voxel mapping device 230 may generate and index an empty set of voxels (e.g., based on a predetermined configuration). See para. 62. For example, voxel mapping device 230 can generate a second set of voxels based on the first set of voxels…. by subdividing the first set of voxels. For example, in a situation where the first set of voxels includes 4 cube-shaped voxels, voxel mapping device can subdivide the 4 voxels (e.g., into a second set of 16 voxels, 4 for each voxel in the first set). Subdividing can be performed, for example, by generating new voxels of the target size or target ratio of the original voxels, and including, in the new voxels, the map data associated with the space included in the new voxels. See paras. 64-65);
determining a transformation between the first voxel space and the reference voxel space based at least in part on the voxel correspondence (e.g., Maher discloses voxel mapping device 230 can subdivide a portion of the voxels included in the first set of voxels. For example, if a first set of voxels has 27 voxels in a 3×3×3 cube arrangement, voxel mapping device 230 can generate the second set of voxels by further subdividing each voxel of the bottom layer (i.e., the bottom 9 voxels of the first set) of the 3D space into 3×3×3 voxels, without subdividing or modifying the voxels of the top two layers. As a result, the second set of voxels would include 18 voxels (i.e., the top two layers of 3×3 cube-shaped voxels) representing relatively large spaces (e.g., the same size as the top 18 voxels of the first set) and 243 voxels for the bottom layer of the 3D space representing relatively small spaces (e.g., the original 9 voxels that made up the bottom layer of the first set can each be sub-divided into 27 cube-shaped voxels). In some implementations, subdividing a portion of the 3D space might be done based on map data density. In the example above, the bottom layer might be more dense (e.g., include more map data) than the middle and/or top layers. See para. 66); and one or more of:
determining, based on the transformation, a map to be used by an autonomous vehicle; or controlling the vehicle based at least in part on the transformation (e.g., Maher discloses: As noted in the examples above, the representative data that replaces points of map data in a voxel can be designed to be used by a computing device that makes use of the voxels (e.g., a computing device used by a UAV for navigating, and/or an autonomous vehicle for collision avoidance. See para. 57. In some implementations, voxel mapping device 230 generates the second set of voxels based on the manner in which the map data included in the voxels is to be used and/or the type of user device 210 that will make use of the voxels. For example, the first set of voxels can include data relevant to a first type of user device 210, while the second set of voxels can include map data relevant to a second type of user device 210. By way of example, the first or the second set of voxels might include data relevant to an autonomous vehicle. See para. 67).
As per claim 2, Maher discloses: determining a semantic classification associated with the first portion of the sensor data; and determining the voxel correspondence between the first voxel and the reference voxel further based at least in part on the semantic classification (e.g., “different sets of voxel data can include different map data. For example, one set of voxel data might include topography map data, while another set of voxel data does not”; see para. 15; "the first set of voxels might include data relevant to an autonomous vehicle (e.g., street names, building identifiers, addresses, and/or the like), and the second set of voxels might include data relevant to an unmanned aerial vehicle, such as building location data for tall buildings, terrain data for mountains," see para. 67)
As per claim 3, Maher discloses determining a mean value of the first portion of the sensor data; and associating the mean value and the covariance with the first voxel (e.g., Maher discloses: The voxel mapping device can associate a variety of map data with a voxel, which represents a value in 3D space. The voxel mapping device can generate voxels at a variety of resolutions, or scales, and index the voxels at multiple resolutions. Generating multiple indices with different voxel resolutions can enable a device to store and/or make use of 3D map data at a resolution appropriate to a given context. For example, a large commercial aircraft flying at a high speed might make use of relatively large scale airspace voxels (e.g., 10 kilometer by 10 kilometer by 10 kilometer voxels storing data related to airspace) while a small unmanned aerial vehicle (UAV) moving slowly might make use of relatively small scale airspace voxels (e.g., 5 meter by 5 meter by 5 meter voxels storing data related to airspace). See para. 9).
As per claim 4, Maher discloses the first voxel space is part of a multi-resolution voxel space; and the first voxel space is associated with a first resolution and a first semantic classification (e.g., Maher discloses: the voxel mapping device indexes multiple different types of voxel data into multiple indices. The indices can be applied at different voxel sizes, or scales. In the example implementation 100, each set of voxel data can represent the area in a different manner (e.g., by changing the resolution of or the map data included in each set of voxel data)… “different sets of voxel data can include different map data. For example, one set of voxel data might include topography map data, while another set of voxel data does not”; see para. 15; and "voxel data can include the same data but at different resolutions," para. 67, wherein Maher implies that varying type and/or resolution between voxel data sets can be determined).
As per claim 6, Maher discloses the covariance is a weighted covariance (e.g., voxel mapping device 230 can generate voxels based on density of the map data and an amount of map data to be included in each voxel. For example, voxel mapping device 230 might generate voxels in a manner designed to ensure that voxel density does not exceed a threshold density. See para. 51. Some implementations are described herein in connection with thresholds. As used herein, satisfying a threshold can refer to a value being greater than the threshold, more than the threshold, higher than the threshold, greater than or equal to the threshold, less than the threshold, fewer than the threshold, lower than the threshold, less than or equal to the threshold, equal to the threshold, greater or less than the threshold for a period of time, and/or the like. See para. 89).
As per claims 8-9, Maher discloses associating a second portion of the sensor data with a second voxel of the first voxel space, wherein the first voxel space is associated with a first resolution and wherein the first voxel and the second voxel are adjacent within the first voxel space. (e.g., "different sets of voxel data can include different map data. For example, one set of voxel data might include topography map data, while another set of voxel data does not," para. 15; "the first set of voxels might include data relevant to an autonomous vehicle (e.g., street names, building identifiers, addresses, and/or the like), and the second set of voxels might include data relevant to an unmanned aerial vehicle, such as building location data for tall buildings, terrain data for mountains," para. 67, wherein each of the first and second voxel data sets correspond to a first and second voxel space, respectively and the first voxel data set encompasses the first and second voxels); and
determining, based at least in part on the first voxel and the second voxel, a third voxel associated with a second resolution that is coarser than the first resolution (e.g., one set of voxel data might include topography map data, while another set of voxel data does not," (see para. 15); and “voxel data can include the same data but at different resolutions,"; see para. 67, wherein the second set of voxels encompass a third voxel that differs in resolution from a second voxel included in the first voxel data sets from the data map).
The subject-matter of independent claim 10 is similar in scope to that of claim 1, and the rationale raised above to reject the later also apply, mutatis mutandis, to the former.
Claim 11 is rejected under the same rationale as claim 2.
Claim 12 is rejected under the same rationale as claim 3.
Claim 13 is rejected under the same rationale as claim 4.
Claim 16 is rejected under the same rationale as claims 8-9.
The subject-matter of independent claim 17 is similar in scope to that of claim 1, and the rationale raised above to reject the later also apply, mutatis mutandis, to the former.
Claim 18 is rejected under the same rationale as claim 2.
Claim 19 is rejected under the same rationale as claim 3.
Claim 20 is rejected under the same rationale as claim 8.
Claim Rejections - 35 USC § 103
6. 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.
7. Claims 5, 7, and 14-15 are rejected under 35 U.S.C. 103 as being unpatentable over Maher et al. (US 20190272665) in view of Link et al. (US 20190258225).
As per claim 5, Maher fails to teach the voxel correspondence is based at least on a distance between a first centroid associated with the first voxel and a second centroid associated with the reference voxel, which is disclosed by Link.
Particularly, Link discloses performing alignment between a laser scanned object and a CAD model representing point cloud data. Link registers a point cloud for a laser scanned object with the point cloud for a CAD model. Link determines a minimum total variance between the CAD model and the point cloud for each point in the CAD model and the laser scanned object. See paras. 178-179. Additionally, Link describes performing computation for matching differences between centroids of objects, based on alignment positions between a target point cloud or voxel and a main or reference point cloud. See paras. 185-189.
Accordingly, it would have been obvious to one of the ordinary skilled in the art, before the effective filling date of the invention was made, to have modified the teachings of Maher to include the voxel correspondence is based at least on a distance between a first centroid associated with the first voxel and a second centroid associated with the reference voxel, in the same conventional manner as taught by Link, in order to best align each target point to its match found in the reference point registered from the scanned object, so as to filtering out artifacts in the connected point clouds from the scanned object. See paras. 186-187 of Link.
As per claim 7, Maher fails to teach, but Link discloses: determining the transformation further comprises determining a measurement uncertainty based at least in part on modelling an alignment of the first voxel space and the reference voxel space as a Gaussian distribution (e.g., Maher discloses generating an initial corresponding geometric transformation between the target point cloud and the reference mesh model. The translation is computed as the difference in the position of the centroids between the image from the 2D projection of the target point cloud and the closest match determined above. Next, the geometric transformation obtained is applied to the target point cloud 1835. The output of this step is a translated and rotated target point cloud that will be coarsely aligned with the identified reference mesh model. This may be implemented as a 3D transformation matrix, T, using the computed translation and rotation. The transformation matrix T is applied to align the target point cloud with the CAD model, producing a registration between the point cloud and the CAD model.
[0186] This is followed by a fine 3D registration step 1836 that completes the whole registration process. … see paras. 185-186. [0189] The fine 3D registration 1836 may use algorithms such as the Iterative Closest Point (ICP), which is a popular algorithm due to its simplicity. The inputs of the algorithm are the target and reference point clouds, initial estimation of the geometric transformation (from step 1834) to align the target to the reference, and criteria for stopping the iterations. The output of the algorithm is a refined geometric transformation matrix. The algorithm includes: [0190] 1. For each point (from the whole set of vertices usually referred to as dense or a selection of pairs of vertices from each model) in the target point cloud, matching the closest point in the reference point cloud (or a selected set). [0191] 2. Estimating the combination of rotation and translation using a root mean square point to point distance metric minimization technique, which best aligns each target point to its match found in the previous step. In addition, the points may be weighted and outliers may be rejected prior to alignment. [0192] 3. Transforming the target points using the obtained transformation. [0193] 4. Iterating (re-associating the points, and so on). [0194] Then, the final geometric transform between the target point cloud and the reference mesh model is determined 1837 based on the refined geometric transformation matrix obtained in the above fine 3D registration step. Note that in general a geometric transform is an affine transform consisting of one or a combination of translation, scale, shear, or rotation transformations. See paras. 189-194 of Link).
Accordingly, it would have been obvious to one of the ordinary skilled in the art, before the effective filling date of the invention was made, to have modified the teachings of Maher to include determining a measurement uncertainty based at least in part on modelling an alignment of the first voxel space and the reference voxel space as a Gaussian distribution, in the same conventional manner as taught by Link, in order to best align each target point to its match found in the reference point registered from the scanned object, so as to filtering out artifacts in the connected point clouds from the scanned object. See paras. 186-187 of Link.
Claim 14 is rejected under the same rationale as claim 5.
Claim 15 is rejected under the same rationale as claim 7.
Conclusion
8. The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
Levinson et al. (US 20170248963) discloses systems and methods for autonomous vehicles and associated mechanical, electrical and electronic hardware, computer software and systems, and wired and wireless network communications to provide map data for autonomous vehicles. In particular, a method may include accessing subsets of multiple types of sensor data, aligning subsets of sensor data relative to a global coordinate system based on the multiple types of sensor data to form aligned sensor data, and generating datasets of three-dimensional map data. The method further includes detecting a change in data relative to at least two datasets of the three-dimensional map data and applying the change in data to form updated three-dimensional map data. The change in data may be representative of a state change of an environment at which the sensor data is sensed. The state change of the environment may be related to the presence or absences of an object located therein.
9. Any inquiry concerning this communication or earlier communications from the examiner should be directed to WESNER SAJOUS whose telephone number is (571) 272-7791. The examiner can normally be reached on M-F 10:00 TO 7:30 (ET).
Examiner interviews are available via telephone 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 or email the Examiner directly at wesner.sajous@uspto.gov.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Said Broome can be reached on 571-272-2931. 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. 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. 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.
/WESNER SAJOUS/Primary Examiner, Art Unit 2612
WS
09/18/2026
Prosecution Insights