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 .
Response to Arguments
Applicant’s arguments filed 17 March 2026, have been fully considered. Claims 1-12 are pending. Claims 1 and 7 have been amended.
Applicant’s efforts to overcome the rejections under 35 USC 101 are satisfactory. The additions of a LiDAR sensor, a vehicle, and controlling the vehicle’s driving based on a result of the clustering integrate the judicial exceptions into a practical application of the invention.
Applicant’s arguments concerning the prior art rejections have been considered. However, new grounds of rejection have been given. See 103 rejections below.
Claim Objections
Claim 1 is objected to because of the following informalities: “around of a vehicle” should be replaced with “around a vehicle”. Appropriate correction is required.
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.
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 1-3, 5-9, and 11-12 are rejected under 35 U.S.C. 103 as being unpatentable over Chen (US 20210026355 A1) in view of Kirillov (“Panoptic Segmentation”).
Regarding claim 1, Chen discloses a method for clustering point cloud data (Abstract: “A deep neural network(s) (DNN) may be used to perform panoptic segmentation by performing pixel-level class and instance segmentation of a scene”; ¶37: the sensor data can be point cloud data, as from LIDAR) which is performed by a processor executing instructions stored in a non-transitory computer-readable storing medium (¶31: “various functions may be carried out by a processor executing instructions stored in memory”), the method comprising:
obtaining, by a LiDAR sensor, point cloud data (see ¶37 as referenced above) for objects around of a vehicle while the vehicle travels on a road (Abstract: The invention is used to plan a safe path for controlling an autonomous vehicle (AV); ¶22: the systems and methods detect the environment around an AV; ¶33: LiDAR may perform the detection of the environment around the “ego-object” which may be the AV; see Fig. 10A);
identifying, by the processor, a class of each point data of the point cloud data (Abstract: the DNN performs pixel-level class segmentation); and
controlling the vehicle for driving on the road based on a result of the classes (Abstract).
Chen does not explicitly disclose the remaining limitations.
Kirillov teaches that panoptic segmentation uses semantic segmentation to separate a scene into classes, then clusters on each class to find instances of a given class (See Fig. 1; Also pg. 3, under “Task format” in Section 3: all pixels
i
are mapped to a pair
(
l
i
,
z
i
)
where
l
i
represents a semantic class and
z
i
refers to an instance id. “The
z
i
’s group pixels of the same class into distinct segments.” Note that, given
L
semantic classes, all pixels can be separated into
L
“virtual layers” as demonstrated by assigning each pixel to the space
L
×
N
where N is the number of instances and
L
is the number of semantic classes).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the invention to incorporate the teachings of Kirillov with the invention of Chen by assigning class according to a semantic segmentation processing of the point cloud data;
storing, by the processor, each point data of the point cloud data in a layer of virtual layers, which is associated with the class assigned to each point data;
clustering the point cloud data separately by class by clustering, by the processor, a plurality of point data stored in each of the virtual layers separately across layers; and
controlling the vehicle for driving on the road based on a result of the clustering.
Doing so would implement a known method of panoptic segmentation.
Regarding claim 7, the method of claim 1 is recited in claim 7, and rationale for rejecting these limitations are found in the rejection of claim 1. Regarding the other limitations, Chen discloses an interface (¶33 the AV system) configured to receive point cloud data from a LiDAR sensor of a vehicle (¶33 and Fig. 10A, a LiDAR may be used with the AV); and a processor configured to be electrically connected to or communicatively connected to the interface (¶31: a processor can carry out various functions; ¶137: the vehicle may include a processor).
Regarding claims 2 and 8, Chen in view of Kirillov teaches the limitations of claims 1 and 7, respectively, and further teaches that the semantic segmentation processing of the point cloud data is performed through a pre-trained deep learning network model (Chen, Abstract; the model is be pre-trained to perform its intended function since it is a machine learning model).
Regarding claims 3 and 9, Chen in view of Kirillov teaches the limitations of claims 1 and 7, respectively, and further teaches that storing the plurality of point data in the virtual layers includes/the processor is further configured to perform:
associating the plurality of point data with predetermined groups (groups defined by one of the
L
classes) based on the class assigned to each point data (by definition), the predetermined groups each associated with the at least one class (again by definition); and
storing the plurality of point data in the virtual layers based on a group to which each point data is associated (the “virtual layers” and groups are the class to which a particular point is assigned).
Regarding claims 5 and 11, Chen in view of Kirillov teaches the limitations of claims 1 and 7, respectively. Chen further teaches generating and outputting an occupancy grid of the location of other objects about a vehicle to inform a user (¶122).
It would have been obvious to one of ordinary skill in the art practicing the invention of Chen in view of Kirillov to generate a grid map for the plurality of point data, wherein the virtual layers are generated for each cell of the grid map. Doing so would inform a driver of the virtual map of its environment and the classifications and identifications of the DNN.
Regarding claims 6 and 12, Chen in view of Kirillov teaches the limitations of claims 5 and 11, respectively. While Chen in view of Kirillov does not explicitly teach the limitations of claims 6 and 12, it would have been obvious to one of ordinary skill in the art practicing the invention of Chen in view of Kirillov to cause the clustering of the plurality of point data to include grouping adjacent points of adjacent cells into one cluster for each of the virtual layers. This would enable one to group objects of a particular class extending over multiple contiguous cells into a single cluster.
Allowable Subject Matter
Claims 4 and 10 are objected to as being dependent upon a rejected base claim, but would be allowable if rewritten in independent form including all of the limitations of the base claim and any intervening claims.
Regarding claims 4 and 10, Chen in view of Kirillov teaches the limitations of claims 3 and 9, respectively. However, the prior art of record does not fairly suggest defining the predetermined groups to specifically include a dynamic-object group, a stationary-structure group, a drivable-area-of-a-vehicle group, and an others group for the reasons given in the previous Office action. Therefore, claims 4 and 10 are considered patentably distinguishable from the prior art of record.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure. Liang (US 20210150410 A1) teaches the use of machine learning with autonomous vehicles for environmental perception, and uses panoptic segmentation (see Abstract; ¶2, and ¶26).
Any inquiry concerning this communication or earlier communications from the examiner should be directed to ETHAN WESLEY EDWARDS whose telephone number is (571)272-0266. The examiner can normally be reached Monday - Friday, 7:30am-5pm.
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, Andrew Schechter can be reached at (571) 272-2302. 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.
ETHAN WESLEY EDWARDS
Examiner
Art Unit 2857
/E.W.E./ Examiner, Art Unit 2857
/ANDREW SCHECHTER/ Supervisory Patent Examiner, Art Unit 2857
Prosecution Insights