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 .
DETAILED ACTION
Response to Amendment
The amendment filed 12/17/2025 has been entered.
Claims 2, 10, 12, and 13 have been cancelled.
Claims 1, 3, 11, and 14 have been amended.
Claims 1, 3-9, 11, and 14-20 remain pending within the application.
The amendments filed 12/17/2025 are sufficient to overcome the 35 U.S.C. 101 rejections of claims 1, 3-9, 11, and 14-20. The previous rejections have been withdrawn.
Response to Arguments
Argument 1, regarding the 101 rejections, applicant argues that the rejections should be withdrawn in view of Claim amendments. Examiner agrees. The 101 rejections have been withdrawn.
Argument 2, regarding the prior art rejections, applicant argues that none of the cited art teaches “wherein the convolutional neural network constructs a grid representation of the driving environment by converting the occupancy grid (OG) into an image representation, where the grid cells of the occupancy grid (OG) are coded as image pixels”. Applicant argues the cited portion of Socher is directed towards processing training data with a CNN and does not convert the occupancy grid into an image representation and parsing of the occupancy grid in real-time with the CNN to determine a driving context. Examiner respectfully disagrees because Socher recites manipulating data, including normalizing data to a particular size or number of pixels or voxels, level of granularity, image format (Socher, para [0041], images are in pixels or voxels). Under the broadest reasonable interpretation changing the data format to an image format and manipulating the pixel count may be interpreted as converting data into an image representation, where the data is coded as image pixels.
The full prior art rejections are outlined below.
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.
Claim(s) 1-3, 7-8, and 11, 14, and 18-19 are rejected under 35 U.S.C. 103 as being unpatentable over Natroshvili United States Patent Application Publication US 2019/0047439 in view of Socher International Application Publication WO 2017/031088.
Regarding claim 1, Natroshvili discloses a method for a driving assistance system and determining a driving context of a vehicle (Natroshvili, para [0025], autonomous vehicle), the method comprising:
- receiving sensor data (SD) of one or more sensors of the vehicle (Natroshvilli, para [0037], radar or lidar sensors detects represents receiving data);
- determining an occupancy grid (OG) in real-time based on the sensor data (SD), wherein grid cells of the occupancy grid (OG) represent an occupancy probability (Natroshvilli, para [0037], detected information from sensors used to generate occupancy grid; Natroshvilli, para [0039], generates and stores occupancy grid); and
- parsing the occupancy grid (OG) in real-time for determining the driving context (Natroshvilli, para [0101-105], with regards to fig 11, steps to parse and update occupancy grid with driver’s current position, current position represents a driving context);
-using the driving context to select a driving strategy (Natroshvili, para [0027], controller uses grid environmental information for steering direction and speed); and
- operating a control system of the vehicle utilizing the driving strategy (Natroshvili, para [0027], “The controller 104 of the automatic vehicle 104 may be configured to control the direction and speed of the automatic vehicle 104.”).
Natroshvili does not disclose :
- parsing the occupancy grid (OG) in real-time with a convolutional neural network for determining the driving context, wherein the convolutional neural network constructs a grid representation of the driving environment by converting the occupancy grid (OG) into an image representation, where the grid cells of the occupancy grid (OG) are coded as image pixels.
Socher discloses:
- parsing the occupancy grid (OG) in real-time with a convolutional neural network (Socher, para [0082], uses a CNN to analyze occupancy or curvature grid for characterization), wherein the convolutional neural network constructs a grid representation of the driving environment by converting the occupancy grid (OG) into an image representation, where the grid cells of the occupancy grid (OG) are coded as image pixels (Socher, para [0041], images are in pixels or voxels. Manipulating data, including normalizing data to a particular size or number of pixels or voxels, level of granularity, image format).
Before the time of the effective filing date of the claimed invention, it would have been obvious to one of ordinary skill in the art to have modified the parsing to include a CNN. The motivation for doing so would have been to improve the utilization of resources such as power and memory (Socher, para [0002]).
Regarding claim 3, Natroshvili in view of Socher discloses the method according to claim 1. Natroshvili additionally discloses wherein the occupancy grid (OG) is constructed using the Dempster-Shafer theory (Natroshvili, para [0082], combines occupancy grids using the Dempster Shafer theory).
Regarding claim 7, Natroshvili in view of Socher discloses the method according to any of the preceding claims. Socher additionally discloses wherein the convolutional neural network comprises three fully connected layers linked to a final Softmax activation function for calculating driving context probabilities (Socher, para [0047], CNN uses softmax activation).
Regarding claim 8, Natroshvili in view of Socher discloses the method according to any of the preceding claims. Natroshvilli additionally discloses wherein the sensor data (SD) are at least one of Sonar data, Lidar data, and Radar data (Natroshvilli, para [0037], radar or lidar sensors detects represents receiving data).
Regarding claim 11, Natroshvili discloses an apparatus for determining a driving context of a vehicle, the apparatus comprising:
- an input interface for receiving sensor data (SD) of one or more sensors of the vehicle (Natroshvilli, para [0037], radar or lidar sensors detects represents receiving data);
- a processor for determining an occupancy grid (OG) in real-time based on the sensor data (SD), wherein grid cells of the occupancy grid (OG) represent an occupancy probability (Natroshvilli, para [0037], detected information from sensors used to generate occupancy grid; Natroshvilli, para [0039], generates and stores occupancy grid); and
- parsing the occupancy grid (OG) in real-time for determining the driving context (Natroshvilli, para [0101-105], with regards to fig 11, steps to parse and update occupancy grid with driver’s current position, current position represents a driving context);
-an electronic controller that uses the driving context to select a driving strategy (Natroshvili, para [0027], controller uses grid environmental information for steering direction and speed) and operates a control system of the vehicle utilizing the driving strategy (Natroshvili, para [0027], “The controller 104 of the automatic vehicle 104 may be configured to control the direction and speed of the automatic vehicle 104.”).
Natroshvili does not disclose :
- parsing the occupancy grid (OG) in real-time with a convolutional neural network for determining the driving context, wherein the convolutional neural network constructs a grid representation of the driving environment by converting the occupancy grid (OG) into an image representation, where the grid cells of the occupancy grid (OG) are coded as image pixels.
Socher discloses:
- parsing the occupancy grid (OG) in real-time with a convolutional neural network (Socher, para [0082], uses a CNN to analyze occupancy or curvature grid for characterization), wherein the convolutional neural network constructs a grid representation of the driving environment by converting the occupancy grid (OG) into an image representation, where the grid cells of the occupancy grid (OG) are coded as image pixels (Socher, para [0041], images are in pixels or voxels. Manipulating data, including normalizing data to a particular size or number of pixels or voxels, level of granularity, image format).
Before the time of the effective filing date of the claimed invention, it would have been obvious to one of ordinary skill in the art to have modified the parsing to include a CNN. The motivation for doing so would have been to improve the utilization of resources such as power and memory (Socher, para [0002]).
Regarding claim 14, it is substantially similar to claim 3 and thus similarly rejected.
Regarding claim 18, it is substantially similar to claim 7 and thus similarly rejected.
Regarding claim 19, it is substantially similar to claim 8 and thus similarly rejected.
Claim(s) 4 and 15 are rejected under 35 U.S.C. 103 as being unpatentable over Natroshvili United States Patent Application Publication US 2019/0047439 in view of Socher International Application Publication WO 2017/031088 in further view of Natroshvili_2 United States Patent Application Publication US 2019/0049580.
Regarding claim 4, Natroshvili in view of Socher discloses the method according to any of the preceding claims. Natroshvili in view of Socher does not disclose the additional limitations of claim 4.
Natroshvili_2 discloses wherein the occupancy information of the grid cells of the occupancy grid (OG) is gradually decreased over time (Natroshvili_2, para [0131], occupancy of a grid cell may substantially decreases with an increase of a distance of the location of the object detected by the sensor from a center of the grid cell. This would be over time because it would take time to travel the distance used).
Before the time of the effective filing date of the claimed invention, it would have been obvious to one of ordinary skill in the art to have modified information decrease based on the teachings of Natroshvili_2. The motivation for doing so would have been to improve the processing of sensor information (Natroshvili_2, para [0002]).
Regarding claim 15, it is substantially similar to claim 4 and thus similarly rejected.
Claim 5 and 16 are rejected under 35 U.S.C. 103 as being unpatentable over Natroshvili United States Patent Application Publication US 2019/0047439 in view of Socher International Application Publication WO 2017/031088 in further view of Huang United States Patent Application Publication US2018/0173571.
Regarding claim 5, Natroshvili in view of Socher discloses the method according to any of the preceding claims. Natroshvili in view of Socher does not disclose the additional limitations of claim 5.
Huang discloses the method according to any of the preceding claims, wherein the convolutional neural network (23) consists of a first convolutional layer with 48 kernels and a second convolutional layer with 96 kernels (Huang, para [0138], could be set to 48 or 96).
Before the time of the effective filing date of the claimed invention, it would have been obvious to one of ordinary skill in the art to have modified the convolutional layers. The motivation for doing so would have been to improve the latency and power consumption (Huang, para [0003]).
Regarding claim 16, it is substantially similar to claim 5 and thus similarly rejected.
Claim 6 and 17 are rejected under 35 U.S.C. 103 as being unpatentable over Natroshvili United States Patent Application Publication US 2019/0047439 in view of Socher International Application Publication WO 2017/031088 in further view of Huang United States Patent Application Publication US2018/0173571 as modified by “Artificial Neural Networks Implementation in Digital Signal Processing Courses” Sergey Vishnyakov, 2018 IV International Conference on Information Technologies in Engineering Education (Inforino), 23-26 October 2018.
Regarding claim 6, Natroshvili in view of Socher in further view of Huang discloses the method according to any of the preceding claims. Natroshvili in view of Socher in further view of Huang does not disclose the additional limitations of claim 5.
wherein the size of the convolution kernel is 9x9 for the first convolutional layer and 5x5 for the second convolutional layer (Vishnyakov, section IV A, CNN has a primary 9x9 layer and a secondary 5x5 layer).
Before the time of the effective filing date of the claimed invention, it would have been obvious to one of ordinary skill in the art to have modified the convolutional layers. The motivation for doing so would have been to improve computational cost (Vishnyakov, last paragraph of introduction).
Regarding claim 17, it is substantially similar to claim 6 and thus similarly rejected.
Claim 9 and 20 are rejected under 35 U.S.C. 103 as being unpatentable over Natroshvili United States Patent Application Publication US 2019/0047439 in view of Socher International Application Publication WO 2017/031088 in further view of Nehmadi United States Patent Application Publication US 2018/0232947.
Regarding claim 9, Natroshvili in view of Socher discloses the method according to any of the preceding claims. Natroshvili in view of Socher does not disclose the additional limitations of claim 9.
Nehmadi discloses wherein the driving context is one of inner city, motorway, and parking lot (Nehmadi, para [0166], highway, parking lot, or city road classification).
Before the time of the effective filing date of the claimed invention, it would have been obvious to one of ordinary skill in the art to have modified the context to include road context. The motivation for doing so would have been to increase capabilities for an autonomous vehicle (Nehmadi, para [0003]).
Regarding claim 20, it is substantially similar to claim 9 and thus similarly rejected.
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 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 ISHAN MOUNDI whose telephone number is (703)756-1547. The examiner can normally be reached 8:30 A.M. - 5 P.M..
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, Matthew Ell can be reached at (571) 270-3264. 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.
/I.M./Examiner, Art Unit 2141
/MATTHEW ELL/Supervisory Patent Examiner, Art Unit 2141
