CTNF 18/898,873 CTNF 95410 DETAILED ACTION Notice of Pre-AIA or AIA Status 07-03-aia AIA 15-10-aia The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA. Information Disclosure Statement The information disclosure statement (IDS) submitted on September is in compliance with the provisions of 37 CFR 1.97. Accordingly, the information disclosure statement is considered by examiner. Claim Rejections - 35 USC § 112(b) 07-30-02 AIA The following is a quotation of 35 U.S.C. 112(b): (b) CONCLUSION.—The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the inventor or a joint inventor regards as the invention. The following is a quotation of 35 U.S.C. 112 (pre-AIA), second paragraph: The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the applicant regards as his invention. 07-34-01 Claim 13 is rejected under 35 U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA), second paragraph, as being indefinite for failing to particularly point out and distinctly claim the subject matter which the inventor or a joint inventor (or for applications subject to pre-AIA 35 U.S.C. 112, the applicant), regards as the invention. Claim 13 recites the preamble as “The second computer of claim 12” and should be “The system of claim 12” because the independent claim, claim 1, in which claim 12 and 13 each depend upon is “A system”. The limitation recited in the body of the claim of claim 13 is correct claim construction. Thus, Applicant has failed to particularly point out and distinctly claim the subject matter which the inventor or a joint inventor regards as the invention. For purposes of examination claim 13 will be interpreted as “The second computer system of claim 12”. No claims are dependent on claim 13. Claim Rejections - 35 USC § 103 07-06 AIA 15-10-15 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. 07-20-aia AIA 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. 07-21-aia AIA Claim s 1-3, 8, 14-16 are rejected under 35 U.S.C. 103 as being unpatentable over Yogamani et al (DaF-BEVSeg: Distortion-aware Fisheye Camera based Bird’s Eye View Segmentation with Occlusion Reasoning) in view of Swerdlow et al (Street-View Image Generation From a Bird’s Eye View Layout) . Regarding Claim 1, Yogamani et al teach a system (server; V. Experiments ¶ 1) , comprising: a computer that includes a processor and a memory (the server has four Nvidia Quadro RTX5000 GPUs; V. Experiments ¶ 1) , the memory including instructions executable by the processor (the server stores and executes the instructions to implement the DaF-BEVSeg model; Fig 3 and V. Experiments ¶ 1) to: transform fisheye images that include objects at first, second, and third angles into rectilinear images with a first image transformation (the multi-camera fisheye image inputs (images with objects at least first, second, third angles, are input to the multi-scale image features and depth distribution encoder to transform the images to a perspective view (PV) image, which lists a rectilinear model as a type of PV image; Fig 3 and III. Method ¶ 1, III.A. Fisheye Camera BEV features ¶ 2); and transform the rectilinear images into bird’s eye view images with a second image transformation (the PV image is modeled into a BEV projection; Fig 2, 3 and III.A. Fisheye Camera BEV features ¶ 3) . Yogamani et al does not teach to transform the bird’s eye view images into multiple images that include objects at multiple angles intermediate between the first, second, and third angles to generate a training dataset that includes ground truth regarding the objects at multiple angles with a third image transformation; and train a machine learning model with the training dataset. Swerdlow et al is analogous art pertinent to the technological problem addressed in the current application and teaches to transform the bird’s eye view images into multiple images that include objects at multiple angles intermediate between the first, second, and third angles (BEV images are encoded, processed with an autoregressive transformer and decoded to generate multiple synthetic street-view images based on multiple angle representations; Fig 1, 2 and III. Method ¶ 1-2) to generate a training dataset that includes ground truth regarding the objects at multiple angles with a third image transformation (a pairwise matrix to encode a given source image to the BEV/image token is generated and used to train the BEVGen model; Fig 2 and III.C Camera Bias, V. Applications – Data augmentation for BEV segmentation) ; and train a machine learning model with the training dataset (the BEVGen model is trained by incorporating the augmented samples and the synthetic instances are associated with the ground truth BEV layout for training; V. Applications – Data augmentation for BEV segmentation) . It would have been obvious to one of ordinary skill in the art before the effective filing date of the current application to combine the teachings of Yogamani et al with Swerdlow et al including to transform the bird’s eye view images into multiple images that include objects at multiple angles intermediate between the first, second, and third angles to generate a training dataset that includes ground truth regarding the objects at multiple angles with a third image transformation; and train a machine learning model with the training dataset. By generating street-view images from a bird’s-eye view layout, traffic scenarios can be identified at the semantic level to generate synthetic training data for perception models and to visualize safety-critical situations, thereby improving the data for training autonomous vehicles for safe operation, as recognized by Swerdlow et al (I. Introduction ¶ 1-2). Regarding Claim 2, Yogamani et al in view of Swerdlow et al teach the system of claim 1 (as described above), wherein the first image transformation is based on fisheye camera intrinsic parameters including fisheye distortion parameters (Yogamani et al, the fisheye images include camera intrinsics for distortion-aware transformations based on a radial distortion and inverse mappings; III.A Method Fisheye Camera BEV features ¶ 1) . Regarding Claim 3, Yogamani et al in view of Swerdlow et al teach the system of claim 1 (as described above), wherein the second image transformation is based on camera intrinsic parameters including (interpreted as at least one of the following and not all of the following parameters) focal length in x and y, optical center in x and y, magnification, optical center in x and y, and skew (Yogamani et al, the fisheye images include camera intrinsics for camera focal length with direction in x, y; III.A Method Fisheye Camera BEV features ¶ 1-2) . Regarding Claim 8, Yogamani et al in view of Swerdlow et al teach the system of claim 1 (as described above), wherein the machine learning model is a convolutional neural network (Yogamani et al, the DaF-BEVSeg model is interpreted as a CNN based on the use of the encoder – decoder structure and training; Fig 3 and III. Method) . Regarding Claim 14, Yogamani et al teach a method (method to implement the DaF-BEVSeg model; Fig 3 and III. Method ¶ 1, V. Experiments ¶ 1) , comprising: steps identical to claim 1 (as described above). Regarding Claim 15, Yogamani et al in view of Swerdlow et al teach the method of claim 14 (as described above), with further limitations identical to claim 2 (as described above). Regarding Claim 16, Yogamani et al in view of Swerdlow et al teach the method of claim 14 (as described above), with further limitations identical to claim 3 (as described above) . 07-21-aia AIA Claim s 4, 6, 12, 13, 17, 19 are rejected under 35 U.S.C. 103 as being unpatentable over Yogamani et al (DaF-BEVSeg: Distortion-aware Fisheye Camera based Bird’s Eye View Segmentation with Occlusion Reasoning) in view of Swerdlow et al (Street-View Image Generation From a Bird’s Eye View Layout) and Xiao et al (US 2025/0222950) . Regarding Claim 4, Yogamani et al in view of Swerdlow et al teach the system of claim 3 (as described above), including the second image transformation (Yogamani et al, the PV image is modeled into a BEV projection; Fig 2, 3 and III.A. Fisheye Camera BEV features ¶ 3) . Yogamani et al in view of Swerdlow et al do not teach wherein the second image transformation is based on camera extrinsic parameters including camera six degree of freedom pose. Xiao et al is analogous art pertinent to the technological problem addressed in the current application and teaches to wherein the second image transformation is based on camera extrinsic parameters including camera six degree of freedom pose (the vehicle sensor 126 can generate images to create top-down (BEV) images and includes an inertial measurement unit that can sense 6-degree-of-freedom movements; Fig 1-3 and ¶ [0030], [0032]). It would have been obvious to one of ordinary skill in the art before the effective filing date of the current application to combine the teachings of Yogamani et al in view of Swerdlow et al with Xiao et al including wherein the second image transformation is based on camera extrinsic parameters including camera six degree of freedom pose. By using a six degree of freedom sensor, the vehicle’s vertical movement may be tracked and analyzed for determining motion and orientation in 3D space, thereby improving measurements and orientation analysis of the vehicle, as recognized by Xiao et al (¶ [0032]). Regarding Claim 6, Yogamani et al in view of Swerdlow et al teach the system of claim 1 (as described above). Yogamani et al in view of Swerdlow et al do not teach wherein the first angle is 0 degrees, the second angle is 90 degrees, and the third angle is 180 degrees. Xiao et al is analogous art pertinent to the technological problem addressed in the current application and teaches wherein the first angle is 0 degrees, the second angle is 90 degrees, and the third angle is 180 degrees (the fisheye camera captures the surroundings of the environment to generate images used to create BEV images, with a standard fisheye camera lens capturing 180 degrees (see Kim et al in pertinent art below); ¶ [0048]-[0049]) . It would have been obvious to one of ordinary skill in the art before the effective filing date of the current application to combine the teachings of Yogamani et al in view of Swerdlow et al with Xiao et al including wherein the first angle is 0 degrees, the second angle is 90 degrees, and the third angle is 180 degrees. Furthermore, it would have been obvious to one of ordinary skill in the art that Xiao et al would include (“obvious to try” rationale for Prima Facie Case of Obviousness; see MPEP § 2143(I)(E)) the angles of 0 degrees, 90 degrees and 180 degrees as the fisheye image data converted to the bird’s eye view image data. By using the extreme angles (zero and 180 degrees) and a right angle (90) the fisheye image data is maximized for conversion to create a bird’s eye view for the full detection of objects in the field of view (180 degrees), thereby improving the comprehensive portrayal of a scene from multiple viewpoints with a clear understandings of depth to objects, as recognized by Xiao et al (¶ [0022]-[0024]). Regarding Claim 12, Yogamani et al in view of Swerdlow et al teach the system of claim 1 (as described above). Yogamani et al in view of Swerdlow et al do not teach wherein the trained machine learning model is included in a second computer for a vehicle wherein the second computer is programmed to operate the vehicle by determining a vehicle trajectory based on predictions output from the trained machine learning model. Xiao et al is analogous art pertinent to the technological problem addressed in the current application and teaches wherein the trained machine learning model is included in a second computer for a vehicle wherein the second computer is programmed to operate the vehicle by determining a vehicle trajectory based on predictions output from the trained machine learning model (a computing system 600 to implement the vehicle electronic control unit includes multiple processors in the processing circuitry 604 to implement the machine learning models to operate the sensors connected to a bus 602 and an engine control unit 616 for control of the vehicle, which may be based on the processed sensor data; Fig 6 and ¶ [0079]-[0082]) . It would have been obvious to one of ordinary skill in the art before the effective filing date of the current application to combine the teachings of Yogamani et al in view of Swerdlow et al with Xiao et al including wherein the trained machine learning model is included in a second computer for a vehicle wherein the second computer is programmed to operate the vehicle by determining a vehicle trajectory based on predictions output from the trained machine learning model. By using multiple processing circuitry, the processors may be specially-programmed to perform operations, thereby improving specific functionality and computing, while reducing failure of the entire vehicle through localized synchronized programming logic for operations, as recognized by Xiao et al (¶ [0079], [0085]-[0086]). Regarding Claim 13, Yogamani et al in view of Swerdlow et al and Xiao et al teach the system of claim 12 (as described above), wherein the second computer is programmed to operate the vehicle on the vehicle trajectory by commanding controllers to operate vehicle components (Xiao et al, the vehicle is operated by the engine control unit 616 to control the movement of the vehicle, for example, during a parking procedure (vehicle trajectory); ¶ [0081]) . Regarding Claim 17, Yogamani et al in view of Swerdlow et al teach the method of claim 16 (as described above), with further limitations identical to claim 4 (as described above). Regarding Claim 19, Yogamani et al in view of Swerdlow et al teach the method of claim 14 (as described above), with further limitations identical to claim 6 (as described above) . 07-21-aia AIA Claim s 5, 18 are rejected under 35 U.S.C. 103 as being unpatentable over Yogamani et al (DaF-BEVSeg: Distortion-aware Fisheye Camera based Bird’s Eye View Segmentation with Occlusion Reasoning) in view of Swerdlow et al (Street-View Image Generation From a Bird’s Eye View Layout), Xiao et al (US 2025/0222950) and Chen et al (US 2019/0335100) . Regarding Claim 5, Yogamani et al in view of Swerdlow et al and Xiao et al teach the system of claim 4 (as described above). Yogamani et al in view of Swerdlow et al and Xiao et al do not teach wherein the second image transformation includes an affine transformation that places a hitch ball at a predetermined location in the images. Chen et al is analogous art pertinent to the technological problem addressed in the current application and teaches wherein the second image transformation includes an affine transformation that places a hitch ball at a predetermined location in the images (camera extrinsic parameters include the coordinate system transformations (affine transformation) to position the trailer 200 and two vehicle 100 (at the coupler 212 and hitch 120 tow-ball 122 at a distance in a trained pattern (predetermined distance); Fig 4A-C, 6 7A-C) and ¶ [0068]-[0069]) . It would have been obvious to one of ordinary skill in the art before the effective filing date of the current application to combine the teachings of Yogamani et al in view of Swerdlow et al and Xiao et al with Chen et al including wherein the second image transformation includes an affine transformation that places a hitch ball at a predetermined location in the images. By using a trained pattern for the positioning of the hitch to the coupler, the trailer will be positioned to the tow vehicle in a given position consistently, thereby resulting in effective hitching the vehicle to trailer consistently, as recognized by Chen et al (¶ [0004]-[0006]). Regarding Claim 18, Yogamani et al in view of Swerdlow et al teach the method of claim 17 (as described above), with further limitations identical to claim 5 (as described above) . 07-21-aia AIA Claim s 9-11 are rejected under 35 U.S.C. 103 as being unpatentable over Yogamani et al (DaF-BEVSeg: Distortion-aware Fisheye Camera based Bird’s Eye View Segmentation with Occlusion Reasoning) in view of Swerdlow et al (Street-View Image Generation From a Bird’s Eye View Layout) and Chen et al (US 2019/0335100) . Regarding Claim 9, Yogamani et al in view of Swerdlow et al teach the system of claim 1 (as described above). Yogamani et al in view of Swerdlow et al do not teach wherein the objects include a trailer. Chen et al is analogous art pertinent to the technological problem addressed in the current application and teaches wherein the objects include a trailer (images data is of a tow vehicle 100 and trailer 200; Fig 1 and ¶ [0034]) . It would have been obvious to one of ordinary skill in the art before the effective filing date of the current application to combine the teachings of Yogamani et al in view of Swerdlow et al with Chen et al including wherein the objects include a trailer. By using a sensor system to generate image data on the back portion of a tow vehicle, a tow vehicle may be trained to autonomously maneuver towards the location of interest in real-world coordinates, thereby assisting in hitching a vehicle to a trailer, as recognized by Chen et al (¶ [0004]-[0006]). Regarding Claim 10, Yogamani et al in view of Swerdlow et al teach the system of claim 1 (as described above). Yogamani et al in view of Swerdlow et al do not teach wherein the first, second and third angles are based on an angle of a trailer tongue with respect to a location of a hitch ball. Chen et al is analogous art pertinent to the technological problem addressed in the current application and teaches wherein the first, second and third angles are based on an angle of a trailer tongue with respect to a location of a hitch ball (fisheye images are of the tow-bar 214 and the tow vehicle hitch 120 and hitch ball 122 are used to generate top-down views ; Fig 1 and ¶ [0032]-[0034], [0036], [0041]) . It would have been obvious to one of ordinary skill in the art before the effective filing date of the current application to combine the teachings of Yogamani et al in view of Swerdlow et al with Chen et al including wherein the first, second and third angles are based on an angle of a trailer tongue with respect to a location of a hitch ball. By using fisheye images to generate the top-down image data used for a trailer detection system, the image data includes a wider range of visual data to more effectively and efficiently detect the trailer for effective hitching, as recognized by Chen et al (¶ [0004], [0010]-[0011]). Regarding Claim 11, Yogamani et al in view of Swerdlow et al and Chen et al teach the system of claim 10 (as described above), wherein the machine learning model is trained to determine a location and angle of the trailer tongue with respect to the location of the hitch ball (the images are used to determine the tow-bar 214, coupler 212 relationship within the images using the detection module 160 (DNN ¶ [0066]); Fig 1, 5A and ¶ [0038], [0059]) . Allowable Subject Matter 12-151-08 AIA 07-43 12-51-08 Claim s 7, 20 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. In each of claim 7, 20, the prior art did not readily teach in a non-obvious way the following limitations in combination (recited for claim 7 below and claimed in parallel for claim 7): 7. The system of claim 1, wherein the third image transformation is based on generating intermediate angle images at 10 degree increments between 0 degrees and 180 degrees. Conclusion 07-96 AIA The prior art made of record and not relied upon is considered pertinent to applicant's disclosure. Kim et al (Three-dimensional simulation method of fish-eye lens distortion for a vehicle backup rear-view camera) teach the use of fisheye lens used for vehicles rear-view camera, including the lens type including a field of view as 180 degrees. Choi (US 2023/0016304) teach a fisheye collage transformation for road object detection including detecting a plurality of objects at multiple angles. Sen et al (US 2025/0042416) teach a method and system for trailer angle estimation based on machine learning techniques. Any inquiry concerning this communication or earlier communications from the examiner should be directed to KATHLEEN M BROUGHTON whose telephone number is (571)270-7380. The examiner can normally be reached Monday-Friday 8:00-5:00. 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, John Villecco can be reached at (571) 272-7319. 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. /KATHLEEN M BROUGHTON/Primary Examiner, Art Unit 2661 Application/Control Number: 18/898,873 Page 2 Art Unit: 2661 Application/Control Number: 18/898,873 Page 3 Art Unit: 2661 Application/Control Number: 18/898,873 Page 4 Art Unit: 2661 Application/Control Number: 18/898,873 Page 5 Art Unit: 2661 Application/Control Number: 18/898,873 Page 6 Art Unit: 2661 Application/Control Number: 18/898,873 Page 7 Art Unit: 2661 Application/Control Number: 18/898,873 Page 8 Art Unit: 2661 Application/Control Number: 18/898,873 Page 9 Art Unit: 2661 Application/Control Number: 18/898,873 Page 10 Art Unit: 2661 Application/Control Number: 18/898,873 Page 11 Art Unit: 2661 Application/Control Number: 18/898,873 Page 12 Art Unit: 2661
Prosecution Insights