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 .
Continued Examination Under 37 CFR 1.114
A request for continued examination under 37 CFR 1.114, including the fee set forth in 37 CFR 1.17(e), was filed in this application after final rejection. Since this application is eligible for continued examination under 37 CFR 1.114, and the fee set forth in 37 CFR 1.17(e) has been timely paid, the finality of the previous Office action has been withdrawn pursuant to 37 CFR 1.114. Applicant's submission filed on 5/18/2026 has been entered.
Response to Amendment
Status of claims: Claims 1-2, 4- 12, and 14-20 are pending. Claims 1, 2, 4, 10, 11, 12 14, and 20 are amended. Claims 3 and 13 are canceled.
Response to Arguments
Applicant’s arguments, see “Remarks”, filed 5/18/2026, with respect to rejection of claims 1-3, 5-8, 10-13, 15-18, and 20 under 35 U.S.C. §102 as being anticipated by U.S. Publication No. 2021/0042535 ("Abbott et al") have been fully considered and are persuasive. The rejection has been withdrawn. However, upon further considerations and updated searches, claims 1-2, 4- 12, and 14-20 are rejected based on new grounds of rejection in view of US-20210172756-A1 (Wheeler) and US-20220215603-A1 (Goldman).
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.
This application currently names joint inventors. In considering patentability of the claims the examiner presumes that the subject matter of the various claims was commonly owned as of the effective filing date of the claimed invention(s) absent any evidence to the contrary. Applicant is advised of the obligation under 37 CFR 1.56 to point out the inventor and effective filing dates of each claim that was not commonly owned as of the effective filing date of the later invention in order for the examiner to consider the applicability of 35 U.S.C. 102(b)(2)(C) for any potential 35 U.S.C. 102(a)(2) prior art against the later invention.
Claims 1-2, 4- 12, and 14-20 are rejected under 35 U.S.C. 103 as being unpatentable over US-20210042535-A1 (Abbott) in view of US-20210172756-A1 (Wheeler) and US-20220215603-A1 (Goldman).
Regarding claim 1, Abbott teaches receiving sensor/image data from a vehicle, detecting an object in an image, generating a bounding shape or object fence for the object, receiving lane data, generating a lane mask, determining overlap between the object fence and one or more lanes defined by the lane mask, and assigning the object to at least one lane based on the overlap. See Abbott, FIG. 1 (sensor data 102, object detection 104, free space detection 106, fence generation 108, object fence 110, lane detection 112, lane triangulation 114, lane mask 116, overlap determination 118, lane assignment 120); FIG. 3 (blocks B302-B314); FIG. 5 (blocks B502-B514); FIGS. 7A-8; paragraphs [0003], [0007], [0027]-[0032], [0068]-[0074]. Abbott therefore teaches much of the claimed limitations of obtaining image data, identifying an object, generating a bounding shape, generating lane data, and determining lane overlap for assignment. However, Abbott does not expressly teach the full claim recitation of “the image data includes a digital image of a roadway as a digital representation of imagery in a field-of-view of the camera including an operational environment with one or more objects and a roadway having a plurality of lanes,” nor does Abbott expressly teach the claimed combination of “generating a plurality of segments of the image data, the digital image segmented into the plurality of segments, the plurality of segments including at least one of i) image segments of the vehicle or ii) a lane of the plurality of lanes, each image segment of the vehicle containing a portion of the vehicle in the image data, each image segment of the vehicle including a plurality of pixels contained within the bounding box,” and the claimed limitation of “detecting the lane containing at least a portion of the vehicle in response to determining that at least one image segment of the vehicle overlaps the lane in the image data of the roadway.” Wheeler teaches lane-line creation from camera imagery, including identifying lane-line points, generating a 3D representation of lane-line points, grouping those points into clusters, locating center lines, and connecting cluster centers into a complete lane line. See Wheeler, FIG. 28A (lane line module 460), FIG. 28B (lane line creation process), FIGS. 31B-31C (2D-to-3D mapping), FIGS. 32A-32F (clustering and skeleton point analysis), FIGS. 33A-33H (center-line polyline generation and outlier removal), FIGS. 34A-34C (lane connection), FIGS. 36-37 (lane element graph and lane cuts), and paragraphs [0156]-[0181], [0186]-[0193], [0212]-[0224], [0230]. Wheeler therefore teaches lane segmentation and lane geometry generation from vehicle camera imagery in a manner that would have been useful to refine Abbott’s lane-mask and lane-assignment process.
At the time of effective filing of the present application, it would have been obvious to combine Abbott with Wheeler because both references address the same general problem of identifying lanes and objects in a vehicle environment, and Wheeler’s lane-line clustering and centerline extraction would predictably improve Abbott’s lane-mask generation and lane-overlap analysis by providing more accurate lane geometry and lane boundaries. Under KSR, combining familiar elements according to known methods to yield predictable results is obvious, and here the combination merely uses known lane geometry extraction to improve object-to-lane assignment.
Goldman further teaches accessing a map representative of a road segment, including one or more splines representative of road features, localizing a host vehicle relative to a drivable path represented among the splines, and determining points associated with the splines based on the localization of the host vehicle. See Goldman, FIG. 8 (sparse map), FIGS. 9A-9B (road geometry/polynomial representation), FIGS. 11A-11D (trajectories and landmarks), FIGS. 24E-25D (mapped lane marks and localization correction), FIGS. 43-47 (electronic horizon / splines / points on splines), and paragraphs [0003], [0061], [0096]-[0097], [0525]-[0560], [0585]-[0614]).
At the time of effective filing of the present application, it would have been obvious to combine Abbott in view of Wheeler with Goldman because Goldman supplies map-based localization and spline-based drivable-path representation, which would predictably enhance Abbott’s image-based lane assignment by relating the detected vehicle and lane data to a vehicle-centered roadway model. Again under KSR, the combination is a predictable use of prior art elements to improve accuracy and robustness in autonomous driving. In combination, Abbott, Wheeler, and Goldman teach or render obvious the full scope of claim 1 because Abbott supplies the object-fence/lane-mask overlap assignment workflow, Wheeler supplies lane-line segmentation, clustering, and complete lane-line formation from camera imagery, and Goldman supplies roadway splines, vehicle-relative localization, and map-based lane/path context. Taken together as a whole, the references teach receiving roadway image data, identifying a vehicle and lanes in the image, generating vehicle image segments within a bounding box, determining overlap between vehicle pixels and lane pixels, and detecting the lane containing at least a portion of the vehicle based on that overlap, as claimed.
Regarding claim 11, which recites a system that corresponds to and parallels method claim 1. Therefore, the rejection of claim 1 is fully incorporated herein. Abbott also teaches a system (Fig. 1 and Summary of the Invention).
Regarding claim 2, Abbott does not expressly teach “determining an object position of the object in the image data relative to the autonomous vehicle, the object position including a predicted distance and a predicted angle relative to the autonomous vehicle” in the exact claimed manner. Goldman teaches vehicle localization relative to a drivable path, determining points associated with splines based on vehicle localization, and generating navigation information tied to predicted vehicle position along road geometry. See Goldman, FIGS. 25B-25D, FIGS. 43-47, paragraphs [0256]-[0258], [0581]-[0599], [0600]-[0614]. At the time of effective filing of the present application, it would have been obvious to combine Abbott in view of Wheeler with Goldman because Goldman’s vehicle-relative localization and predicted path/point outputs would predictably improve Abbott’s lane-assignment system by providing distance/angle context for the object. Under KSR, using known localization techniques to refine a known lane-assignment workflow is a predictable combination of prior art elements.
Regarding claim 4, Abbott does not expressly teach “for each portion of the vehicle, generating the bounding box for the portion of the vehicle in the image data” in the exact claim wording. Abbott itself, however, already discloses cropping the bounding shape to more closely approximate the vehicle footprint, which is similar technical concept. However, Goldman and Wheeler both rely on precise map/image geometry and feature segmentation in vehicle environments. See Goldman FIG. 25A-25D; Wheeler FIGS. 31B-33H. It would have been obvious under KSR to generate bounding boxes for vehicle portions to improve footprint accuracy and reduce false lane overlap using known bounding boxes techniques to yield predictable result.
Regarding claim 5, Abbott teaches lane detection and lane mask generation, but does not expressly teach applying “a lane label associated with the particular lane and indicating a lane index value for each driving lane” in the exact claimed wording. Wheeler teaches lane elements, lane graphs, lane topology, lane connections, lane boundaries, and lane-element graph construction. See Wheeler, FIGS. 35-43, paragraphs [0186]-[0204], [0488]-[0493]. Goldman also teaches lane assignment information, ego lane references, and lane indexing relative to the host vehicle. See Goldman, FIGS. 33-34, FIG. 38, FIG. 47, paragraphs [0498]-[0500], [0611]-[0614]. It would have been obvious to combine Abbott with Wheeler and Goldman because lane indexing and labeling are routine ways of organizing lane geometry once lanes are detected. Under KSR, adding lane labels and indices to known lane masks yields predictable results for vehicle navigation and planning. Together, the references teach claim 5 because Abbott supplies the detected lanes and Wheeler/Goldman supply lane indexing and labeling.
Regarding claim 6, Abbott teaches object detection and assignment of the object to lanes based on overlap. However, Abbott does not expressly teach “applying to the image data a vehicle object label indicating a lane index value for the driving lane having the vehicle and lane information for the vehicle” in the exact claim form. Goldman teaches lane assignment information associated with a vehicle’s ego lane and neighboring lanes, and lane-topology information suitable for labeling vehicle context. See Goldman, FIGS. 33-34, FIG. 47, paragraphs [0498]-[0500], [0611]-[0614]. Wheeler further teaches lane element graphs and lane connectivity suitable for associating objects with lane indices. It would have been obvious under KSR to attach lane-index labels to detected vehicles once the vehicle’s lane has been determined, because such labels are a predictable implementation detail that supports downstream planning. In combination, the references teach claim 6 because Abbott determines the lane and Goldman/Wheeler provide the lane-index annotation framework.
Regarding claim 7, Abbott teaches comparing object-fence pixels to lane-mask pixels to determine overlap, but it does not expressly teach “comparing location information in a vehicle object associated with the image segment of the vehicle against lane location information in a lane label associated with the lane” using the exact claim language. Goldman teaches determining a host vehicle’s position relative to mapped lane features and comparing observed image positions to expected image positions of mapped landmarks. See Goldman, FIGS. 25B-25D, FIG. 47, paragraphs [0357]-[0362], [0607]-[0614]. Wheeler also teaches lane-center and lane-boundary geometry that can be used to characterize lane location. It would have been obvious to combine Abbott with Goldman and Wheeler because comparing vehicle location to lane location is a predictable way to refine lane assignment and support navigation. Under KSR, the combination merely applies known location-comparison techniques to Abbott’s overlap-based system. The references in combination teach claim 7 because Abbott supplies the object-lane overlap, and Goldman/Wheeler supply explicit lane-location comparison.
Regarding claim 8, Abbott expressly teaches comparing pixels of the object fence with pixels of the lane mask and determining overlap. See Abbott, FIG. 7A-7B, FIG. 8, paragraphs [0058]-[0062], [0089]-[0097].
Regarding claim 9, Abbott teaches detecting objects in image data, but it does not expressly teach “predicting an object class by applying an object recognition engine on a single frame” in the exact wording of the claim. Goldman teaches image-based recognition and road-feature analysis from captured images, and Wheeler teaches deep-learning-based lane/feature detection from images. See Goldman, FIGS. 5A-5D; Wheeler, FIGS. 28A-31C. It would have been obvious to use a single-frame object recognition engine to classify a detected object because single-frame object classification is a routine and predictable implementation of Abbott’s object detection pipeline. Under KSR, applying known recognition engines to a single frame to classify objects is a straightforward substitution of known image-processing techniques. Together, the references teach claim 9 because Abbott provides the detected object, and Goldman/Wheeler supply the object-recognition/classification techniques.
Regarding claim 10, Abbott discloses multiple sensor modalities but does not expressly teach “obtaining the image data from a plurality of cameras of the autonomous vehicle” in the exact claimed wording. Goldman expressly teaches multi-camera vehicle configurations, including stereo, wide-view, surround, and long-range cameras. See Goldman, FIGS. 2A-2F, FIGS. 9A-9C, paragraphs [0103]-[0139]. It would have been obvious to use multiple cameras in Abbott’s system to improve lane detection, object detection, and overlap-based lane assignment, because multiple viewpoints predictably improve robustness and coverage. Under KSR, combining multiple camera feeds for a known autonomous-driving perception task is a routine and predictable design choice. The references in combination teach claim 10 because Goldman supplies the plurality of cameras and Abbott supplies the lane-assignment framework.
Claim 12 corresponds to and parallels claim 2 and rejected on similar ground.
Claim 14 corresponds to and parallels claim 4 and rejected on similar ground.
Claim 15 corresponds to and parallels claim 5 and rejected on similar ground.
Claim 16 corresponds to and parallels claim 6 and rejected on similar ground.
Claim 17 corresponds to and parallels claim 7 and rejected on similar ground.
Claim 18 corresponds to and parallels claim 8 and rejected on similar ground.
Claim 19 corresponds to and parallels claim 9 and rejected on similar ground.
Claim 20 corresponds to and parallels claim 10 and rejected on similar ground.
Contact Information
Any inquiry concerning this communication or earlier communications from the examiner should be directed to VU LE whose telephone number is (571)272-7332. The examiner can normally be reached M-F 8:00 - 17:00.
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 can be reached at 2-7332. 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.
/VU LE/Supervisory Patent Examiner, Art Unit 2668
Prosecution Insights