公开(公告)号：US20210201145A1

公开(公告)日：2021-07-01

申请号：US17116138

申请日：2020-12-09

Applicant: NVIDIA Corporation

Inventor： Trung Pham ,  Berta Rodriguez Hervas ,  Minwoo Park ,  David Nister ,  Neda Cvijetic

IPC: G06N3/08 ,  G06N3/04 ,  G06K9/00 ,  G06T7/33 ,  B60W30/18

Abstract: In various examples, a three-dimensional (3D) intersection structure may be predicted using a deep neural network (DNN) based on processing two-dimensional (2D) input data. To train the DNN to accurately predict 3D intersection structures from 2D inputs, the DNN may be trained using a first loss function that compares 3D outputs of the DNN—after conversion to 2D space—to 2D ground truth data and a second loss function that analyzes the 3D predictions of the DNN in view of one or more geometric constraints—e.g., geometric knowledge of intersections may be used to penalize predictions of the DNN that do not align with known intersection and/or road structure geometries. As such, live perception of an autonomous or semi-autonomous vehicle may be used by the DNN to detect 3D locations of intersection structures from 2D inputs.

公开(公告)号：US11928822B2

公开(公告)日：2024-03-12

申请号：US17864026

申请日：2022-07-13

Applicant: NVIDIA Corporation

Inventor： Trung Pham ,  Berta Rodriguez Hervas ,  Minwoo Park ,  David Nister ,  Neda Cvijetic

IPC: G06T7/11 ,  G05B13/02 ,  G06F18/21 ,  G06F18/24 ,  G06N3/04 ,  G06N3/08 ,  G06T5/00 ,  G06T11/20 ,  G06V10/26 ,  G06V10/34 ,  G06V10/44 ,  G06V10/82 ,  G06V20/56 ,  G06V30/19 ,  G06V30/262

CPC classification number: G06T7/11 ,  G05B13/027 ,  G06F18/21 ,  G06F18/24 ,  G06N3/04 ,  G06N3/08 ,  G06T3/4046 ,  G06T5/002 ,  G06T11/20 ,  G06V10/267 ,  G06V10/34 ,  G06V10/454 ,  G06V10/82 ,  G06V20/56 ,  G06V30/19173 ,  G06V30/274 ,  G06T2207/20081 ,  G06T2207/20084 ,  G06T2207/30252 ,  G06T2210/12

Abstract: In various examples, live perception from sensors of a vehicle may be leveraged to detect and classify intersection contention areas in an environment of a vehicle in real-time or near real-time. For example, a deep neural network (DNN) may be trained to compute outputs—such as signed distance functions—that may correspond to locations of boundaries delineating intersection contention areas. The signed distance functions may be decoded and/or post-processed to determine instance segmentation masks representing locations and classifications of intersection areas or regions. The locations of the intersections areas or regions may be generated in image-space and converted to world-space coordinates to aid an autonomous or semi-autonomous vehicle in navigating intersections according to rules of the road, traffic priority considerations, and/or the like.

公开(公告)号：US12299892B2

公开(公告)日：2025-05-13

申请号：US18391276

申请日：2023-12-20

Applicant: NVIDIA Corporation

Inventor： Trung Pham ,  Berta Rodriguez Hervas ,  Minwoo Park ,  David Nister ,  Neda Cvijetic

IPC: G06T7/11 ,  G05B13/02 ,  G06F18/21 ,  G06F18/24 ,  G06N3/04 ,  G06N3/08 ,  G06T3/4046 ,  G06T5/70 ,  G06T11/20 ,  G06V10/26 ,  G06V10/34 ,  G06V10/44 ,  G06V10/82 ,  G06V20/56 ,  G06V30/19 ,  G06V30/262

Abstract: In various examples, live perception from sensors of a vehicle may be leveraged to detect and classify intersection contention areas in an environment of a vehicle in real-time or near real-time. For example, a deep neural network (DNN) may be trained to compute outputs—such as signed distance functions—that may correspond to locations of boundaries delineating intersection contention areas. The signed distance functions may be decoded and/or post-processed to determine instance segmentation masks representing locations and classifications of intersection areas or regions. The locations of the intersections areas or regions may be generated in image-space and converted to world-space coordinates to aid an autonomous or semi-autonomous vehicle in navigating intersections according to rules of the road, traffic priority considerations, and/or the like.

公开(公告)号：US20240282118A1

公开(公告)日：2024-08-22

申请号：US18323795

申请日：2023-05-25

Applicant: NVIDIA Corporation

Inventor： Yang ZHENG ,  Trung Pham ,  Minwoo Park

IPC: G06V20/58 ,  G06V10/764 ,  G06V10/774 ,  G06V10/82 ,  G06V20/56

CPC classification number: G06V20/58 ,  G06V10/764 ,  G06V10/774 ,  G06V10/82 ,  G06V20/588

Abstract: In various examples, one or more object detectors may regress bounding polygons for detected objects in systems (e.g., autonomous or semi-autonomous driving systems and applications) that provide object awareness, object identification, object avoidance, and/or object localization. The object detector may determine regression data representing a regressed polygon associated with a given shape of a detected object represented by classification data determined from a scene. The object detector may determine regression data for different regressed angles between different pairs of successive vertices of the regressed polygon and regressed lengths of vectors from a regressed geometric center of the regressed polygon to vertices of the regressed polygon. The object detector may generate, based at least in part on the regression data, a bounding shape for a detected object in the scene. In some embodiments, the object detector may be trained by deforming a regressed polygon to match a ground truth polygon.

公开(公告)号：US20240230339A1

公开(公告)日：2024-07-11

申请号：US18615894

申请日：2024-03-25

Applicant: NVIDIA Corporation

Inventor： Trung Pham ,  Hang Dou ,  Berta Rodriguez Hervas ,  Minwoo Park ,  Neda Cvijetic ,  David Nister

IPC: G01C21/26 ,  G06N3/04 ,  G06N3/08 ,  G06V10/44 ,  G06V10/46 ,  G06V10/764 ,  G06V10/82 ,  G06V20/56

CPC classification number: G01C21/26 ,  G06N3/04 ,  G06N3/08 ,  G06V10/454 ,  G06V10/462 ,  G06V10/764 ,  G06V10/82 ,  G06V20/56 ,  G06F2218/12

Abstract: In various examples, live perception from sensors of a vehicle may be leveraged to generate potential paths for the vehicle to navigate an intersection in real-time or near real-time. For example, a deep neural network (DNN) may be trained to compute various outputs—such as heat maps corresponding to key points associated with the intersection, vector fields corresponding to directionality, heading, and offsets with respect to lanes, intensity maps corresponding to widths of lanes, and/or classifications corresponding to line segments of the intersection. The outputs may be decoded and/or otherwise post-processed to reconstruct an intersection—or key points corresponding thereto—and to determine proposed or potential paths for navigating the vehicle through the intersection.

公开(公告)号：US12013244B2

公开(公告)日：2024-06-18

申请号：US16848102

申请日：2020-04-14

Applicant: NVIDIA Corporation

Inventor： Trung Pham ,  Hang Dou ,  Berta Rodriguez Hervas ,  Minwoo Park ,  Neda Cvijetic ,  David Nister

IPC: G05D1/00 ,  G01C21/26 ,  G06N3/04 ,  G06N3/08 ,  G06V10/44 ,  G06V10/46 ,  G06V10/764 ,  G06V10/82 ,  G06V20/56 ,  B60W30/18 ,  B60W60/00 ,  G06F18/2413 ,  G06N3/02 ,  G06N3/044 ,  G06N3/045 ,  G06N3/047 ,  G06N3/048 ,  G06N3/088 ,  G06N5/01 ,  G06N7/01 ,  G06N20/00 ,  G06N20/10 ,  G08G1/16

CPC classification number: G01C21/26 ,  G05D1/0083 ,  G05D1/0246 ,  G06N3/04 ,  G06N3/08 ,  G06V10/454 ,  G06V10/462 ,  G06V10/764 ,  G06V10/82 ,  G06V20/56 ,  G06F2218/12

Abstract: In various examples, live perception from sensors of a vehicle may be leveraged to generate potential paths for the vehicle to navigate an intersection in real-time or near real-time. For example, a deep neural network (DNN) may be trained to compute various outputs—such as heat maps corresponding to key points associated with the intersection, vector fields corresponding to directionality, heading, and offsets with respect to lanes, intensity maps corresponding to widths of lanes, and/or classifications corresponding to line segments of the intersection. The outputs may be decoded and/or otherwise post-processed to reconstruct an intersection—or key points corresponding thereto—and to determine proposed or potential paths for navigating the vehicle through the intersection.

公开(公告)号：US11897471B2

公开(公告)日：2024-02-13

申请号：US18162576

申请日：2023-01-31

Applicant: NVIDIA Corporation

Inventor： Sayed Mehdi Sajjadi Mohammadabadi ,  Berta Rodriguez Hervas ,  Hang Dou ,  Igor Tryndin ,  David Nister ,  Minwoo Park ,  Neda Cvijetic ,  Junghyun Kwon ,  Trung Pham

IPC: B60W30/18 ,  G06N3/08 ,  G08G1/01 ,  B60W30/095 ,  B60W60/00 ,  B60W30/09 ,  G06V20/56 ,  G06V10/25 ,  G06V10/764 ,  G06V10/80 ,  G06V10/82 ,  G06V20/70 ,  G06V10/75

CPC classification number: B60W30/18154 ,  B60W30/09 ,  B60W30/095 ,  B60W60/0011 ,  G06N3/08 ,  G06V10/25 ,  G06V10/751 ,  G06V10/764 ,  G06V10/803 ,  G06V10/82 ,  G06V20/56 ,  G06V20/588 ,  G06V20/70 ,  G08G1/0125

Abstract: In various examples, live perception from sensors of a vehicle may be leveraged to detect and classify intersections in an environment of a vehicle in real-time or near real-time. For example, a deep neural network (DNN) may be trained to compute various outputs—such as bounding box coordinates for intersections, intersection coverage maps corresponding to the bounding boxes, intersection attributes, distances to intersections, and/or distance coverage maps associated with the intersections. The outputs may be decoded and/or post-processed to determine final locations of, distances to, and/or attributes of the detected intersections.

公开(公告)号：US11436837B2

公开(公告)日：2022-09-06

申请号：US16911007

申请日：2020-06-24

Applicant: NVIDIA Corporation

Inventor： Trung Pham ,  Berta Rodriguez Hervas ,  Minwoo Park ,  David Nister ,  Neda Cvijetic

IPC: G06V20/56 ,  G06N3/04 ,  G06T5/00 ,  G06N3/08 ,  G05B13/02 ,  G06T3/40 ,  G06T7/11 ,  G06T11/20 ,  G06K9/62 ,  G06V30/262

Abstract: In various examples, live perception from sensors of a vehicle may be leveraged to detect and classify intersection contention areas in an environment of a vehicle in real-time or near real-time. For example, a deep neural network (DNN) may be trained to compute outputs—such as signed distance functions—that may correspond to locations of boundaries delineating intersection contention areas. The signed distance functions may be decoded and/or post-processed to determine instance segmentation masks representing locations and classifications of intersection areas or regions. The locations of the intersections areas or regions may be generated in image-space and converted to world-space coordinates to aid an autonomous or semi-autonomous vehicle in navigating intersections according to rules of the road, traffic priority considerations, and/or the like.

公开(公告)号：US20200341466A1

公开(公告)日：2020-10-29

申请号：US16848102

申请日：2020-04-14

Applicant: NVIDIA Corporation

Inventor： Trung Pham ,  Hang Dou ,  Berta Rodriguez Hervas ,  Minwoo Park ,  Neda Cvijetic ,  David Nister

IPC: G05D1/00 ,  G06N3/08 ,  G06N3/04 ,  G06K9/00 ,  G05D1/02

Abstract: In various examples, live perception from sensors of a vehicle may be leveraged to generate potential paths for the vehicle to navigate an intersection in real-time or near real-time. For example, a deep neural network (DNN) may be trained to compute various outputs—such as heat maps corresponding to key points associated with the intersection, vector fields corresponding to directionality, heading, and offsets with respect to lanes, intensity maps corresponding to widths of lanes, and/or classifications corresponding to line segments of the intersection. The outputs may be decoded and/or otherwise post-processed to reconstruct an intersection—or key points corresponding thereto—and to determine proposed or potential paths for navigating the vehicle through the intersection.

公开(公告)号：US12286115B2

公开(公告)日：2025-04-29

申请号：US17116138

申请日：2020-12-09

Applicant: NVIDIA Corporation

Inventor： Trung Pham ,  Berta Rodriguez Hervas ,  Minwoo Park ,  David Nister ,  Neda Cvijetic

IPC: B60W30/18 ,  G06N3/04 ,  G06N3/08 ,  G06T7/33 ,  G06V10/764 ,  G06V10/82 ,  G06V20/56 ,  G06V20/64 ,  G06N3/045

Abstract: In various examples, a three-dimensional (3D) intersection structure may be predicted using a deep neural network (DNN) based on processing two-dimensional (2D) input data. To train the DNN to accurately predict 3D intersection structures from 2D inputs, the DNN may be trained using a first loss function that compares 3D outputs of the DNN—after conversion to 2D space—to 2D ground truth data and a second loss function that analyzes the 3D predictions of the DNN in view of one or more geometric constraints—e.g., geometric knowledge of intersections may be used to penalize predictions of the DNN that do not align with known intersection and/or road structure geometries. As such, live perception of an autonomous or semi-autonomous vehicle may be used by the DNN to detect 3D locations of intersection structures from 2D inputs.