公开(公告)号：US12292495B2

公开(公告)日：2025-05-06

申请号：US17655783

申请日：2022-03-21

Applicant: NVIDIA CORPORATION

Inventor： Amir Akbarzadeh ,  Andrew Carley ,  Birgit Henke ,  Si Lu ,  Ivana Stojanovic ,  Jugnu Agrawal ,  Michael Kroepfl ,  Yu Sheng ,  David Nister ,  Enliang Zheng

IPC: G01S13/04 ,  B60W40/10 ,  B60W40/12 ,  B60W60/00 ,  G01S7/00 ,  G01S7/40 ,  G01S13/86 ,  G01S13/89 ,  G01S13/931 ,  G01S17/04 ,  G01S17/931 ,  G06T7/73 ,  G06V10/26 ,  G06V10/28

Abstract: One or more embodiments of the present disclosure relate to generation of map data. In these or other embodiments, the generation of the map data may include determining whether objects indicated by the sensor data are static objects or dynamic objects. Additionally or alternatively, sensor data may be removed or included in the map data based on determinations as to whether it corresponds to static objects or dynamic objects.

公开(公告)号：US20250083704A1

公开(公告)日：2025-03-13

申请号：US18958669

申请日：2024-11-25

Applicant: NVIDIA Corporation

Inventor： Julia Ng ,  Sachin Pullaikudi Veedu ,  David Nister ,  Hanne Buur ,  Hans Jonas Nilsson ,  Hon Leung Lee ,  Yunfei Shi ,  Charles Jerome Vorbach, Jr.

IPC: B60W60/00 ,  B60W30/095 ,  G06F9/50

Abstract: In various examples, a safety decomposition architecture for autonomous machine applications is presented that uses two or more individual safety assessments to satisfy a higher safety integrity level (e.g., ASIL D). For example, a behavior planner may be used as a primary planning component, and a collision avoidance feature may be used as a diverse safety monitoring component—such that both may redundantly and independently prevent violation of safety goals. In addition, robustness of the system may be improved as single point and systematic failures may be avoided due to the requirement that two independent failures—e.g., of the behavior planner component and the collision avoidance component—occur simultaneously to cause a violation of the safety goals.

公开(公告)号：US12249163B2

公开(公告)日：2025-03-11

申请号：US17234487

申请日：2021-04-19

Applicant: NVIDIA Corporation

Inventor： Josh Abbott ,  Miguel Sainz Serra ,  Zhaoting Ye ,  David Nister

IPC: G06K9/00 ,  G06T7/12 ,  G06T7/70 ,  G06T11/20 ,  G06V20/56

Abstract: In various examples, object fence corresponding to objects detected by an ego-vehicle may be used to determine overlap of the object fences with lanes on a driving surface. A lane mask may be generated corresponding to the lanes on the driving surface, and the object fences may be compared to the lanes of the lane mask to determine the overlap. Where an object fence is located in more than one lane, a boundary scoring approach may be used to determine a ratio of overlap of the boundary fence, and thus the object, with each of the lanes. The overlap with one or more lanes for each object may be used to determine lane assignments for the objects, and the lane assignments may be used by the ego-vehicle to determine a path or trajectory along the driving surface.

公开(公告)号：US12189018B2

公开(公告)日：2025-01-07

申请号：US17655778

申请日：2022-03-21

Applicant: NVIDIA CORPORATION

Inventor： Amir Akbarzadeh ,  Andrew Carley ,  Birgit Henke ,  Si Lu ,  Ivana Stojanovic ,  Jugnu Agrawal ,  Michael Kroepfl ,  Yu Sheng ,  David Nister ,  Enliang Zheng ,  Niharika Arora

IPC: G01S13/04 ,  B60W40/10 ,  B60W40/12 ,  B60W60/00 ,  G01S7/00 ,  G01S7/40 ,  G01S13/86 ,  G01S13/89 ,  G01S13/931 ,  G01S17/04 ,  G01S17/931 ,  G06T7/73 ,  G06V10/26 ,  G06V10/28

Abstract: One or more embodiments of the present disclosure relate to generating RADAR (RAdio Detection And Ranging) point clouds based on RADAR data obtained from one or more RADAR sensors disposed on one or more ego-machines. In these or other embodiments, the RADAR point clouds may be communicated to a distributed map system that is configured to generate map data based on the RADAR point clouds. In some embodiments of the present disclosure, certain compression operations may be performed on the RADAR point clouds to reduce the amount of data that is communicated from the ego-machines to the map system.

公开(公告)号：US20240403640A1

公开(公告)日：2024-12-05

申请号：US18799229

申请日：2024-08-09

Applicant: NVIDIA Corporation

Inventor： Yilin Yang ,  Bala Siva Sashank Jujjavarapu ,  Pekka Janis ,  Zhaoting Ye ,  Sangmin Oh ,  Minwoo Park ,  Daniel Herrera Castro ,  Tommi Koivisto ,  David Nister

IPC: G06N3/08 ,  B60W30/14 ,  B60W60/00 ,  G06F18/214 ,  G06V10/762 ,  G06V20/56

Abstract: In various examples, a deep neural network (DNN) is trained to accurately predict, in deployment, distances to objects and obstacles using image data alone. The DNN may be trained with ground truth data that is generated and encoded using sensor data from any number of depth predicting sensors, such as, without limitation, RADAR sensors, LIDAR sensors, and/or SONAR sensors. Camera adaptation algorithms may be used in various embodiments to adapt the DNN for use with image data generated by cameras with varying parameters—such as varying fields of view. In some examples, a post-processing safety bounds operation may be executed on the predictions of the DNN to ensure that the predictions fall within a safety-permissible range.

公开(公告)号：US20240400098A1

公开(公告)日：2024-12-05

申请号：US18674639

申请日：2024-05-24

Applicant: NVIDIA Corporation

Inventor： David Nister

IPC: B60W60/00

Abstract: Path planning may be performed under non-holonomic constraints based at least on discretizing and selectively analyzing a solution space using a graph that includes vertices corresponding to machine configurations in a configuration space, along with associated maneuver types used by the machine to traverse these configurations. The graph may include transition edges associating costs with machine transitions between maneuver types and maneuvers. One or more of the vertices may correspond to a transition state between maneuver types. In some examples, a maneuver type may be used as a transition state between maneuver types to reduce the vertices and edges of the graph. The graph may incorporate vertices and edges representing optimal maneuver types for traversing the configuration space, including longitudinally extremal and/or laterally extremal maneuvers based on machine models.

公开(公告)号：US20240362929A1

公开(公告)日：2024-10-31

申请号：US18767222

申请日：2024-07-09

Applicant: NVIDIA Corporation

Inventor： Josh Abbott ,  Miguel Sainz Serra ,  Zhaoting Ye ,  David Nister

IPC: G06V20/56 ,  G06T7/12 ,  G06T7/70 ,  G06T11/20

CPC classification number: G06V20/588 ,  G06T7/12 ,  G06T7/70 ,  G06T11/20 ,  G06T2207/20084 ,  G06T2207/20132 ,  G06T2207/30256 ,  G06T2210/12

Abstract: In various examples, object fence corresponding to objects detected by an ego-vehicle may be used to determine overlap of the object fences with lanes on a driving surface. A lane mask may be generated corresponding to the lanes on the driving surface, and the object fences may be compared to the lanes of the lane mask to determine the overlap. Where an object fence is located in more than one lane, a boundary scoring approach may be used to determine a ratio of overlap of the boundary fence, and thus the object, with each of the lanes. The overlap with one or more lanes for each object may be used to determine lane assignments for the objects, and the lane assignments may be used by the ego-vehicle to determine a path or trajectory along the driving surface.

公开(公告)号：US12131556B2

公开(公告)日：2024-10-29

申请号：US17234475

申请日：2021-04-19

Applicant: NVIDIA Corporation

Inventor： Josh Abbott ,  Miguel Sainz Serra ,  Zhaoting Ye ,  David Nister

IPC: G06T7/12 ,  G06T7/70 ,  G06T11/20 ,  G06V20/56

CPC classification number: G06V20/588 ,  G06T7/12 ,  G06T7/70 ,  G06T11/20 ,  G06T2207/20084 ,  G06T2207/20132 ,  G06T2207/30256 ,  G06T2210/12

Abstract: In various examples, object fence corresponding to objects detected by an ego-vehicle may be used to determine overlap of the object fences with lanes on a driving surface. A lane mask may be generated corresponding to the lanes on the driving surface, and the object fences may be compared to the lanes of the lane mask to determine the overlap. Where an object fence is located in more than one lane, a boundary scoring approach may be used to determine a ratio of overlap of the boundary fence, and thus the object, with each of the lanes. The overlap with one or more lanes for each object may be used to determine lane assignments for the objects, and the lane assignments may be used by the ego-vehicle to determine a path or trajectory along the driving surface.

公开(公告)号：US20240339035A1

公开(公告)日：2024-10-10

申请号：US18745370

申请日：2024-06-17

Applicant: NVIDIA Corporation

Inventor： Davide Marco Onofrio ,  Hae-Jong Seo ,  David Nister ,  Minwoo Park ,  Neda Cvijetic

IPC: G08G1/16 ,  G06F18/23 ,  G06N3/08 ,  G06V20/56

CPC classification number: G08G1/167 ,  G06F18/23 ,  G06N3/08 ,  G06V20/588

Abstract: In various examples, a path perception ensemble is used to produce a more accurate and reliable understanding of a driving surface and/or a path there through. For example, an analysis of a plurality of path perception inputs provides testability and reliability for accurate and redundant lane mapping and/or path planning in real-time or near real-time. By incorporating a plurality of separate path perception computations, a means of metricizing path perception correctness, quality, and reliability is provided by analyzing whether and how much the individual path perception signals agree or disagree. By implementing this approach—where individual path perception inputs fail in almost independent ways—a system failure is less statistically likely. In addition, with diversity and redundancy in path perception, comfortable lane keeping on high curvature roads, under severe road conditions, and/or at complex intersections, as well as autonomous negotiation of turns at intersections, may be enabled.

公开(公告)号：US12050285B2

公开(公告)日：2024-07-30

申请号：US17976581

申请日：2022-10-28

Applicant: NVIDIA Corporation

Inventor： Alexander Popov ,  Nikolai Smolyanskiy ,  Ryan Oldja ,  Shane Murray ,  Tilman Wekel ,  David Nister ,  Joachim Pehserl ,  Ruchi Bhargava ,  Sangmin Oh

IPC: G01S7/41 ,  G01S13/86 ,  G01S13/89 ,  G06N3/04 ,  G06N3/08

CPC classification number: G01S7/417 ,  G01S13/865 ,  G01S13/89 ,  G06N3/04 ,  G06N3/08

Abstract: In various examples, a deep neural network(s) (e.g., a convolutional neural network) may be trained to detect moving and stationary obstacles from RADAR data of a three dimensional (3D) space. In some embodiments, ground truth training data for the neural network(s) may be generated from LIDAR data. More specifically, a scene may be observed with RADAR and LIDAR sensors to collect RADAR data and LIDAR data for a particular time slice. The RADAR data may be used for input training data, and the LIDAR data associated with the same or closest time slice as the RADAR data may be annotated with ground truth labels identifying objects to be detected. The LIDAR labels may be propagated to the RADAR data, and LIDAR labels containing less than some threshold number of RADAR detections may be omitted. The (remaining) LIDAR labels may be used to generate ground truth data.