公开(公告)号：US20250137813A1

公开(公告)日：2025-05-01

申请号：US18493984

申请日：2023-10-25

Applicant: NVIDIA Corporation

Inventor： Yu SHENG ,  Amir AKBARZADEH ,  Vishisht GUPTA ,  Jordan MARR ,  Shaun LIU

IPC: G01C21/00 ,  G01C21/34 ,  G06T7/536 ,  G06T7/73 ,  G06V20/56

Abstract: Embodiments of the present disclosure relate to a system and method used to localize one or more systems using 2D map data. The method may include determining an image location of a representation of a portion of an object in an image corresponding to an environment. In some embodiments, the method may additionally include determining one or more predicted image locations corresponding to the image location of the representation of the portion of the object. The method may additionally include comparing one or more ground plane locations of the portion of the object with the one or more predicted image locations, and determining a cost based at least on the comparison between the one or more ground plane locations and the one or more predicted image locations. Further, the method may include localizing a system to the 2D map data based on the determined cost.

公开(公告)号：US20230296748A1

公开(公告)日：2023-09-21

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 ,  G01S17/04 ,  G01S17/931 ,  G01S13/931

CPC classification number: G01S13/04 ,  G01S17/04 ,  G01S17/931 ,  G01S13/931

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：US20230324194A1

公开(公告)日：2023-10-12

申请号：US17658997

申请日：2022-04-12

Applicant: NVIDIA Corporation

Inventor： Amir AKBARZADEH ,  Raul Correal TEZANOS ,  Hon Leung LEE

IPC: G01C21/34 ,  G01C21/36

CPC classification number: G01C21/3492 ,  G01C21/3635 ,  G01C21/367 ,  G01C21/3415

Abstract: Embodiments of the present disclosure relate to a method of translating routes between maps. The method may include obtaining a graph based on data of an area. The graph may include one or more nodes representing different locations along one or more navigable paths as defined by the map. The method may also include obtaining one or more waypoints that define a route to traverse in the area and selecting, from the nodes, one or more path nodes based on locations of the path nodes corresponding to locations of the way points. The selected path nodes may define a path in the data that corresponds to the route.

公开(公告)号：US20230296756A1

公开(公告)日：2023-09-21

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: G01S13/89 ,  G01S13/931 ,  G01S7/00

CPC classification number: G01S13/89 ,  G01S13/931 ,  G01S7/003 ,  G01S2013/9316

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：US20230294726A1

公开(公告)日：2023-09-21

申请号：US17655776

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

IPC: B60W60/00 ,  B60W40/12 ,  B60W40/10

CPC classification number: B60W60/001 ,  B60W40/12 ,  B60W40/10 ,  B60W2420/52

Abstract: One or more embodiments of the present disclosure relate to aligning sensor data. In some embodiments, the aligning may be used for performing localization. In these or other embodiments, the aligning may be used for map creation.

公开(公告)号：US20240281988A1

公开(公告)日：2024-08-22

申请号：US18171016

申请日：2023-02-17

Applicant: NVIDIA Corporation

Inventor： Joshua Edward ABBOTT ,  Amir AKBARZADEH ,  Joachim PEHSERL ,  Samuel Ogden ,  David WEHR ,  Ke CHEN

IPC: G06T7/50 ,  G01S17/89

CPC classification number: G06T7/50 ,  G01S17/89 ,  G06T2207/10028 ,  G06T2207/20084 ,  G06T2207/30256

Abstract: In various examples, perception of landmark shapes may be used for localization in autonomous systems and applications. In some embodiments, a deep neural network (DNN) is used to generate (e.g., per-point) classifications of measured 3D points (e.g., classified LiDAR points), and a representation of the shape of one or more detected landmarks is regressed from the classifications. For each of one or more classes, the classification data may be thresholded to generate a binary mask and/or dilated to generate a densified representation, and the resulting (e.g., dilated, binary) mask may be clustered into connected components that are iteratively: fitted a shape (e.g., a polynomial or Bezier spline for lane lines, a circle for top-down representations of poles or traffic lights), weighted, and merged. As such, the resulting connected components and their fitted shapes may be used to represent detected landmarks and used for localization, navigation, and/or other uses.

公开(公告)号：US20240280372A1

公开(公告)日：2024-08-22

申请号：US18171004

申请日：2023-02-17

Applicant: NVIDIA Corporation

Inventor： Joshua Edward ABBOTT ,  Amir AKBARZADEH ,  Joachim PEHSERL ,  Samuel OGDEN ,  David WEHR ,  Ke CHEN

IPC: G01C21/36 ,  B60W60/00 ,  G06V10/82

CPC classification number: G01C21/3644 ,  B60W60/001 ,  G06V10/82 ,  B60W2420/403

Abstract: In various examples, one or more DNNs may be used to detect landmarks (e.g., lane lines) and regress a representation of their shape. A DNN may be used to jointly generate classifications of measured 3D points using one output head (e.g., a classification head) and regress a representation of one or more fitted shapes (e.g., polylines, circles) using a second output head (e.g., a regression head). In some embodiments, multiple DNNs (e.g., a chain of multiple DNNs or multiple stages of a DNN) are used to sequentially generate classifications of measured 3D points and a regressed representation of the shape of one or more detected landmarks. As such, classified landmarks and corresponding fitted shapes may be decoded and used for localization, navigation, and/or other uses.

公开(公告)号：US20230296758A1

公开(公告)日：2023-09-21

申请号：US17655781

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: G01S13/89 ,  G01S7/40 ,  G01S13/86

CPC classification number: G01S13/89 ,  G01S7/40 ,  G01S13/86

Abstract: 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 used to generate map data. Additionally or alternatively, the RADAR point clouds may be used for performing localization.