公开(公告)号：US12117298B2

公开(公告)日：2024-10-15

申请号：US18057619

申请日：2022-11-21

Applicant: NVIDIA Corporation

Inventor： Chen Chen

IPC: G01C21/32 ,  G05D1/00 ,  G05D1/246

CPC classification number: G01C21/32 ,  G05D1/246 ,  G05D1/0088 ,  G05D1/0274

Abstract: According to an aspect of an embodiment, operations may comprise obtaining a pose graph that comprises a plurality of nodes. The operations may also comprise dividing the pose graph into a plurality of pose subgraphs, each pose subgraph comprising one or more respective pose subgraph interior nodes and one or more respective pose subgraph boundary nodes. The operations may also comprise generating one or more boundary subgraphs based on the plurality of pose subgraphs, each of the one or more boundary subgraphs comprising one or more respective boundary subgraph boundary nodes and comprising one or more respective boundary subgraph interior nodes. The operations may also comprise obtaining an optimized pose graph by performing a pose graph optimization. The pose graph optimization may comprise performing a pose subgraph optimization of the plurality of pose subgraphs and performing a boundary subgraph optimization of the plurality of boundary subgraphs.

公开(公告)号：US12031824B2

公开(公告)日：2024-07-09

申请号：US17664653

申请日：2022-05-23

Applicant: NVIDIA Corporation

Inventor： Mark Damon Wheeler ,  Gregory William Coombe ,  Di Zeng ,  Jeff Adachi ,  Chen Chen

IPC: G01C21/16 ,  G01C21/00 ,  G01S19/39 ,  G01S19/46 ,  G01S19/47 ,  G01S19/52 ,  G05D1/00

CPC classification number: G01C21/165 ,  G01C21/1652 ,  G01C21/1656 ,  G01C21/3848 ,  G01S19/393 ,  G01S19/46 ,  G01S19/47 ,  G01S19/52 ,  G05D1/0231 ,  G05D1/0255 ,  G05D1/0257 ,  G05D1/027 ,  G05D1/0278 ,  G01C21/1654

Abstract: A vehicle computing system validates location data received from a Global Navigation Satellite System receiver with other sensor data. In one embodiment, the system calculates velocities with the location data and the other sensor data. The system generates a probabilistic model for velocity with a velocity calculated with location data and variance associated with the location data. The system determines a confidence score by applying the probabilistic model to one or more of the velocities calculated with other sensor data. In another embodiment, the system implements a machine learning model that considers features extracted from the sensor data. The system generates a feature vector for the location data and determines a confidence score for the location data by applying the machine learning model to the feature vector. Based on the confidence score, the system can validate the location data. The validated location data is useful for navigation and map updates.

公开(公告)号：US11512964B2

公开(公告)日：2022-11-29

申请号：US16810796

申请日：2020-03-05

Applicant: NVIDIA CORPORATION

Inventor： Chen Chen

IPC: G01C21/32 ,  G05D1/02 ,  G05D1/00

Abstract: According to an aspect of an embodiment, operations may comprise obtaining a pose graph that comprises a plurality of nodes. The operations may also comprise dividing the pose graph into a plurality of pose subgraphs, each pose subgraph comprising one or more respective pose subgraph interior nodes and one or more respective pose subgraph boundary nodes. The operations may also comprise generating one or more boundary subgraphs based on the plurality of pose subgraphs, each of the one or more boundary subgraphs comprising one or more respective boundary subgraph boundary nodes and comprising one or more respective boundary subgraph interior nodes. The operations may also comprise obtaining an optimized pose graph by performing a pose graph optimization. The pose graph optimization may comprise performing a pose subgraph optimization of the plurality of pose subgraphs and performing a boundary subgraph optimization of the plurality of boundary subgraphs.

公开(公告)号：US12223593B2

公开(公告)日：2025-02-11

申请号：US17655784

申请日：2022-03-21

Applicant: NVIDIA CORPORATION

Inventor： Chen Chen ,  Mark Damon Wheeler ,  Liang Zou

IPC: G06T17/05 ,  B60W40/06 ,  G01C11/06 ,  G01C11/12 ,  G01C11/30 ,  G01C21/00 ,  G01C21/36 ,  G01S19/42 ,  G05D1/00 ,  G06T7/11 ,  G06T7/246 ,  G06T7/55 ,  G06T7/593 ,  G06T7/68 ,  G06T7/70 ,  G06T7/73 ,  G06T17/20 ,  G06V10/46 ,  G06V10/75 ,  G06V20/56 ,  G06V20/58 ,  G08G1/00 ,  G01S17/89 ,  G01S19/46 ,  G01S19/47

Abstract: A high-definition map system receives sensor data from vehicles travelling along routes and combines the data to generate a high definition map for use in driving vehicles, for example, for guiding autonomous vehicles. A pose graph is built from the collected data, each pose representing location and orientation of a vehicle. The pose graph is optimized to minimize constraints between poses. Points associated with surface are assigned a confidence measure determined using a measure of hardness/softness of the surface. A machine-learning-based result filter detects bad alignment results and prevents them from being entered in the subsequent global pose optimization. The alignment framework is parallelizable for execution using a parallel/distributed architecture. Alignment hot spots are detected for further verification and improvement. The system supports incremental updates, thereby allowing refinements of sub-graphs for incrementally improving the high-definition map for keeping it up to date.

公开(公告)号：US20230083343A1

公开(公告)日：2023-03-16

申请号：US18057619

申请日：2022-11-21

Applicant: NVIDIA Corporation

Inventor： Chen Chen

IPC: G01C21/32

Abstract: According to an aspect of an embodiment, operations may comprise obtaining a pose graph that comprises a plurality of nodes. The operations may also comprise dividing the pose graph into a plurality of pose subgraphs, each pose subgraph comprising one or more respective pose subgraph interior nodes and one or more respective pose subgraph boundary nodes. The operations may also comprise generating one or more boundary subgraphs based on the plurality of pose subgraphs, each of the one or more boundary subgraphs comprising one or more respective boundary subgraph boundary nodes and comprising one or more respective boundary subgraph interior nodes. The operations may also comprise obtaining an optimized pose graph by performing a pose graph optimization. The pose graph optimization may comprise performing a pose subgraph optimization of the plurality of pose subgraphs and performing a boundary subgraph optimization of the plurality of boundary subgraphs.

公开(公告)号：US20230031260A1

公开(公告)日：2023-02-02

申请号：US17664653

申请日：2022-05-23

Applicant: NVIDIA Corporation

Inventor： Mark Damon Wheeler ,  Gregory William Coombe ,  Di Zeng ,  Jeff Adachi ,  Chen Chen

IPC: G01C21/16 ,  G05D1/02 ,  G01S19/39 ,  G01S19/47 ,  G01S19/46 ,  G01S19/52 ,  G01C21/00

Abstract: A vehicle computing system validates location data received from a Global Navigation Satellite System receiver with other sensor data. In one embodiment, the system calculates velocities with the location data and the other sensor data. The system generates a probabilistic model for velocity with a velocity calculated with location data and variance associated with the location data. The system determines a confidence score by applying the probabilistic model to one or more of the velocities calculated with other sensor data. In another embodiment, the system implements a machine learning model that considers features extracted from the sensor data. The system generates a feature vector for the location data and determines a confidence score for the location data by applying the machine learning model to the feature vector. Based on the confidence score, the system can validate the location data. The validated location data is useful for navigation and map updates.

公开(公告)号：US12189065B2

公开(公告)日：2025-01-07

申请号：US16919222

申请日：2020-07-02

Applicant: NVIDIA CORPORATION

Inventor： Chen Chen ,  Ziqiang Huang

IPC: G01S7/497 ,  E21B23/06 ,  E21B43/12 ,  G01S17/89 ,  G01S17/931 ,  G05D1/00

Abstract: A method includes obtaining first user input identifying at least one LIDAR point in a set of LIDAR points associated with an object in an image, and obtaining second user input identifying the object in the image. The method may also include generating a constraint on a relationship between a LIDAR sensor used to capture the set of LIDAR points and a camera used to capture the image. The method may additionally include reducing a cost associated with the LIDAR point being inconsistent with the object in the image subject to the constraint.

公开(公告)号：US11675083B2

公开(公告)日：2023-06-13

申请号：US16733143

申请日：2020-01-02

Applicant: NVIDIA CORPORATION

Inventor： Chen Chen ,  Liang Zou ,  Derik Schroeter ,  Mark Damon Wheeler

IPC: G01S17/89 ,  G05D1/00 ,  G05D1/02 ,  B60W60/00 ,  G06T19/00 ,  B60W50/00

CPC classification number: G01S17/89 ,  B60W50/00 ,  B60W60/0027 ,  G05D1/0088 ,  G05D1/0231 ,  G06T19/003 ,  B60W2050/0052 ,  B60W2420/52 ,  G05D2201/0213

Abstract: An autonomous vehicle system removes ephemeral points from lidar samples. The system receives a plurality of light detection and ranging (lidar) samples captured by a lidar sensor. Along with the lidar samples, the system receives an aligned pose and an unwinding transform for each of the lidar samples. The system determines one or more occupied voxel cells in a three-dimensional (3D) space using the lidar samples, their aligned poses, and their unwinding transforms. The system identifies occupied voxel cells representative of noise associated with motion of an object relative to the lidar sensor. The system filters the occupied voxel cells by removing the cells representative of noise. The system inputs the filtered occupied voxel cells in a 3D map comprising voxel cells, e.g., during the map generation and/or a map update.