Sign and lane creation for high definition maps used for autonomous vehicles

An autonomous vehicle and map technology, applied in the field of high-definition maps and safe navigation, can solve the problem of not being able to provide enough accurate and up-to-date correct data for safe navigation of autonomous vehicles

Pending Publication Date: 2020-08-14
NVIDIA CORP
View PDF0 Cites 19 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

As a result, conventional techniques for maintaining maps do not provide correct data that is sufficiently accurate and up-to-date for safe navigation of autonomous vehicles

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Sign and lane creation for high definition maps used for autonomous vehicles
  • Sign and lane creation for high definition maps used for autonomous vehicles
  • Sign and lane creation for high definition maps used for autonomous vehicles

Examples

Experimental program
Comparison scheme
Effect test

Embodiment approach

[0204] In one embodiment, the HD mapping system creates an occupancy map (OMap) by merging LIDAR scans from many track samples and multiple data collection runs. Since the orbital samples are already aligned, the individual point clouds can be converted to common coordinates of OMap, merged and voxelized into small cubes (e.g., 5cm x 5cm x5cm cubes), where each cube Indicates the space it occupies. Since the LIDAR sensor provides intensity for each point, the HD map system populates the intensity values ​​into OMap voxels (for example, by taking the mean or median intensity from all points falling inside the cube). Additionally, since the lidar sensor and camera sensor are already calibrated, the HD map system projects the LIDAR points onto nearby camera images to assign a color to each point. Similarly, HD map systems fill color information into OMap voxels.

[0205] If not all points within a voxel are visible from the camera view, the voxel may not have any color informat...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

An HD map system represents landmarks on a high definition map for autonomous vehicle navigation, including describing spatial location of lanes of a road and semantic information about each lane, andalong with traffic signs and landmarks. The system generates lane lines designating lanes of roads based on, for example, mapping of camera image pixels with high probability of being on lane lines into a three-dimensional space, and locating/connecting center lines of the lane lines. The system builds a large connected network of lane elements and their connections as a lane element graph. The system also represents traffic signs based on camera images and detection and ranging sensor depth maps. These landmarks are used in building a high definition map that allows autonomous vehicles to safely navigate through their environments.

Description

[0001] Cross References to Related Applications [0002] This application claims the benefit of U.S. Provisional Application No. 62 / 441,065, filed December 30, 2016, and U.S. Provisional Application No. 62 / 441,080, filed December 30, 2016, both of which are incorporated by reference in their entirety Incorporated into this article. Background technique [0003] The present disclosure relates generally to maps for autonomous vehicles, and more particularly to providing high-definition maps with high accuracy and up-to-date map data to autonomous vehicles for safe navigation. [0004] An autonomous vehicle, also known as a self-driving car, driverless car, car, or robotic car, travels from a source location to a destination without the need for a human driver to control and navigate the vehicle. Automating driving is difficult for several reasons. For example, autonomous cars use sensors to make driving decisions instantaneously, but vehicle sensors cannot see everything all t...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Applications(China)
IPC IPC(8): G06T11/20G06K9/00G06V10/34
CPCG06T17/00G01C21/3638G01C21/3811G06V20/582G06V20/588G06V10/34G06V10/457G01C21/3867G06T17/05B60W2420/42B60W40/04B60W2420/52G05D1/0088G01C21/3635
Inventor 杨林马克·达蒙·惠乐张宇德雷克·托马斯·米勒莱诺德·梅尔维克斯·约瑟夫斯蒂芬马克斯朴东振崔明
Owner NVIDIA CORP
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap