Supercharge Your Innovation With Domain-Expert AI Agents!

Automatic driving automobile test scene construction method and device, and storage medium

A technology for vehicle testing and autonomous driving, applied in structured data retrieval, design optimization/simulation, image data processing, etc., can solve problems such as inability to achieve diversification and comprehensiveness, similar test scene content, and insufficient road type comprehensiveness.

Pending Publication Date: 2020-10-30
广东中科臻恒信息技术有限公司
View PDF0 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0002] Autonomous vehicles need to be tested before they are put into use. Existing test scenarios are often simulated manually with reference to car accidents. comprehensive

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
  • Automatic driving automobile test scene construction method and device, and storage medium
  • Automatic driving automobile test scene construction method and device, and storage medium
  • Automatic driving automobile test scene construction method and device, and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0026] The vehicle of this embodiment is a self-driving car, which is equipped with a conventional laser sensor (Ibeo), a visual sensor (binocular vision camera), a position sensor (GPS), front and rear radars, and a main control computer (Nuvo-5095GC industrial computer) The composed automatic driving system can implement conventional sensor detection and driving control required for automatic driving.

[0027] see figure 1 , the self-driving car test scene construction method of the present embodiment includes the following steps S1-S3:

[0028] Step S1. Randomly combine narrow roads, curves, ramps, and straight roads to generate a virtual map, and at the ends of any two connected roads, control one of them to gradually change to converge to the other so as to realize the connection.

[0029] Since the road types can be divided into four types: narrow roads, curves, ramps, and straight roads, in order to ensure comprehensiveness, narrow roads, curves, ramps, and straight r...

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

The invention relates to an automatic driving automobile test scene construction method and device and a storage medium. The method comprises the following steps: S1, randomly combining four types ofroads including a narrow road, a curve road, a ramp road and a straight road to generate a virtual map, and controlling one of the end parts of any two connected roads to gradually change to tend to the other road so as to realize connection; s2, specifying a departure place and a destination on the virtual map, and generating a driving path according to the departure place and the destination; and S3, randomly generating an obstacle on a road related to the driving path. According to the invention, the narrow lane, the bent lane, the ramp and the straight lane are randomly combined to ensurethe comprehensiveness of the road types in the test map, and the diversification of the types and positions of the obstacles is ensured by randomly generating the obstacles on the roads involved in the driving path, so that the purposes of enriching the test scenes and improving the diversity and variability of the test scenes are achieved.

Description

technical field [0001] The present invention relates to the field of automatic driving, in particular to a method, device and storage medium for constructing a test scene of an automatic driving vehicle. Background technique [0002] Autonomous vehicles need to be tested before they are put into use. Existing test scenarios are often simulated manually with reference to car accidents. Comprehensiveness. Contents of the invention [0003] The present invention solves or partly solves the deficiencies in the prior art, and provides a method, device and storage medium for constructing an autonomous vehicle test scene. [0004] For this reason, a kind of self-driving car test scene construction method is provided, comprising the following steps: [0005] Step S1. Randomly combine narrow roads, curves, ramps, and straight roads to generate a virtual map, and at the ends of any two connected roads, control one of them to gradually change to converge to the other so as to real...

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): G06T11/20G06F16/29G06F30/20
CPCG06F30/20G06T11/206G06F16/29
Inventor 杨敬锋王立张南峰蓝飞腾刘晓松魏忠伟杨峰
Owner 广东中科臻恒信息技术有限公司
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

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

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com