Intelligent vehicle dynamic obstacle avoidance path continuous planning method, system and storage medium

A dynamic obstacle avoidance and path planning technology, applied in control/regulation systems, vehicle position/route/height control, motor vehicles, etc., can solve problems such as no longer reliable, high collision risk, and affecting the safety of automatic driving, and achieve Enhance adaptability, improve real-time performance, and ensure the effect of curvature continuity

Active Publication Date: 2022-05-03
WUHAN UNIV OF TECH
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, for a complex and dynamic traffic environment, when the ego vehicle is driving along the obstacle avoidance path, once the movement state of the obstacle changes suddenly, the path planned before the obstacle avoidance is no longer reliable, and the interference between the obstacle avoidance path and the obstacle path is very likely to occur. There is a great risk of collision, which will affect the driving safety of automatic driving

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
  • Intelligent vehicle dynamic obstacle avoidance path continuous planning method, system and storage medium
  • Intelligent vehicle dynamic obstacle avoidance path continuous planning method, system and storage medium
  • Intelligent vehicle dynamic obstacle avoidance path continuous planning method, system and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0044] Such as figure 1 As shown, this embodiment provides a method for continuous planning of a dynamic obstacle avoidance path for an intelligent vehicle. In this embodiment, when planning the path, the real-time movement state of the obstacle is considered, and the local path of the vehicle is updated in real time with a certain time step, and the curvature is guaranteed to be continuous.

[0045] The method of this embodiment includes: building a local path planning framework based on the Frenet coordinate system; curvature continuity path planning based on Bezier curves; and real-time obstacle avoidance path update in a complex dynamic environment.

[0046] In this embodiment, a local path planning framework based on the Frenet coordinate system is constructed, including:

[0047] (1) The global path needs to be known. The global path on a structured road is usually the lane centerline, and the global path in an open environment is a static obstacle avoidance path from t...

Embodiment 2

[0105] The present embodiment provides a dynamic obstacle avoidance path continuous planning system for smart cars, including: a building module for building a local path planning framework based on the Frenet coordinate system; a path planning module for performing local path planning and planning based on Bezier curves Re-planning, and the curvature of the re-planned path is continuous with the curvature of the originally planned path; the tracking driving module is used to track the vehicle according to the planned local path, obtain the movement state information of the obstacle at a predetermined time step, and When the motion state of the object changes, the path planning module is triggered to re-plan the path.

[0106] In this embodiment, the local path planning framework based on the Frenet coordinate system is constructed by building modules, and the conversion from Frenet coordinates to Cartesian coordinates is realized, and the real-time status information in the Ca...

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 discloses a method, a system and a storage medium for the continuous planning of a dynamic obstacle avoidance path for an intelligent vehicle. The method includes: using Frenet coordinate transformation to transform the local path planning problem when the vehicle is driving along a complex curved road into a double-lane path planning problem on a straight road, which greatly reduces the complexity of planning; and divides the double-lane path into avoidance The two parts of the obstacle road section and the return road section are based on the Bezier curve for path planning; when the surrounding environment changes dynamically, especially when the vehicle is tracking a local path, the obstacle suddenly accelerates, decelerates, or undergoes lateral displacement. The end point of will be updated accordingly, and the local path will be re-planned at the same time, and the curvature continuity at the path connection points will be guaranteed. The invention can improve the real-time performance of the route planning of the smart car and help to enhance the adaptability of the smart car to complex traffic environments.

Description

technical field [0001] The present invention relates to the technical field of automatic driving decision-making planning, in particular to a method for continuous re-planning of a dynamic obstacle-avoiding path for an intelligent vehicle based on a Frenet coordinate system and a Bezier curve, specifically a method, a system and a storage system for continuously planning a dynamic obstacle-avoiding path for an intelligent vehicle medium. Background technique [0002] Autonomous driving technology can effectively guarantee traffic safety, improve traffic efficiency, and improve travel methods. The underlying architecture of autonomous driving and 95% of conventional technical problems have been solved, and the remaining 5% of long-tail problems have become the key to restricting the application of autonomous driving. These long-tail problems involve key technologies such as reliable perception, fast prediction, and optimal decision planning in various complex scenarios. [0...

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 Patents(China)
IPC IPC(8): G05D1/02
CPCG05D1/0214G05D1/0274G05D2201/0212
Inventor 吴超仲冷姚鲁哲宋春晖罗鹏陈志军
Owner WUHAN UNIV OF TECH
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