Static obstacle avoidance method for unmanned vehicle

By comprehensively considering kinematics, boundary value, curvature and collision constraints, the static obstacle avoidance path for unmanned vehicles is generated, which solves the problem that the existing technology cannot take into account efficiency, safety and adaptability, and achieves better obstacle avoidance effects.

CN119645031AActive Publication Date: 2025-03-18NORTHWEST UNIV
9 Cites 0 Cited by

Patent Information

Application Number
CN202411787813.X
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-12-06
Publication Date
2025-03-18
Estimated Expiration
2044-12-06

AI Technical Summary

Technical Problem

The existing static obstacle avoidance technology of unmanned vehicles fails to comprehensively consider kinematic constraints, two-point boundary value constraints, curvature constraints and collision constraints, and cannot take into account driving efficiency, safety and adaptability in complex scenarios.

Method used

By obtaining the vehicle's physical dynamic information and obstacle information in the static local map, a curve fitting and path search algorithm is used to comprehensively consider kinematic constraints, two-point boundary value constraints, curvature constraints and collision constraints to generate the optimal obstacle avoidance path.

Benefits of technology

It realizes that driving efficiency, safety and adaptability are taken into account in complex scenarios, and the generated obstacle avoidance path can better cope with changes in different road scenarios and vehicle kinematic characteristics.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The invention discloses a static obstacle avoidance method for an unmanned vehicle, which relates to the technical field of static obstacle avoidance and comprises the following steps: acquiring a current pose of the vehicle, static obstacle information and a local end point pose; performing curve fitting and collision detection on the current pose and the local end point pose of the vehicle, if the collision detection is passed, obtaining an optimal obstacle avoidance path, and if the collision detection is not passed, taking the current pose of the vehicle as a reference, and considering kinematics constraints to generate a plurality of next-step poses of the vehicle; and performing curve fitting and collision detection on the current pose of the vehicle and the next pose of each vehicle by considering boundary value constraints and curvature constraints of two points, replacing the current pose of the vehicle with the next pose of the vehicle corresponding to the optimal curve, and performing circulation. According to the method, the optimal obstacle avoidance path is generated by comprehensively considering the kinematics constraint, the two-point boundary value constraint, the curvature constraint and the collision constraint, and the driving efficiency, the safety and the adaptability in a complex scene are considered.
Need to check novelty before this filing date? Find Prior Art