Unmanned vehicle trajectory planning method, device, equipment and medium

By constructing a multi-reference line penalty function and optimizing the trajectory smoothing model under the Cartesian coordinate system, the problem of multi-reference line constraints in trajectory planning of unmanned vehicles is solved, and high-quality planning and safety improvement of trajectory are achieved.

CN119247966BActive Publication Date: 2025-03-28BEIJING INST OF TECH +1
2 Cites 0 Cited by

Patent Information

Application Number
CN202411773624.7
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-12-05
Publication Date
2025-03-28
Estimated Expiration
2044-12-05

AI Technical Summary

Technical Problem

The existing unmanned vehicle trajectory planning methods are difficult to effectively consider multi-reference line constraints in structured scenarios, resulting in smoothness, optimality and real-time problems in trajectory planning, and the trajectory continuity cannot be ensured.

Method used

The multi-reference line constrained autonomous driving vehicle trajectory planning method based on Cartesian coordinate system is adopted to obtain the initial conjecture trajectory through dynamic programming and region division, a multi-reference line punishment function is constructed, and the optimal trajectory smoothing model is solved to obtain the final trajectory.

Benefits of technology

The lateral error of the converging trajectory and the reference line composed of straight-bends under the Cartesian coordinate system is realized, which improves the quality of the trajectory and reduces the risk of unmanned driving.

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

Abstract

The present application discloses a method, device, equipment and medium for unmanned vehicle trajectory planning, and relates to the field of unmanned vehicle trajectory planning. The method comprises: performing dynamic planning according to reference line information to obtain an initial guess of the unmanned vehicle driving trajectory, dividing the target road into regions according to the initial guess and the road shape of the target reference line to obtain the region division result, constructing a multi-reference line penalty function according to the region division result, constructing an optimization-based trajectory smoothing model based on the multi-reference line penalty function, solving the optimization-based trajectory smoothing model with the initial guess as the initial iteration value, and obtaining the final trajectory of the unmanned vehicle. The method can converge the trajectory and the lateral error of the reference line composed of straight lines and curves in a Cartesian coordinate system, does not rely on the traditional curve coordinate system, improves the quality of the trajectory, and reduces the danger of unmanned driving.
Need to check novelty before this filing date? Find Prior Art