Trajectory planning is essential for self-driving vehicles and has stringent requirements for accuracy and efficiency. The existing trajectory planning methods have limitations in the feasibility of planned trajectories and computational efficiency. This paper proposes a life-long learning framework to achieve effective and high-accuracy direct trajectory planning (DTP) tasks. Based on generative adversarial networks (GANs), this study develops a lightweight GDTP model to map the initial/final states and the control action sequence. Additionally, by embedding the GDTP into the rapidly-exploring random tree (RRT), a GDTP-RRT algorithm is further designed for long-distance and multi-stage planning tasks. Taking the tractor-trailer as an application case, we test the proposed method in multiple scenarios with varying characteristics. The experimental results show that the method can plan highly feasible trajectories in a short time, compared with the most applied algorithm – the cubic curve RRT* (CCRRT*). It is found that the tracking errors of our method are 29.1% and 44.1% lower than the CCRRT* in terms of position and heading angle. This paper provides an effective and stable vehicle trajectory planning method for complex self-driving tasks.
A Novel Direct Trajectory Planning Approach Based on Generative Adversarial Networks and Rapidly-Exploring Random Tree
IEEE Transactions on Intelligent Transportation Systems ; 23 , 10 ; 17910-17921
01.10.2022
3921159 byte
Aufsatz (Zeitschrift)
Elektronische Ressource
Englisch
British Library Conference Proceedings | 2021
|Safety-Compliant Generative Adversarial Networks for Human Trajectory Forecasting
IEEE | 2023
|Simplified and Smoothed Rapidly-Exploring Random Tree Algorithm for Robot Path Planning
BASE | 2023
|