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.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    A Novel Direct Trajectory Planning Approach Based on Generative Adversarial Networks and Rapidly-Exploring Random Tree


    Beteiligte:
    Zhao, Cong (Autor:in) / Zhu, Yifan (Autor:in) / Du, Yuchuan (Autor:in) / Liao, Feixiong (Autor:in) / Chan, Ching-Yao (Autor:in)

    Erschienen in:

    Erscheinungsdatum :

    01.10.2022


    Format / Umfang :

    3921159 byte




    Medientyp :

    Aufsatz (Zeitschrift)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Local Trajectory Planning for Autonomous Racing Vehicles Based on the Rapidly-Exploring Random Tree Algorithm

    Tramacere, Eugenio / Luciani, Sara / Feraco, Stefano et al. | British Library Conference Proceedings | 2021


    Simultaneous Learning and Planning using Rapidly Exploring Random Tree* and Reinforcement Learning

    Sadhu, Arup Kumar / Shukla, Shubham / Sortee, Sarvesh et al. | IEEE | 2021


    Safety-Compliant Generative Adversarial Networks for Human Trajectory Forecasting

    Kothari, Parth / Alahi, Alexandre | IEEE | 2023

    Freier Zugriff

    Simplified and Smoothed Rapidly-Exploring Random Tree Algorithm for Robot Path Planning

    Gültekin, Ayhan / Diri, Samet / Becerikli, Yaşar | BASE | 2023

    Freier Zugriff

    Vehicle Trajectory Prediction at Intersections using Interaction based Generative Adversarial Networks

    Roy, Debaditya / Ishizaka, Tetsuhiro / Mohan, C. Krishna et al. | IEEE | 2019