As a fundamental component of autonomous driving systems, motion planning has garnered significant attention from both academia and industry. This paper focuses on efficient and spatial-temporal optimal trajectory optimization in unstructured environments using compact convex approximations of vehicle shapes. Conventional approaches typically model the task as an optimal control problem by discretizing the motion process in state configuration space. However, this often results in a tradeoff between optimality and efficiency since generating high-quality motion trajectories often requires high-precision discretization of the dynamic process, which imposes a substantial computational burden. To address this issue, we leverage the differential flatness property of car-like robots to simplify the trajectory representation and analytically formulate the spatial-temporal joint optimization problem with flat outputs in a compact manner, while ensuring the feasibility of nonholonomic dynamics. Moreover, we achieve efficient obstacle avoidance with a collision-free driving corridor for unmodelled obstacles and signed distance approximations for dynamic moving objects. We present comprehensive benchmarks with State-of-the-Art methods, demonstrating the significance of the proposed method in terms of efficiency and trajectory quality. Real-world experiments verify the practicality of our algorithm. We will release our codes for the research community.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    An Efficient Spatial-Temporal Trajectory Planner for Autonomous Vehicles in Unstructured Environments


    Beteiligte:
    Han, Zhichao (Autor:in) / Wu, Yuwei (Autor:in) / Li, Tong (Autor:in) / Zhang, Lu (Autor:in) / Pei, Liuao (Autor:in) / Xu, Long (Autor:in) / Li, Chengyang (Autor:in) / Ma, Changjia (Autor:in) / Xu, Chao (Autor:in) / Shen, Shaojie (Autor:in)


    Erscheinungsdatum :

    2024-02-01


    Format / Umfang :

    4538129 byte




    Medientyp :

    Aufsatz (Zeitschrift)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    UNSTRUCTURED VEHICLE PATH PLANNER

    HUANG ZHENQI / KOBILAROV MARIN | Europäisches Patentamt | 2024

    Freier Zugriff

    UNSTRUCTURED VEHICLE PATH PLANNER

    HUANG ZHENQI / HUDECEK JANEK / KOBILAROV MARIN et al. | Europäisches Patentamt | 2023

    Freier Zugriff

    Unstructured vehicle path planner

    HUANG ZHENQI / HUDECEK JANEK / KULARATNE DHANUSHKA NIRMEVAN et al. | Europäisches Patentamt | 2022

    Freier Zugriff

    UNSTRUCTURED VEHICLE PATH PLANNER

    HUANG ZHENQI / HUDECEK JANEK / KOBILAROV MARIN et al. | Europäisches Patentamt | 2021

    Freier Zugriff

    Neural task planner for autonomous vehicles

    ZHANG LIANGJUN / ZHAO JINXIN | Europäisches Patentamt | 2022

    Freier Zugriff