In the fight against COVID-19, many robots replace human employees in various tasks that involve a risk of infection. Among these tasks, the fundamental problem of navigating robots among crowds, named robot crowd navigation, remains open and challenging. Therefore, we propose HGAT-DRL, a heterogeneous GAT-based deep reinforcement learning algorithm. This algorithm encodes the constrained human-robot-coexisting environment in a heterogeneous graph consisting of four types of nodes. It also constructs an interactive agent-level representation for objects surrounding the robot, and incorporates the kinodynamic constraints from the non-holonomic motion model into the deep reinforcement learning (DRL) framework. Simulation results show that our proposed algorithm achieves a success rate of 92%, at least 6% higher than four baseline algorithms. Furthermore, the hardware experiment on a Fetch robot demonstrates our algorithm’s successful and convenient migration to real robots.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Navigating Robots in Dynamic Environment With Deep Reinforcement Learning


    Contributors:
    Zhou, Zhiqian (author) / Zeng, Zhiwen (author) / Lang, Lin (author) / Yao, Weijia (author) / Lu, Huimin (author) / Zheng, Zhiqiang (author) / Zhou, Zongtan (author)

    Published in:

    Publication date :

    2022-12-01


    Size :

    3159204 byte




    Type of media :

    Article (Journal)


    Type of material :

    Electronic Resource


    Language :

    English



    NAVIGATING AERIAL VEHICLES USING DEEP REINFORCEMENT LEARNING

    CANDIDO SALVATORE J / GONG JUN / GENDRON-BELLEMARE MARC et al. | European Patent Office | 2021

    Free access

    Systems and Methods for Navigating Aerial Vehicles Using Deep Reinforcement Learning

    CANDIDO SALVATORE J / GONG JUN / GENDRON-BELLEMARE MARC | European Patent Office | 2021

    Free access

    Navigating autonomous coverage robots

    OZICK DANIEL N / OKERHOLM ANDREA M / MAMMEN JEFFREY W et al. | European Patent Office | 2015

    Free access

    Reinforcement learning with scene decomposition for navigating complex environments

    BOUTON MAXIME / NAKHAEI SARVEDANI ALIREZA / FUJIMURA KIKUO et al. | European Patent Office | 2022

    Free access

    Navigating semi-autonomous mobile robots

    STORFER LIOR / GAIDAR TAMARA / LAPIDOT IDO | European Patent Office | 2024

    Free access