Deep reinforcement learning (DRL) frameworks have shown their remarkable effectiveness in learning navigation policy for the mobile robot navigating in a human crowded environment. Moreover, attention mechanisms coupled with DRL allows the robot to identify neighbors with different level of influence and incorporate them into the robot’s decision. However, as the crowd density increases, attention mechanisms may fail to identify critical neighbors which can lead to significant drops in navigation efficiency. In this work, we aim to address this limitation by encoding both human-human and human-robot interaction using a special class of Graph Convolutional Networks (GCN) known as Message-Passing GCN (MP-GCN). In contrast to existing methods, where attention between robot and humans are encoded uniformly, the proposed approach named MP-GatedGCN-RL encodes asymmetric interactions using the combination of novel message-passing function and edge-wise gating mechanisms. We evaluate our approach on the simulated environments of ETH/UCY pedestrians datasets consisting of different scenarios like collision avoidance, group forming, diverging, crossing, and so on. Experimental results demonstrate that our proposed method outperforms the conventional benchmark dynamic avoidance method ORCA with a 20.6% increase in success rate and a 9.1% reduction in navigation time. Moreover, we also achieve a 5.5% enhancement in success rate compared to other state-of-the-art DRL-based methods without any additional labeled expert data nor prior supervised learning.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Learning Relation in Crowd Using Gated Graph Convolutional Networks for DRL-Based Robot Navigation


    Beteiligte:
    Jiang, Haoge (Autor:in) / Bhujel, Niraj (Autor:in) / Lin, Zhuoyi (Autor:in) / Wan, Kong-Wah (Autor:in) / Li, Jun (Autor:in) / Jayavelu, Senthilnath (Autor:in) / Jiang, Xudong (Autor:in)


    Erscheinungsdatum :

    01.06.2024


    Format / Umfang :

    2064434 byte




    Medientyp :

    Aufsatz (Zeitschrift)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Interaction-Aware Crowd Navigation via Augmented Relational Graph Learning

    Xu, Qing / He, Wangli / Kubota, Naoyuki | British Library Conference Proceedings | 2021


    Multi-Level Dynamic Graph Convolutional Networks for Weakly Supervised Crowd Counting

    Miao, Zhuangzhuang / Zhang, Yong / Ren, Hao et al. | IEEE | 2024


    Robot Crowd Navigation Based on Spatio-Temporal Interaction Graphs and Danger Zones

    Shi, Jiamin / Qiu, Zhuo / Zhang, Tangyike et al. | IEEE | 2023


    Generating Crowd-Sourced Navigation Data

    BITRA SURESH KUMAR / AGRAWAL MEGHNA | Europäisches Patentamt | 2018

    Freier Zugriff

    Extended Multi-Component Gated Recurrent Graph Convolutional Network for Traffic Flow Prediction

    Zhao, Junhui / Xiong, Xincheng / Zhang, Qingmiao et al. | IEEE | 2024