Seamlessly operating an autonomous vehicles in a crowded pedestrian environment is a very challenging task. This is because human movement and interactions are very hard to predict in such environments. Recent work has demonstrated that reinforcement learning-based methods have the ability to learn to drive in crowds. However, these methods can have very poor performance due to inaccurate predictions of the pedestrians’ future state as human motion prediction has a large variance. To overcome this problem, we propose a new method, SARL-SGAN-KCE, that combines a deep socially aware attentive value network with a human multimodal trajectory prediction model to help identify the optimal driving policy. We also introduce a novel technique to extend the discrete action space with minimal additional computational requirements. The kinematic constraints of the vehicle are also considered to ensure smooth and safe trajectories. We evaluate our method against the state of art methods for crowd navigation and provide an ablation study to show that our method is safer and closer to human behaviour.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Socially Aware Crowd Navigation with Multimodal Pedestrian Trajectory Prediction for Autonomous Vehicles


    Beteiligte:
    Li, Kunming (Autor:in) / Shan, Mao (Autor:in) / Narula, Karan (Autor:in) / Worrall, Stewart (Autor:in) / Nebot, Eduardo (Autor:in)


    Erscheinungsdatum :

    2020-09-20


    Format / Umfang :

    794301 byte




    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Are socially-aware trajectory prediction models really socially-aware?

    Saadatnejad, Saeed / Bahari, Mohammadhossein / Khorsandi, Pedram et al. | Elsevier | 2022



    Crowd Prediction and Autonomous Navigation with Partial Observations

    Li, Kunming / Shan, Mao / Worrall, Stewart et al. | IEEE | 2022