Autonomous obstacle avoidance technology is the key to determine whether the autonomous underwater vehicle (AUV) can reach its destination safely. The Q-Learning based guidance vector field is proposed to solve the 3-dimensional obstacle avoidance problem for AUV. Firstly the initial guidance vector field in free space is constructed to guide AUV reach the destination along the shortest path. Then the modulation matrix is proposed to quantify the influence generated by the obstacles so that the modified guidance vector field in obstacle environment is obtained. For the case of AUV entering the trap area, the Q-learning algorithm is used to find the shortest path from the current position to the destination. A virtual target is chosen to guide AUV escape from the trap area. Finally the simulation results show that this method is useful for AUV to complete the obstacle avoidance task in complex marine environment.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Obstacle Avoidance for AUV by Q-Learning based Guidance Vector Field


    Beteiligte:
    Wu, Keqiao (Autor:in) / Yao, Peng (Autor:in)


    Erscheinungsdatum :

    27.11.2020


    Format / Umfang :

    421923 byte




    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch





    Circumnavigation and obstacle avoidance guidance for UAVs using Gradient Vector Fields

    Wilhelm, Jay / Clem, Garrett / Casbeer, David et al. | AIAA | 2019


    Obstacle avoidance guidance for ground vehicles

    ZHU JIANCHAO / LIN LETIAN | Europäisches Patentamt | 2024

    Freier Zugriff

    Circumnavigation and Obstacle Avoidance Guidance for UAV Using Gradient Vector Fields

    Wilhelm, Jay / Clem, Garrett / Casbeer, David et al. | TIBKAT | 2019