We introduce a deep reinforcement learning framework that enables the generation of trained policy networks (agents) that incorporate local knowledge of current fields to provide energy-minimizing guidance for unmanned underwater vehicles (UUVs). Agents trained using this framework are capable of generating heading, depth, and speed commands that yield nearly-optimal, minimum-energy transits through spatially varying current fields. Numerical simulations in two and three spatial dimensions demonstrate that the energy cost of transits executed under the guidance of a trained agent are better than dead-reckoning and approach known optimal performance in a set of test scenarios.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Reinforcement Learning for Improved Guidance and Power Management of Unmanned Underwater Vehicles


    Contributors:


    Publication date :

    2023-09-25


    Size :

    585115 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Feature-Related Acoustic Guidance of Unmanned Underwater Vehicles

    Caccia, M. / International Federation of Automatic Control | British Library Conference Proceedings | 2002


    Modeling, Identification, Control and Guidance of Unmanned Underwater Vehicles

    Caccia, M. / Veruggio, G. | British Library Conference Proceedings | 2001


    A review of guidance laws applicable to unmanned underwater vehicles

    Naeem, W. / Sutton, R. / Ahmad, S.M. et al. | Tema Archive | 2003


    Motion control of unmanned underwater vehicles via deep imitation reinforcement learning algorithm

    Chu, Zhenzhong / Sun, Bo / Zhu, Daqi et al. | Wiley | 2020

    Free access

    Motion control of unmanned underwater vehicles via deep imitation reinforcement learning algorithm

    Chu, Zhenzhong / Sun, Bo / Zhu, Daqi et al. | IET | 2020

    Free access