Minimizing experimental data while maintaining good AUV path-following performance is essential to reduce controller design costs and ensure AUV safety, particularly in complex and dynamic underwater environments with unknown ocean currents. To address this, we propose a conservative offline model-based Q-learning (CMQL) algorithm. This algorithm is robust to unknown disturbance and efficient in data utilization. The CMQL-based controller is trained offline with dynamics and kinematics models constructed from limited AUV motion data and requires no additional fine-tuning for deployment. These models, constructed by improved conditional neural processes, enable accurate long-term motion state predictions within the data distribution. Additionally, the carefully designed state space, action space, reward function, and domain randomization ensure strong generalization and disturbance rejection without extra compensation. Simulation results demonstrate that CMQL achieves effective path-following under unknown ocean currents with a limited dataset of only 1000 data points. This method also achieves zero-shot transfer, demonstrating its generalization and potential for real-world applications.


    Access

    Download


    Export, share and cite



    Title :

    Model-Based Offline Reinforcement Learning for AUV Path-Following Under Unknown Ocean Currents with Limited Data


    Contributors:
    Xinmao Li (author) / Lingbo Geng (author) / Kaizhou Liu (author) / Yifeng Zhao (author)


    Publication date :

    2025




    Type of media :

    Article (Journal)


    Type of material :

    Electronic Resource


    Language :

    Unknown




    Path Following Control of Unmanned Surface Vessel with Unknown Ocean Currents Disturbances

    Qin, Jinmeng / Guo, Chen | British Library Conference Proceedings | 2022


    Data-driven offline reinforcement learning approach for quadrotor’s motion and path planning

    ZHAO, Haoran / FU, Hang / YANG, Fan et al. | Elsevier | 2024

    Free access

    Runway Configuration Management with Offline Reinforcement Learning

    Milad Memarzadeh / Tejas Puranik / Jarrett Battistini et al. | NTRS


    Airport Runway Configuration Management with Offline Model-Free Reinforcement Learning

    Memarzadeh, Milad / Puranik, Tejas G. / Kalyanam, Krishna M. et al. | TIBKAT | 2023


    Airport Runway Configuration Management with Offline Model-Free Reinforcement Learning

    Memarzadeh, Milad / Puranik, Tejas G. / Kalyanam, Krishna M. et al. | AIAA | 2023