Falling is inevitable for legged robots in challenging real-world scenarios, where environments are unstructured and situations are unpredictable, such as uneven terrain in the wild. Hence, to recover from falls and achieve all-terrain traversability, it is essential for intelligent robots to possess the complex motor skills required to resume operation. To go beyond the limitation of handcrafted control, we investigated a deep reinforcement learning approach to learn generalized feedback-control policies for fall recovery that are robust to external disturbances. We proposed a design guideline for selecting key states for initialization, including a comparison to the random state initialization. The proposed learning-based pipeline is applicable to different robot models and their corner cases, including both small-/large-size bipeds and quadrupeds. Further, we show that the learned fall recovery policies are hardware-feasible and can be implemented on real robots.


    Access

    Download


    Export, share and cite



    Title :

    Learning Complex Motor Skills for Legged Robot Fall Recovery


    Contributors:
    Yang, C (author) / Pu, C (author) / Xin, G (author) / Zhang, J (author) / Li, Z (author)

    Publication date :

    2023-07-01


    Remarks:

    IEEE Robotics and Automation Letters , 8 (7) pp. 4307-4314. (2023)


    Type of media :

    Article (Journal)


    Type of material :

    Electronic Resource


    Language :

    English



    Classification :

    DDC:    629



    Legged Robot

    KENNEALLY GAVIN / PARIKH JIREN | European Patent Office | 2024

    Free access

    Legged Robot

    KENNEALLY GAVIN / PARIKH JIREN | European Patent Office | 2022

    Free access

    LEGGED ROBOT

    KENNEALLY GAVIN / PARIKH JIREN | European Patent Office | 2020

    Free access

    LEGGED ROBOT

    KENNEALLY GAVIN / PARIKH JIREN | European Patent Office | 2021

    Free access

    Legged Robot

    KENNEALLY GAVIN / PARIKH JIREN | European Patent Office | 2025

    Free access