Teleoperation is vital in the construction industry, allowing safe machine manipulation from a distance. However, controlling machines at a joint level requires extensive training due to their complex degrees of freedom. Task space control offers intuitive maneuvering, but precise control often requires dynamic models, posing challenges for hydraulic machines. To address this, we use a data-driven actuator model to capture machine dynamics in real-world operations. By integrating this model into simulation and reinforcement learning, a control policy for task space control is obtained. A 3t hydraulic construction machine, Brokk 170, serves as the platform for implementing the proposed approach. Through a series of experiments, the framework’s validity is established by comparing it against a well-established Jacobian-based approach.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Task Space Control of Hydraulic Construction Machines Using Reinforcement Learning


    Additional title:

    Springer Proceedings in Advanced Robotics



    Conference:

    International Workshop on Human-Friendly Robotics ; 2023 ; Munich, Germany September 20, 2023 - September 21, 2023



    Publication date :

    2024-03-10


    Size :

    15 pages





    Type of media :

    Article/Chapter (Book)


    Type of material :

    Electronic Resource


    Language :

    English




    Reinforcement Learning Control of Six-Phase Permanent Magnet Synchronous Machines

    Broghammer, Lara / Hufnagel, Dennis / Schindler, Tobias et al. | IEEE | 2023


    TRANSMISSION ASSEMBLY WITH TWO HYDRAULIC MOTORS FOR CONSTRUCTION MACHINES

    ALLEVI ALESSIO / NORO RICCARDO / TORCELLI ANDREA | European Patent Office | 2025

    Free access


    Latent Space Reinforcement Learning

    Luck, Kevin Sebastian | BASE | 2014

    Free access

    Virtual Task Machines

    Tewkesbury, G. E. / Sanders, D. A. / Hollis, J. E. L. | British Library Conference Proceedings | 1994