The research on force control among manipulators has attracted more and more attention from a large of scholars and researcher. In this chapter, from perspective of optimization, we investigated the collision-free compliance control of redundant robot manipulators using recurrent neural network. The position-force control is constructed as an equality constraint in velocity level together with the kinematic property of robots. Both the joint angles and joint speed limitations on robots physical structure are also considered, and are described by a group of inequality constraints. To avoid collision between robots and obstacles, they are described as two set of points, the Euclidean norm of distance between robots and obstacles, greater than zero, is established as the condition of collision-free occurrence. Minimizing joint velocities as the secondary task, a time-varying QP-type problem description is given with equality and inequality constraints, then an RNN-based controller is designed to solve it. Based on theoretical analysis and simulative experiments, the effectiveness of the designed controller is validated.


    Zugriff

    Download


    Exportieren, teilen und zitieren



    Titel :

    Optimization-Based Compliant Control for Manipulators Under Dynamic Obstacle Constraints


    Beteiligte:
    Zhou, Xuefeng (Autor:in) / Xu, Zhihao (Autor:in) / Li, Shuai (Autor:in) / Wu, Hongmin (Autor:in) / Cheng, Taobo (Autor:in) / Lv, Xiaojing (Autor:in)

    Erschienen in:

    Erscheinungsdatum :

    2020-06-03


    Format / Umfang :

    22 pages




    Medientyp :

    Aufsatz/Kapitel (Buch)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch





    Deep RNN Based Obstacle Avoidance Control for Redundant Manipulators

    Zhou, Xuefeng / Xu, Zhihao / Li, Shuai et al. | Springer Verlag | 2020

    Freier Zugriff

    Towards Dynamic Obstacle Avoidance for Robot Manipulators with Deep Reinforcement Learning

    Zindler, Friedemann / Lucchi, Matteo / Wohlhart, Lucas et al. | TIBKAT | 2022


    Towards Dynamic Obstacle Avoidance for Robot Manipulators with Deep Reinforcement Learning

    Zindler, Friedemann / Lucchi, Matteo / Wohlhart, Lucas et al. | Springer Verlag | 2022


    Formation Control and Obstacle/Collision Avoidance with Dynamic Constraints

    Mu, Shaoyang / Zhou, Pingfang | Springer Verlag | 2020