Dynamic traversal of uneven terrain is a major objective in the field of legged robotics. The most recent model predictive control approaches for these systems can generate robust dynamic motion of short duration; however, planning over a longer time horizon may be necessary when navigating complex terrain. A recently-developed framework, Trajectory Optimization for Walking Robots (TOWR), computes such plans but does not guarantee their reliability on real platforms, under uncertainty and perturbations. We extend TOWR with analytical costs to generate trajectories that a state-of-the-art whole-body tracking controller can successfully execute. To reduce online computation time, we implement a learning-based scheme for initialization of the nonlinear program based on offline experience. The execution of trajectories as long as 16 footsteps and 5.5 s over different terrains by a real quadruped demonstrates the effectiveness of the approach on hardware. This work builds toward an online system which can efficiently and robustly replan dynamic trajectories.


    Zugriff

    Download


    Exportieren, teilen und zitieren



    Titel :

    Reliable trajectories for dynamic quadrupeds using analytical costs and learned initializations


    Beteiligte:
    Melon, O (Autor:in) / Geisert, M (Autor:in) / Surovik, D (Autor:in) / Havoutis, I (Autor:in) / Fallon, M (Autor:in)

    Erscheinungsdatum :

    2020-10-20



    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch


    Klassifikation :

    DDC:    629



    Control of Wheeled-Legged Quadrupeds Using Deep Reinforcement Learning

    Lee, Joonho / Bjelonic, Marko / Hutter, Marco | Springer Verlag | 2022


    Velocity Estimation for Quadrupeds Based on Extended Kalman Filter

    Li, Man Tian ;Wang, Cong Wei ;Wang, Peng Fei | Trans Tech Publications | 2014




    WHEELCHAIR DEVICE FOR MOBILITY-CHALLENGED QUADRUPEDS WITH USER-ACTUATED SIT-DOWN ACTION

    ROBINSON MARK C / JONES JAMES | Europäisches Patentamt | 2023

    Freier Zugriff