Legged robots can outperform wheeled machines for most navigation tasks across unknown and rough terrains. For such tasks, visual feedback is a fundamental asset to provide robots with terrain awareness. However, robust dynamic locomotion on difficult terrains with real-time performance guarantees remains a challenge. We present here a real-time, dynamic foothold adaptation strategy based on visual feedback. Our method adjusts the landing position of the feet in a fully reactive manner, using only on-board computers and sensors. The correction is computed and executed continuously along the swing phase trajectory of each leg. To efficiently adapt the landing position, we implement a self-supervised foothold classifier based on a convolutional neural network. Our method results in an up to 200 times faster computation with respect to the full-blown heuristics. Our goal is to react to visual stimuli from the environment, bridging the gap between blind reactive locomotion and purely vision-based planning strategies. We assess the performance of our method on the dynamic quadruped robot HyQ, executing static and dynamic gaits (at speeds up to 0.5 m/s) in both simulated and real scenarios; the benefit of safe foothold adaptation is clearly demonstrated by the overall robot behavior.


    Zugriff

    Download


    Exportieren, teilen und zitieren



    Titel :

    Fast and Continuous Foothold Adaptation for Dynamic Locomotion Through CNNs


    Beteiligte:
    Magaña, OAV (Autor:in) / Barasuol, V (Autor:in) / Camurri, M (Autor:in) / Franceschi, L (Autor:in) / Focchi, M (Autor:in) / Pontil, M (Autor:in) / Caldwell, DG (Autor:in) / Semini, C (Autor:in)

    Erscheinungsdatum :

    2019-04-01


    Anmerkungen:

    IEEE Robotics and Automation Letters , 4 (2) pp. 2140-2147. (2019)


    Medientyp :

    Aufsatz (Zeitschrift)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Klassifikation :

    DDC:    629



    BIPEDAL LOCOMOTION HAVING VARIABLE FOOTHOLD AND BIPEDAL LOCOMOTION ASSEMBLY

    LEE JONG MIN / KIM CHANG HYUN / LIM JAE WON et al. | Europäisches Patentamt | 2016

    Freier Zugriff


    PORTABLE FOOTHOLD

    KIM GYO JUNE / NOH TAEHYEONG / YUN HEEJEONG et al. | Europäisches Patentamt | 2024

    Freier Zugriff

    Foothold supporting apparatus

    AN DAE YOUNG / OH SIM KWAN / JANG KI BOK | Europäisches Patentamt | 2021

    Freier Zugriff

    SUBWAY SAFETY FOOTHOLD

    KIM SUNG MO | Europäisches Patentamt | 2015

    Freier Zugriff