Self-supervised Locomotion Learning

Self-Supervised Locomotion Learning is a machine learning framework within the domain of robotic or embodied agent control that leverages unlabeled sensorimotor data to autonomously generate supervisory signals for training locomotion policies, thereby distinguishing itself from supervised and reinforcement learning approaches by eliminating the need for external rewards or annotated trajectories.

3

Publications

89

Citations

10

Authors

4

Institutions

Publications per year

2017–2026

2

Authors

10

  1. HH
    Huang Huang

    University of California, Berkeley, United States

    1 publications · 38 citations

    1

    h-index

  2. AD
    Artur Dubrawski

    Carnegie Mellon University, United States

    1 publications · 38 citations

    1

    h-index

  3. JI
    Jeffrey Ichnowski

    University of California, Berkeley, United States

    1 publications · 38 citations

    1

    h-index

  4. JW
    Jonathan Wang

    Sunnybrook Health Science Centre, Canada

    1 publications · 38 citations

    1

    h-index

  5. HZ
    Harry Zhang

    University of New Brunswick, Canada

    1 publications · 38 citations

    1

    h-index

1–5 of 10

Venues

  1. Bioinspiration & Biomimetics

    1 publications · 13 citations

    1

    h-index

  2. Robotics and Autonomous Systems

    1 publications · 38 citations

    1

    h-index

  3. IEEE Robotics and Automation Letters

    1 publications · 12 citations

1–3