Learning-based Locomotion

Learning-Based Locomotion is a computational approach to robotic movement control that, as a subset of locomotion strategies in legged robotics, employs machine learning methodologies to enable adaptive and autonomous generation of dynamic walking, running, or climbing behaviors through experience-driven optimization rather than explicit programming.

119

Publications

6.2K

Citations

343

Authors

129

Institutions

Publications per year

2017–2026

62

Authors

343

  1. SL
    Sergey Levine

    University of California, Berkeley, United States

    7 publications · 678 citations

    7

    h-index

  2. CG
    Christopher G. Atkeson

    Carnegie Mellon University, United States

    6 publications · 338 citations

    6

    h-index

  3. JM
    Jun Morimoto

    Advanced Telecommunications Research Institute International, Japan

    6 publications · 251 citations

    6

    h-index

  4. PM
    Poramate Manoonpong

    University of Southern Denmark, Denmark

    4 publications · 251 citations

    4

    h-index

  5. SH
    Sehoon Ha

    Georgia Institute of Technology, United States

    2 publications · 105 citations

    4

    h-index

1–5 of 343

Venues

  1. IEEE Robotics and Automation Letters

    7 publications · 462 citations

    8

    h-index

  2. arXiv (Cornell University)

    Repository · 6 publications · 169 citations

    6

    h-index

  3. Frontiers in Neurorobotics

    5 publications · 84 citations

    5

    h-index

  4. The International Journal of Robotics Research

    IJRR · 4 publications · 267 citations

    4

    h-index

  5. ACM Transactions on Graphics

    TOG · 3 publications · 273 citations

    3

    h-index

1–5