Segev Shlomov, Avi Yaeli
CHI 2024
Many robot applications require legged robots to traverse rough or unmodeled terrain. This paper explores strategies that would enable legged robots to respond to two common types of surface contact error: slipping and tripping. Because of the rapid response required and the difficulty of sensing uneven terrain, we propose a set of reflexes that would permit the robot to react without modeling or analyzing the error condition in detail. These reflexive responses allow robust recovery from a variety of contact errors. We present simulation trials for single-slip tasks with varying coefficients of friction and single-trip tasks with varying obstacle heights.
Segev Shlomov, Avi Yaeli
CHI 2024
Zahra Ashktorab, Djallel Bouneffouf, et al.
IJCAI 2025
Arthur Nádas
IEEE Transactions on Neural Networks
Anurag Ajay, Seungwook Han, et al.
NeurIPS 2023