Humans are highly adept at walking in environments with foot placement constraints, including stepping-stone scenarios where the footstep locations are fully constrained. Finding good solutions to stepping-stone locomotion is a longstanding and fundamental challenge for animation and robotics. We present fully learned solutions to this difficult problem using reinforcement learning. We demonstrate the importance of a curriculum for efficient learning and evaluate four possible curriculum choices compared to a non-curriculum baseline. Results are presented for a simulated human character, a realistic bipedal robot simulation and a monster character, in each case producing robust, plausible motions for challenging stepping stone sequences and terrains.
@article{arxiv.2005.04323,
title = {ALLSTEPS: Curriculum-driven Learning of Stepping Stone Skills},
author = {Zhaoming Xie and Hung Yu Ling and Nam Hee Kim and Michiel van de Panne},
journal= {arXiv preprint arXiv:2005.04323},
year = {2020}
}