Reproduce “CompliantBot: Learning Whole-Body Compliance across Task Interfaces for Humanoid Control” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Haoyang Li, Keqi Zhu, Zhanxiang Cao, Yang Zhang, Yizhi Chen, Xuekang Yang, Yue Gao
CompliantBot trains humanoid controllers to yield to pulls without replacing motion-tracking or walking commands. In simulation, a spring attached to a sampled body link changes force with the robot’s movement; rewards prioritize unloading during contact and restore task tracking after release. Tests report greater yielding and lower spring loads than matched baselines, and highest completion among compared methods in stronger-pull trials.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.