Reproduce “Agile legged locomotion in reconfigurable modular robots” 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
Chen Yu, David Matthews, Jingxian Wang, Jing Gu, Douglas Blackiston, Michael Rubenstein, Sam Kriegman
The system comprises modular legged robots built from self-sufficient units that join into body plans. A design-search algorithm explores arrangements, and learned policies control locomotion. Multimodule robots trained in simulation on a flat plane transferred without fine-tuning to tested terrains. A shared policy reached 105.3% of the original speed when intact; after tested amputations, robots moved but did not self-repair.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.