Reproduce “Learning Purposeful Co-designs of Bio-inspired Quadrupedal 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
Fabio Boekel, Jiatao Ding, Cosimo Della Santina
Dogger makes quadruped leg lengths and passive knee-spring settings adjustable, then uses Bayesian optimization to select task-specific designs under one policy trained across designs. On hardware, these designs reduced cost of transport by 18.6% ± 1.7% for inspection and 35.7% ± 3.1% for payload transport, versus a nominal design. Results cover two tasks, with the policy fixed during selection.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.