Reproduce “ReCo: Response-Consistent Locomotion with Policy-Aware MPC for Legged Manipulation” 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

Kuankuan Sima, Yichao Gao, Chenxi Gu, Kefan Zhao, Lin Zhao

ReCo coordinates a quadruped’s arm and locomotion to track end-effector paths in world coordinates. It shapes the walker’s command response, identifies a compact motion model, and uses model predictive control to plan base commands and arm motion together. In simulation, it achieved position RMSE of 0.135 m, orientation RMSE of 23.8°, and 75/100 successes on a defined benchmark.

Summary by alphaXiv.

Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.