Reproduce “GeMuCo: Generalized Multisensory Correlational Model for Body Schema Learning” 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

Kento Kawaharazuka, Kei Okada, Masayuki Inaba

GeMuCo presents a shared model of relationships among robot movements, sensors, body, and tools. It learns sensor–action relationships from data, selects usable inputs and outputs, and supports estimation, control, simulation, and anomaly detection. In a PR2 grasp-change simulation, updating weights lowers immediate error, while parametric-bias updating performs better in a tested different posture. Demonstrations address specific tasks and mainly static relationships.

Summary by alphaXiv.

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