MOMO: A framework for seamless physical, verbal, and graphical robot skill learning and adaptation

The paper introduces MOMO, a framework that allows industrial robots to be adapted by non-experts using kinesthetic touch, natural language, and a graphical web interface. It combines energy‑based intention detection, a tool‑based LLM for safe language adaptation, Kernelized Movement Primitives for motion encoding, probabilistic Virtual Fixtures for guided demonstrations, and ergodic control for surface finishing. The authors validate the system on a 7‑DoF torque‑controlled robot at the Automatica 2025 trade fair, showing its practical applicability in industrial settings.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

• llms
• robotics