ETH Zurich Trains Humanoid Locomotion with Just 13 Minutes of Human Data

ETH Zurich RSL, together with Apple, NVIDIA and NUS, released the Attention-based Contacts (ACP) project, which trains humanoid locomotion policies with only about 13.2 minutes of human data, enabling a single policy to traverse complex terrains.

2026-10-23 ~ 2026-10-23 · 2 related posts

• ETH Zurich robot learns humanoid mobility from 13 minutes of human motion, no reference at deployment — ChongZzZhang · 2026-10-23
• ETH Zurich humanoid walks any terrain with one policy, trained on just 13.2 minutes of motion data — ChongZzZhang · 2026-10-23