Article

ROOF: A Learning Method for Humanoid Fall Recovery in Overhead-Constrained Environments

ROOF proposes a reinforcement learning method with contact-supported geometric escape guidance that enables proprioception-only humanoid robots to first create clearance and then complete the rise under overhead obstacles. In simulation, the recovery success rate was 88.5% under plates that can only be lifted, compared with 18.9% without geometric guidance; it was 98.6% under free plates with randomized size, mass, and placement. After deployment on a Unitree G1, the policy successfully recovered in 95 of 150 attempts across seven real-world obstacle scenes, including furniture and multi-object arrangements not seen in training.

Part of the event: New Method for Fall Recovery with Constrained Headroom for Humanoid Robots

This page provides a summary and source link only.