SOURCE-LINKED INTELLIGENCE

ResSafe: Learning Safety Filtering with Residual Reinforcement Learning for Humanoids

arXiv · AI, language, vision and robotics · article · Sep 14, 2026 · UTC

Safe control of humanoid robots remains challenging due to their high-dimensional dynamics, contact-rich interactions, and sensitivity to disturbances. Although reinforcement learning has enabled effective locomotion and motion tracking, learned policies can still generate unsafe actions that lead to instability or falls. In this work, we propose residual reinforcement learning as an implicit safety-filtering mechanism for safe humanoid control. Instead of relying on a single nominal policy to simultaneously balance performance, safety, and robustness, we decouple performance and safety. The n

Read original source ↗ Open in workspace

recordType

paper

region

Global