{"ID":2839064,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2511.16330","arxiv_id":"2511.16330","title":"Safe and Optimal Variable Impedance Control via Certified Reinforcement Learning","abstract":"Reinforcement learning (RL) offers a powerful approach for robots to learn complex, collaborative skills by combining Dynamic Movement Primitives (DMPs) for motion and Variable Impedance Control (VIC) for compliant interaction. However, this model-free paradigm often risks instability and unsafe exploration due to the time-varying nature of impedance gains. This work introduces Certified Gaussian Manifold Sampling (C-GMS), a novel trajectory-centric RL framework that learns combined DMP and VIC policies while guaranteeing Lyapunov stability and actuator feasibility by construction. Our approach reframes policy exploration as sampling from a mathematically defined manifold of stable gain schedules. This ensures every policy rollout is guaranteed to be stable and physically realizable, thereby eliminating the need for reward penalties or post-hoc validation. Furthermore, we provide a theoretical guarantee that our approach ensures bounded tracking error even in the presence of bounded model errors and deployment-time uncertainties. We demonstrate the effectiveness of C-GMS in simulation and verify its efficacy on a real robot, paving the way for reliable autonomous interaction in complex environments.","short_abstract":"Reinforcement learning (RL) offers a powerful approach for robots to learn complex, collaborative skills by combining Dynamic Movement Primitives (DMPs) for motion and Variable Impedance Control (VIC) for compliant interaction. However, this model-free paradigm often risks instability and unsafe exploration due to the...","url_abs":"https://arxiv.org/abs/2511.16330","url_pdf":"https://arxiv.org/pdf/2511.16330v2","authors":"[\"Shreyas Kumar\",\"Ravi Prakash\"]","published":"2025-11-20T13:10:42Z","proceeding":"cs.RO","tasks":"[\"cs.RO\"]","methods":"[\"Reinforcement Learning\",\"LoRA\"]","has_code":false}