ContactRL: Safe Reinforcement Learning based Motion Planning for Contact based Human Robot Collaboration

2025-12-03

AI Summary

To address the challenge of simultaneously ensuring safety and task efficiency during physical human–robot interaction, this paper proposes a motion planning framework integrating force-feedback reinforcement learning (RL) with kinetic-energy-aware control barrier functions (eCBFs). The method explicitly incorporates contact-force safety constraints into the RL reward function in a differentiable manner and employs eCBFs as a real-time safety layer to enforce provable safety guarantees within continuous action spaces. This enables co-optimization of policy learning and safety-critical control. Simulation results demonstrate a safety violation rate of only 0.2% and a task success rate of 87.7%. In physical experiments, the system successfully completed 360 handover trials of small objects, maintaining contact forces strictly below 10 N throughout. To the best of our knowledge, this is the first work to achieve end-to-end safe policy deployment via differentiable, explicit modeling of contact-force safety in the RL reward, rigorously enforced by eCBFs.

Technology Category

• Intelligent Robots: Human-Robot Interaction
• Humans and AI: Human-Aware Planning and Behavior Prediction
• Natural Language Processing: Safety and Robustness

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Economics, Online Markets and Human Computation: Trust and reliance of crowd workers and data experts on GenAI

Abstract

In collaborative human-robot tasks, safety requires not only avoiding collisions but also ensuring safe, intentional physical contact. We present ContactRL, a reinforcement learning (RL) based framework that directly incorporates contact safety into the reward function through force feedback. This enables a robot to learn adaptive motion profiles that minimize human-robot contact forces while maintaining task efficiency. In simulation, ContactRL achieves a low safety violation rate of 0.2% with a high task success rate of 87.7%, outperforming state-of-the-art constrained RL baselines. In order to guarantee deployment safety, we augment the learned policy with a kinetic energy based Control Barrier Function (eCBF) shield. Real-world experiments on an UR3e robotic platform performing small object handovers from a human hand across 360 trials confirm safe contact, with measured normal forces consistently below 10N. These results demonstrate that ContactRL enables safe and efficient physical collaboration, thereby advancing the deployment of collaborative robots in contact-rich tasks.

Problem

• Ensuring safe intentional physical contact in human-robot collaboration
• Minimizing contact forces while maintaining task efficiency via RL
• Guaranteeing deployment safety with a control barrier function shield

Innovation

• Incorporates contact safety into reward function via force feedback
• Uses kinetic energy based Control Barrier Function shield for safety
• Learns adaptive motion profiles to minimize contact forces efficiently