GentleHumanoid: Learning Upper-body Compliance for Contact-rich Human and Object Interaction
This work addresses the need for humanoid robots to operate safely in human-centered environments, representing an incremental improvement over existing impedance-augmented methods by extending compliance to the whole upper body.
The paper tackled the problem of enabling safe and natural physical interaction for humanoid robots by developing GentleHumanoid, a framework that integrates impedance control into whole-body motion tracking to achieve upper-body compliance, resulting in reduced peak contact forces and smoother interactions in tasks like hugging and object manipulation.
Humanoid robots are expected to operate in human-centered environments where safe and natural physical interaction is essential. However, most recent reinforcement learning (RL) policies emphasize rigid tracking and suppress external forces. Existing impedance-augmented approaches are typically restricted to base or end-effector control and focus on resisting extreme forces rather than enabling compliance. We introduce GentleHumanoid, a framework that integrates impedance control into a whole-body motion tracking policy to achieve upper-body compliance. At its core is a unified spring-based formulation that models both resistive contacts (restoring forces when pressing against surfaces) and guiding contacts (pushes or pulls sampled from human motion data). This formulation ensures kinematically consistent forces across the shoulder, elbow, and wrist, while exposing the policy to diverse interaction scenarios. Safety is further supported through task-adjustable force thresholds. We evaluate our approach in both simulation and on the Unitree G1 humanoid across tasks requiring different levels of compliance, including gentle hugging, sit-to-stand assistance, and safe object manipulation. Compared to baselines, our policy consistently reduces peak contact forces while maintaining task success, resulting in smoother and more natural interactions. These results highlight a step toward humanoid robots that can safely and effectively collaborate with humans and handle objects in real-world environments.