Search papers, labs, and topics across Lattice.
This paper introduces LAC, a novel whole-body controller that achieves simultaneous Linear and Angular Compliance in humanoid robots, addressing the limitations of existing controllers that either reject external forces or restrict compliance. By synthesizing a large-scale augmented dataset of compliant responses to external wrenches and employing teacher-student reinforcement learning, LAC effectively tracks compliant motions in real-world scenarios. The results show that LAC can adaptively respond to external forces while maintaining control over stiffness commands, demonstrating its potential for complex teleoperated tasks.
LAC enables humanoid robots to maintain compliant control in the face of external forces, revolutionizing how they interact with dynamic environments.
Real-world humanoid tasks involve physical interaction with objects and humans, yet current controllers either reject external forces as disturbances or restrict compliance to limited body links while ignoring angular effects. We present LAC, a general whole-body controller that simultaneously realizes commanded Linear and Angular Compliance for wrenches applied to the upper body. First, we synthesize whole-body compliant responses into a large-scale augmented dataset. Sampled force and couple events are imposed on contact frames extracted from human interaction data. At each contact link, the external force and a virtual torque from the passively yielding kinematic chain drive a virtual admittance under the commanded stiffness. Subsequently, teacher-student reinforcement learning trains a single policy to track the compliant motions under external wrenches. Finally, extensive simulation and real-world experiments demonstrate whole-body compliant responses to wrenches across the upper body, monotonic modulation over the full range of both stiffness commands, and applicability to teleoperated loco-manipulation tasks. Project website: https://lac-humanoid.github.io/
Tsinghua AI