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 ignore external forces or restrict compliance to specific body parts. By synthesizing a large-scale augmented dataset of human interaction data, the authors train a reinforcement learning policy that effectively tracks compliant motions in response to external wrenches. The results from both simulations and real-world experiments demonstrate the controller's ability to adaptively manage compliance across the upper body, enhancing performance in teleoperated loco-manipulation tasks.
LAC enables humanoid robots to dynamically adapt their compliance to external forces, significantly improving their interaction capabilities in real-world tasks.
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