Search papers, labs, and topics across Lattice.
This paper introduces the Weightlessness Mechanism (WM), a novel approach for humanoid robot control that mimics how humans exploit "weightless" states during non-self-stabilizing (NSS) motions by selectively relaxing joints to leverage passive body-environment contact. The method uses a weightlessness-state auto-labeling strategy for dataset annotation and dynamically determines which joints to relax and to what degree. Experiments on a Unitree G1 robot across tasks like sitting, lying down, and leaning demonstrate strong generalization to diverse environmental configurations without task-specific tuning, showcasing improved motion stability and environmental interaction.
Humanoid robots can now adapt to diverse environments without task-specific tuning by selectively "relaxing" joints, mimicking how humans exploit weightlessness for stability.
The integration of imitation and reinforcement learning has enabled remarkable advances in humanoid whole-body control, facilitating diverse human-like behaviors. However, research on environment-dependent motions remains limited. Existing methods typically enforce rigid trajectory tracking while neglecting physical interactions with the environment. We observe that humans naturally exploit a"weightless"state during non-self-stabilizing (NSS) motions--selectively relaxing specific joints to allow passive body--environment contact, thereby stabilizing the body and completing the motion. Inspired by this biological mechanism, we design a weightlessness-state auto-labeling strategy for dataset annotation; and we propose the Weightlessness Mechanism (WM), a method that dynamically determines which joints to relax and to what level, together enabling effective environmental interaction while executing target motions. We evaluate our approach on 3 representative NSS tasks: sitting on chairs of varying heights, lying down on beds with different inclinations, and leaning against walls via shoulder or elbow. Extensive experiments in simulation and on the Unitree G1 robot demonstrate that our WM method, trained on single-action demonstrations without any task-specific tuning, achieves strong generalization across diverse environmental configurations while maintaining motion stability. Our work bridges the gap between precise trajectory tracking and adaptive environmental interaction, offering a biologically-inspired solution for contact-rich humanoid control.
