BRACE: Adapting Whole-Body References for Force and Terrain Aware Humanoid Motion Tracking

2026-10-04

AI Summary

This study addresses the limitations of existing whole-body tracking methods for humanoid robots, which lack interaction force and terrain awareness and thus struggle with external loads and inclined surfaces. To overcome these challenges, this work proposes a robust, proprioception-only motion control framework. Methodologically, it unifies external force application and compensation mechanisms for the first time, leveraging Wrench transformations to reconstruct reference trajectories that seamlessly integrate terrain adaptation with force control. Furthermore, a student policy is trained via flow matching distillation, enabling teleoperation without requiring height maps or physical force measurements. Extensive simulations and real-world experiments on the Unitree G1 platform demonstrate that the proposed approach successfully executes and compensates for hand-applied interaction forces across complex terrains, validating its effectiveness and robustness in practical deployment scenarios.

Abstract

Whole-body tracking has become the interface through which operators drive humanoid robots, yet the references it consumes are recorded on level ground and carrying nothing, so the tracker is aware of neither the forces the robot must exchange with objects nor the terrain it must stand on. Existing controllers address one side of this gap: force-capable policies command an end-effector force but prescribe no whole-body pose, while terrain-adaptive trackers treat loads as disturbances to reject rather than wrenches to command. We present BRACE, a whole-body tracker that exerts and compensates commanded hand forces from diverse poses while following a flat-ground reference on sloped terrain. Rather than leaving the tracker to absorb the load and the slope, BRACE folds both into the reference it follows: terrain conformance lifts footholds and root onto the local surface, and a wrench transformation resolves the hand displacement that produces a force jointly with the center-of-mass and center- of-pressure shifts it induces, bounded by teacher-specific arm-effort limits. Separate exertion and compensation teachers are distilled by DAgger into one flow-matching student that runs on proprioception alone, without a height map or measured wrench, so a teleoperator (even in remote locations) can supply a flat- ground trajectory and the robot resolves slope and load onboard. We extensive experiments on the Unitree-G1 to demonstrate the ability of BRACE to exert, compensate force and handle diverse terrain in simulation and real robot experiments.

Problem

• humanoid motion tracking
• whole-body control
• force interaction
• terrain adaptation
• load compensation

Innovation

• whole-body tracking
• wrench transformation
• DAgger distillation
• flow matching
• proprioception