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

Sudarshan Harithas, Chen Yu, Juan Borbon, Shubhankar Mondal, Winston Zha, Srinath Sridhar, Dingqi Zhang, Jiuguang Wang · N/A · 2026

Summary

Abstract Summary

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.

Key Points

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.

Method

BRACE enables humanoid whole-body motion tracking under force exertion and force compensation on uneven terrain.

The framework operates given two operator inputs: a flat-ground kinematic reference trajectory $x_{\mathrm{ref}}$ retargeted from human motion capture [ 1 , 2 , 22 , 3 ] , and a set of commanded hand wrenches $w_{\mathrm{cmd}}=\{w_{h}\}_{h}$, where $w_{h}=[F_{h};M_{h}]\in\mathbb{R}^{6}$ specifies the force $F_{h}$ and moment $M_{h}$ for hand $h$.

Method — BRACE: Adapting Whole-Body References for Force and Terrain Aware Humanoid Motion Tracking — Figure 2 : BRACE overview. Left: terrain- and wrench-adapted reference synthesis (Sec. III-A ). The flat-ground reference $x_{\mathrm{ref}}$ is adjusted to the terrain (given by the heightmap $\mathcal{H}$) through foot alignment, giving $x_{\mathrm{ref}}^{T}$, and to the commanded wrench through \raisebox{-.9pt} {1}⃝ feasibility limits, \raisebox{-.9pt} {2}⃝ hand lead, and \raisebox{-.9pt} {3}⃝ COM brace, giving $x_{E}^{\star}$. Top right: privileged teacher policies (Sec. III-B ). Teacher-E learns force exertion under a virtual wrench field while tracking $x_{E}^{\star}$; Teacher-C learns force compensation under an external wrench while tracking $x_{C}^{\star}=x_{\mathrm{ref}}^{T}$. Bottom right: flow-based student distillation (Sec. III-C ). DAgger distills both teachers, selected by the mode flag $\mu$, into a single student: a task encoder consumes the flat-ground goals $s_{g}^{E,C}$, the mode, and the wrench command $w_{\mathrm{cmd}}$, a flow-matching base models the action distribution from the proprioceptive history $s_{p}$, and an action decoder fuses both into the executed action.

Experiments & Results

We evaluate the whole-body tracking, force compensation, and force exertion capabilities of BRACE on flat ground and sloped terrain. Fig. 3 summarizes all four settings. Baselines. We compare with the state of the art whole motion trackers SONIC [ 1 ] , TWIST2 [ 2 ] , and Any2Track [ 3 ] , and the payload-oriented HEFT [ 22 ] .

Force-commanding controllers [ 10 , 14 ] are not included: neither accepts a whole-body reference trajectory, so neither admits this protocol without redefining its command interface.

Experiments & Results — BRACE: Adapting Whole-Body References for Force and Terrain Aware Humanoid Motion Tracking — Figure 3 : Force compensation on (a) flat ground and (b) sloped terrain; force exertion on (c) flat ground and (d) sloped terrain. Columns are success, global error ( MPJPE-G ), local error ( MPJPE-L ), velocity error, and force error (exertion only). Each point is the equal-weight mean over the PHUMA and Bones-seed test splits. The horizontal axis is the sustained load per hand (compensation, 0–20 N) or the commanded force per hand (exertion, 3–9 N). Shading marks the gap between BRACE and the better of SONIC and HEFT (orange where BRACE leads, gray where it trails); brackets give this margin at the heaviest command, in percentage points (pp) of success or as relative change in error.

Sources and Demonstrations

Figures are reproduced from Harithas et al. See the full paper for experimental details and the project page, when the paper links one, for demonstrations and videos.