Backend
RoboForge: Cross-space Motion Refinement for Physically Executable Humanoid Whole-body Tracking
arXiv cs.RO0 views
arXiv:2603.17927v3 Announce Type: replace Abstract: Whole-body motion tracking has rapidly expanded the skill repertoire of humanoid robots, yet nearly all of this progress has come from stronger tracking policies, while the motion references they imitate are treated as fixed supervision. We argue that reference quality is a first-order factor in tracking performance. Human motion data carry capture and estimation artifacts, and retargeting adds physical inconsistencies due to the human-robot embodiment gap; discarding such motions sacrifices valuable skill content, whereas retaining them uncorrected undermines policy learning. We present RoboForge, a data-centric framework that resolves this dilemma by refining references instead of filtering them, repairing each error in the space where it arises. In human motion space, a quality-guided diffusion model localizes corrupted segments and inpaints only those segments, leaving the rest of the motion intact. In robot motion space, kinematic repair corrects foot-contact and self-collision defects, and annealed sampling-based optimization under physics rollouts turns kinematically plausible references into dynamically executable ones. RoboForge requires no change to the tracker: it improves three retargeting methods and four tracking policies, raising the success rate of BeyondMimic from 89.51% to 96.20% while reducing the mean per-joint position error (MPJPE-L) by 31.6%. Refined references also accelerate policy learning, restore tracking performance from heavily corrupted inputs, and enable more than 30 high-dynamic motions, including flips and the Thomas flare, on a real Unitree G1.
Source:https://arxiv.org/abs/2603.17927PreviousLearning Object-Centric Spatial Reasoning for Sequential Manipulation in Cluttered EnvironmentsNextAgent-Centric Observation Adaptation for Robust Visual Control under Dynamic Perturbations
Related posts
Splunk's Empty Cluster Secret Turns a Standalone Default into an Authentication Bypass
0dev.to
Pragmatic zero-trust: what to ship in the first 90 days
0dev.to
The EKS cost playbook: 7 levers we pull on every audit
0dev.to
Building a hearing test in the browser with the Web Audio API (and why we refuse to call it an audiogram)
0dev.to
How we score French speaking with AI: an honest look at limits
0dev.to
What a Four-Letter Word Ladder Taught Me About Planning Under Constraints
0dev.to