WARP: Whole-Body Retargeting for Learning from Offline Human Demonstrations
2026-06-29 • Robotics
Robotics
AI summaryⓘ
The authors developed a method called WARP that helps robots copy human movements more precisely by accounting for the differences between human and robot bodies. Unlike previous methods that were inconsistent or unclear, WARP uses a special geometric solver to track arm movements exactly while keeping the robot’s whole-body posture in mind. This approach produces accurate robot motions from human demonstrations without needing people to guide the robot directly during training. Their tests showed WARP can reliably make robots perform whole-body tasks right away from recorded human actions.
retargetingembodiment gapwhole-body mobile manipulationend-effector trackingpose estimationgeometric solverrobot trajectoryopen-loop controlhuman demonstrationmobile-base control
Authors
Zhenyang Chen, Chuizheng Kong, Chuye Zhang, Yuanshao Yang, Lawrence Y. Zhu, Shreyas Kousik, Danfei Xu
Abstract
Direct transfer from human demonstration to learnable robot action is a crucial step towards scalable whole-body mobile manipulation. While human data scales better than mobile teleoperation, it requires overcoming significant embodiment gaps. Existing retargeting methods yield imprecise or inconsistent solutions, causing action multi-modality that prevents supervised policies from reliably converging. We present Whole-body-Aware Retargeting from human Pose (WARP), an offline pipeline that explicitly models embodiment differences to extract precise, unique whole-body actions. WARP leverages a closed-form Shoulder-Elbow-Wrist (SEW) geometric solver for exact end-effector tracking while preserving whole-body structural intent. Paired with lazy mobile-base control, it extracts accurate, consistent robot trajectories. Evaluations show WARP provides highly reliable data for open-loop real-world replay. To our knowledge, WARP is the first framework to achieve zero-shot whole-body mobile manipulation directly from offline human demonstrations, eliminating the need for human-in-the-loop teleoperation action data. More details on https://warp-retarget.github.io/