Robot Motion Transition with a Human Motion Prior

Taehyun Byun; Taemoon Jeong; Yoonbyung Chai; Woojin Wie; Insu Park; Kyungjae Lee; Sungjoon Choi

cs.ROOct 22, 2026

Robot Motion Transition with a Human Motion Prior

Authors: Taehyun Byun, Taemoon Jeong, Yoonbyung Chai, Woojin Wie, Insu Park, Kyungjae Lee, Sungjoon Choi

Organizations: Department of Artificial Intelligence, Korea University, Seoul, Republic of Korea. · ROBOTIS · Department of Statistics, Korea University, Seoul, Republic of Korea.

Abstract

Humanoid motion-tracking policies can reproduce diverse behaviors, yet connecting independently acquired motions into a continuous sequence remains challenging. Interpolation connects boundary poses without considering whether their relative position, heading, and timing provide suitable conditions for a transition. A generative motion prior can produce richer motion, but poorly arranged boundaries may cause it to generate excessive locomotion, turning, or another unintended action. We present Spatio-Temporal Alignment with a Motion Prior (STAMP), a framework for connecting independently acquired humanoid motions through a Robot-to-Human-to-Robot process. STAMP uses human motion space to draw on rich motion priors and reuse transition knowledge across robot embodiments. Its key component is a learned alignment model that determines the boundary conditions for motion inbetweening. Given the two motions retargeted to a human rig, the alignment model ranks candidate positions, headings, and transition durations for the following motion. A human motion prior generates the transition under the selected alignment. The completed sequence is retargeted to the robot and used as a reference to train a motion-tracking policy. We evaluate the tracking success of the generated transitions on Unitree~~G1 and~~ROBOTIS K1. Physical robot demonstrations further show that STAMP connects independently acquired motions into long-horizon sequences. Project page: https://childtoy.github.io/STAMP-project

Figures & tables

Fig. 1 : Overview of STAMP. Robot motions are transferred to a human rig. The alignment model predicts a transition cost for each candidate position, heading, and duration. The lowest-cost candidate is selected to condition motion inbetweening in human space. The completed sequence is retargeted to the robot and used as a motion-tracking reference.

Term	Definition	Weight
$E_{\mathrm{root}}$	$\mathcal{Q}(\ddot{\mathbf{p}}_{r};3)+0.25\mathcal{Q}(\dddot{\mathbf{p}}_{r};25)$	1.0
$E_{\mathrm{body}}$	$\mathcal{Q}(\ddot{\mathbf{p}}_{b};6)+0.25\mathcal{Q}(\dddot{\mathbf{p}}_{b};50)$	0.6
$E_{\mathrm{foot}}$	$\mathcal{Q}(\ddot{\mathbf{p}}_{f};5)+0.25\mathcal{Q}(\dddot{\mathbf{p}}_{f};45)$	0.8
$E_{\mathrm{stance}}$	$\mathcal{Q}(\dot{\mathbf{s}};1)+0.25\mathcal{Q}(\ddot{\mathbf{s}};6)$	0.6
$E_{\mathrm{yaw}}$	$\mathcal{Q}(\dot{\psi};\pi)+0.5\mathcal{Q}(\ddot{\psi};2\pi)$	0.5
	${}+0.1\mathcal{Q}(\dddot{\psi};8\pi)$

TABLE I: Kinematic supervision costs and combination weights. Normalization scales use the corresponding SI units.

Method	Success Rate (%) $\uparrow$	$E_{\mathrm{vel}}$ (m/s) $\downarrow$	$E_{\mathrm{acc}}$ (rad/s 2 ) $\downarrow$
Root/heading interpolation	69.59	0.2581	13.57
MotionBricks	56.91	0.3433	17.67
Kimodo †	50.69	0.5293	18.98
STAMP	80.69	0.2289	12.43

TABLE II: Unitree G1 transition tracking over 18 motion pairs. Kimodo † denotes the Kimodo-based inbetweening model.

Method	Success Rate (%) $\uparrow$	$E_{\mathrm{vel}}$ (m/s) $\downarrow$	$E_{\mathrm{acc}}$ (rad/s 2 ) $\downarrow$
Root/heading interpolation	84.70	0.1964	11.74
Kimodo †	64.55	0.5303	16.50
STAMP	87.52	0.1860	11.12

TABLE III: ROBOTIS K1 transition tracking over 18 motion pairs. Kimodo † denotes the Kimodo-based inbetweening model.

Robot	Candidate	Success Rate (%) $\uparrow$	$E_{\mathrm{vel}}$ (m/s) $\downarrow$	$E_{\mathrm{acc}}$ (rad/s 2 ) $\downarrow$
Unitree G1	Rank 1	80.69	0.2289	12.43
	Rank 100	71.33	0.3001	15.97
ROBOTIS K1	Rank 1	87.52	0.1860	11.12
	Rank 100	71.90	0.2875	14.34

TABLE IV: Tracking performance at alignment ranks 1 and 100. Rank 1 has the lowest predicted transition cost.

Fig. 2 : Running-to-punching transitions on ROBOTIS K1 using interpolation (top) and STAMP (bottom), progressing from right to left. STAMP places the punching motion farther forward, providing space for a connecting step during the transition.

Fig. 3 : Motor-current response during a transition from looking around to making a stop gesture on ROBOTIS K1. Both methods use a 1.5 s transition. Lines and shading indicate the mean and $\pm 1$ standard deviation across five executions of the RMS signal over 23 motors. Time zero denotes transition onset. Values are in driver-reported units.

Fig. 4 : Long-horizon compositions of the same four traffic-control motions executed on the ROBOTIS K1. Each row shows a different composition. STAMP selects the spatial and temporal alignment and generates the transitions between consecutive motions.

Robot Motion Generation

Robot motion generation creates feasible, task-directed trajectories for robots to move, manipulate objects, and interact with people and environments.

See all 198 papers

Human2Humanoid: Physics-Aware Cross-Morphology Motion Retargeting for Humanoid Robots
Jun 2, 2026Tianchen Huang, Feiyang Yuan, Junchi Gu +5Cross-Embodiment Robot Learning Motion Retargeting
Institute of Humanoid Robots, Department of Precision Machinery and Precision Instrumentation, University of Science and Technology of China, Hefei, Anhui 230026, China
GenTrack: Physical Alignment for Robot-Native Motion Generation and Zero-Shot Humanoid Tracking
Aug 2, 2026Zeyu Ling, Xinyao Yu, Renye Yan +4Zero-Shot Learning Humanoid Robot Control
Zhejiang University · Peking University · Tencent +1
Whole-Body Humanoid Control via Stochastic Motion Tokenization
Oct 27, 2026Michael Drolet, Oleg Arenz, Jan PetersHumanoid Robot Control Humanoid Motion Tracking
Technical University of Darmstadt · German Research Center for AI (DFKI) · Robotics Institute Germany (RIG)

Jun 2, 2026J/K move · Enter open · S save

Human2Humanoid: Physics-Aware Cross-Morphology Motion Retargeting for Humanoid Robots

Tianchen Huang, Feiyang Yuan, Junchi Gu, Shurui Fang+4

Institute of Humanoid Robots, Department of Precision Machinery and Precision Instrumentation, University of Science and Technology of China, Hefei, Anhui 230026, China

Cross-Embodiment Robot Learning Motion Retargeting Humanoid Robotics Human-to-Robot Motion Imitation

Open paper AskPDF arXiv

Retargeting human motion to humanoid robots is critical for teleoperation, imitation learning and human-robot interaction. However, it remains challenging because of substantial morphological discrepancies between humans and robots, including differences in skeletal topology, limb proportions and degrees of freedom, as well as the scarcity of paired motion data. This paper presents Human2Humanoid, an unsupervised motion retargeting framework that transfers human motions to humanoid robot behaviors with high fidelity. To bridge the domain gap under unpaired data, we adopt a CycleGAN-based architecture equipped with a skeleton-aware graph convolutional network to capture topology-dependent motion features. To address cross-domain scale mismatches, we introduce a morphology-invariant end-effector consistency loss that aligns normalized end-effector trajectories to preserve motion semantics across embodiments. To improve physical plausibility and reduce contact artifacts, we impose explicit physics-aware feasibility constraints to encourage reproduction of the contact patterns in the source motion. Experimental results show that the proposed method successfully retargets human motion to the Unitree G1 humanoid robot without paired data, and outperforms existing methods in both downstream controllability and physical feasibility.

Abstract

Robot Motion Generation

Explore similar work

Human2Humanoid: Physics-Aware Cross-Morphology Motion Retargeting for Humanoid Robots

GenTrack: Physical Alignment for Robot-Native Motion Generation and Zero-Shot Humanoid Tracking

Whole-Body Humanoid Control via Stochastic Motion Tokenization