Event
STAMP framework connects independent humanoid motions
1 reports · 1 sources
Taehyun Byun and other authors propose the STAMP framework, which uses a "robot-to-human-to-robot" pipeline to connect independently collected humanoid motions into continuous sequences. Its approach first retargets motions to a human skeleton, then a learned alignment model ranks candidate positions, orientations, and transition durations for subsequent motions, and finally uses human motion priors to generate transitions under the selected alignment. The authors evaluate the tracking success rate of generated transitions on the Unitree G1 and ROBOTIS K1, and use real-robot demonstrations to show that the framework can connect independently collected motions into long-horizon sequences.
Report timeline
- STAMP: Humanoid Motion Transitions with Human Motion Priors
The paper proposes the STAMP framework, which uses a "robot-to-human-to-robot" process to connect independently captured humanoid motions into continuous sequences. Its core is a learned alignment model: after motions are retargeted to a human skeleton, the model ranks candidate positions, headings, and transition durations for the subsequent motion, and a human motion prior then generates the transition under the selected alignment. The study evaluates the tracking success rate of the generated transitions on the Unitree G1 and ROBOTIS K1, and demonstrates long-horizon motion transitions in real-robot demos.
arXiv cs.RO ·