DIRIGENt, an end-to-end diffusion model conditioned on RGB images, generates robot joint values that let a humanoid robot imitate human arm poses, beating a state-of-the-art baseline on the authors' new paired human-robot dataset.
Human to robot whole-body motion transfer
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.RO 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
DIRIGENt: End-To-End Robotic Imitation of Human Demonstrations Based on a Diffusion Model
DIRIGENt, an end-to-end diffusion model conditioned on RGB images, generates robot joint values that let a humanoid robot imitate human arm poses, beating a state-of-the-art baseline on the authors' new paired human-robot dataset.