analiza aiqbench
DemoDiffusion advances robot manipulation by leveraging pre-trained diffusion policies to adapt a single human demonstration into feasible robotic trajectories without task-specific training. This approach significantly improves success rates on diverse real-world tasks compared to standard kinematic retargeting or standalone generalist policies, addressing the critical gap between human motion and physical actuator constraints.
DemoDiffusion: One-Shot Human Imitation using pre-trained Diffusion Policy
arXiv:2506.20668v3 Announce Type: replace-cross Abstract: We propose DemoDiffusion, a simple method for enabling robots to perform manipulation tasks by imitating a single human demonstration, without requiring task-specific training or paired human-robot data. Our approach is based on two insights. First, the hand motion in a human demonstration provides a useful prior for the robot's end-effector trajectory, which we can convert into a rough open-loop robot motion trajectory via kinematic retargeting. Second, while this retargeted motion captures the overall structure of the task, it may not align well with plausible robot actions in-context. To address this, we leverage a pre-trained generalist diffusion policy to modify the trajectory, ensuring it both follows the human motion and remains within the distribution of plausible robot actions. Unlike approaches based on online reinforcement learning or paired human-robot data, our method enables robust adaptation to new tasks and scenes with minimal effort. In real-world experiments across 8 diverse manipulation tasks, DemoDiffusion achieves 83.8\% average success rate, compared to 13.8\% for the pre-trained policy and 52.5\% for kinematic retargeting, succeeding even on tasks where the pre-trained generalist policy fails entirely. Project page: https://demodiffusion.github.io/
Abstract:We propose DemoDiffusion, a simple method for enabling robots to perform manipulation tasks by imitating a single human demonstration, without requiring task-specific training or paired human-robot data. Our approach is based on two insights. First, the hand motion in a human demonstration provides a useful prior for the robot's end-effector trajectory, which we can convert into a rough open-loop robot motion trajectory via kinematic retargeting. Second, while this retargeted motion captures the overall structure of the task, it may not align well with plausible robot actions in-context. To address this, we leverage a pre-trained generalist diffusion policy to modify the trajectory, ensuring it both follows the human motion and remains within the distribution of plausible robot actions. Unlike approaches based on online reinforcement learning or paired human-robot data, our method enables robust adaptation to new tasks and scenes with minimal effort. In real-world experiments across 8 diverse manipulation tasks, DemoDiffusion achieves 83.8\% average success rate, compared to 13.8\% for the pre-trained policy and 52.5\% for kinematic retargeting, succeeding even on tasks where the pre-trained generalist policy fails entirely. Project page: this https URL
11 pages. Published at ICRA 2026
Robotics (cs.RO); Machine Learning (cs.LG)
arXiv:2506.20668 [cs.RO]
(or arXiv:2506.20668v3 [cs.RO] for this version)
Text integral sub licența deschisă a publicației · 202 cuvinte
Subiecte conexe
RoboPrompt: Intuitive Robot Policy Steering with Sparse Human Input
arXiv · 8 oct. 2026
Runway’s WorldPrompt and the Engineering of Real-Time Worlds
Latent Space · 25 sept. 2026
LeRobot v0.6.0: Imagine, Evaluate, Improve
Hugging Face · 7 iul. 2026
Against Export Controls (and China Threat Models)
LessWrong · 24 sept. 2026