Diffusion policy: Visuomotor policy learning via action diffusion

This paper introduces Diffusion Policy, a new way of generating robot behavior by representing a robot’s visuomotor policy as a conditional denoising diffusion process. We benchmark Diffusion Policy across 15 different tasks from 4 different robot manipulation benchmarks and find that it consistently outperforms existing state-of-the-art robot learning methods with an average improvement of 46.9%. Diffusion Policy learns the gradient of the action-distribution score function and iteratively optimizes with respect to this gradient field during inference via a series of stochastic Langevin dynamics steps. We find that the diffusion formulation yields powerful advantages when used for robot policies, including…

• TR
  Toyota Research Institute
• DO
  Division of Information and Intelligent Systems

  Award: 2132519
• DO
  Division of Civil, Mechanical and Manufacturing Innovation

  Award: 2037101