Back to timeline

Research · March 7, 2023

Diffusion policies for visuomotor control

Instead of predicting a single action, Diffusion Policy represents the robot’s motion as a diffusion process over action sequences; across 12 tasks from four existing benchmarks this gave an average improvement of 46.9% over prior methods.

Why it matters

Behaviour cloning was undone by averaging: when two motions are correct, a regression model returns something between them, which is a third and wrong one. Modelling the distribution of actions rather than its mean removed that fault, and diffusion became the standard action output for the generalist policies that followed.

Cheng Chi, Zhenjia Xu, Siyuan Feng, Eric Cousineau, Yilun Du, Benjamin Burchfiel, Russ Tedrake and Shuran Song worked together across Columbia University, Toyota Research Institute and MIT. The policy is represented as a conditional denoising diffusion process over action sequences, which allows it to handle multimodal distributions where several different motions are equally correct. Evaluation ran on 12 different tasks from 4 different manipulation benchmarks, that is against other people’s already published baselines rather than against an earlier version of itself. The average improvement was 46.9%.

Event record

Event date
March 7, 2023
Timeline date
Event date
Verification
Sources gathered automatically · September 20, 2026
Lines
ID
evt-0437

The date the first version was posted to arXiv; the paper was presented at RSS 2023.

Sources

Records that link to this one