amazon-science/Spherical_Diffusion_Policy

[ICML 2025] Official implementation of Spherical Diffusion Policy: A SE(3) Equivariant Visuomotor Policy with Spherical Fourier Representation

39
/ 100
Emerging

This project provides a robust solution for controlling robot arms to perform intricate manipulation tasks, even when objects are positioned differently. It takes visual input of a scene and desired task, then generates precise robot movements. Robotics researchers and engineers can use this to develop and test policies for robots that need to interact with objects reliably in various 3D orientations.

No commits in the last 6 months.

Use this if you need to train a robot to perform manipulation tasks with high accuracy and generalization across diverse 3D object placements and scene configurations.

Not ideal if you are looking for a simple, plug-and-play solution for basic robot movements without complex 3D rotational generalization requirements.

robotics robot-manipulation visuomotor-control robot-learning automation
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 7 / 25
Maturity 15 / 25
Community 15 / 25

How are scores calculated?

Stars

39

Forks

7

Language

Python

License

MIT

Last pushed

Jul 08, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/amazon-science/Spherical_Diffusion_Policy"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.