Skills
.Work. You
Rest

diffusion-pusht

Community

Deployable robot agent policy for PushT benchmark tasks

#robotics#robot policy#VLA policy#PushT benchmark#diffusion policy
Authorbensonlee5
Version1.0.0
Installs0

System Documentation

What problem does it solve?

This Skill addresses the challenge of creating robot agents capable of pushing a t-shape object in the PushT benchmark environment.

Core Features & Use Cases

  • Vision-Language-Action Policy: Provides a robust vision-language-action policy for robot agents.
  • PushT Benchmark Support: Tailored specifically for the PushT 2-DoF pushing benchmark.
  • Denoising Diffusion Policy: Employs a diffusion policy with denoising diffusion probability models for robust inference.
  • Model Installation: Easy to install via OpenRAL's package management system.

Quick Start

Install the rskill package with openral rskill install OpenRAL/rskill-diffusion-pusht.

Dependency Matrix

Required Modules

None required

Components

Standard package

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: diffusion-pusht
Download link: https://github.com/bensonlee5/openral/archive/main.zip#diffusion-pusht

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 620,000+ vetted skills library on demand.