act-libero

Community

Automate robotic manipulation tasks with Vision-Language-Action policy.

Authorbensonlee5
Version1.0.0
Installs0

System Documentation

What problem does it solve?

This Skill provides a robust Vision-Language-Action policy for robotic manipulation tasks, enabling automation of pick, place, open, and close actions on various objects.

Core Features & Use Cases

  • Vision-Language-Action Policy: Employs an ACT (Action Chunking Transformer) on HuggingFaceVLA/libero for robotic tasks.
  • Robotic Actions: Performs pick, place, open, and close actions on bowls, cups, drawers, and objects.
  • Embodiment Support: Specifically designed for the LIBERO Franka-Panda embodiment.
  • Sensor Requirements: Utilizes RGB images and proprioception data.
  • Quick Start: Run with openral sim run --config scenes/benchmark/libero_spatial.yaml --rskill rskills/act-libero

Quick Start

Run the Skill using the command openral sim run --config scenes/benchmark/libero_spatial.yaml --rskill rskills/act-libero.

Dependency Matrix

Required Modules

None required

Components

scriptsreferences

💻 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: act-libero
Download link: https://github.com/bensonlee5/openral/archive/main.zip#act-libero

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.