act-aloha

Automate bimanual cube transfer using vision-language-action policies.

Updated Jul 5, 2026
One-click install
npx skills add https://github.com/bensonlee5/openral --skill act-aloha
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: act-aloha
Source: https://github.com/bensonlee5/openral/tree/main/rskills/act-aloha
Command: npx skills add https://github.com/bensonlee5/openral --skill act-aloha

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill automates the complex task of transferring cubes using bimanual robots, leveraging vision-language-action policies to streamline operations.

Core Features & Use Cases

  • Vision-Language-Action Policy: Utilizes an Action Chunking Transformer to interpret visual input and execute precise actions.
  • Bimanual Robot Support: Designed for robots with two 7-DoF arms, enabling complex manipulation tasks.
  • Simulation-Ready: Ready for use in simulations for training and testing purposes.
  • Use Case: Ideal for robotic assembly lines or research into bimanual manipulation.

Quick Start

Use the act-aloha skill to transfer a cube from one position to another on the ALOHA bimanual robot.

Frequently Asked Questions about act-aloha

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I automate bimanual cube transfer tasks using vision-language-action policies?▼

Bimanual cube transfer tasks are automated using vision-language-action policies that leverage an Action Chunking Transformer to interpret visual input and execute precise robotic manipulation actions.

What is a vision-language-action policy for bimanual manipulation?▼

A vision-language-action policy for bimanual manipulation uses an Action Chunking Transformer to process visual input and generate precise actions for robots with two 7-DoF arms to transfer cubes.

Do I need a specific simulation environment to train bimanual manipulation policies?▼

You need a suitable simulation environment and OpenRAL to train and execute bimanual manipulation policies, enabling safe testing of vision-language-action tasks before physical deployment.

How does the Action Chunking Transformer work for robotic assembly automation?▼

The Action Chunking Transformer works for robotic assembly automation by interpreting visual input and translating it into precise, chunked actions for bimanual robots handling cube transfers.

Can I use this vision-language-action approach for robots without two 7-DoF arms?▼

This vision-language-action approach is specifically designed for robots with two 7-DoF arms, making it unsuitable for robotic platforms that do not support bimanual manipulation configurations.

What is the best way to train bimanual robots for assembly line cube transfers?▼

The best way to train bimanual robots for assembly line cube transfers is by using simulation-ready vision-language-action policies to streamline the training and testing of complex manipulation operations.