3d-diffuser-actor-rlbench

Community

3D Vision-Language-Action policy for robotic manipulation tasks.

Authorbensonlee5
Version1.0.0
Installs0

System Documentation

What problem does it solve?

This Skill provides a 3D Vision-Language-Action policy to automate robotic manipulation tasks on the RLBench benchmark, enabling precise control and execution of actions like opening drawers, picking up objects, and more.

Core Features & Use Cases

  • Vision-Language-Action Integration: Combines multi-view RGB-D imagery with language instructions for end-effector keypose prediction.
  • 3D Manipulation Tasks: Designed for tasks like opening drawers, manipulating food on a grill, and closing jars in a RLBench simulation environment.
  • Robot Embodyment: Optimized for the Franka Panda robot with CoppeliaSim/PyRep backend.
  • Use Case: A user can input a language instruction such as "open drawer" and the Skill will predict the next end-effector keypose, guiding the robot's motion planner to perform the action.

Quick Start

Execute the Skill using the command: openral benchmark scene --config scenes/benchmark/rlbench_open_drawer.yaml --rskill rskills/3d-diffuser-actor-rlbench

Dependency Matrix

Required Modules

openralzmqmsgpack

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: 3d-diffuser-actor-rlbench
Download link: https://github.com/bensonlee5/openral/archive/main.zip#3d-diffuser-actor-rlbench

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.