RoboGen
A robotic agent that autonomously generates and masters new skills.
- Type
- Agent Skill
- Open source
- Yes
- GitHub Stars
- ★ 1.2k
- Source
- skill-github
- Repository
- github.com/Genesis-Embodied-AI/RoboGen
Overview
RoboGen is a generative and self-guided robotic agent capable of continuously proposing and mastering new skills. It enables automated robotic learning by generating new tasks and environments, and persistently learning novel robotic skills. Built on the Genesis engine, RoboGen uses PyBullet to implement generation and learning for rigid manipulation and mobility tasks. Ideal for researchers and developers needing automated robotic learning.
Capabilities
- ▪Autonomously generate new tasks
- ▪Generate corresponding environments
- ▪Continuously learn new skills
- ▪Generate rigid manipulation tasks
- ▪Generate mobility tasks
Use cases
Setup
git clone https://github.com/Genesis-Embodied-AI/RoboGen.git && conda env create -f environment.yaml && conda activate robogen
This information was compiled by AI from public sources and may contain inaccuracies — please refer to the source.
FAQ
How can I install the OMPL library?
You can use pre-compiled Python wheels or install from source.
Where can I get the dataset?
You can download the parsed dataset from the provided Google Drive link.
Related skills
gemini-cli
Gemini CLI is an open-source AI agent that brings Gemini's powerful capabilities directly into the terminal.
private-gpt
Provides a complete API layer for local models, supporting RAG, skills, tools, and more.
planning-with-files
File-based persistent planning skill, ideal for AI coding agents and long-running tasks.
scientific-agent-skills
Transform any AI agent into a scientific assistant with 147 ready-to-use research skills.
susi_alexa_skill
A skill that enables question-and-answer interactions between Alexa and Susi AI.
claude-context
Provides code search capabilities for Claude Code, turning the entire codebase into context.