Skip to main content

Isaac Lab Simulation

🧠 Overview​

Welcome to the OpenArm Isaac Lab Simulation Documentation.

We use OpenArm to develop and evaluate reinforcement learning, imitation learning, and foundation model–based approaches within the Isaac Sim / Isaac Lab environment. The OpenArm model and its associated code are currently released as open source and are officially integrated into NVIDIA’s Isaac Sim / Isaac Lab ecosystem.

All pipelines, environments, and related code are planned to be released as open source, enabling the community to freely use, reproduce, and extend our work. Through this project, we aim to contribute practical simulation assets, training workflows, and benchmarks that can be directly applied to real-world robotic systems.

🎥 Demo Videos​

Currently, four reinforcement learning–based environments using OpenArm are publicly available:

  • Reaching Task
  • Lifting a Cube
  • Opening a Drawer
  • Opening a Drawer

Detailed implementation code, configuration files, and usage instructions can be found on our GitHub repository.

🚧 Coming Soon...​

The following codebases are currently under active development and will be released as part of an open beta in the near future.

  • 🧠 Teleoperation code
  • 🤖 Imitation Learning Code
  • 🔄 Sim2Real Code

Stay tuned for updates!

Last updated on