Isaac ROS Physical AI

Application-level bringup packages for deploying whole-body control and teleoperation on humanoid robots.

Overview

Isaac ROS Physical AI provides application-level bringup packages for deploying whole-body control and teleoperation on humanoid robots.

The current release supports the Unitree G1 with:

• AGILE locomotion: Whole-body control policy for balance and walking
• Bimanual inverse kinematics: Real-time IK for both arms using cuMotion
• Finger control: Hand tracking from an XR headset
• XR teleoperation: End-effector and locomotion control using an XR headset with Isaac Teleop

Both MuJoCo simulation and real hardware are supported.

For a fine-tuned GR00T policy deployed end-to-end — teleoperate, record, convert to LeRobot, fine-tune GR00T N, export via LEAPP, deploy — see the Isaac for Physical AI reference workflow.

---

Documentation

Please visit the Isaac ROS Documentation to learn how to use this repository.

---

Packages

• isaac_ros_data_flywheel
• isaac_ros_unitree_g1_gr00t
  • Overview
  • Tutorial: Deploy a Fine-Tuned GR00T Policy
  • Real-Hardware Prerequisite Details
  • API
  • Troubleshooting
• isaac_ros_unitree_g1_recorder
  • Overview
  • Tutorial: Record Demonstrations
  • API
  • Troubleshooting
• isaac_ros_unitree_g1_teleop_bringup
  • Overview
  • Tutorial: Unitree G1 XR Teleop
  • API
  • Troubleshooting

Latest

Update 2026-07-06: Support CloudXR runtime without Docker