← All projects

Qualisys FBX → Unitree G1

A motion-retargeting pipeline that converts Qualisys motion-capture recordings into Unitree G1 humanoid joint angles, ready for simulation or robot deployment. Developed at the CSUSB Robotics Lab.

Motion GenerationSimulationRobot Learning

Architecture

Qualisys Lab
person moves in capture volume
→
FBX export
skeleton + global positions
→
Blender (headless)
reads skeleton data
→
GMR retargeting
inverse kinematics → G1 joints
→
MuJoCo viewer
.pkl output

Blender runs headless to parse the FBX skeleton, auto-corrects the actor's starting orientation so the robot faces forward, then GMR (General Motion Retargeting, Stanford/CMU) solves the IK mapping human motion onto the G1's body proportions before saving/visualizing the result.

Media

Overview

Requirements

  • Python 3.10+
  • Blender 3.6 LTS+ (reads FBX files)
  • MuJoCo, installed alongside GMR, for 3D playback
  • A Qualisys FBX export with skeleton + global positions enabled

Export requirements from QTM

  • AIM skeleton model fitted to the recording (not raw marker data)
  • Binary FBX, Z up-axis, meters, all frames
  • "Skeleton" and "Global Positions" both checked on export