YanjieZe/GMR

Health v2 · maintenance only

Flags: no_releases

Adoption not part of the score

2633 stars · 456 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

GMR is a Python library for general motion retargeting that converts human motions into joint commands for diverse humanoid robots in real time on CPU. It supports many humanoid robot models and multiple human motion data formats, and serves as the retargeter for the TWIST teleoperation system.

Use cases

• retarget human motion capture data to humanoid robots
• real-time whole-body teleoperation of humanoids
• prepare motion datasets for RL tracking policies
• convert SMPL or BVH motion files to robot joint commands
• support new humanoid robots with URDF or MJCF models

When to choose

• you need fast, real-time retargeting on CPU
• you work with humanoid robots and want broad robot and motion-format support
• you train RL tracking policies and need well-tuned retargeted motions

When to avoid

• you need retargeting for non-humanoid robots
• you require GPU-accelerated batch offline processing at scale

Facets

library · maturity active

robotics simulation machine-learning robotics machine-learning simulation python cross-platform motion-retargeting humanoid-robots teleoperation motion-capture reinforcement-learning bvh smpl linux

Member repositories

For agents

markdown · JSON · MCP: product_card(name="YanjieZe/GMR")