# YanjieZe/GMR

[ICRA 2026] GMR: General Motion Retargeting. Retarget human motions into diverse humanoid robots in real time on CPU. Retargeter for TWIST.

Repository: https://github.com/YanjieZe/GMR
Canonical: https://ross.abutalabs.com/products/gmr
Language: Python
License: MIT
License Family: permissive
Last push: 2026-04-02T09:34:42+00:00

## Health v2 (maintenance only)
Score: 52/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 75, release rhythm 35, longevity 28
- inputs: {"age_days": 395, "days_push": 153, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2633, forks 456 (observed 2026-08-28T04:07:06.148005+00:00)

## What it is
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
- artifact type: library
- maturity: active
- function: robotics, simulation, machine-learning
- domain: robotics, machine-learning, simulation
- platform: python, cross-platform
- tags: motion-retargeting, humanoid-robots, teleoperation, motion-capture, reinforcement-learning, bvh, smpl, linux

## Member repositories
- YanjieZe/GMR (main) score 52

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:06.148005+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T02:19:35.017569+00:00, confidence not recorded.
  - readme: https://github.com/YanjieZe/GMR (fetched 2026-08-28T04:07:06.148005+00:00, sha 71a9706058e2)
- Data as of 2026-08-30T08:39:29.467469+00:00.