# erwincoumans/motion_imitation

Code accompanying the paper "Learning Agile Robotic Locomotion Skills by Imitating Animals"

Repository: https://github.com/erwincoumans/motion_imitation
Canonical: https://ross.abutalabs.com/products/motion_imitation
Language: Python
License: Apache-2.0
License Family: permissive
Last push: 2023-03-24T23:54:56+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 2318, "days_push": 1258, "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 1457, forks 315 (observed 2026-08-28T04:04:47.008768+00:00)

## What it is
A Python research codebase accompanying the paper 'Learning Agile Robotic Locomotion Skills by Imitating Animals'. It provides a Gym environment for training a simulated quadruped robot to imitate reference motion capture clips, plus MPC-based locomotion for the real A1 robot and PyBullet.

## Use cases
- train a simulated quadruped robot to imitate animal motion capture
- learn agile locomotion policies with reinforcement learning
- run model predictive control locomotion on a Unitree A1 robot
- test pretrained quadruped locomotion policies in PyBullet
- reproduce results from the motion imitation paper

## When to choose
- you need a ready-made Gym environment for quadruped motion imitation research
- you want pretrained policies and reference motion clips to experiment with
- you are reproducing or extending the paper's locomotion results

## When to avoid
- you need a production robotics framework rather than research code
- you work with bipeds or non-quadruped robots without adaptation
- you need long-term support or frequent updates

## Facets
- artifact type: library
- maturity: maintenance
- function: reinforcement-learning, simulation, machine-learning, robotics
- domain: robotics, reinforcement-learning, machine-learning, simulation
- platform: windows, python
- tags: motion-imitation, quadruped-robot, pybullet, gym-environment, mpc, locomotion, research-code, linux, macos

## Member repositories
- erwincoumans/motion_imitation (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:47.008768+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 2026-08-30T04:35:33.002785+00:00, confidence not recorded.
  - readme: https://github.com/erwincoumans/motion_imitation (fetched 2026-08-28T04:04:47.008768+00:00, sha 8433028d0ec1)
- Data as of 2026-08-30T08:39:29.467469+00:00.