# ZhengyiLuo/PHC

Official Implementation of the ICCV 2023 paper:  Perpetual Humanoid Control for Real-time Simulated Avatars

Repository: https://github.com/ZhengyiLuo/PHC
Canonical: https://ross.abutalabs.com/products/phc
Homepage: https://zhengyiluo.github.io/PHC/
Language: Python
License: NOASSERTION
License Family: other
Topics: avatar, humanoid-control, humanoid-robot, isaac-gym, physics-simulation
Last push: 2025-08-21T18:34:47+00:00

## Health v2 (maintenance only)
Score: 44/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 38, release rhythm 35, longevity 75
- inputs: {"age_days": 1053, "days_push": 377, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license, no_readme
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1280, forks 125 (observed 2026-08-28T04:04:13.625022+00:00)

## What it is
Official implementation of the ICCV 2023 paper 'Perpetual Humanoid Control for Real-time Simulated Avatars'. It provides a Python codebase for training physics-based humanoid controllers that drive real-time simulated avatars using Isaac Gym.

## Use cases
- simulate physically realistic humanoid avatars in real time
- train reinforcement learning policies for humanoid motion control
- reproduce results from the PHC ICCV 2023 paper
- build physics-based character animation for games or VR
- track motion capture data with simulated humanoid agents

## When to avoid
- you need kinematic animation without physics simulation
- you lack a CUDA GPU or Isaac Gym environment
- you want a production-ready animation middleware rather than research code

## Facets
- artifact type: library
- maturity: active
- function: simulation, machine-learning, deep-learning, graphics
- domain: simulation, machine-learning, graphics, robotics
- platform: python
- tags: humanoid-control, avatar-animation, physics-simulation, isaac-gym, reinforcement-learning, research-code, linux, gpu

## Member repositories
- ZhengyiLuo/PHC (main) score 44

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:13.625022+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 2026-08-30T05:02:35.859669+00:00, confidence not recorded.
  - homepage: https://zhengyiluo.github.io/PHC/ (fetched 2026-08-29T12:13:16.039657+00:00, sha a51a5cbd0d4f)
- Data as of 2026-08-30T08:39:29.467469+00:00.