# NVlabs/GR00T-WholeBodyControl

Welcome to GR00T Whole-Body Control (WBC)! This is a unified platform for developing and deploying advanced humanoid controllers. This includes: Decoupled WBC models used in NVIDIA Isaac-Gr00t, Gr00t N1.5 and N1.6 and GEAR-SONIC

Repository: https://github.com/NVlabs/GR00T-WholeBodyControl
Canonical: https://ross.abutalabs.com/products/gr00t-wholebodycontrol
Homepage: https://nvlabs.github.io/GR00T-WholeBodyControl/
Language: Python
License: NOASSERTION
License Family: other
Last push: 2026-08-21T04:45:24+00:00

## Health v2 (maintenance only)
Score: 61/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 98, release rhythm 35, longevity 21
- inputs: {"age_days": 301, "days_push": 12, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 3428, forks 536 (observed 2026-08-28T04:08:03.961449+00:00)

## What it is
NVIDIA's unified platform for developing, training, and deploying whole-body controllers for humanoid robots, including the decoupled WBC models used in Isaac-GR00T N1.5/N1.6 and the GEAR-SONIC controller series. It provides model checkpoints, training and evaluation scripts, teleoperation support, and a C++ inference stack for deployment.

## Use cases
- train a humanoid whole-body controller with reinforcement learning
- deploy a whole-body controller on a Unitree G1 robot
- collect teleoperation data for VLA fine-tuning
- run whole-body teleoperation with a low-latency controller
- fine-tune Isaac-GR00T N1.7 and deploy with SONIC control
- evaluate humanoid locomotion controllers in Isaac Lab
- generate text-to-motion for animation and robotics

## When to choose
- you are working with humanoid robots and need state-of-the-art whole-body control
- you want to train or fine-tune controllers for the Isaac-GR00T VLA pipeline
- you need RL-based lower-body control combined with upper-body IK
- you want pretrained humanoid controller checkpoints to deploy or study

## When to avoid
- you need controllers for non-humanoid robots like arms or quadrupeds
- you want a lightweight simulation-only project without GPU requirements
- you need a general-purpose robotics middleware rather than humanoid WBC
- you cannot use NVIDIA Isaac Lab / Isaac Sim infrastructure

## Facets
- artifact type: framework
- maturity: active
- function: machine-learning, reinforcement-learning, simulation, robotics, llm-training
- domain: robotics, machine-learning, simulation, artificial-intelligence
- platform: python
- tags: humanoid-robots, whole-body-control, reinforcement-learning, teleoperation, vla, isaac-lab, motion-control, model-checkpoints, linux, gpu, docker

## Member repositories
- NVlabs/GR00T-WholeBodyControl (main) score 61

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:03.961449+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 2026-08-29T18:37:48.190214+00:00, confidence not recorded.
  - readme: https://github.com/NVlabs/GR00T-WholeBodyControl (fetched 2026-08-28T04:08:03.961449+00:00, sha 3e122e258203)
  - homepage: https://nvlabs.github.io/GR00T-WholeBodyControl/ (fetched 2026-08-29T09:32:10.657646+00:00, sha 3247b94c9fb7)
- Data as of 2026-08-30T08:39:29.467469+00:00.