# NVlabs/curobo

CUDA Accelerated Robot Library

Repository: https://github.com/NVlabs/curobo
Canonical: https://ross.abutalabs.com/products/curobo
Homepage: https://nvlabs.github.io/curobo
Language: Python
License: Apache-2.0
License Family: permissive
Topics: cuda, motion-planning, pytorch, robotics, inverse-kinematics, trajectory-optimization, tsdf
Last push: 2026-07-23T05:40:10+00:00

## Health v2 (maintenance only)
Score: 77/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 94, release rhythm 56, longevity 75
- inputs: {"age_days": 1055, "days_push": 41, "days_rel": 137, "gap_med": 153, "n_releases_24m": 4}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1794, forks 334 (observed 2026-08-28T04:05:37.209984+00:00)

## What it is
cuRobo is a CUDA-accelerated Python library for robot motion generation built on PyTorch, CUDA, and Warp. It provides GPU-parallel algorithms for forward/inverse kinematics, collision checking, trajectory optimization, geometric planning, GPU-native ESDF perception, and whole-body motion generation for manipulators and high-DoF humanoids.

## Use cases
- generate collision-free motion plans for robot arms on GPU
- compute inverse kinematics in parallel with CUDA
- optimize smooth dynamics-aware trajectories respecting torque limits
- build signed distance fields from depth images for collision avoidance
- plan whole-body motions for high-DoF humanoid robots
- check self-collisions and environment collisions quickly during planning

## When to choose
- you need fast GPU-parallel motion planning or IK for manipulators or humanoids
- your stack already uses PyTorch and NVIDIA GPUs
- you need depth-image-based distance fields for perception-aware planning

## When to avoid
- you have no NVIDIA CUDA-capable GPU
- you need a lightweight CPU-only planner
- you depend on the cuRobo v1 API without pinning to v0.7.8

## Facets
- artifact type: library
- maturity: active
- function: simulation, machine-learning, graphics, math
- domain: robotics, gpu-computing, autonomous-vehicles, simulation
- platform: python
- tags: cuda, motion-planning, inverse-kinematics, trajectory-optimization, pytorch, warp, collision-checking, esdf, tsdf, humanoids, manipulators, perception, linux, gpu

## Member repositories
- NVlabs/curobo (main) score 77

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:37.209984+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 2026-08-30T03:22:52.810533+00:00, confidence not recorded.
  - readme: https://github.com/NVlabs/curobo (fetched 2026-08-28T04:05:37.209984+00:00, sha d759e37ab484)
  - homepage: https://nvlabs.github.io/curobo (fetched 2026-08-29T11:01:41.262117+00:00, sha 611e9142d869)
- Data as of 2026-08-30T08:39:29.467469+00:00.