cuRobo
- Software
- Robot arms and industry
- Library
A CUDA-accelerated library for robot motion generation, covering kinematics, collision checking, trajectory optimization and GPU perception. It targets arms up to high-DoF humanoids.
Made by NVIDIA Research.
Source on GitHub: github.com/NVlabs/curobo (opens in a new tab). Facts read at commit 78fd485 (opens in a new tab).
Licenses
- Code
- Apache-2.0 (opens in a new tab)
Read by Robotheca from LICENSE (opens in a new tab) (Apache-2.0) and LICENSE_ASSETS (opens in a new tab) (Apache-2.0) at commit 78fd485 (opens in a new tab), on 16 Oct 2026.
- Commercial use
- Yes
What it does
- Dynamics-aware trajectory optimization using B-spline trajectories that enforce smoothness and torque limits.
- GPU-native ESDF perception that builds dense signed distance fields from depth images.
- Whole-body computation with topology-aware kinematics, differentiable inverse dynamics and map-reduce self-collision for high-DoF robots.
- Collision-free motion generation that combines inverse kinematics, geometric planning and trajectory optimization.
- Built on PyTorch, CUDA and Warp.
Written by Robotheca from the project's README (opens in a new tab) at commit 78fd485.
Getting started
- Difficulty
- Advanced
- How to start
- The project's website (opens in a new tab)
Maintenance
- Status
- Active: a commit in the last 90 days
- Newest commit
- 10 Sept 2026 on main
- Latest release
- cuRoboV2 research and Open Source (Apache 2.0) (18 Apr 2026)
Checked on GitHub on 16 Oct 2026.
Links
Robots on Robotheca that use it
No robot on Robotheca is linked to it yet. Links come from a robot's robot.yaml, from its dependency files read as text, or from Robotheca's editors.
Robotheca lists software as a reference: nothing is hosted or run here, and every fact links to where it was read.