CudaRobotics Docs

GPU robotics toolkit

CudaRobotics Docs

Install the v0.1.0 release, run GPU MPPI from Python, load the CUDA MPPI controller in Nav2, and reproduce the checked-in benchmark reports without hunting through the repository tree.

Start installing Open Python API Open Nav2 guide

Fast Paths

Choose the entry point that matches how you want to try the project.

Browser

Colab quickstart

Build the Python package and run MPPI plus registration demos from a notebook.

Open Colab

Release

v0.1.0 assets

Download the source distribution or Linux x86_64 wheels from GitHub Releases.

Open release

Container

Docker demo

Run the Nav2 CUDA MPPI plugin smoke and benchmark path from GHCR.

Run Docker demo

Core Guides

Nav2 CUDA MPPI Controller

Plugin setup, parameter validation, motion models, smoke tests, and the controller architecture boundary.

Benchmark Results

Fixed-seed MPPI suites, Nav2 CPU-vs-GPU comparisons, and registration external baselines.

Research Notes

MPPI reproduction zoo, planning demos, perception demos, and reproducibility notes.

Nav2 CUDA MPPI Gazebo demo
Nav2 CUDA MPPI controller running through a Gazebo mission.

Release Snapshot

v0.1.0 turns the repository from a demo gallery into a usable GPU robotics toolkit.

Area What is included Where to go
Python GPU MPPI planner and point-cloud registration bindings. Python API
Nav2 CUDA MPPI controller plugin with DiffDrive, Ackermann, and Omni support. Nav2 guide
Distribution GitHub release assets, Colab quickstart, and GHCR demo image. Install guide
Evidence Checked-in benchmark reports with reproducible scripts and visible caveats. Results index