Metadata-Version: 2.1
Name: csdecomp
Author: Peter Werner
Author-email: wernerpe@mit.edu
Home-page: https://github.com/wernerpe/csdecomp
License: MIT
Description-Content-Type: text/markdown
Summary: GPU-accelerated configuration space decomposition for robot motion planning
Classifier: Development Status :: 4 - Beta
Classifier: Intended Audience :: Science/Research
Classifier: License :: OSI Approved :: MIT License
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Classifier: Topic :: Scientific/Engineering :: Physics
Requires-Dist: numpy>=2.0.0
Version: 0.1.2

# CSDecomp: Configuration Space Decomposition Toolbox

GPU-accelerated configuration space decomposition for robot motion planning.

CSDecomp provides GPU-accelerated collision checking and algorithms for computing approximate convex decompositions of robot configuration spaces, including Dynamic Roadmaps (DRMs) and the Edge Inflation Zero-Order (EI-ZO) algorithm.

- **Paper:** [Superfast Configuration-Space Convex Set Computation on GPUs for Online Motion Planning](https://arxiv.org/pdf/2504.10783)
- **Project Website:** [https://sites.google.com/view/GPUpolytopes](https://sites.google.com/view/GPUpolytopes)
- **GitHub:** [https://github.com/wernerpe/csdecomp](https://github.com/wernerpe/csdecomp)

## Requirements

- Linux (x86_64)
- NVIDIA GPU with CUDA support
- Python 3.10, 3.11, or 3.12

## Installation

```bash
pip install csdecomp
```

