Patchwork++
- Software
- Navigation and mapping
- Library
Patchwork++ is a fast, robust, self-adaptive algorithm that segments the ground from 3D point clouds, available as C++, Python, and ROS2 packages.
Made by Urban Robotics Lab. @ KAIST, South Korea (checked on github.com/url-kaist (opens in a new tab)).
Source on GitHub: github.com/url-kaist/patchwork-plusplus (opens in a new tab). Facts read at commit 3e6903a (opens in a new tab).
Licenses
- Code
- BSD-2-Clause (opens in a new tab)
Read by Robotheca from LICENSE (opens in a new tab) (BSD-2-Clause) at commit 3e6903a (opens in a new tab), on 16 Oct 2026.
- Commercial use
- Yes
What it does
- Separates ground points from 3D point cloud data using adaptive elevation and flatness thresholds.
- Extends the earlier Patchwork method with reflected noise removal, vertical structure suppression, and probability-based ground revert.
- Ships a C++ library, a Python binding installable from PyPI as pypatchworkpp, and a ROS2 node.
- Also includes the classic Patchwork algorithm, selectable in the Python API and the ROS2 launch file.
- Provides a SemanticKITTI evaluation script for reproducible comparison of Patchwork and Patchwork++.
Written by Robotheca from the project's README (opens in a new tab) at commit 3e6903a.
Getting started
- Difficulty
- Intermediate
- How to start
- The project's README (opens in a new tab)
Maintenance
- Status
- Maintained: a commit in the last 12 months
- Newest commit
- 23 May 2026 on master
- Latest release
- v1.4.1 — Kill per-patch heap traffic in Patchwork++ (+14.8% Hz) (23 May 2026)
Checked on GitHub on 16 Oct 2026.
Links
Robots that can run 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.