urban_road_filter
- Software
- Perception
- Library
A ROS 2 package that filters LIDAR point clouds to find drivable road and curb points in urban scenes, intended for autonomous vehicles. It runs in real time.
Made by jkk-research.
Source on GitHub: github.com/jkk-research/urban_road_filter (opens in a new tab). Facts read at commit eb74c4c (opens in a new tab).
Licenses
- Code
- BSD-3-Clause (opens in a new tab)
Read by Robotheca from LICENSE (opens in a new tab) (BSD-3-Clause) at commit eb74c4c (opens in a new tab), on 22 Oct 2026.
- Commercial use
- Yes
What it does
- Detects roadside points with three methods: x_zero_method, z_zero_method and star_shaped_method, each configurable on or off.
- Crops the point cloud to a configurable detection area and filters points by LIDAR vertical resolution.
- Detects curbs using height and point-count parameters, and can simplify the road polygon.
- Publishes road, curb, region-of-interest and road visualization markers as ROS topics.
- Reports segmentation statistics counting points classified as road, curb or non-road.
- Configured through a parameters.yaml file; a launch file starts the node with sample data and visualization.
Written by Robotheca from the project's README (opens in a new tab) at commit eb74c4c.
Getting started
- Difficulty
- Advanced
- How to start
- The project's website (opens in a new tab)
Maintenance
- Status
- Maintained: a commit in the last 12 months
- Newest commit
- 6 Jul 2026 on ros2
- Latest release
- v.1.2.0 (16 Jun 2025)
Checked on GitHub on 22 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.