Stairway Detection
Index
3D Graph Based Stairway Detection and Localization for Mobile Robots
Perception is the main key in enabling robots to react to and interact with their environment. Particularly, for multi-floor operations, the robot must robustly detect and localize stairs to allow for safe climbing. In this research, we developed a graph-based (right figure) stairway detection method for point cloud data, that can detect a large variety of stairways. The approach first segments planar regions and extracts the stair tread- and stair riser-shaped segments. With these segments, a dynamic graph model is initialized that is used to detect stairs including the railing system in the surroundings. Our system can accurately detect and localize different stairways from a variety of different positions, including descending stairs and circular stairs (see figure below).
Detailed overview
A detailed version, explaining the algorithm in detail can be found at in the following two publications
Robust stairway-detection and localization method for mobile robots using a graph-based model and competing initializations
3D Graph Based Stairway Detection and Localization for Mobile Robots
Stairway Detection Code
The code for the stairway detection has been published on github and can be found at:
https://github.com/ThomasWestfechtel/StairwayDetectionGUI for the GUI version and
https://github.com/ThomasWestfechtel/StairwayDetection for the stand alone version
Stairway Dataset
The dataset is accesible at --> click here <---
The dataset contains of pointcloud data acquired of three different stairs from different positions.
For the acquisition a UTM-30LX Lidar was used that was mounted with a tilting angle on a rotating platform.
Contact
Do you have any questions or comments? Please contact: