Projects

Road Features Detection Using 3D LIDAR

Curb Detection

Our approach introduces the use of robust regression method for curb detection named least trimmed squares (LTS) to deal with occluding scenes in contrast of temporal filters and spline fitting methods.

Link to paper: Here

Road Marking Detection

We propose a road marking detector based on Otsu thresholding method that make possible segment intensity data of LIDAR point clouds into asphalt and road marking. The method is invariant to illumination, rotation and possible to detect any type of road marking (e.g. crosswalks, continuous lines, dashed lines).

Link to paper: Here

Road Shape Classification

The road data was trained with an artificial neural network (ANN) and classified into eight road geometries: straight road, left turn, right turn, left side road, right side road, T intersection, Y intersection and crossroad. The ANN is trained with features extracted from curb detection point cloud.

Link to paper: Here

Robot/Autonomous Car Localization

Vehicle localization using road features

In order to detect curbs even in occluding scenes, a method based on ring compression analysis and least trimmed squares has been developed. For road marking detection, we developed a modified version of the Otsu thresholding method to segment road painting from road surfaces. Finally, the feature detection methods were integrated with a Monte Carlo localization method to estimate the vehicle position. Experimental tests in urban streets have been used to validate the proposed approach with favorable results.

Link to paper: Here

Robot localization using continuous maps (GPOM)

Gaussian process occupancy map (GPOM) is a environment representation based on Gaussian Process that enables the construction of continuous maps (i.e. without discretization) using few laser measurements. This paper addresses a new localization method that uses GPOM to estimate the robot pose in areas not directly observed during mapping and generally provides higher accuracy compared to occupancy grid maps localization.

Link to paper: Here

Autonomous car localization using continuous maps in urban environments

Taking into account the superiority of GPOM over OGM, we devise a novel vehicle localization technique for urban environments. This solution enables more accurate localization due to the use of a representation that better models the real environment. The development of the proposed method is based on Monte Carlo localization (MCL) which is a popular map-aided localization method. Two road features commonly found in urban cities were chosen to build the maps: road curbs and road markings. Specifically, the proposed localization method relies on a GPOM constructed with curb data and an OGM built with road marking data.

Link to paper: Here