Road geometry classification using ANN

Abstract

An autonomous car must have a robust perception system to navigate safely in urban streets. An important issue of environment perception is the road (navigable area) detection and the identification of the road geometry. The road geometry information can be used to determine the vehicle control according to the street and also for topological localization. Existing road geometry identifiers only work with a limited number of classes and, due to the use of cameras, some solutions depend on filters to deal with shadows and light variations. This paper presents a road detector that extracts curb and navigable surface information from a multilayer laser sensor data. 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 main advantage of our method is its robustness to light variations for detecting distinct roads even in the presence of noisy data thanks to the ANN. In order to determine which road information has the best features for ANN training, three approaches were explored: ANN trained with curb data, ANN trained with surface data and ANN trained with both curb and surface data. Performed experiments resulted in the superiority of the network trained with both curb and surface data, with an accuracy of 0.91799. The trained ANN was validated in different urban scenarios and, evaluating a 1 Km track, we obtained a 94.48% of correct classifications. These results are superior than other works that detect fewer number of road shapes.