Obstacle and Lane Detection on the ARGO Autonomous Vehicle

This work presents ARGO, the autonomous experimental vehicle developed at the Dipartimento di Ingegneria dell’Informazione of the University of Parma, Italy. ARGO integrates the main results that have been extensively tested on the MOB-LAB mobile laboratory, namely the GOLD (Generic Obstacle and Lane Detection) system: a stereo vision-based hardware and software architecture that allows to detect both generic obstacles (without constraints on shape, color, or symmetry) and the lane position in a structured environment (with painted lane markings). In addition, ARGO is currently used to test a new approach that allows to handle also non-flat roads. ARGO has autonomous steering capabilities and is expected to be soon enhanced with an automatic speed control. Different processing engines, ranging from dedicated systems to general-purpose architectures, are being evaluated to support the real-time processing of images on ARGO.