Probabilistic vehicle control under occlusions

Given the progresses done in the autonomous driving, the vehicle control in presence of occlusions is one of the most important challenge in the autonomous driving scenario. Navigating without problems in urban environments is an issue for autonomous vehicles. Occlusion and limited sensor range can pose significant challenges to safely navigate among pedestrians and other vehicles in the environment. Enabling vehicles to quantify the risk posed by unseen regions allows them to anticipate future possibilities, resulting in increased safety, detection and avoidance of vehicle accidents as well as detection of vehicles with unusual behaviour. This thesis describes the implementation and the results of an algorithm useful to deal with occlusions when a car approaches a T-intersection. After the study of the state of art, the better algorithm has been chosen with respect to pros and cons and implemented in the Matlab environment. The last step has been the implementation of the algorithm in the ROS environment through a microscopic and continuous road traffic simulation package known as “Simulation of Urban Mobility (SUMO)”, which is open source, highly portable and able to handle wide road networks.