Ricerc@Sapienza

This paper presents self-driving control experiments applied to a standard vehicle equipped with an autonomous driving kit. The Auto Sapiens project is an experimental platform to test different control strategies and develop new obstacle avoidance algorithms. The Smart Fortwo vehicle is equipped with steering, thrust and brake actuators, and proprioceptive and exteroceptive sensors to identify both real-time vehicle attitude and obstacles on the track. The vehicle is controlled by a hardware in the loop system, in which innovative nonlinear control logics, called Feedback Local Optimality Principle FLOP, are implemented to achieve high performance in maintaining the stability of the vehicle during avoidance abrupt maneuvers. Tests were carried out through an adhoc vehicle-to-vehicle (V2V) communication system to share location, speed, heading and size information between the obstacle and the controlled vehicle. Eventually, a performance analysis of the system is made in terms of crash probability.