Ricerc@Sapienza

The obstacle avoidance maneuver is required for an autonomous vehicle. It is essential to define the system's performance by evaluating the minimum reaction times of the vehicle and analyzing the probability of success of the avoiding operation. This paper presents a collision avoidance algorithm based on the velocity bstacle approach that guarantees collision-free maneuvers. The vehicle is controlled by an optimal feedback control named FLOP, designed to produce the best performance in terms of safety and minimum kinetic collision energy.

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.

Consider the problem of planning collision-free motions for a robot that is assigned a soft task constraint, i.e., a desired path in task space with an associated error tolerance. To this end, we propose an opportunistic planning strategy in which two subplanners take turns in generating motions.

A control system based on multiple sensors is proposed for the safe collaboration of a robot with a human. New constrained and contactless human-robot coordinated motion tasks are defined to control the robot end-effector so as to maintain a desired relative position to the human head while pointing at it. Simultaneously, the robot avoids any collision with the operator and with nearby static or dynamic obstacles, based on distance compu- tations performed in the depth space of a RGB-D sensor.