An hybrid control for avoiding obstacles during a vision-based tracking task

Abstract

This paper presents an hybrid sensor-based controller allowing to drive a mobile robot towards a target in a cluttered environment. We consider the model of a cart-like robot with a camera mounted on a pan-platform. The proposed method combines visual servoing techniques allowing to track the target, with an obstacle avoidance strategy based on the information provided by a 2D laser range sensor. The feasability of the method is deduced from the convergence properties of both control methods. In particular, an algorithm is proposed to tune up the cart velocity so as to insure the obstacle avoidance, while avoiding the saturation of actuators. Simulation results are presented at the end of the paper.