A new controller to perform safe vision-based navigation tasks amidst possibly occluding obstacles

Abstract

This paper provides a new method allowing to safely perform a vision-based task amidst possibly occluding obstacles. Our objective is to fulfill the following two requirements: first, the robot safety by guaranteeing noncollision; second, the ability of keeping on realizing the vision-based task despite possible target occlusions or loss. To this aim, several controllers have been designed and then merged depending on the risks of collisions and occlusions. The presented simulation results validate the proposed approach.