Goal directed reactive robot navigation with relocation using laser and vision

Abstract

This paper presents a method to perform a goal directed reactive navigation in unknown indoor environments. Two sensors cooperate to accomplish this task: trinocular vision and 3D laser rangefinder. Trinocular vision selects the initial goal location for the navigation task. Laser is used to accomplish a reactive navigation to avoid the obstacles and to periodically relocate the goal with respect to the robot, so the dead-reckoning drift is compensated. An extended Kalman filter is used to solve the data association problem and to perform the goal relocation while the robot navigates. Experimental results involving a real mobile robot are presented, validating the proposed method.