Autonomous Navigation of Automated Guided Vehicle Using Monocular Camera

Abstract

This paper presents a hybrid control algorithm for Automated Guided Vehicle (AGV) consisting of two independent control loops: Position Based Control (PBC) for global navigation within manufacturing environment and Image Based Visual Servoing (IBVS) for fine motions needed for accurate steering towards loading/unloading point. The proposed hybrid control separates the initial transportation task into global navigation towards the goal point, and fine motion from the goal point to the loading/unloading point. In this manner, the need for artificial landmarks or accurate map of the environment is bypassed. Initial experimental results show the usefulness of the proposed approach.