Challenges in Visual Navigation of AGV and Comparison Study of Potential Solutions

Abstract

As automation and informatization become a prevailing trend in industries, goods delivery and transportation are pivotal. Autonomous Guided Vehicles (AGV) is such a machine that can navigate while autonomously traveling. Besides saving labor, AGV can work in harsh and brutal conditions, which accounts for its popularity in industrial scenarios. In the following, we intend to discuss the design of the AGV navigation system from the perspective of vision parts. First, an in-depth comparison among different sensors on the existing navigation system will explain our choice of the visual navigation system. Then we will reveal three common challenges faced with visual navigation, i.e., poor illumination, limited view, and video data redundancy, and compare the merits and demerits of state-of-the-art solutions respectively. Our findings may offer practical suggestions for AGV design in real scenarios.