A study on intelligent path following and control for vision-based automated guided vehicle

Abstract

Vision-based AGV is a topic research in intelligent mobile robot field. One difficult problem is the long period of image acquisition and processing, which result in low speed and bad navigation accuracy. In this paper, the vision system and other sensors are integrated. The vision system detects the guideline information and constructs the degree of complication function (DCF). Then the look-ahead intelligent planning of velocity is carried out by the application of fuzzy linguistics. The fused information based on multi-sensors is applied to real time steering control. So the system has intelligent adaptability to the complex lane, which make the AGV realized high speed and accurate path following. And the conflict-free planning, two-phase conflict-free control and path resume method are also proposed for dealing with the accident (an obstacle or a breakdown AGV), which improve the reliability of system. The simulation research and real application results can prove the effectiveness of the method.