Automated guided vehicle (AGV) lane-keeping assist based on computer vision, and fuzzy logic control under varying light intensity
Munadi Munadi, Bagas Radityo, Mochammad Ariyanto, Yoshiaki Taniai
Abstract
This paper discusses the development of an automated guided vehicle (AGV) model equipped with a navigation system. The AGV employs computer vision and fuzzy logic control for the lane-keeping assist system as a steering control. The inputs used in fuzzy logic control are the AGV path line gradient values for the left and right lanes. The navigation system uses a camera with a high level of light sensitivity. A light intensity that is too dim or bright will affect the steering control performance, meaning that a certain range of light intensity will affect the performance of the lane-keeping assist. A path with left and right lanes is built to test the performance steering control based on computer vision. The result shows that the optimal light intensity for the developed lane-keeping assists is from 110 to 150 lux. The AGV can successfully follow the path under these light intensities although the deviation still occurs.