가상 포토 센서 배열을 이용한 자율 주행 시스템

Abstract

We have studied the port-automation system which is requested by the steep increment of cost and complexity for processing the freight. This paper will introduce a new algorithm for navigating and controlling the autonomous guided vehicle (AGV). The camera has the optical distortion in nature and is sensitive to the external ray, the weather, and the shadow, but it is very cheap and flexible to make and construct the automation system for the port. So we tried to apply to the AGV for detecting and tracking the lane using the CCD camera. In order to make the error stable and exact, this paper introduces a new concept and algorithm for obtaining the steering error is generated by the virtual photo-sensor array (VPSA). VPSAs are implemented by programming and very easy to use for the various autonomous systems. Because the load of the computation for extracting the steering error is light, the AGV utilizes the maximal performance of the CCD camera and enables the CPU to take multi-tasks. The disadvantage of VPSA is very sensitive because it depends on the narrow line of the road. If the AGV is insensible to control, it is easy to miss the line so that it is impossible to recover the status. We introduce the dynamic virtual photo-sensor array(DVPSA) which searches and tracks the line dynamically. For using the DVPSA, the current location and the orientation of the VPSA are always updated to estimate the location of the line when the value of the VPSA is zero, that is, the scope of the current VPSA can’t find the region of the line as feature points. We experimented on the proposed algorithm using the mobile robot and the moving pictures. We confirmed the stable and excellent performance for tracking the lane. Although the quality of the tracking performance is improved, the time of the calculation for the error generation is reduced. Among the characteristics of the VPSA, the fast speed for processing the error is very important, that is, the real time control is possible.