Object Following Controller Design for Four Wheel Independent Steering Automatic Guided Vehicle

This paper presents a vision-based object following four wheel independent steering automatic guided vehicle (4WIS-AGV) system using Kinect camera sensor. To do this task, the following steps are executed. Firstly, an image processing is done for object detection using Kinect camera sensor. A candidate colored object is detected using color-based object detection method and its position in local coordinates is obtained. NAV200 navigation sensor is used to obtain global position of the detected object and the 4WIS-AGV. Secondly, the position of the detected moving object is estimated using Kalman filter algorithm. Kalman filter is used to estimate the global position of the detected moving object. Thirdly, a backstepping controller based on Lyapunov stability is proposed to achieve object following task. Finally, the effectiveness of the proposed system is verified by using simulation and experimental results. The results show that the proposed controller makes the 4WIS-AGV follow the detected moving object well with an acceptable error.