The Research Of Road Recognition And Tracking Control On Automated Guided Vehicle

Automated Guided Vehicles (AGV) have many potential applications in manufacturing, medicine, space and military fields etc. AGV can successfully reach its destination or move along a desired path in an environment characterized by a terrain. Path tracking is a basic ability of AGV, which is also the goal of AGV guidance. The control strategy and real-time are two main factors to navigation capability and tracking precision of AGV.In order to improve the capability and flexibility in navigating, the thesis makes an improvement based on the primary structure of AGV. And an AGV experiment platform with visual navigation system is done and a real-time control system of integrated by software and hardware is developed. Applying the theory of kinematics, the kinematics model of AGV body is given. According to the load of AGV and kinematics demands, the style of the motor and battery has been chose.The image processing is a key technique among the researches of AGV. The image collection card is developed using Visual C++ language, making it implement image collection, landmark recognition and motor control, which resolves the problems such as noise elimination, the edge of the mark line obtaining and the location of the AGV during the process of image processing.Tracking control is another key technique among the researches of AGV. Therefore, it is very important to design a control system which has a little tracking error, rapid dynamic response and which is fit for various work-status, having a better robust. With Simulation, which is a part of the world-wide used computing tool, Matlab, the Human-Imitating Intelligent Control model for AGV is built. The control-system is simulated and analyzed at various work-status and the controller parameters are amended. The simulation results show that the algorithm can satisfy the requirements of navigation control system of the AGV. The Human-Imitating Intelligent Control model has a wide wedge for different tracking paths, and has a better capability of anti-yawp.In order to verify the simulation, all software needed is programmed with Visual C++ language and realizes all functions. Tracking and controlling experiments of AGV have been done at various work-status. The data and pictures obtained in experiments show that Human-Imitating control system of AGV can achieve the goals. The experiment results show that visual navigation controlling system of AGV implemented is valid, it can efficiently perform the real-time control task, and possess the characteristics with little tracking error and dynamic response.