Tracking a Ground Moving Target with UAV Based on Interval Type-2 Fuzzy Logic

In recent years, tracking a ground moving target with an unmanned aerial vehicle (UAV) has played a key role in navigation, military reconnaissance, field rescue, and traffic monitoring tasks. However, due to the maneuvering uncertainty of the moving target and various uncertainties in the complex environment, it has brought many difficulties to the tracking task. In this paper, aiming at addressing the various uncertainties in the process of target tracking with UAV, we present a control strategy based on interval type-2 fuzzy logic. We design two interval type-2 fuzzy controllers to control the yaw angle and speed of the UAV, respectively. Images obtained from an embedded camera on the UAV platform are visually processed by the target recognition and tracking algorithms in the early stage to detect the pixel position of the target in every frame, which is used as the input of the controller we have designed. Through the analysis of the input and output data of controllers designed by us and the analysis of the tracking error, the reliability of control strategy proposed by us is proved. At last, a series of simulation experiments are implemented in ROS to demonstrate the performance of the target-tracking strategy we proposed.