摘要：The current method which is used to track and control the motion trajectory of an unmanned vehicle has poor stability and uniqueness of the extracted feature points, resulting in large tracking deviations of vehicle speed and displacement, and low control accuracy. In this study, a SIFT algorithm-based tracking control method for unmanned vehicles in urban environments is proposed, which can obtain high stability and unique feature points. We input the feature points into the Kalman predictor to obtain the motion information and position information of the unmanned vehicle and realize the tracking of the un-manned vehicle's trajectory. The expert PID control-ler is used to control the trajectory of the unmanned vehicle in the urban environment according to the tracking result of the vehicle trajectory. The experi-mental results show that the speed and displacement curve deviation of tracking the unmanned vehicle is small, and the path tracking effect only slightly de-viates from the turning point and the path after tum-ing. The control accuracy obtained in multiple itera-tions is above 80%, which proves that the proposed method has small tracking deviation and high control accuracy.
关键词：Urban environment;SIFT algorithm;unmanned vehicle;vehicle tracking;trajectory control
