The identification and positioning of a master is essential for the master-slave cooperative operation of agricultural machinery. This study aimed to develop an agricultural vehicle dynamic identification and tracking method for agricultural master-slave follow-up operation using improved YOLO v4 and binocular positioning. The regular pruning algorithm was used to trim the original YOLO v4 channel to achieve a fast and accurate identification of master vehicle. The principle of binocular vision positioning was used to calculate the position of the master. The method (IYO-BPO) proposed in this study fused target detection and binocular vision positioning together, which was used to identify and track the master vehicle in real time. To evaluate the performance of the developed method, RTK-GPS and a gyroscope were installed on the master vehicle to obtain the reference position and heading angle. Identification and tracking experiments of both the linear and S-shaped movement of the master were conducted. The RMS errors were 0.067 m, 0.203 m, and 2.602° in terms of the longitudinal, lateral, and heading angle deviation, respectively, when the master moved along a straight line. The results show that the master vehicle could be identified and tracked by the IYO-BPO correctly and effectively.

Existing agricultural tractor path tracking methods rarely consider tracking accuracy and driving stability simultaneously. To solve this problem, a novel path tracking method of tractor is proposed in this paper. The method contains two layers of controllers. The first layer is the desired front wheel steering angle controller based on path prediction, and the desired yaw rate of tractor can be obtained by reference model expression. The second layer is the front wheel steering angle compensation controller based on improved second-order sliding mode (SOSMC) to improve tractor driving stability. The innovation of SOSMC is a combination of nonlinear integral sliding mode (NISM) surface and improved Super-Twisting algorithm, which can not only improve the rate of the control system to the sliding mode surface, but also suppress chattering. To verify the performance of SOSMC, the simulations are carried out on three paths at the constant speed of 10 km/h through Matlab/Simulink and Carsim. Three working paths including arched, pear-shape and lemniscate are constructed in Carsim. The results show that the control effect under three controllers is better than no control. Compared with no control, the maximum value and root mean square (RMS) of lateral error under SOSMC are reduced by 13.09% and 25.07% on average in three paths, and that of yaw rate are decreased 53.29% and 54.64%. The tracking accuracy of SOSMC is the best of three controllers, and that of NISMC is better than SMC. Compared with NISMC, the maximum value and RMS of yaw rate under SOSMC are reduced by 37.74% and 43.62% on average. The yaw rate, front wheel steering angle compensation value and chattering amplitude of front wheel steering angle under SOSMC are significantly smaller than those of SMC and NISMC. In summary, the novel path tracking method can simultaneously satisfy the accuracy and stability of the tractor when it tracks the field working path.