To recognize the tender shoots for high-quality tea and to determine the picking points accurately and quickly, this paper proposes a method of recognizing the picking points of the tender tea shoots with the improved YOLO-v3 deep convolutional neural network algorithm. This method realizes the end-to-end target detection and the recognition of different postures of high-quality tea shoots, considering both efficiency and accuracy. At first, in order to predict the category and position of tender tea shoots, an image pyramid structure is used to obtain the characteristic map of tea shoots at different scales. The residual network block structure is added to the downsampling part, and the fully connected part is replaced by a 1 × 1 convolution operation at the end, ensuring accurate identification of the result and simplifying the network structure. The K-means method is used to cluster the dimension of the target box. Finally, the image data set of picking points for high-quality tea shoots is built. The accuracy of the trained model under the verification set is over 90%, which is much higher than the detection accuracy of the research methods.

Dynamic obstacle avoidance is essential for unmanned surface vehicles (USVs) to achieve autonomous sailing. This paper presents a dynamic navigation ship domain (DNSD)-based dynamic obstacle avoidance approach for USVs in compliance with COLREGs. Based on the detected obstacle information, the approach can not only infer the collision risk, but also plan the local avoidance path trajectory to make appropriate avoidance maneuvers. Firstly, the analytical DNSD model is established taking into account the ship parameters, maneuverability, sailing speed, and encounter situations regarding COLREGs. Thus, the DNSDs of the own and target ships are utilized to trigger the obstacle avoidance mode and determine whether and when the USV should make avoidance maneuvers. Then, the local avoidance path planner generates the new avoidance waypoints and plans the avoidance trajectory. Simulations were implemented for a single obstacle under different encounter situations and multiple dynamic obstacles. The results demonstrated the effectiveness and superiority of the proposed DNSD-based obstacle avoidance algorithm.

This paper presents a weight optimization method for a nonlinear model predictive controller (NMPC) based on the genetic algorithm (GA) for ship trajectory tracking. The weight coefficients Q and R of the objective function in NMPC are obtained via the real-time optimization of the genetic algorithm instead of the trial and error method, which improves the efficiency and accuracy of the controller. In addition, targeted improvements are made to the internal crossover operator, mutation operator, crossover rate, and mutation rate of the genetic algorithm. The simulation comparison of trajectory tracking between NMPC with real-time-optimized weight coefficients and the one with constant coefficients is performed. Finally, the simulation result shows that the controller with real-time-optimized weight coefficients has a better trajectory tracking effect than that with constant weight coefficients.

Modified adaptive observer based backstepping control system for dynamic positioning of ship is proposed. As an improvement, the adaptive observer takes the first-order wave frequency model and the bias term which represent the slowly varying environmental disturbances and the unmodeled dynamics. Thus, the wave-frequency motions are filtered out, and only the reconstructed low-frequency motions are sent as inputs of the controller. Furthermore, as the ship dynamics parameters are unknown, the adaptive estimation law is designed for both the unknown ship dynamics and the unmeasured state variables. Based on the estimated states and parameters, backstepping controller considering the integral action is designed. Global exponential stability (GES) for the total system is proved using Lyapunov direct method. Simulation results show a good performance of the observer and control system.