Due to the shortage of rural labor and an increasingly aging population, promoting the mechanized plucking of bulk tea and improving plucking efficiency have become urgent problems for tea plantations. Previous bulk tea plucking machines have not fully adapted to tea plantations in hilly areas, necessitating enhancements in the performance of cutter profiling. In this paper, we present an automatic cutter profiling method based on an RGB-D camera, which utilizes the depth information of bulk tea shoots to tackle the issues mentioned above. Specifically, we use improved super-green features and the Otsu method to detect and segment the shoots from the RGB images of the tea canopy taken from different lighting conditions. Furthermore, the cutting pose based on the depth value of the tea shoots can be generated as a basis for cutter profiling. Lastly, the profiling task is completed by the upper computer controlling motors to adjust the cutter pose. Field tests were conducted in the tea plantation to verify the proposed profiling method’s effectiveness. The average bud and leaf integrity rate, leakage rate, loss rate, tea making rate, and qualified rate were 81.2%, 0.91%, 0.66%, and 90.4%, respectively. The results show that the developed algorithm can improve cutting pose calculation accuracy and that the harvested bulk tea shoots meet the requirements of machine plucking quality standards and the subsequent processing process.

Neural Network has been used in approximation of dead zone nonlinearity when modeling the manipulator control systems. However the existed method fail to minimize the possible input saturation effect and the NN mapping accuracy also be degraded, which leads to degrading in tracking precise and accuracy. To establish an accurate control model of the tea picking robot, an adaptive compensator of m-RBF (modified radial basis function neural network) and adaptive law were designed aimed at the nonlinearity units and dead zone. The closed-loop tracking error of the proposed control system is eventually going to be stable and bounded. A simulation was carried out with Simulink, which show that m-RBF provides a good approximation to characteristic of Dead zone nonlinearity, and that the control scheme based on m-RBF had a excellent and stable tracking accuracy. The tea picking experiment with six-axis manipulator verifies the effectiveness of the proposed algorithm, in which the proposed method got a higher score of 95.3, near two times that of traditional PID control methods. It can be drown that the m-RBF has a faster learning rate and can avoid local minima; the control scheme based on m-RBF has a excellent performance on control accuracy, robustness and self-adaption, which is especially appropriate for real-time control, like tea picking robot.