Search

A row-following system based on end-to-end learning for an agricultural robot in an apple orchard was developed in this study. Instead of dividing the navigation into multiple traditional subtasks, the designed end-to-end learning method maps images from the camera directly to driving commands, which reduces the complexity of the navigation system. A sample collection method for network training was also proposed, by which the robot could automatically drive and collect data without an operator or remote control. No hand labeling of training samples is required. To improve the network generalization, methods such as batch normalization, dropout, data augmentation, and 10-fold cross-validation were adopted. In addition, internal representations of the network were analyzed, and row-following tests were carried out. Test results showed that the visual navigation system based on end-to-end learning could guide the robot by adjusting its posture according to different scenarios and successfully passing through the tree rows.

Traveling along straight lines and headland turning are two common motions during the automatic guidance of agricultural machines. However, most studies focus on accurately following parallel tracks in the field and seldom consider the maneuvers at the end of each row. Moreover, numerous studies have mainly focused on planning the global trajectories in the entire field to increase field efficiency, and very few works are related to maneuver generation and vehicle control in headlands. In this study, a feedforward-plus-proportional–integral–derivative controller for a differential drive robot in headland turning was developed. The feedforward-plus-proportional–integral–derivative controller consisted of a feedforward and a feedback loop. The feedforward loop was designed based on the heading errors of a lookahead point on the planning path. The feedback loop was designed based on radial errors to improve the tracking accuracy. Field comparison tests of feedforward, feedback, and feedforward-plus-proportional–integral–derivative controllers were conducted. Experimental results showed that the feedforward-plus-proportional–integral–derivative had better tracking results and took less turning time.

A row-following system based on machine vision for a picking robot was designed in our previous study. However, the visual perception could not provide reliable information during headland turning according to the test results. A complete navigation system for a picking robot working in an orchard needs to support accurate row following and headland turning. To fill this gap, a headland turning method for an autonomous picking robot was developed in this paper. Three steps were executed during headland turning. First, row end was detected based on machine vision. Second, the deviation was further reduced before turning using the designed fast posture adjustment algorithm based on satellite information. Third, a curve path tracking controller was developed for turning control. During the MATLAB simulation and experimental test, different controllers were developed and compared with the designed method. The results show that the designed turning method enabled the robot to converge to the path more quickly and remain on the path with lower radial errors, which eventually led to reductions in time, space, and deviation during headland turning.