Development of autonomous navigation system for rice transplanter

Abstract

Rice transplanting requires the operator to manipulate the rice transplanter in straight trajectories. Various markers are proposed to help experienced drivers in keeping straightforward and parallel to the previous path, which are extremely boring in terms of large-scale fields. The objective of this research was to develop an autonomous navigation system that automatically guided a rice transplanter working along predetermined paths in the field. The rice transplanter used in this research was commercially available and originally manually-operated. An automatic manipulating system was developed instead of manual functions including steering, stop, going forward and reverse. A sensor fusion algorithm was adopted to integrate measurements of the Real-Time Kinematic Global Navigation Satellite System (RTK-GNSS) and Inertial Measurement Unit (IMU), and calculate the absolute moving direction under the UTM coordinate system. A headland turning control method was proposed to ensure a robust turning process considering that the rice transplanter featured a small turning radius and a relatively large slip rate at extreme steering angles. Experiments were designed and conducted to verify the performance of the newly developed autonomous navigation system. Results showed that both lateral and heading errors were less than 8 cm and 3 degrees, respectively, in terms of following straight paths. And headland turns were robustly executed according to the required pattern.