Robotic weeding of a maize field based on navigation data of the tractor that performed the seeding (Preprint)

This research presents robotic weeding of a maize field based on navigation data of the tractor that performed the seeding. The availability of tractors equipped with RTK-DGPS based automatic guidance potentially enables robots to perform subsequent tasks in the same field. In an experiment a tractor guidance system generated a route for sowing based on an initial path consisting of two logged positions (A-B line) and then planned the subsequent paths parallel to the initial path one working width apart. After sowing the maize, the A-B line was transferred to the Intelligent Autonomous Weeder (IAW) of Wageningen University. The IAW generated a route plan based on this A-B line and eight coordinates defining the borders of the field and the two headlands. It then successfully performed autonomous weeding of the entire field except of the headlands. The row width was 75 cm and the width of the hoes mounted on the robot was 50 cm. The results show that it is possible to perform robot weeding at field level with high accuracy based on navigation data of the tractor that performed the sowing