T. Bakker

An autonomous weeding robot for organic farming

The objective of this research is the replacement of hand weeding in organic farming by a device working autonomously at field level. The autonomous weeding robot was designed using a structured design approach, giving a good overview of the total design. A vehicle was developed with a diesel engine, hydraulic transmission, four-wheel drive and four-wheel steering. The available power and the stability of the vehicle does not limit the freedom of research regarding solutions for intra-row weed detection and weeding actuators. To fulfill the function of navigation along the row a new machine vision algorithm was developed. A test in sugar beet in a greenhouse showed that the algorithm was able to find the crop row with an average error of less than 25 mm. The vehicle is a versatile design for an autonomous weeding robot in a research context. The result of the design has good potential for autonomous weeding in the near future.

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

Abstract 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.