Autonomous Agricultural Robot and its Row Guidance

Abstract

A vision-based row guidance method is presented to guide a robot platform which is designed independently to drive through the row crops in a field according to the design concept of open architecture. Then, the offset and heading angle of the robot platform are detected in real time to guide the platform on the basis of recognition of a crop row using machine vision. And the control scheme of the platform is proposed to carry out row guidance. Finally, the preliminary experiments of row guidance were implemented in a vegetable field. Experimental results show that algorithms of row identification and row guidance are effective according to the parameters measured and analyzed such as the heading angle and the offset for row guidance and the difference between the motion trajectory of the robot and the expected trajectory. And the accuracy of row guidance is up to ± 35 mm, which means that the robot can move with a sufficiently high accuracy.