Development of machine vision and laser radar based autonomous vehicle guidance systems for citrus grove navigation

Current production navigation systems for agricultural vehicles rely on GPS as the primary sensor for steering control. In citrus groves, where the tree canopy frequently blocks the satellite signals to the GPS receiver, an alternative method is required. This paper discusses the development of an autonomous guidance system for use in a citrus grove. The vehicle used for this study was a common tractor. Machine vision and laser radar (ladar) were individually used for guidance and a rotary encoder was used to provide feedback on the steering angle. A PID controller was developed to minimize the path error. The vehicle's guidance accuracy was tested in flexible test paths constructed of common hay bales. Path tracking performance was observed. The guidance system guided the tractor automatically through straight and curved paths. An average error of 2.8 cm using machine vision guidance and an average error of 2.5 cm using ladar guidance was observed, when the vehicle was tested in a curved path at a speed of 3.1 m/s. The guidance system successfully guided the vehicle in a citrus grove alleyway.