Finding a pathway between crop rows is essential for automated guidance of some agricultural vehicles. The research reported in this paper developed a vision-based method for detecting crop rows. This method applied the Hough transform and connectivity analysis to process images of a vehicle's forward view and to use them to find the appropriate pathway in the field. The Hough transform was used to detect crop rows and the connectivity analysis was applied to identify the most suitable path from all possible choices. This system was implemented in an agricultural tractor and tested in both laboratory and field experiments. The methodology devised overcame image noise problems and successfully determined the proper trajectory for the tractor.

No abstract

No abstract

Most off-road vehicles employ fluid power to actuate their steering system. Although the actual force that turns the wheels is exerted by hydraulic cylinders, the critical element of a steering control system is the directional control valve. Auto-steering control is typically achieved by sending electrical signals to the valve solenoid drivers. A fuzzy logic controller was designed to create such steering signals. The fuzzy control algorithm was implemented in a hardware-in-the-loop electrohydraulic steering simulator. A set of 25 logic rules was defined to represent the four types of valve characteristic curve observed in different steering operations. The performance of the steering system depended on both the steering signal characteristics and the controller functionalities. The results obtained from this research provided some fundamental information for designing high-performance electrohydraulic steering controllers for autonomous off-road vehicles.

This paper presents the use of a feedforward-plus-proportional-integral-derivative ( FPID) controller for improving the control performance of the electrohydraulic steering system on an oroad vehicle. The FPID controller used an inverse valve transform in the feedforward loop to compensate for an electrohydraulic steering system deadband and used a conventional PID feedback loop to minimize the tracking error in steering control. On-simulator evaluation tests veri ed that the FPID resulted in a superior steering rate tracking performance over both a feedforward controller and a PID controller. On-vehicle evaluation tests veri ed that this FPID controller could achieve prompt and accurate steering angle tracking for agricultural vehicle automated guidance applications.