Click on “Download PDF” for the PDF version or on the title for the HTML version.
If you are not an ASABE member or if your employer has not arranged for access to the full-text, Click here for options.
Digitalizing and controlling a conventional tractor for autonomous farming work
Published by the American Society of Agricultural and Biological Engineers, St. Joseph, Michigan www.asabe.org
Citation: 2021 ASABE Annual International Virtual Meeting 2100107.(doi:10.13031/aim.202100107)
Authors: Hao Wang, Yaxin Ren, Weiqiang Fu, Zhijun Meng
Keywords: Dynamic mode decomposition, Pure pursuit control, Robot tractor, Smart agriculture.
Abstract. We present a solution to converting a conventional tractor to an autonomous vehicle. The solution consists of two steps: digitalizing vehicle status, and developing an autonomous navigation system. A vehicle control unit is designed to analyze the driver operations, transmit the commands to actuators, and broadcast tractor statuses following the ISO 11783 protocol. A dual-antenna GNSS position system provides centimeter-level accuracy vehicle position, velocity, orientation, and roll angle. This configuration enables the robot tractor to work in auto-steering mode and fully autonomous mode. A vehicle state simulator based on the dynamic mode decomposition method is developed to improve the vehicle positioning accuracy. In addition, a modified pure pursuit control algorithm provides about 4.4 cm path tracking accuracy with the vehicle speed up to 4 m/s. The solution of digitalizing and controlling a tractor is proved to be a sustainable and effective way to reduce human labor dependency and to improve the working quality.
(Download PDF) (Export to EndNotes)