Performance Evaluation of an Autonomously Driven Agricultural Vehicle in an Orchard Environment

• Published in: Sensors (Basel, Switzerland) Vol. 22; no. 1; p. 114
• Main Authors: Han, Joong-Hee, Park, Chi-Ho, Jang, Young Yoon, Gu, Ja Duck, Kim, Chan Young
• Format: Journal Article
• Language: English
• Published: Switzerland MDPI AG 24.12.2021; MDPI
• Subjects: A C motors; Accuracy; agricultural vehicle; Agriculture; Automobile Driving; autonomous driving; Farm machinery; Field tests; Global positioning systems; GNSS; GPS; Internet of Things; Lasers; Microelectromechanical systems; Motion; motion sensor; Motion sensors; Navigation systems; Orchards; Path tracking; Performance evaluation; Pesticides; Population; Robots; Satellites; sensor fusion; Sensors; Software; Spraying; Technology; Tracked vehicles; Vehicles; sensor fusion; motion sensor; agricultural vehicle; GNSS; autonomous driving
• ISSN: 1424-8220; 1424-8220
• DOI: 10.3390/s22010114

To address the problems of inefficient agricultural production and labor shortages, there has been active research to develop autonomously driven agricultural machines, using advanced sensors and ICT technology. Autonomously driven speed sprayers can also reduce accidents such as the pesticide poisoning of farmers, and vehicle overturn that frequently occur during spraying work in orchards. To develop a commercial, autonomously driven speed sprayer, we developed a prototype of an autonomously driven agricultural vehicle, and conducted performance evaluations in an orchard environment. A prototype of the agricultural vehicle was created using a rubber-tracked vehicle equipped with two AC motors. A prototype of the autonomous driving hardware consisted of a GNSS module, a motion sensor, an embedded board, and an LTE module, and it was made for less than $1000. Additional software, including a sensor fusion algorithm for positioning and a path-tracking algorithm for autonomous driving, were implemented. Then, the performance of the autonomous driving agricultural vehicle was evaluated based on two trajectories in an apple farm. The results of the field test determined the RMS, and the maximums of the path-following errors were 0.10 m, 0.34 m, respectively.