Document Type : Research Paper
Authors
1
MSc student of Biosystems Engineering, Faculty of Agricultural Engineering, Sari Agricultural Sciences and Natural Resources University, Sari, Iran
2
Assistant Professor of Agricultural Machinery-Faculty of Agricultural Engineering- Sari Agricultural Sciences and Natural Resources University
3
Associate Professor of Biosystems Engineering, Faculty of Agricultural Engineering, Sari Agricultural Sciences and Natural Resources University, Sari, Iran
10.22059/ijbse.2025.393592.665594
Abstract
Robotics is a branch of engineering science that includes the design, construction, operation, and use of robots by computer systems, control, sensor feedback, and information processing. The ultimate goal of using robots in agriculture is to increase speed, accuracy, and precision in the stages of planting, tending, and harvesting crops. The overall goal of the present study is to evaluate the deviation of an automated solar sprayer robot used in gardens from the trained path. For this purpose, after training the path using the optimized YOLO v8 model for the solar-powered automatic sprayer robot, tests were conducted considering 2 input variables including 3 types of surfaces (asphalt, concrete, and gravel soil) and 3 forward speeds (1, 2, and 3 km/h), and the amount of deviation of the robot from the trained path was measured as the output variable. The results showed that the optimized YOLO v8 model, with its high accuracy and generalizability, is suitable for practical applications such as autonomous robot navigation in garden environments. Both factors of forward speed and surface type had a significant effect on the amount of deviation of the robot from the trained path, such that the robot had the highest amount of deviation at high speed (3 km/h) and uneven road surface (dirt road with gravel) and the lowest amount of deviation at low speed (1 km/h) and smooth surface (asphalt).
Keywords
Main Subjects
)