Optimizing multi-machine path planning for crop precision seeding with Lovebird Algorithm

Abstract

This paper investigates path planning in agriculture, with a specific focus on the seeding process. It underscores the crucial role of path planning in enhancing the efficiency and productivity of agricultural machinery operations. The research is centered on minimizing the operational times for agricultural robots, encompassing sowing activities and auxiliary travel periods. The study compares the effectiveness of the Lovebird Algorithm against the Genetic Algorithm (GA) and Ant Colony Optimization (ACO) in optimizing routes for precision seeding across various field layouts, addressing a range of geometric and operational challenges. The proposed Lovebird Algorithm demonstrates a runtime efficiency approximately three times faster than GA and one and a half times faster than ACO. Furthermore, it consistently reduces auxiliary travel distances by 14% compared to GA and 28% compared to ACO in the crop-seeding scenario. The findings align with the objectives of precision seeding by efficiently guiding machinery, thereby reducing travel-time and auxiliary travel distances. The proposed algorithm exhibits efficient computational performance, suggesting its suitability for time-sensitive agricultural operations that demand timely decision-making. Overall, the results have the potential to provide a tool that conserves resources and enhances efficiency in the agricultural sector, contributing to future advancements in precision agriculture technology.