Optimized Path Planning for UGV Based on Sampling Maps

摘要

This work proposes an optimized path-planning approach for soil sampling using an autonomous uncrewed ground vehicle (UGV) in precision agriculture. The field is divided into homogeneous management zones based on electrical conductivity (ECa) measurements, with sampling points strategically distributed within each zone. A path-planning algorithm minimizes the travel distance for the UGV while ensuring thorough data collection. The methodology combines geospatial analysis, inverse distance weighting interpolation, and clustering to assign accurate ECa values to grid points and classify zones. The novelty of this study lies not in the development of new algorithms but in the integration of established methods into a unified framework, implemented on a UGV and validated under real field conditions. The Greedy algorithm is applied to solve the <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">travelling salesman problem</i> to optimize the UGV’s route, ensuring efficient sampling. The sampling plan is uploaded to an Android application for manual guidance or to the UGV for autonomous operation. Equipped with sensors for measuring soil pH and compaction, the vehicle follows the predefined path, and data are stored for analysis. Experimental validation shows that the system reduces operational costs and improves soil health assessment, demonstrating the potential of autonomous robotic platforms in precision agriculture.