CPP-DIP: Multi-objective coverage path planning for MAVs in dispersed and irregular plantations

Abstract

Coverage Path Planning (CPP) is vital in precision agriculture to improve efficiency and resource utilization. In irregular and dispersed plantations, traditional grid-based CPP often causes redundant coverage over non-vegetated areas, leading to waste and pollution. To overcome these limitations, we propose CPP-DIP, a multi-objective CPP framework designed for Micro Air Vehicles (MAVs). The framework transforms the CPP task into a Traveling Salesman Problem (TSP) and optimizes flight paths by minimizing travel distance, turning angles, and intersection counts. Unlike conventional approaches, our method does not rely on GPS-based environmental modeling. Instead, it uses aerial imagery and a Histogram of Oriented Gradients (HOG)-based approach to detect trees and extract image coordinates. A density-aware waypoint strategy is applied: Kernel Density Estimation (KDE) is used to reduce redundant waypoints in dense regions, while a greedy algorithm ensures complete coverage in sparse areas. To verify the generality and scalability of the framework, TSP instances of varying sizes are solved using three methods: Greedy Heuristic Insertion (GHI), Ant Colony Optimization (ACO), and Monte Carlo Reinforcement Learning (MCRL). An object-based optimization is subsequently applied to further refine the paths. Additionally, CPP-DIP integrates ForaNav, our insect-inspired navigation method, for accurate tree localization and tracking. Experimental results show that MCRL provides a balanced solution, reducing travel distance by 16.9 % compared to ACO while maintaining comparable performance to GHI. It also improves path smoothness by reducing turning angles by 28.3 % and 59.9 % relative to ACO and GHI, respectively, and eliminates intersections. Computational resource comparisons further highlight that GHI scales efficiently with increasing waypoints, whereas ACO and MCRL incur higher computational costs. These results confirm the robustness, efficiency, and scalability of the proposed CPP-DIP.