A hawk-inspired metaheuristic for trajectory optimization of UAVs in precision agriculture

Abstract

Unmanned Aerial Vehicles (UAVs) have become central to precision agriculture, where efficient trajectory planning over large fields directly determines mission feasibility, energy use, and the quality of acquired data. We address the problem of generating an optimal, fully covering trajectory for a single UAV operating over a plantation field modeled as a graph of waypoints. The problem is a constrained variant of the Travelling Salesman Problem in which all waypoints must be visited, total path length and turning cost must be minimized, and an energy budget must be respected. Existing metaheuristics such as Particle Swarm Optimization, Grey Wolf Optimizer, and Harris’s Hawks Optimization struggle to balance exploration with the strict coverage constraint of plantation scenarios, and tend to converge prematurely on irregular layouts. We propose the Hawk-Inspired Trajectory Optimizer (HITO), a new population-based metaheuristic whose search behavior is inspired by the soaring, patrolling, and stooping phases of hawks. HITO introduces a thermal-soaring exploration operator, a territorial-patrol transition operator, and a stoop-dive exploitation operator, supported by a coverage-repair mechanism that guarantees feasibility at every iteration. We provide a Markov-chain argument for convergence and an O(N·n²) per-iteration complexity bound, where N is population size and n are the number of waypoints. HITO is benchmarked on simulated plantation fields of 1, 3, and 5 hectares against seven baselines, and on twelve CEC 2017 benchmark functions. Across thirty independent runs, HITO reduces path length by 12.4 % on average over the best baseline, lowers energy consumption by 14.1 %, improves coverage robustness, and converges in fewer generations. Statistical significance is confirmed using Wilcoxon signed-rank and Friedman tests.