Cooperative Mission Planning for Multiple Aerial and Ground Vehicles Based on Evolutionary Computation

Abstract

The limited flight endurance of unmanned aerial vehicles (UAVs) necessitates multiple battery replacements to complete long-duration missions. In this paper, we address the cooperative mission planning of multiple UAVs and unmanned ground vehicles (UGVs), where UAVs are tasked with visiting a predetermined set of waypoints, and UGVs act as mobile battery replenishment platforms. The objective is to determine a cooperative mission plan that minimizes the overall mission completion time while respecting UAV flight time constraints. To this end, the mission is decomposed into a set of flight-and-recharge segments, and a genetic algorithm is applied to solve the resulting optimization problem. The proposed approach is evaluated using real-world datasets from three different operational areas. Extensive experiments are conducted to analyze parameter settings and validate the robustness of the method. Simulation results show that the algorithm adapts to variations in mission layout and can efficiently plan large-scale missions with thousands of waypoints, involving multiple UAVs and UGVs. A comparative study demonstrates that the proposed method achieves mission times very close to optimal solutions with a single-robot pair and remains competitive with a theoretical lower bound in multi-robot scenarios.