Solving Complex Multi-UAV Mission Planning Problems using Multi-objective Genetic Algorithms

TL;DR

This work tackles complex multi-UAV mission planning with multiple ground control stations by introducing a hybrid MOGA-CSP framework. It encodes six alleles to capture task–UAV assignments, sequencing, GCS control, flight profiles, and sensors, then applies a two-phase fitness: CSP-based feasibility penalties followed by Pareto optimization over six objectives. The NSGA-II–style algorithm uses tailored crossover and mutation for each allele and stops when the Pareto front stabilizes, reporting strong hypervolume performance on several datasets, though larger problems require more generations. Overall, the approach enables coordinated, multi-GCS UAV missions with NFZ avoidance and time/resource constraints, offering a scalable method for high-stakes aerial planning.

Abstract

Due to recent booming of UAVs technologies, these are being used in many fields involving complex tasks. Some of them involve a high risk to the vehicle driver, such as fire monitoring and rescue tasks, which make UAVs excellent for avoiding human risks. Mission Planning for UAVs is the process of planning the locations and actions (loading/dropping a load, taking videos/pictures, acquiring information) for the vehicles, typically over a time period. These vehicles are controlled from Ground Control Stations (GCSs) where human operators use rudimentary systems. This paper presents a new Multi-Objective Genetic Algorithm for solving complex Mission Planning Problems (MPP) involving a team of UAVs and a set of GCSs. A hybrid fitness function has been designed using a Constraint Satisfaction Problem (CSP) to check if solutions are valid and Pareto-based measures to look for optimal solutions. The algorithm has been tested on several datasets optimizing different variables of the mission, such as the makespan, the fuel consumption, distance, etc. Experimental results show that the new algorithm is able to obtain good solutions, however as the problem becomes more complex, the optimal solutions also become harder to find.

Figures (7)

• Figure 1: Hypervolume for two optimization variables. The optimal POF is represented in red, the solutions obtained using a specific algorithm are represented in blue, and the hypervolume comprised between them is represented in yellow.
• Figure 2: Mission with 7 tasks (2 of them Multi-UAV), 5 UAVs and 3 GCSs.
• Figure 3: Example of assignment of a UAV to two tasks. The path to each task, the task performance, the loiter and the return phases are represented, as well as every time point and duration related.
• Figure 4: Example of an individivual that represents a possible solution for a problem with 5 tasks, 3 UAVs and 2 GCSs.
• Figure 5: Example of crossover of two parents with 5 tasks, 3 UAVs and 2 GCSs. Each allele is performed a different type of crossover: UAV, FpPath and SensUsed are performed a 2-point crossover; Order is applied a PMX crossover, and GCS and FpReturn are applied another 2-point crossover.

Theorems & Definitions (5)

• definition thmcounterdefinition
• definition thmcounterdefinition
• definition thmcounterdefinition
• definition thmcounterdefinition
• definition thmcounterdefinition