Evolutionary path planner for UAVs in realistic environments

Abstract

This paper presents a path planner for Unmanned Air Vehicles (UAVs) based on Evolutionary Algorithms (EA) that can be used in realistic risky scenarios. The path returned by the algorithm fulfills and optimizes multiple criteria which (1) are calculated based on properties of real UAVs, terrains, radars and missiles, and (2) are used to rank the solutions according to the priority levels and goals selected for each mission. Developed originally to work with only one UAV, the planner currently allows us to obtain the optimal path of several UAVs that are flying simultaneously. It works globally offline and locally online to recalculate a part of the path when an unexpected threat appears. Finally, the effectiveness of the solutions given by this planner has been successfully tested against a simulator that implements a complex model of the UAV and its environment.

Comparison of 3D Versus 4D Path Planning for Unmanned Aerial Vehicles

“…The study includes the most comprehensive set of requirements including the ones overlooked in a wide range of studies. This study extends existing literature 1,3,20,21,[32][33][34][35][36][37][38][39][40][41][42][43][44][45][46][47][48][49][50][51] by placing a special importance on aviation rules and utilisation considerations. The model generates suitable paths that address UAV performance limitations, environmental factors, basic aviation rules, flight dynamics, UAV utilisation considerations and user requirements.…”

“…A complex dynamic environment is the one that includes many constraints with different characteristics and various mission, flight, and environment related requirements. Even though, studies in autonomous path planning 1,3,20,21,[32][33][34][35][36][37][38][39][40][41][42][43][44][45][46][47][48][49][50][51] address many challenges, domainspecific operational issues, such as utilisation considerations and aviation rules, did not receive adequate attention. This is important if the UAV under study is a medium altitude high endurance (MALE) UAV, because these types of UAVs are subject to aviation rules in addition to other criteria.…”

“…In addition, decomposition methods are also used to reduce the number of samples in the generated graph by dividing the world space into regions 30,31 . UAV path planning studies addresses multiple flight objectives under several flight criteria 12,20,21,[32][33][34][35][36][37][38][39][40][41][42][43][44][45][46][47][48][49][50][51] . In this study, we try to address an extensive set of criteria (see Table 1) in online path planning by implementing multiple constraints to provide more effective and safer UAV paths.…”

UAV Fleet Mobility Model with Multiple Pheromones for Tracking Moving Observation Targets

“…However most existing works consider either centralised methods or distributed ones but using offline pre-computation and online decision taking [6,7].…”

Evolutionary Coordination System for Fixed-Wing Communications Unmanned Aerial Vehicles

“…After studying the evolutionary path planner for single UAVs in realistic environments, [5] propose a solution to the coordination of multiple UAV flying simultaneously, while minimising the costs of global cooperative objectives. As long as the UAVs are able to exchange some information during their evaluation step, the proposed system is able to provide off-line as well as on-line solutions, global and local respectively.…”