Dynamic Target Search Using Multi-UAVs Based on Motion-Encoded Genetic Algorithm With Multiple Parents

Abstract

In this paper, a new optimization algorithm called Motion-Encoded Genetic Algorithm with Multiple Parents (MEGA-MPC) is developed to locate moving targets using multiple Unmanned Aerial Vehicles (UAVs). Bayesian theory is used to formulate the moving target tracking as an optimization problem where target detection probability defines the objective function as the probability of detecting the target. In the developed MEGA-MPC algorithm, a series of UAV motion paths encodes the search trajectory. In every iteration of the MEGA-MPC algorithm, UAV motion paths undergo evolution. The proposed approach for dynamic target search using multi-UAVs uses parallel computations to solve the optimization problem based on the MEGA-MPC algorithm where Each UAV can communicate with other UAVs if requested. The algorithm's performance is tested with various characteristics under six distinct scenarios using a different number of UAVs and targets. The statistical analysis of the results obtained using MEGA-MPC compared with other well-known metaheuristics shows that MEGA-MPC offers better solutions to find dynamic targets since it outperforms all the compared algorithms. INDEX TERMSDynamic target search, motion-encoded genetic algorithm, probabilistic targets, unmanned aerial vehicles I. INTRODUCTION VOLUME x, 20xx

An Aerial Robotic Missing-Person Search in Urban Settings—A Probabilistic Approach

“…While autonomous UAVs have seen limited use in urban searches, they have been widely proposed for mobile target searches in other environments [10][11][12][13][14][15][16][17]27]. These have included both homogeneous teams of UAVs [17,27,28], as well as heterogeneous teams with different UAVs and UGVs [10,12]. Central to these methods is the generation and use of probabilistic maps of the lost person's potential location, using predicted behavior to produce density maps [10,[27][28][29] and other representations [11,12,15,17] of a lost person's location for guiding the search.…”

“…These have included both homogeneous teams of UAVs [17,27,28], as well as heterogeneous teams with different UAVs and UGVs [10,12]. Central to these methods is the generation and use of probabilistic maps of the lost person's potential location, using predicted behavior to produce density maps [10,[27][28][29] and other representations [11,12,15,17] of a lost person's location for guiding the search. Further details on the lost-person behavior used to motivate such probability maps are examined below in Section 1.3.…”

Cooperative search for moving targets with the ability to perceive and evade using multiple UAVs

“…In order to compare the optimization effectiveness of the proposed optimization algorithm, a set of optimization algorithms will be used as a comparison in the following experiment. First of all, a motion-encoded particle swarm optimization [10] (ME-PSO) and a motion-encoded genetic algorithm [15] (ME-GA) are chosen as the comparison group of the direct motion-encoding method as these are commonly used to solve similar problems in recent research. Secondly, to test the proposed priority-encoding method, these optimization algorithms have been rewritten with corresponding encoding methods and denoted as PE-PSO and PE-GA, respectively.…”

“…On the topic of the encoding method of the search path, Shorakaei et al [14] proposed a path planning method that considers obstacles or threat areas using a novel encoding method by a matrix, which uniformly considers all UAVs and the coordinates of their waypoint positions. Alanezi et al [15] propose a motion-encoded genetic algorithm with multiple parents, which realizes a unified motion-encoding on a series of UAVs. For optimization, Luo et al [16] used the fruit fly optimization algorithm to solve the search path, in which multiple fruit fly swarms are used to enhance the global search ability.…”

An Air Target Course Prediction Method Based on Sub-Regions Divide and Conquer With Double Variable Weight

“…The research idea is to evenly decompose the motion region into a large number of sub-regions [15], [16], and search for the sub-regions set that satisfies the objective function in the passable regions to achieve the optimal path planning. Scholars from various countries focus on improving the search-path time, searchpath integrity and search-path optimality, and their research results are mainly divided into heuristic algorithms,(such as A* algorithm [17], D* algorithm [18]) evolutionary algorithms(such as ant colony algorithm [19], particle swarm algorithm [20], genetic algorithm [21]) and potential field algorithms (vector field [22], artificial potential field [23]). Among them, the evolutionary algorithm has the characteristics of self-organization, self-adaptation and selflearning.…”