An Efficient Genetic Fuzzy Approach to UAV Swarm Routing

Abstract

Fuzzy logic is used in a variety of applications because of its universal approximator attribute and nonlinear characteristics. But, it takes a lot of trial and error to come up with a set of membership functions and rule-base that will effectively work for a specific application. This process could be simplified by using a heuristic search algorithm like Genetic Algorithm (GA). In this paper, genetic fuzzy is applied to the task assignment for cooperating Unmanned Aerial Vehicles (UAVs) classified as the Polygon Visiting Multiple Traveling Salesman Problem (PVMTSP). The PVMTSP finds a lot of applications including UAV swarm routing. We propose a method of genetic fuzzy clustering that would be specific to PVMTSP problems and hence more efficient compared to k-means and c-means clustering. We developed two different algorithms using genetic fuzzy. One evaluates the distance covered by each UAV to cluster the search-space and the other uses a cost function that approximates the distance covered thus resulting in a reduced computational time. We compare these two approaches to each other as well as to an already benchmarked fuzzy clustering algorithm which is the current state-of-the-art. We also discuss how well our algorithm scales for increasing number of targets. The results are compared for small and large polygon sizes.

Optimization approaches for civil applications of unmanned aerial vehicles (UAVs) or aerial drones: A survey

“…For instance, Gentilini et al propose a branch‐and‐cut algorithm for a TSP with ellipsoid or polyhedral neighborhoods. If we interpret neighborhoods as a set of distinct nodes of a graph, so that exactly one node of the graph in each neighborhood must be visited and each neighborhood must be visited by exactly one drone, then a one‐in‐a‐set problem arises . We refer the interested reader to Arkin and Hassin , de Berg et al , and Elbassioni et al for approximation results on some variants of the TSP with neighborhoods.…”

“…Overall, the most common objectives in routing for a set of locations include minimizing operational cost , minimizing fixed costs (mostly the number of required drones ), and minimizing makespan . Several articles consider objectives related to customer service and customer satisfaction, such as expected waiting time of customers for service , share of successfully served customer orders , total customer satisfaction , and resolution of photographed images .…”

“…Second, they should analyze alternative designs for systems of drones, other robots and vehicles, and humans, such as an automatic landing capability on a moving truck. Finally, future research should provide guidance on infrastructure development, such as layout of depots and battery recharging stations. Whereas the majority of existing studies focus on minimizing completion time or total travel distance , operations planning may significantly benefit from incorporating demand into planning models . Future research should develop suitable revenue management approaches (such as segmentation and smart pricing) that may shift demand to the most attractive services and, thus, increase the profitability of commercial drone applications. It is essential to understand the economic and social value of drones in various applications and work out detailed business cases.…”

Development of a Genetic Fuzzy Controller and Its Application to a Noisy Inverted Double Pendulum

“…In a GFS, GA tunes the parameters of the FLS to minimize a cost function that is carefully chosen such that minimizing it provides the desired behavior of the system. Such GFSs have been developed with much success for clustering and task planning [10], aircraft conflict resolution [11], simulated air-to-air combat [12], collaborative control of UAVs, etc. Since fuzzy logic systems are made up of a set of membership functions that define the inputs and a set of linguistic rules that define the relationship between the inputs and the outputs, it is more interpretable compared to other machine learning techniques like neural networks and support vector machines.…”

Genetic Fuzzy System in Weapon Control Module of Unmanned Tanks

“…Nicholas Ernest et al propose Genetic Cascading Fuzzy System [1,2] and Genetic Fuzzy Tree [3,4,5,6,7], which divide the intelligent control system into independent submodules and are respectively optimized by genetic algorithm. However, the fitness function of the genetic algorithm they use is kind of inappropriate.…”