UAV Swarm Routing Through Genetic Fuzzy Learning Methods

Abstract

Utilizing a combination of heuristic and stochastic techniques, this work approximates solutions for complex variants of the Traveling Salesman Problem. Within this study, we seek to develop a Pareto front of time optimal solutions for a large scale, multi-objective, multi-agent, multi-depot, traveling salesman problem with turning constraints that emulates a UAV operator monitoring a swarm of autonomous vehicles. This research is a culmination of years of investigation and past publications [1, 2, 3] which sought to solve portions of this problem individually. Solving the entire problem, more precisely named the Multi-Objective Min-Max Multi-Depot Polygon Visiting Dubins Multiple Traveling Salesman Problem, follows similar processes of simpler variants. With a focus on military applications, run-time is very critical to the success of this software. Through the cooperation of these algorithms, accurate solutions for large scale problems can be produced within a quick timeframe.

Genetic Fuzzy Approach for Control and Task Planning Applications

“…3 The higher computational time is due to the clustering algorithm 7 which solves the TSP in each iteration to come up with an optimal solution. The computational time could be decreased by using certain parameters characterising the topology of the problem instead of solving the TSP in each iteration.…”

“…3,4 The mapping of sensor information, collected in real-time, is fused with the dynamic system model and operational and environmental databases onto a set of control actions and/or decisions which need to be computationally efficient, robust in face of uncertainties and noise, scalable and adaptable to dynamic variations to the mission while adhering to all the constraints of the specific application. The basic approach is to make most of what resources are available in order to get the best possible results.…”

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

“…The first 9 elements in the vector, R (1)(2)(3)(4)(5)(6)(7)(8)(9), represent the rules as shown in Table 1 and R (10)(11)(12)(13)(14)(15) represent the boundaries of the membership functions as shown in Figure 3. The membership functions are assumed to be symmetric around zero.…”

“…With the increase in computational capability and the advent of new and improved machine learning algorithms over the last decade, there has been an increase in the development of intelligent systems for various engineering applications such as path planning, target tracking, satellite attitude control systems [3], collaborative control of a swarm of UAVs [4], etc. Such intelligent systems provide various advantages, a few of which include adaptability, robustness to uncertainties and improved efficiency.…”

Fuzzy Logic Based Intelligent Agents for Unmanned Combat Aerial Vehicle Control

“…Of note in Figure 2 is the ease in which other methods and algorithms can be incorporated into the system in different levels. A Cooperative Task Assignment Algorithm, Fuzzy Clustering Route Solver, and No Communications Fire Control System are directly incorporated [6][7][8]. This system requires a strong learning system, as the solution space is quite large.…”