This book is a beginner's guide for exciting and modern applications of AI techniques. Reader will be introduced to basic concepts and principles of AI to develop skills readily-applicable to be used in real engineering projects. Through step-by-step instructions, reader will learn how to implement typical AI tasks including control for autonomous drones, speech and character recognition, natural language processing, dietary menu planning, optimal selections for project management tasks and maximizing profits in algorithmic stock trading. We believe that all readers, regardless of their area of expertise, will enjoy their new empowerment stemming from relatively straightforward procedures of AI used in tackling otherwise formidable problems.
View Full Publication
Abstract — Autonomous unmanned aerial vehicles (uavs) operating as a swarm can be deployed in austere environments, where cyber electromagnetic activities often require speedy and dynamic adjustments to swarm operations. Use of central controllers, uav synchronization mechanisms or pre-planned set of actions to control a swarm in such deployments would hinder its ability to deliver expected services. We introduce artificial intelligence and game theory based flight control algorithms to be run by each autonomous uav to determine its actions in near real-time, while relying only on local spatial, temporal and electromagnetic (em) information. Each uav using our flight control algorithms positions itself such that the swarm main-tains mobile ad-hoc network (manet) connectivity and uniform asset distribution over an area of interest. Typical tasks for swarms using our algorithms include detection, localization and tracking of mobile em transmitters. We present a formal analysis showing that our algorithms can guide a swarm to maintain a connected manet, promote a uniform network spread-ing, while avoiding overcrowding with other swarm members. We also prove that they maintain manet connectivity and, at the same time, they can lead a swarm of autonomous uavs to follow or avoid an em transmitter. Simulation experiments in opnet modeler verify the results of formal analysis that our algorithms are capable of providing an adequate area coverage over a mobile em source and maintain manet connectivity. These algorithms are good candidates for civilian and military applications that require agile responses to the changes in dynamic environments for tasks such as detection, localization and tracking mobile em transmitters.
View Full Publication
Abstract — Uninterrupted communication is crucial for modern electromagnetic (EM) spectrum operations where successes of situational awareness,
defensive and offensive missions depend on ongoing control of a wireless spectrum. Preventing an adversary from dominating cyberspace becomes
challenging as rapid technological developments allow state and non-state actors to engage in a broad range of destructive cyber electromagnetic
activities (CEMA). Digital threats to communication networks can range from eavesdropping and impersonation attempts to various forms of denial-of-service attacks.
In this paper, we present bio-inspired and game theory based flight control algorithms for a swarm of autonomous UAVs.
Each UAV considers MANET connectivity, overshadowed ground area coverage and signal strength from interfering mobile radio emitters.
Our algorithms use 3D Voronoi tessellations and linear interpolation for EM mapping of local neighborhood as a part of decision making process.
Simulation experiments in OPNET show that our algorithms can successfully guide autonomous UAVs while requiring limited near neighbor communications to provide a high percentage area coverage with anuninterrupted MANET connectivity.
By providing alight weight solution for rapidly deployable swarm of autonomous UAVs, our flight control algorithms are good candidates for deployment in complex environments in presence of adaptive
and mobile sources of EM interference.
View Full Publication
Abstract — A self-organizing swarm of autonomous unmanned aerial vehicles (UAVs) can provide a quick response to cyberattacks in austere civilian and military environments.
However, if a UAV swarm relies on centralized control, synchronization of swarm members, pre-planned actions or rule-based systems, it may not provide adequate and timely response against cyber attacks.
We introduce game theory (GT) and biologically inspired flight control algorithms to be run by each autonomous UAV to detect, localize and counteract rogue electromagnetic signal emitters.
Each UAV positions itself such that the swarm tracks mobile adversaries while maintaining uniform node distribution and connectivity of the mobile ad-hoc network (MANET). UAVs use only their respective local neighbor information to determine their individual actions.
Simulation experiments in OPNET show that our algorithms can provide an adequate area coverage over mobile interference sources. Our solution can be employed for civilian and military applications that require agile responses in dynamic environments.
View Full Publication
Abstract — Artificial intelligence (AI) based flight control algorithms can be successfully utilized to deploy a swarm of autonomous Unmanned Aerial Vehicles (UAVs). In a swarm of autonomous UAVs operating as a mobile ad-hoc network (MANET),
use of centralized control, pre-planned missions, synchronization of nodes and reliance on conditional procedures are not feasible. We introduce near real-time AIbased flight control algorithms for autonomous UAVs to position
themselves over an area of interest. Each UAV uses only local neighbor information toadvance the swarm toward a desired MANET topology. Simulation experiments in OPNET show that our algorithms can provide high percentage area coverage over a target,
while requiring limited near neighbor communication. They are lightweight and power-efficient, hence well-suited for military applications.
View Full Publication