Cooperative Control of Unmanned Fighter Aircraft. Nicholas Ernest1, David Carroll1, Noah Bogart1, and Kelly Cohen2. 1Psibernetix Inc., Cincinnati, USA.
Proceedings of the 2017 World Congress on Unmanned Systems Engineering
Perspectives on Genetic Fuzzy Based Artificial Intelligence for Cooperative Control of Unmanned Fighter Aircraft Nicholas Ernest1, David Carroll1, Noah Bogart1, and Kelly Cohen2 1 Psibernetix Inc., Cincinnati, USA 2 Universtiy of Cincinnati, College of Engineering, Cincinnati USA INTRODUCTION Recent developments in genetic fuzzy systems have enabled the methodology to scale to significantly more complex problems than previously. Within the domain of aerial combat, significant strides have been made in both air to ground and air to air control of Unmanned Combat Aerial Vehicles (UCAVs) [1,2]. The authors’ perspectives regarding the impact of these developments in genetic fuzzy logic within air combat is the focus of this publication. IMPACT The raw capabilities of the Genetic Fuzzy Tree (GFT) methodology enables these early systems to rival expert humans, even when the GFT’s simulated platforms are handicapped; Fig. 2 [2]. Within the context of Beyond Visual Range (BVR) air combat, a swarm of significantly cheaper unmanned vehicles, controlled by GFTs, could be an incredibly difficult foe that has significantly lower economic impact. Additionally, these systems can be Verified & Validated utilizing formal methods, process information linguistically and thus are easy to communicate and cooperate with, and are incredibly computational efficient [1,2]. A significant impact is also present for Live, Virtual, & Constructive (LVC) training, which is especially important for today’s extremely expensive manned aircraft. Utilizing genetic fuzzy systems, extreme performance as well as security and deployability can be achieved for this cost-reducing training methodology.
Fig. 1: Alpha, an air to air combat GFT, controlling red forces within a simulation [2]. REFERENCES 1. Ernest N, Cohen K, Kivelevitch E, Schumacher C and Casbeer D. (2015). Genetic fuzzy trees and their application towards autonomous training and control of a squadron of unmanned combat aerial vehicles. Unmanned Systems. 3: 185-204. 2. Ernest N, Carroll D, Schumacher C, Clark M, Cohen K and Lee G. (2016). Genetic Fuzzy based Artificial Intelligence for unmanned combat aerial vehicles in simulated air combat missions. Journal of Defense Management. 6: 144-151.