Multi-UAV Tactic Switching via Model Predictive Control and Fuzzy Q-Learning

Abstract

Teams of cooperative Unmanned Aerial Vehicles (UAVs) require intelligent and flexible control strategies to allow the accomplishment of a multitude of challenging group tasks. In this paper, we introduce a solution for the problem of tactic switching between the formation flight tactic and the dynamic encirclement tactic for a team of ? cooperative UAVs using a predictive decentralize control approach. Decentralized Model Predictive Control (MPC) is used to generate tactics for a team of ? UAVs in simulation and real-world validation. A high-level Linear Model Predictive Control (LMPC) policy is used to control the UAV team during the execution of a desired formation, while a combination of decentralized LMPC and Feedback Linearization (FL) is applied to the UAV team to accomplish dynamic encirclement. The decision of switching from one tactic to the other is derived by a fuzzy logic controller, which, in its turn, is derived by a Reinforcement Learning (RL) approach. The main contributions of this paper are: (i) solution of the problem of tactic switching for a team of cooperative UAVs using LMPC and a fuzzy controller derived via RL; (ii) simulations demonstrating the efficiency of the method; and (iii) implementation of the solution to on-board real-time controllers on Qball-X4 quadrotors.