Brain Emotional Learning-Based Path Planning and Intelligent Control Co-Design for Unmanned Aerial Vehicle in Presence of System Uncertainties and Dynamic Environment

This paper proposes a novel intelligent path planning and control co-design for Unmanned Aerial Vehicles (UAVs) in the presence of system uncertainties and dynamic environments. In order to simultaneously handle the uncertainties from both the UAV platform itself and from the environment, a novel biologically-inspired approach based on a computational model of emotional learning in mammalian limbic system is adopted. The methodology, known as Brain Emotional Learning (BEL), is implemented in this application for the first time. Making use of the multi-objective properties and the real-time learning capabilities of BEL, the path planning and control co-design are applied in a synthetic UAV path planning scenario, successfully dealing with the challenges caused by system uncertainties and dynamic environments. A Lyapunov analysis demonstrates the convergence of the co-design, and a set of numerical results illustrate the effectiveness of the proposed approach. Furthermore, it is shown that the low computational complexity of the method guarantees its implementation in real-time applications.