Sense and collision avoidance of Unmanned Aerial Vehicles using Markov Decision Process and flatness approach

This paper presents a new development of collision avoidance algorithm that ensures an Unmanned Aerial Vehicle (UAV) can avoid multiple intruders autonomously. Firstly, the Markov Decision Process (MDP) based approach generates the multiple threats resolution logic for the collision avoidance system. Secondly, the optimal trajectory is smoothed by the differential flatness technique where the constraints of the UAV dynamics are considered. In such a way, the planned trajectory is feasible for the UAV. The effectiveness of the developed scheme is illustrated by the numerical simulation studies.