Co-operative Collision Avoidance for Unmanned Aerial Vehicles using both Centralised and Decoupled Approaches

Abstract

Abstract This paper presents the design of co-operative collision avoidance algorithms for Unmanned Aerial Vehicles (UAVs) using vertical avoidance manoeuvres. The co-operative collision avoidance problem is formulated as an optimal control problem and solved using an A⁎ search algorithm. Two different approaches are developed and compared: a centralised approach where the collision avoidance trajectories for all UAVs are planned simultaneously, and a decoupled approach where the individual collision avoidance trajectories for each UAV is planned sequentially, with the planning sequence determined by a UAV priority order. The UAVs co-operate by sharing their state and intent information with one another and with a central node, if present. The co-operative collision avoidance algorithms are verified and evaluated using illustrative simulations. These simulations support the expected behaviour of the algorithms. The centralised approach finds the most optimal solution to the problem while the solution found by the decoupled approach depends on the priority allocation of the UAVs. The decoupled approach can find either the most optimal or a sub-optimal solution to the problem, with the priority allocation occasionally resulting in the decoupled approach being unable to find a solution. This suggests that the centralised approach will, on average, find solutions more often and find more optimal solutions than the decoupled approach.