Skip to Main Content
A key challenge for the unmanned aerial vehicles (UAVs) is to develop an overall system architecture that can perform optimal coordination of the UAVs and reconfigure to account for changes in the dynamic environment with uncertainty. This paper presents a multi-task allocation and path planning optimal coordination algorithm for UAVs based on dynamic Bayesian network (DBN) perceiving architecture, which leads to solve above autonomous problems in dynamic aerospace surroundings. Learning and inference will be based on Bayesian approach, by representing uncertainty in observed data, and by using probability techniques to compute the goal attributes given the observation data. Under given missions and guidelines, learning, inference and prediction can be carried out by the same principle and these clarify the new direction for the decision-making optimization. The valid overall approach is demonstrated on example scenarios which show that, during execution, the coordination tasks of multi-task allocation and path planning for UAVs, which react to changes in the dynamic aerospace environments, can be achieved autonomously.