Intelligent flight for UAV via integration of dynamic MOEA, Bayesian network and fuzzy logic

Intelligent flight is a key technology for an unmanned aerial vehicle (UAV) to react to the changing environment. Online path planning (OPP) is a basic issue for intelligent flight and is indeed a dynamic multi-objective optimization problem (DMOP). In this paper, we use an OPP scheme in the sense of model predictive control to continuously update the environmental information for the planner. This method is in fact a DMOP. For solving the problem at hand we propose a dynamic multi-objective evolutionary algorithm based on linkage and prediction (LP-DMOEA).Within this algorithm the historical Pareto sets are collected and analyzed to enhance the performance. For intelligently selecting the best path from the output (a set of Pareto solutions obtained by the LP-DMOEA) of the OPP, the Bayesian network and fuzzy logic are used to quantify the bias to each optimal objective. The experimental results show the LP-DMOEA works more effectively for OPP in contrast to the restart method and the intelligent methods for solution selection can automatically assess the changing environment and adapt the path planner.