Research On Unmanned Combat Aerial Vehicles Path Planning Based On Evolutionary Computation

The unmanned combat aerial vehicle(UCAV)path planning problem is a complex global optimization problem that aims to seek an optimal flight route that connects the starting and ending points and avoids the threats and constraints on certain flying scenes,which is of great social value and practical significance to the civilian and military UCAV utilization.Evolutionary Algorithms(EA)have been successfully applied to the UCAV path planning problem due to its ability for complex global optimization.However,different EA algorithms present various performances for UCAV pathplanning since each algorithm has its own strengths and weaknesses.In this study,we first provide a comparative study of twelve EA algorithms that published in major journals and conference proceedings for UCAV path planning research.We design different small scales of problem cases for those comparative algorithms and the experimental results show that most EA algorithms successfully seek for an optimal path.In particular,the Spider Monkey Optimization(SMO)is more effective and robust than other algorithms in handling the UCAV path planning problem.However,in the real situation,as the number and degree of the path threats increases,the recent EA algorithms all suffer from being trapped into local optima with a low convergence rate,which leads to the poor performance.Therefore,to resolve these problems,we propose a Cooperative Co-Evolution(CE)-based SMO algorithm,named CESMO to address UCAV path planning problem for avoiding obstacles.First,a cooperative co-evolution strategy is proposed to prevent the algorithms from falling into local optima easily,enhancing the coherence of the path.After that,a further division is applied to the algorithm for diversifying the search direction of each individual in the sub-groups.Finally,the SMO-based search mechanism is designed to further strengthen the search efficiency and boost the convergence rate.To verify the effectiveness of the proposed CESMO algorithm,we use a stochastic generative method to design a series of large-scale UCAV flight scenarios with different scene ranges,path obstacle scales,and the number of obstacles.The experiments are conducted on different path optimization dimensions,respectively.Experimental results demonstrate that our proposed method is more competitive than other state-ofthe-art evolutionary algorithms for UCAV path planning problem considering the quality and stability of the final path.Meanwhile,CESMO shows superior path finding performance compared to other state-of-the-art evolutionary algorithms in the application of ultra-scale scenarios.