Chaotic Random Opposition-Based Learning and Cauchy Mutation Improved Moth-Flame Optimization Algorithm for Intelligent Route Planning of Multiple UAVs

UAV route planning is the key issue for application of in real-world scenarios. Compared with traditional methods, although intelligent optimization algorithm has stronger applicability and performance, it also problem poor convergence accuracy easy to fall into local optimization. Therefore, an method based on chaotic random opposition-based learning cauchy mutation improved Moth-flame (OLTC-MFO) proposed. First, terrain environment constructed by digital elevation map, threat model established realize equivalent three-dimensional (3D) environment. Then, opposite population introduced increase diversity solutions improve search speed algorithm. Logistic-Tent chaos map perturbation flame position, which improves global capability Finally, probability operator Cauchy are introduced, makes not only accept current solution a certain probability, but jump out sub-optimal solution, thus enhancing The simulation results show that when number iterations 1000, length OLTC-MFO 45.3716km shorter than MFO algorithm, result this stable more accurate, achieves purpose assisting combat decision-making.