Neural network based online predictive guidance for high lifting vehicles

Abstract In this paper, a data-driven online entry guidance framework is proposed. Based on the proposed framework, a novel neural network based online predictive guidance algorithm for high lifting vehicles is developed, which combines the benefits of the existing predictive guidance and the neural network predictor. By introducing the neural network predictor, the proposed algorithm can effectively overcome the long-standing contradiction between guidance accuracy and real-time guidance of existing numerical predictive guidance methods. Take the augmented predictor–corrector guidance algorithm as guidance pattern, a large number of sample trajectory data can be generated by performing full envelop trajectory simulations with different perturbation terms. Based on the sample data, the mapping relationship between the real-time flight states of high lifting vehicles and guidance commands is approximated by multi-layer feedforward neural network. By substituting the off-line trained neural network predictor for the trajectory integrations of each guidance cycle in the augmented algorithm, the proposed algorithm can successfully realize the online precision guidance for high lifting vehicles. The simulation results for nominal and dispersed cases show that the proposed algorithm has better performance on real-time capability and robustness than the existing numerical predictive guidance methods, and it is suitable for engineering practice.