Neural predictor-corrector guidance based on optimized trajectory

A predictor-corrector guidance method that tracks the optimized trajectory of hypersonic reentry glide process is presented. First, aiming at the minimum heating rate problem with multiple constraints, the hp-adaptive pseudospectral method generates optimized trajectory rapidly. Then a BPNN (Back-Propagation neural network) is trained by parameter profiles of optimized trajectory considering different dispersions to simulate the nonlinear mapping relationship between the current flight states and terminal states. Hence, the predictor algorithm substituted by the BPNN can be more efficient and the guidance is achieved by nullifying the terminal errors. Simulation examples show that the guidance method based on trajectory optimization and neural network can well satisfy both path and terminal constraints and has good validity and robustness.