RBF neural network identifier based constrained optimal guidance for Mars entry vehicles

In this paper, a radial basis function (RBF) neural network (NN) identifier based approximate constrained optimal guidance law is proposed for Mars entry vehicles guidance. Firstly, an RBF NN identifier is used to identify the system uncertain parameters. With the identified parameters, the optimal guidance problem of Mars entry vehicles is transformed into an optimal tracking control one, which depends on the solution of the Hamilton-Jacobi-Bellman (HJB) equation. Due to the control input constraints, a generalized non-quadratic performance function is proposed. In general, the HJB equation is a nonlinear partial differential equation that is difficult or even impossible to be solved analytically. We use an NN to solve the HJB equation approximately. Finally, the Monte-Carlo simulation results on the Mars entry vehicles demonstrate the effectiveness of the proposed method.