Nonlinear Optimal Guidance for Cooperatively Imposing Relative Intercept Angles

TL;DR

Using the neural networks, an approach for real-time generation of the nonlinear cooperative optimal guidance command is developed and it is shown that a nonlinear optimal guidance command with specific relative angles can be generated within a faction of a millisecond.

Abstract

The optimal cooperative guidance in the nonlinear setting for intercepting a target by multiple pursuers is studied in the paper. As certain relative angles can improve observability, the guidance command is required to cooperatively control the pursuers to intercept the target with specific relative angles. By using the neural networks, an approach for real-time generation of the nonlinear cooperative optimal guidance command is developed. Specifically, the optimal control problem with constraints on relative intercepting angles is formulated. Then, Pontryagin's maximum principle is used to derive the necessary conditions for optimality, which are further employed to parameterize the nonlinear optimal guidance law. As a result, the dataset for the mapping from state to nonlinear optimal guidance command can be generated by a simple propagation. A simple feedforward neural network is trained by the dataset to generate the nonlinear optimal guidance command. Finally, numerical examples are presented, showing that a nonlinear optimal guidance command with specific relative angles can be generated within a faction of a millisecond.

Figures (11)

• Figure 1: Engagement geometry.
• Figure 2: Diagram of dataset generation.
• Figure 3: Diagram for guidance loop.
• Figure 4: Trajectories for case 1.
• Figure 5: Control profiles for case 1.