An online intelligent planning method for missile track

Abstract

The invention discloses an online intelligent planning method for missile tracks, which combines the traditional track planning method APF and the new generation artificial intelligence method A3C represented by deep reinforcement learning. It is easy to fall into the local minimum shortcomings, and it can effectively solve the problem of slow network convergence in artificial intelligence methods. The algorithm to be established is as follows: in the initial stage of terminal guidance, use the offline and online APF method to plan the missile track, and at the same time, use the generated track to train the A3C network "underground" to obtain stable network parameters. Since the track accuracy of the APF method at this stage is much higher than that obtained by the A3C algorithm, it can greatly speed up the network training speed and improve the efficiency of the algorithm. When the A3C network parameters are stable, a two-stage fast switching method is proposed to make the algorithm switch from APF to A3C autonomously and quickly, and the network-stabilized A3C algorithm is used to provide the missile suboptimal / optimal planning track.

Description

technical field [0001] The invention belongs to the field of aircraft control, and in particular relates to an online intelligent planning method for an aircraft track. Background technique [0002] In recent years, the continuous development of missile technology in various countries has greatly improved the reliability, effectiveness, and precision strike capabilities of missiles. In addition, with the widespread application and integration of technologies such as artificial intelligence, cloud computing, and big data, new technologies continue to flow into the military field, making warfare develop rapidly in the direction of intelligence. It can be seen that the performance and intelligence level of my country's missiles need to be improved urgently. Among them, missile trajectory planning is one of the key technologies that needs to be improved. Missile trajectory planning refers to finding a feasible and optimal trajectory from the starting point to the target point ...

AI Technical Summary

Problems solved by technology

[0011] (1) Most of them can only solve the trajectory planning problem of known static / slow obstacles existing in the environment;

[0012] (2) The real-time performance and reliability of the planned trajectory cannot be well guaranteed, resulting in the inability to be directly applied to missile trajectory planning in complex combat environments

Images