Missile track on-line intelligent planning method

Abstract

The invention discloses a missile track on-line intelligent planning method, which combines a traditional track planning method APF and a new generation artificial intelligence method A3C with deep reinforcement learning as a representative, the advantages of the two methods are complementary, the defect that the traditional track planning method is easy to fall into local minimum can be overcome, and the problem of low network convergence speed of an artificial intelligence method can be effectively solved. The algorithm to be established specifically comprises the steps that in the initial stage of terminal guidance, an off-line and on-line combined APF method is used for planning a missile track, meanwhile, the generated track is used for 'dark ground' training of an A3C network, and stable network parameters are obtained. The track precision of the APF method at the stage is far higher than that of the track obtained by the A3C algorithm, so that the network training speed can be greatly increased, and the algorithm operation efficiency is improved. When A3C network parameters are stable, the algorithm is automatically and rapidly switched from the APF to the A3C through a two-stage rapid switching method designed, and the network stabilization A3C algorithm is used for providing a missile sub-optimal / 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 integrated development of technologies such as artificial intelligence, cloud computing, and big data, new technologies continue to pour into the military field, making warfare rapidly develop 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 need to be improved. Missile trajectory planning refers to finding the feasible and optimal trajectory from the starting point to the t...

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