Multi-aircraft flight path planning method based on deep Q learning algorithm

Abstract

The invention relates to a multi-aircraft flight path planning method based on a deep Q learning algorithm. The method comprises the following steps: S1, constructing a kinematic model of an aircraftbased on the performance of the aircraft; S2, constructing a task model of the aircraft based on a deep Q learning algorithm according to a to-be-hit target; S3, constructing a state space of the aircraft according to the kinematics model and the task model; S4, constructing an action space of the aircraft according to the kinematics model and the task model; S5, constructing a neural network anda reward function based on the deep Q learning algorithm based on the state space and the action space; S6, training the neural network based on the reward function; and S7, performing target strike verification on the trained neural network. And multi-aircraft cooperative flight path planning is completed through a deep Q learning algorithm, and target strike under the constraints of minimum energy loss, shortest strike time, air defense threat area avoidance and the like is realized.

Description

technical field [0001] The invention relates to the technical field of multi-aircraft cooperative track planning, in particular to a multi-aircraft track planning method based on a deep Q-learning algorithm. Background technique [0002] In future wars, the battlefield environment will become increasingly complex and the performance of various defense systems will be improved day by day. The war has transitioned from a confrontation between individual weapons to a confrontation between systems. In this context, multi-aircraft coordinated operations have become a new form of combat. Specifically, coordinated operations require all aircraft to share, distribute and organize combat information and combat resources, and then make quick and accurate decisions to complete tasks such as coordinated reconnaissance, coordinated attack, and coordinated interception. [0003] From a system perspective, the key to realizing multi-aircraft cooperative operations lies in effective missio...

AI Technical Summary

Problems solved by technology

Coupled with the complex and changeable battlefield environment and the correlation coupling of various influencing factors, the complexity of modeling, combination complexity and time complexity of multi-aircraft cooperative trajectory planning are greatly increased.

Images