A multi-UAV task decision-making method based on maddpg

Abstract

The invention discloses a multi-UAV task decision-making method based on MADDPG. The MADDPG algorithm is introduced into the multi-UAV task assignment. First, according to the actual combat environment of the multi-UAV, a two-dimensional combat required for deep reinforcement learning is established. The environment model, secondly, establishes the mathematical description of various threats such as air defense missiles in the multi-UAV combat environment, and finally takes the trajectory, distance of the multi-UAV and the defense threat of the battlefield as constraints, conducts learning and training, and then obtains Multi-UAV mission decision model. This method adopts the experience pool and dual network structure, which greatly improves the operation and convergence speed of the entire network. In the process of high-speed flight of the UAV, the results can be obtained faster, and the purpose of autonomous decision-making of multiple UAVs can be realized. , it can also ensure the efficiency of its mission decision-making in the unknown combat environment.

Description

technical field [0001] The invention belongs to the field of flight control, and particularly relates to a method for multi-unmanned aerial vehicle task decision-making. Background technique [0002] For the military of various countries, drones will become one of the indispensable weapons in the future battlefield. UAVs are likely to become the target of attacks and counterattacks by multiple combat platforms, becoming the most common and deadly "sword" in air combat. Although the existing multi-UAV system can complete some complex combat tasks, as a large fleet cooperative system, the traditional multi-UAV mission decision-making is generally carried out under the conditions of the known battlefield environment. If the set combat plan cannot meet the actual combat environment, it is difficult to make a timely response plan. Therefore, finding a method that can quickly and efficiently assign tasks to multiple UAVs in an unknown combat environment is particularly important...

AI Technical Summary

Problems solved by technology

However, in a multi-UAV environment, it is difficult for traditional reinforcement learning methods to play a role, because in a multi-UAV environment, each UAV is constantly changing, and the environment is no longer stable, and for traditional reinforcement learning algorithms For the strategy gradient method in , as the number of drones increases, the complexity of the environment also increases, which leads to the optimization method of estimating the gradient by sampling, the variance increases sharply, and it is difficult to calculate the final result

Images