Unmanned system cluster control method based on deep reinforcement learning

Abstract

The invention relates to an unmanned system cluster control method based on deep reinforcement learning. The invention relates to the technical field of unmanned system cluster control, and aims at solving a problem that an existing unmanned system cluster control method is poor in environmental adaptability. The method comprises the steps of in an unmanned system cluster, using each unmanned system to detect environment information; dividing the environment information into target information, obstacle information and other unmanned system state information; standardizing the obtained information respectively; processing the standardized information through a deep neural network to obtain a probability value of a selection action; selecting an action according to the obtained probabilityvalue, observing new environment information and obtaining an action evaluation value; collecting all data of interaction between the unmanned system and the environment to train a deep neural network; and performing unmanned system cluster control by using the trained deep neural network. The method is applied to the technical field of unmanned system cluster control.

Description

technical field [0001] The invention relates to the technical field of unmanned system cluster control, and is an unmanned system cluster control method based on deep reinforcement learning. Background technique [0002] Deep learning DL (Deep Learning) is deep learning, which is a kind of method in machine learning methods. Among them, depth means deep neural network, which is a complex network system that simulates the function of human brain neural network by extensive interconnection of a large number of simple processing units. It is a highly complex nonlinear dynamic learning system. The neural network model is described based on the mathematical model of neurons, which can approximate any complex nonlinear function. Deep learning is to learn the internal laws and representation levels of sample data. The information obtained during the learning process is of great help to the interpretation of data such as text, images and sounds. Its ultimate goal is to enable mach...

AI Technical Summary

Problems solved by technology

[0004] In order to solve the problem of poor environmental adaptability of the existing unmanned system cluster control method, the present invention provides an unmanned system cluster control method based on deep reinforcement learning , the invention provides the following technical solutions:

Images