Supercharge Your Innovation With Domain-Expert AI Agents!

Unmanned combat simulation map generation method based on improved generative adversarial network

A simulation map and network technology, applied in the field of simulation, can solve complex and uncertain unmanned combat simulation maps and other problems, and achieve the effect of improving intuitiveness, improving training speed and accuracy, and unlimited map size

Inactive Publication Date: 2021-07-02
BEIHANG UNIV
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The invention proposes an unmanned combat simulation map generation system and method based on the improved generative confrontation network by self-made simulation map data with terrain characteristics, and improving the structure of the basic generative confrontation network, aiming at solving complex and uncertain unmanned combat The problem of generating simulation maps

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Unmanned combat simulation map generation method based on improved generative adversarial network
  • Unmanned combat simulation map generation method based on improved generative adversarial network
  • Unmanned combat simulation map generation method based on improved generative adversarial network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0070] The effectiveness of the method for generating the unmanned combat simulation map proposed by the present invention is verified below through specific examples. The simulation environment configuration of this example is AMD R5 4600H processor, 3.00GHz main frequency, 16GB memory, the software used for data generation and display is MATLAB 2020b version, and the software used for generating confrontation network construction, training, and map generation is PyCharmCommunity 2020.3.2 version.

[0071] The method of generating unmanned combat simulation map based on improved generative confrontation network, its realization process is as follows Figure 7 As shown, the specific practical steps of this example are as follows:

[0072] Step 1: Establish a map database with typical features

[0073] S11. Generate featureless terrain data

[0074] Firstly, 300 random number matrices of 60×60 are generated, the mean value of the random numbers is set to 0, and the standard d...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses an unmanned combat simulation map generation method based on an improved generative adversarial network. The unmanned combat simulation map generation method comprises the steps: 1, establishing a map database with typical characteristics; 2, carrying out database data training preprocessing; 3, constructing a basic generative adversarial network; 4, improving the structural design of the generative adversarial network; and 5, generating a data mapping application. The invention provides a processing thought of unmanned combat map data, and improves the intuition of data observation while reducing the data storage dimension; and a stepped training structure of the generative adversarial network is provided, and the training speed and precision are improved through a staggered network of a plurality of generators and discriminators. According to the method, the size of the generated map is not restrained, a data matrix of any dimension can be generated, the proportion is set according to needs when the map is mapped into the longitude and latitude, edge smoothing processing can be carried out on the output map of each network, splicing of a plurality of maps is achieved, and a complex map composed of any size and any terrain is obtained.

Description

technical field [0001] The invention relates to an unmanned combat simulation map generation method based on an improved generative confrontation network, and belongs to the field of simulation technology. Background technique [0002] UAV is a kind of aircraft controlled by radio remote control equipment and its own related program control device. At present, civilian drones are mostly used in agriculture, plant protection, aerial photography, disaster relief, etc. With the development of aviation technology and radio technology, various uses of drones are being developed, and more and more drones are appearing in military scenes. In addition to the rapid development of the application of military drones, the application of ground unmanned vehicles has gradually attracted people's attention. Since the unmanned combat system has the advantages of high safety factor and low cost, its development is an inevitable trend, and it is very important to improve its application rel...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): G06F30/27G06F16/29G06N3/04G06N3/08
CPCG06F30/27G06F16/29G06N3/08G06N3/045
Inventor 段海滨向宏程邓亦敏魏晨陈琳
Owner BEIHANG UNIV
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More