Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Digital twin intelligent parking method and system based on reinforcement learning

A reinforcement learning and twinning technology, applied in the computer field, can solve problems such as increased difficulty in construction and debugging, increased scale and complexity, and achieve the effects of reducing manual parking time costs, avoiding collisions, and realizing full-cycle management

Active Publication Date: 2021-02-26
EAST CHINA NORMAL UNIV
View PDF13 Cites 11 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Due to the improvement of real-time requirements and the increasing difficulty of overall system construction and debugging, the scale and complexity of cyber-physical fusion systems are increasing, which brings great challenges to the design of safe and reliable smart city systems

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
  • Digital twin intelligent parking method and system based on reinforcement learning
  • Digital twin intelligent parking method and system based on reinforcement learning
  • Digital twin intelligent parking method and system based on reinforcement learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0079] The Unity3D project of this system is built based on the 2018.4.17 version and released in the form of an .exe executable file. Double-click to run the packaged CarPark.exe program to start the Unity3D project. Such as Figure 8 shown. When the CarPark.exe program is started, a setting box pops up such as Figure 9 shown.

[0080] The control algorithm is written in Python language, and will use websocket to establish a connection with the Unity3D program locally, and control the movement of the virtual car through the MADDPG multi-agent reinforcement learning algorithm. Going back to the Unity3D program interface, we can see that the car has been able to automatically park in place with anti-collision under the control of the algorithm, such as Figure 10 shown. After a period of time, all three cars have found vacant parking spaces and successfully parked in the parking spaces, and no collisions occurred during the process. Figure 11shown. Moreover, the car wi...

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 a digital twin smart parking method based on reinforcement learning, and provides an intelligent and easy-to-use system model for smart city information physical fusion Internet-of-things construction. The intelligent parking system supports real-time control over the multi-vehicle automatic parking process in an actual scene, collision can be effectively avoided, the manual parking time cost is reduced, and safety accidents caused by manual misoperation are reduced. For an intelligent parking lot project to be implemented to the ground, a digital twin prototype can befirstly adopted to carry out tasks of feasibility analysis, algorithm testing and function verification. For an intelligent parking lot project which is realized on the ground, a digital twinning technology can be used to realize data acquisition and submission, full-cycle management of parking lot data is realized, and help is provided for subsequent development and utilization of data resources.

Description

technical field [0001] The invention belongs to the field of computer technology, and in particular relates to a digital twin intelligent parking method and system based on reinforcement learning. Background technique [0002] With the gradual digitalization of human society and the development of artificial intelligence, Internet of Things, cloud computing, 5G and other technologies, the demand for information-physical fusion systems is also increasing at this stage. In the past, a single system implemented simple " It is difficult to meet the needs of the people and the country. Accurate and real-time cognition, control and coordination of macroscopic multi-heterogeneous systems (such as smart city systems covering heterogeneous systems such as smart transportation, smart fire protection, and smart parks) are gradually Become the development direction of information-physical fusion system. The smart city information-physical fusion system is a networked physical equipment...

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): G08G1/14H04L29/08H04L12/24G06F30/20
CPCG08G1/148H04L67/125H04L67/10G06F30/20H04L41/145
Inventor 陈铭松黄红兵韩定定曹鹗夏珺周亮焦阳
Owner EAST CHINA NORMAL UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com