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

RFID indoor positioning system and algorithm based on deep Q network

An indoor positioning and network technology, applied in positioning, biological neural network model, radio wave measurement system, etc., can solve the problems of low accuracy of single camera positioning system, RSSI signal is easily interfered, etc., achieve high accuracy and avoid positioning accuracy impact, quality-enhancing effect

Pending Publication Date: 2019-01-18
GUANGXI UNIV
View PDF9 Cites 9 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] Chinese patent CN201610490721.4 An indoor target positioning system and method based on a single camera and RSSI, patentee: Jiangsu Huanya Medical Technology Group Co., Ltd. This patent discloses an indoor target positioning system based on a single camera and RSSI and method, the fusion of RSSI positioning data and camera machine vision positioning information improves the accuracy of target tracking and positioning, avoids the situation of tracking failure, reduces the inaccurate phenomenon of positioning information caused by RSSI signals due to wall refraction, shielding, etc., and improves The accuracy and reliability of the system for target tracking and positioning are improved, but the accuracy of the single camera positioning system is low, and the RSSI signal is susceptible to interference. The above method does not perform too much precision processing on the corresponding signal, and can only be applied to special working environments. has certain limitations
Use BP neural network to correct the error of RSSI measurement value, and finally use the maximum likelihood estimation method to calculate the real coordinates of unknown nodes. Power consumption improves positioning accuracy at the same time, but this method is only used in traditional wireless networks, not in radio frequency identification positioning, and has certain limitations

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
  • RFID indoor positioning system and algorithm based on deep Q network
  • RFID indoor positioning system and algorithm based on deep Q network
  • RFID indoor positioning system and algorithm based on deep Q network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0034] A complete RFID positioning system includes tags, antennas, readers and data processing terminals. Through the data processing terminals, each reader is controlled to identify tags to obtain the RSSI value of the tag, and then obtain the specific location information of the tag. In a large-scale RFID system, there are several readers, many positioning targets, the situation is complicated, and there is serious interference between tags and readers. How to locate the precise tag position in a complex environment It is a problem that needs to be solved urgently. The present invention is based on a deep Q network algorithm, and combines Q learning in reinforcement learning with a neural network for RFID indoor positioning. The main method of deep Q network is experience replay and dual neural network: Q estimation network and The target network stores the data obtained from the system exploration environment in the memory bank, and the Q estimation network has the latest ...

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 relates to a RFID indoor positioning system and an algorithm based on a deep Q network. The system comprises a plurality of RFID tags, a plurality of reader antennas, a reader baseband control module, a wireless transmission device (WIFI) and a computer management system. The RFID tags are used for carrying data information. The reader antennas are used for receiving tag informationand RSSI values. The reader baseband control module is used for driving the tags and the antennas, coding and decoding the date. The wireless transmission device is used for transmitting tag data. Thecomputer management system is used for controlling the sending of read and write commands, training a depth Q network model, and outputting specific tag positions. The algorithm comprises the following steps of: defining an initial state and an action and a Q estimation network and a target network as shown in the description; training sample tag location data to establish a location memory; performing a counter propagation; and updating a neural network and finding the optimal RSSI value to output the target location. Compared to the traditional indoor positioning algorithm based on the neural network, the RFID indoor positioning system and the algorithm based on the deep Q network reduces the power consumption of hardware, improves the sensitivity of the reader and the positioning accuracy of the target tag, and is particularly suitable for the case where the number of positioning targets is large.

Description

technical field [0001] The present invention relates to indoor positioning technology in radio frequency identification (Radio Frequency Identification, RFID), specifically, an RFID indoor positioning algorithm based on deep Q network. Background technique [0002] In recent years, with the development of Internet of Things technology, people's demand for location-based services (LBS) is increasing. When you open a positioning mobile phone, you can see various location-based APPs, covering almost all aspects of life, such as Takeaway software Meituan, Ele.me and other software, open the software, locate various merchants, and eat all kinds of food; taxi software Didi Dache, ofo Xiaohuangche and other software, you can ride a bicycle conveniently and take a taxi. More and more location-based service software makes our life more convenient and promotes the development of location technology. Today's positioning services mainly rely on the Global Positioning System (GPS). Chi...

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): G01S5/08G01C21/20G06N3/02
CPCG06N3/02G01C21/206G01S5/08
Inventor 郑嘉利李丽
Owner GUANGXI 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