Unlock instant, AI-driven research and patent intelligence for your innovation.

AGV positioning method based on fuzzy neural network

A technology of fuzzy neural network and positioning method, applied in the field of AGV vehicle positioning based on fuzzy neural network, can solve the problems of positioning system defects, accuracy, stability, and reliability to be improved, and achieve the effect of improving positioning accuracy

Inactive Publication Date: 2020-02-11
索菲丝智能科技(上海)有限公司
View PDF4 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] However, the positioning system described above has the disadvantage of
For a single sensor, it can only obtain partial information of environmental characteristics or AGV motion status information, and its accuracy, stability, reliability, etc. need to be improved

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
  • AGV positioning method based on fuzzy neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0028] An illustrative embodiment of the invention. A kind of AGV vehicle localization method based on fuzzy neural network, comprises the following steps:

[0029] Step 1: Set several sensors on the AGV car, each sensor obtains the distance data from the obstacle, and each sensor obtains the corresponding decision data according to the distance data;

[0030] Step 2: construct the fuzzy neural network model, use the distance data as the input value of the fuzzy neural network model, and use the speed and angle of the AGV car as the output value of the fuzzy neural network model;

[0031] Step 3: Use expert experience to train the fuzzy neural network model, and when the training error is reduced to the expected value, the fuzzy neural network decision model is obtained.

[0032] Wherein, in step 2, the fuzzy neural network model is a five-layer structure:

[0033] The first layer is the input layer, and the input value is the distance data from obstacles obtained by each se...

Embodiment 2

[0042] A specific embodiment of the present invention.

[0043] Step 1: Set 7 sensors on the AGV car, each sensor obtains the distance data from the obstacle, and each sensor obtains the corresponding decision data according to the distance data;

[0044] Step 2: construct the fuzzy neural network model, use the distance data as the input value of the fuzzy neural network model, and use the speed and angle of the AGV car as the output value of the fuzzy neural network model;

[0045] Step 3: Use expert experience to train the fuzzy neural network model, and when the training error is reduced to the expected value, the fuzzy neural network decision model is obtained.

[0046] Wherein, in step 2, the fuzzy neural network model is a five-layer structure:

[0047] The first layer is the input layer, and the input value is the distance data from obstacles obtained by each sensor, expressed as d i ={d 1 , d 2 , d 3 ,...,d 7}, the number of nodes in the first layer N 1 = 7;

...

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 an AGV positioning method based on a fuzzy neural network, and the method comprises the following steps: 1, setting a plurality of sensors on an AGV, enabling each sensor to obtain the distance data from an obstacle, and enabling each sensor to obtain the corresponding decision data according to the distance data; 2, constructing a fuzzy neural network model, taking the distance data as an input value of the fuzzy neural network model, and taking the speed and angle of the AGV as an output value of the fuzzy neural network model; and 3, training the fuzzy neural network model by adopting expert experience, and obtaining a fuzzy neural network decision model when a training error is reduced to an expected value. The AGV positioning method has the advantages that theinformation is fused through the sensors, the fuzzy neural model is constructed, the fuzzy neural network decision model is obtained through training, the speed and angle of the AGV are obtained, then the real-time position of the AGV is adjusted, the optimal path is found, and the positioning precision of the AGV is improved.

Description

technical field [0001] The invention relates to the field of AGV technology, in particular to an AGV positioning method based on a fuzzy neural network. Background technique [0002] In the navigation of AGV vehicles, positioning is its most basic function, and it is also the problem that must be solved first when it completes navigation. Plan the motion path. [0003] In the AGV vehicle, different positioning systems use different sensors, so their positioning methods are also different. According to the complexity of the working environment of the AGV vehicle, different types and different numbers of sensors can be configured for the positioning system of the AGV vehicle. Among them, for a single sensor, it obtains the environmental characteristics or the part of the motion state information of the AGV vehicle; for multiple sensors, the estimated value of the pose of the AGV is obtained through one sensor, and the other sensors correct the positioning error to obtain the...

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): G06N3/08B62D63/02G01C21/34
CPCB62D63/02G01C21/3407G06N3/084
Inventor 杜玲施丰鸣
Owner 索菲丝智能科技(上海)有限公司