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

AGV (Automatic Guided Vehicle) location algorithm based on DBN (Dynamic Bayesian Network) and Kalman filtering algorithm

A Kalman filter and positioning algorithm technology, applied in the field of robot positioning and deep learning, can solve the problem of filter divergence and achieve the effect of ensuring accurate estimation

Inactive Publication Date: 2017-05-17
JILIN UNIV
View PDF0 Cites 11 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0008] The present invention provides an AGV positioning algorithm based on DBN and Kalman filter algorithm to solve the problem of filter divergence caused by the changeable external environment caused by the traditional Kalman filter algorithm in the AGV positioning process

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 (Automatic Guided Vehicle) location algorithm based on DBN (Dynamic Bayesian Network) and Kalman filtering algorithm
  • AGV (Automatic Guided Vehicle) location algorithm based on DBN (Dynamic Bayesian Network) and Kalman filtering algorithm
  • AGV (Automatic Guided Vehicle) location algorithm based on DBN (Dynamic Bayesian Network) and Kalman filtering algorithm

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0021] In the process of AGV work, various sensors (accelerometers, gyroscopes and electronic compass, etc.) are often arranged on the AGV. According to the data obtained by the sensors, the position, speed and acceleration at any time can be obtained by using the Kalman filter algorithm. And other relevant information, Kalman is a time-domain filtering method, using the state space method to describe the system, the algorithm uses a recursive form (only the current measurement value and the predicted value of the previous sampling period are required), not only can deal with stationary random processes , can also handle multidimensional and non-stationary stochastic processes.

[0022] The present invention comprises the following steps:

[0023] 1. According to the data collected by the sensor on the AGV, the position information of the AGV at different times is estimated through the Kalman filter algorithm;

[0024] First, the equations of the dynamic system and measuremen...

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 (Automatic Guided Vehicle) location algorithm based on a DBN (Dynamic Bayesian Network) and a Kalman filtering algorithm, and belongs to the technical field of robot localization and deep learning. The AGV location algorithm comprises the following steps: collecting velocity and acceleration information in the moving process of a plurality of groups of AGVs, estimating location information of the AGVs at different times based on the Kalman filtering algorithm; establishing a matching degree variable Ink between a theoretical value of new information variance and a practical measured value in the Kalman filtering process, to train the DBN; combining the trained DBN with the Kalman filtering algorithm; when the matching degree deviates 1, calibrating the matching degree variable by means of a self-adaptive regulatory factor, so as to ensure accurate estimation of the Kalman filtering process to the location and the velocity of the AGV. According to the AGV location algorithm disclosed by the invention, the self-adaptive regulatory factor is obtained by means of the DBN to correct a noise variance matrix of a Kalman filter based on consistency degree of a theoretical variance and a practical variance of a new information sequence in the Kalman filtering algorithm, and therefore accurate estimation to the location of the AGV in operation is ensured.

Description

technical field [0001] The invention relates to the field of robot positioning and deep learning, in particular to an AGV positioning algorithm based on DBN and Kalman filter algorithm. Background technique [0002] AGV (Automated Guided Vehicle) refers to a transport vehicle that is equipped with automatic guidance devices such as electromagnetic or optical, can travel along a prescribed guidance path, and has safety protection and various transfer functions. AGV mainly uses wheeled mobile mode, fast and efficient, simple structure, good controllability and safety compared with other production equipment. A complete AGV involves multiple disciplines such as mechanical design, electronic technology, automatic control, artificial intelligence, information processing, computer, sensor, image processing, etc. The wide application of AGV makes it a key equipment in modern logistics, production, and automation systems. Compared with other commonly used equipment, the working are...

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): G01C21/20
CPCG01C21/20
Inventor 王瑞刘明山周原
Owner JILIN UNIV