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

A method for real-time fusion of multi-sensor information for unmanned vehicles

A multi-sensor and sensor technology, applied in the field of information processing, can solve problems such as unsuitable unmanned vehicle systems, achieve the effect of improving the quality of fusion information and avoiding influence

Active Publication Date: 2021-08-13
JILIN UNIV
View PDF8 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0002] In the complex environment of unmanned vehicles, the uncertainty and volatility of sensors will be greatly increased, and the existing multi-sensor information fusion method is mainly based on Bayesian theory, which is not suitable for complex and changeable unmanned vehicle 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
  • A method for real-time fusion of multi-sensor information for unmanned vehicles
  • A method for real-time fusion of multi-sensor information for unmanned vehicles
  • A method for real-time fusion of multi-sensor information for unmanned vehicles

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0034] The present invention will be further described below. It should be noted that this embodiment is based on the technical solution and provides detailed implementation and specific operation process, but the protection scope of the present invention is not limited to this embodiment.

[0035] This embodiment provides a method for real-time fusion of multi-sensor information of an unmanned vehicle, including the following steps:

[0036] S1. Determine the prior probability P of each sensor Q :

[0037] In this embodiment, the prior probability is a subjective probability, which is obtained from subjective analysis, reasoning, and experiments on the sensor, and is generally obtained by the frequency method. Q =m / n(n: number of trials, m meets the expected number), this value determines the initial bias of the sensor system, which can be adjusted through the distribution of posterior data.

[0038] The prior probability will be adjusted in subsequent steps, and the initia...

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 method for real-time fusion of multi-sensor information of an unmanned vehicle, comprising the following steps: determining the prior probability of each sensor; determining the initial mass function; calculating the correlation degree; and obtaining the trust set, fuzzy set and risk according to the correlation degree Set; calculate the risk function of trust set, fuzzy set, and risk set; calculate the posterior probability; compare the posterior probability of each sensor with the preset risk threshold; respectively compare the initial mass of each sensor corresponding to each target information The function is modified according to the following formula; D-S multiplication fusion is performed to obtain the fusion probability of each target information identified by the sensor system of the unmanned vehicle. The present invention introduces a priori factor to measure uncertainty, uses data correlation distribution to carry out risk assessment, and quantifies uncertainty, which can effectively avoid the influence of failure sensors on fusion results, and can greatly improve the quality of fusion information for multi-source target recognition .

Description

technical field [0001] The invention relates to the technical field of information processing, in particular to a method for real-time fusion of multi-sensor information of an unmanned vehicle. Background technique [0002] In the complex environment of unmanned vehicles, the uncertainty and volatility of sensors will be greatly increased, and the existing multi-sensor information fusion methods are mainly based on Bayesian theory, which is not suitable for complex and changeable unmanned vehicle systems. Contents of the invention [0003] Aiming at the deficiencies of the prior art, the present invention aims to provide a method for real-time fusion of multi-sensor information of unmanned vehicles, introduce a priori factor for measuring uncertainty, use data correlation distribution to carry out risk assessment, and quantify the uncertainty. It can effectively avoid the influence of failed sensors on fusion results, and can greatly improve the fusion information quality ...

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 Patents(China)
IPC IPC(8): G06Q10/06G06Q50/30G06F17/15G06F17/18
CPCG06F17/15G06F17/18G06Q10/0635G06Q50/30
Inventor 张晋东乔家乐王宇泽
Owner JILIN UNIV