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

Intelligent voice type guide blind robot control method and control system thereof

A blind-guiding robot and control method technology, applied in the direction of control/regulation system, non-electric variable control, two-dimensional position/channel control, etc., to achieve the effects of improving calculation accuracy, high recognition accuracy, and meeting the needs of life

Inactive Publication Date: 2019-08-09
BEIFANG UNIV OF NATITIES
View PDF8 Cites 14 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

At present, there is no guide robot for the blind, which provides an intelligent guidance for the blind according to the surrounding objects and the angle and distance of the object from the blind.

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
  • Intelligent voice type guide blind robot control method and control system thereof
  • Intelligent voice type guide blind robot control method and control system thereof
  • Intelligent voice type guide blind robot control method and control system thereof

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0076] The object detection flow chart of the embodiment of this application is as follows Figure 5 As shown, there are 20 types of objects in this experiment, so each grid only predicts the conditional class probability Pr(Class_iObject) of 20 types of objects once, i=1,2,...,20; each grid predicts B The location of the bounding box; that is, the B bounding boxes share a set of conditional class probabilities Pr(Class_iObject), i=1,2,...,20. Based on the calculated Pr(Class_iObject), the confidence of a certain bounding box class can be calculated during testing:

[0077] The YOLO neural network training block diagram is as follows Image 6 As shown, the YOLO neural network training process is as follows:

[0078] (1) Convolve the entire image with 64 7×7 convolution kernels;

[0079] (2) Extract features through a series of 3×3 or 1×1 convolutional layers;

[0080] (3) Use two fully connected layers for classification and regression, and finally generate a 7×7×30 matrix...

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 an intelligent voice type guide blind robot control method and a control system thereof. With a YOLO neural network, detection and recognition of an object are realized to obtain obstacle category information; binocular calibration and three-dimensional matching are carried out on a binocular camera to realize a ranging function. On the basis of the espeak speech synthesis,voice broadcasting of the obtained obstacle category information as well as a distance between the obstacle and a robot and orientations of the obstacle and the robot is carried out to realize obstacle broadcasting. A near-infrared sensor is used for detecting an obstacle within a view field; a walking device is used for realizing walking and obstacle avoidance; information is transmitted with the user in a voice manner; and the sensory ability of the user to the ambient environment is enhanced. The recognition accuracy is high and the performance to the complex environment is robust. The accurate and intelligent voice broadcasting is realized; the object type in front of the blind user is warned and a shortest distance to the object is provided, so that the blind user can obtain the environment information accurately, the life quality is improved, and the living need of the blind user is met.

Description

technical field [0001] The invention belongs to a blind-guiding robot, and in particular relates to a control method and a control system of an intelligent voice guiding blind-guiding robot. Background technique [0002] According to the statistics of the national statistics department, there are 17.31 million people with visual impairment in my country, among which there are more than 5 million people who are blind. There are about 400,000 new blind people every year. In our daily life, most of the information is obtained by vision. However, the physical defects of the blind and the influence of the complex social environment have brought great inconvenience to the life of the blind. [0003] The state's support for the blind has been strengthened, and various institutions that provide massage training for the blind have increased. The blind have more opportunities to choose jobs. The appearance of guide canes and guide dogs has greatly helped the blind travel. At present...

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): G05D1/02
CPCG05D1/0231G05D1/0246
Inventor 马行王政博黄全进穆春阳张春涛陈建宇杨玉
Owner BEIFANG UNIV OF NATITIES
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