Multi-olfactory robot collaborative smell source positioning method

A positioning method and robot technology, applied in two-dimensional position/channel control, instruments, motor vehicles, etc., can solve the problems of lack of multi-robot information sharing, inability to better realize iterative training results and motion path planning linkage perception, etc. , to achieve the effect of improving flexibility and efficiency and reducing consumption

Active Publication Date: 2021-09-17
HANGZHOU DIANZI UNIV
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Although the above methods have improved the global fast search ability to a certain extent, they lack the information shari

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
  • Multi-olfactory robot collaborative smell source positioning method
  • Multi-olfactory robot collaborative smell source positioning method
  • Multi-olfactory robot collaborative smell source positioning method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0053] Such as figure 1 As shown, the present invention proposes a method for locating odor sources coordinated by multiple olfactory robots. Firstly, in the phase of odor source discovery, multiple olfactory robots are randomly distributed in different positions of the two-dimensional search plane, and then all the olfactory robots perform a spiral motion that expands outward; once the gas concentrations measured by any three olfactory robots are greater than the low threshold , at this moment, the above-mentioned three olfactory robots enter the phase of tracking the odor source, and start to make s-shaped segmental sinusoidal motion towards the odor source. Based on the BP neural network and RFID positioning system, the BP neural network dynamically adjusts the weights by using the periodic gradient information to control the movement slope of each cycle of the olfactory robot; the RFID positioning system transmits the gas concentration measured by multiple olfactory robots...

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 multi-olfactory robot collaborative smell source positioning method, which comprises the following steps that: olfactory robots quickly discover a smell source through spiral motion, optimize the weight adjustment of a BP (Back Propagation) neural network to improve the accuracy of tracking a motion slope, and quickly track the smell source through s-type segmented sinusoidal motion, meanwhile, the information coupling among the multiple robots is enhanced by utilizing the characteristics of the RFID positioning system, so that the expandability and robustness of the system are improved to a certain extent, and the generalization ability of the model is enhanced while the rapid positioning of the smell source is realized.

Description

technical field [0001] The invention belongs to the field of location and detection of dangerous gas sources, and in particular relates to a method for locating odor sources coordinated by multiple olfactory robots. Background technique [0002] The rapid location of hazardous odor sources is of great significance to human health and environmental safety. Traditional odor source localization methods track odor sources based on local concentration gradients, such as zigzag search and trilateral positioning search. Because such algorithms lack prior knowledge, they usually have to traverse the entire search area, resulting in low search efficiency. And the degree of intelligence is weak. [0003] In recent years, odor source localization methods based on artificial neural networks have been widely used. For example, some studies have combined the hybrid leapfrog algorithm to improve the convergence speed of neural network training, and some studies have introduced radial bas...

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
IPC IPC(8): G05D1/02
CPCG05D1/0212G05D1/0221G05D2201/0217
Inventor 范影乐魏楚洁韩显修武薇
Owner HANGZHOU DIANZI UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap