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

Hybrid adaptive particle filtering method for mobile robot fault diagnosis

A mobile robot and fault diagnosis technology, applied in the direction of manipulators, complex mathematical operations, manufacturing tools, etc., can solve the problems of multiple time and memory space, cost, and the inability to dynamically adjust the number of particles

Inactive Publication Date: 2018-07-24
UNIV OF ELECTRONICS SCI & TECH OF CHINA ZHONGSHAN INST
View PDF4 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The disadvantage of this method is that multiple particle filters are used for different modes, so that the conversion between particle filters takes more time and memory space; in addition, this method cannot dynamically adjust the number of particles

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
  • Hybrid adaptive particle filtering method for mobile robot fault diagnosis
  • Hybrid adaptive particle filtering method for mobile robot fault diagnosis
  • Hybrid adaptive particle filtering method for mobile robot fault diagnosis

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0032] The specific implementation method of the present invention will be described in detail below. The invention relates to a hybrid adaptive particle filter method for fault diagnosis of a mobile robot, which organically combines two mechanisms of state space self-adaptation and particle number self-adaptation. The core idea of ​​state space adaptation is to constrain the sampling space to a fuzzy subset of the "full state space" according to the domain knowledge of mobile robot fault diagnosis, and the number of particles is approximated by two particle sets with different numbers of particles at the same time. The KL distance between the distributions is adjusted, the domain knowledge is used to describe the probability of various failures of the mobile robot in different motion modes, and the domain knowledge uncertainty caused by the drive and the actuator is represented by a fuzzy set.

[0033] Specific steps are as follows:

[0034] Step 1 Initialization steps:

[...

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 a hybrid adaptive particle filtering method for mobile robot fault diagnosis. A state space adaptive mechanism and a particle number adaptive mechanism are organically combined. A core thought of the state space adaptive mechanism is that a sampling space is constrained to a fuzzy subset of a total state space according to domain knowledge of the mobile robot fault diagnosis; a particle number is adjusted through a KL distance between approximate distribution represented by particle sets of two different particle numbers at the same moment; the domain knowledge is usedfor describing occurrence probabilities of various faults of a mobile robot in different motion modes; and domain knowledge uncertainty caused by driver and execution mechanisms is represented by a fuzzy set.

Description

technical field [0001] The invention relates to a hybrid adaptive particle filter method for fault diagnosis of mobile robots, belonging to the field of fault diagnosis of mobile robots. Background technique [0002] Fault diagnosis is critical for mobile robot localization, modeling, navigation, and even safety. Fault diagnosis is a typical state estimation problem for stochastic hybrid systems. A particle filter is a Monte Carlo method for monitoring a dynamic system that non-parametrically approximates a probability distribution through a set of weighted samples (i.e., particles). When particle filters deal with complex high-dimensional problems, the main problem is to overcome the contradiction between precision and efficiency: in order to improve precision, the number of particles must be increased; and in order to improve efficiency, the number of particles must be reduced. [0003] Literature (see "Yu Lingli, Cai Zixing, Tan Ping, Duan Zhuohua: "Fault Diagnosis of M...

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): G06F17/18B25J19/00
CPCB25J19/0095G06F17/18
Inventor 段琢华杨亮
Owner UNIV OF ELECTRONICS SCI & TECH OF CHINA ZHONGSHAN INST
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