Supercharge Your Innovation With Domain-Expert AI Agents!

A Robot Navigation Method Based on Incremental Online Learning

A technology of navigation method and learning method, applied in navigation, mapping and navigation, navigation calculation tools, etc., can solve the problems of complex construction, strong manual dependence, poor flexibility of magnetic track laying, etc.

Active Publication Date: 2020-11-10
HOHAI UNIV CHANGZHOU
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, in practical applications, the flexibility of magnetic track laying is poor, the construction is complicated, and the maintenance cost is high; the manual marking positioning method needs to draw an electronic map of the substation in advance, and the reference column must be laid in advance and the coordinates must be determined, which is too dependent on labor; The positioning and navigation method has high precision, flexibility and reliability, but it needs to set a lot of reflective signs in the station in advance, which brings a certain amount of operation and maintenance costs

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 Robot Navigation Method Based on Incremental Online Learning
  • A Robot Navigation Method Based on Incremental Online Learning
  • A Robot Navigation Method Based on Incremental Online Learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0066] The present invention will be further described below in conjunction with the accompanying drawings. The following examples are only used to illustrate the technical solution of the present invention more clearly, but not to limit the protection scope of the present invention.

[0067] like figure 1 As shown, the robot navigation method based on incremental online learning includes the following steps:

[0068] Step 1. Manually guide the robot to walk around the area. The robot itself carries GPS. The robot samples the real-time position signal to obtain the coordinate information of the robot. When the coordinate information meets the preset conditions, the coordinate information is stored.

[0069] The condition that the coordinate information satisfies is,

[0070] ||x n+1 -x n ||>d,x n ∈ N

[0071] Among them, the position signal input point set N, x n+1 Input point for the n+1th position signal, x n Input point for the nth position signal, d is the preset d...

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 robot navigation method based on incremental online learning. The robot navigation method includes: manually guiding a robot to walk in a circle in an area, allowing the robot to sample a real-time position signal to obtain the coordinate information of the robot, and storing the coordinate information when the coordinate information meets a preset condition; using the coordinate information as the input, and with the constant updating of the storage, using an incremental online learning method and a self-organizing neural network model increasing according to needs to build an area map; using the area map to perform target point positioning, and using an improved A* algorithm to plane an optimal route to a target position to complete the navigation task. The robot navigation method has the advantages that fast navigation is achieved, and the work efficiency of an inspection robot is increased greatly.

Description

technical field [0001] The invention relates to a robot navigation method based on incremental online learning, belonging to the field of robot navigation. Background technique [0002] Substation inspection robot is a kind of intelligent mobile robot, which can replace manual inspection in many cases. It can complete the inspection work of substation equipment in the extreme environment of ultra-high voltage, which not only solves the harm problem of human body working in extreme environment for a long time , but also to ensure the safe and stable operation of substation equipment. [0003] The key tasks of substation inspection robots are to achieve accurate positioning, fast path planning and navigation. There are many substation robot navigation technologies, such as magnetic track laying navigation methods, manual marker positioning methods, laser positioning and navigation methods, and so on. However, in practical applications, the flexibility of magnetic track layin...

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): G01C21/20G01S19/42
CPCG01C21/206G01S19/42
Inventor 倪建军顾亚飞范新南史朋飞
Owner HOHAI UNIV CHANGZHOU
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More