Mobile robot SLAM method based on improved EMM and ORB algorithms

A mobile robot and algorithm technology, applied in computer parts, instruments, calculations, etc., can solve the problems of large error and low robustness, and achieve the effect of small error, no training, and strong robustness.

Active Publication Date: 2018-11-16
SHANGHAI UNIVERSITY OF ELECTRIC POWER
View PDF5 Cites 16 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The robustness of the current SLAM system algorithm is low, and the error is large

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
  • Mobile robot SLAM method based on improved EMM and ORB algorithms
  • Mobile robot SLAM method based on improved EMM and ORB algorithms
  • Mobile robot SLAM method based on improved EMM and ORB algorithms

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0039] The mobile robot SLAM method based on the improved environmental measurement model (EMM) and ORB algorithm proposed by this application is used for the intelligent inspection of robots in various fields involving safety in the inspection robot industry and life, mainly including feature point extraction and matching Algorithm, feature point Mahalanobis distance calculation, observation likelihood calculation of environmental measurement model, loop closure detection and back-end optimization. Such as figure 1 As shown, the method specifically includes the following steps:

[0040] S1. Collect color images and depth images through a 3D camera. In this embodiment, the 3D camera uses Kinect, and the number of pixels in the picture is 640×480. The improved ORB algorithm is used to extract the feature points of the color image and calculate the descriptor. At the same time, the depth image is processed. filtering.

[0041] The process of using the improved ORB algorithm to...

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 mobile robot SLAM method based on an improved EMM and ORB algorithm. The method comprises the following steps that 1, a color image and a depth image are acquired by a 3D camera, feature points of the color image are extracted by using the improved ORB algorithm, descriptors are calculated, and meanwhile the depth image is filtered; 2, pixel points of the color image areconverted into 3D points in a space coordinate system, pose calculation is conducted by using an ICP algorithm, mismatching points are removed, and pose refinement is conducted; 3, loopback detectionis conducted through a Dijkstra algorithm and a random sampling method to obtain optimized pose information; and 4, a sparse point cloud map is established according to the optimized pose informationthrough an observation likelihood calculation method for the improved environment measurement model. Compared with the prior art, the method has the lower cost than laser radar positioning and has the advantages that the robustness is high, the error is small, and training is not needed compared with other visual methods.

Description

technical field [0001] The invention relates to the positioning and navigation technology of an intelligent inspection robot system, in particular to a mobile robot SLAM method based on improved EMM and ORB algorithms. Background technique [0002] It can be seen from the development trend of the industry that inspection robots will occupy a large market in various fields in the future, especially in substations, campuses, factories, military industries, ships and other places. In view of the high price of lidar and the lack of accuracy of GPS module in the research and development process, the depth camera is used for local auxiliary positioning. [0003] The visual positioning system is mainly divided into front-end and back-end, as well as loopback detection. The front-end is used to extract the features in the image and used to establish landmarks, while the back-end is used to optimize the cumulative error of the pose generated by the camera’s own error, making trajecto...

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): G06K9/00G06K9/46
CPCG06V20/10G06V10/462
Inventor 彭道刚陈昱皓赵晨洋彭盖伦王志萍夏飞
Owner SHANGHAI UNIVERSITY OF ELECTRIC POWER
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