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

Joint positioning method based on RGB-D and laser speedometer

An odometer and laser technology, applied in surveying and navigation, re-radiation of electromagnetic waves, utilization of re-radiation, etc., can solve problems such as inability to work, poor relocation ability, blurred images, etc., to improve the correct matching rate and ensure accuracy The effect of rate and robustness

Active Publication Date: 2019-04-16
南京理工大学工程技术研究院有限公司
View PDF6 Cites 13 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, visual SLAM has the following disadvantages: but it is highly dependent on light, and it cannot work in dark places or some texture-free areas
Visual SLAM relies solely on images, and when the movement is too fast, there will inevitably be problems with blurred images
[0005]2. High environmental requirements and high dependence on light
But laser SLAM is not good at localization in dynamic environments, such as those with a large number of people obscuring its measurements, or in similar geometric environments, such as a long, straight environment flanked by walls.
Due to poor relocation ability, laser SLAM is difficult to return to working state after tracking loss

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
  • Joint positioning method based on RGB-D and laser speedometer
  • Joint positioning method based on RGB-D and laser speedometer
  • Joint positioning method based on RGB-D and laser speedometer

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0034] The present invention will be described in further detail below in conjunction with the accompanying drawings.

[0035] combine first figure 2 , to describe the specific process of federated filtering.

[0036] The main idea of ​​federated filtering is that each local filter uses the information provided by the local sensor to operate independently, and the obtained local estimated value and covariance are sent to the global filter, and the global optimal estimate is obtained through the calculation of the global filter. Then, the global optimal estimate is fed back to the local filter, and the estimated value of the local filter is reset for the next update fusion.

[0037] Suppose the motion equation and observation equation of the robot are respectively

[0038] x i (k)=F(k-1)X i (k-1)+W(k) (1)

[0039] Z i (k)=H i (k-1)X i (k)+V i (k) (2)

[0040] where X i (k) is the state vector at time k, F(k-1) and H i (k-1) are state transition matrix and observati...

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 joint positioning method based on a RGB-D and a laser speedometer. In the present invention, visual localization is based on the RGB-D, motion estimation is carried out according to line feature matching, and an EKF-SLAM is used in a laser method to carry out motion estimation, when the two algorithms are successfully positioned at the same moment, the system has two poses, and optimal estimation is obtained by carrying out combined filtering on the two poses; and if positioning failure is caused by certain scenes such as low textures and the like, the pose obtained by laser radar positioning is taken as the optimal pose of the global filter. Therefore, a combined positioning mode is adopted, advantages and disadvantages of a radar system and a depth camera systemare integrated, and visual SLAM based on line features and the EKF-SLAM are combined, so that the positioning and mapping precision of the system is greatly improved.

Description

technical field [0001] The invention belongs to the field of autonomous positioning of mobile robots, and in particular relates to a combined positioning method based on RGB-D and a laser odometer. Background technique [0002] With the expansion of the application field of intelligent mobile robots, people expect intelligent mobile robots to serve humans in more fields and replace humans to complete more complex tasks. However, the environment in which intelligent mobile robots live is often unknown and difficult to predict. The first consideration is autonomous navigation, and SLAM (Simultaneous Localization and Mapping, simultaneous positioning and mapping) is one of the core issues in mobile robot navigation. , is the premise of realizing the robot path planning task. In mobile robot navigation, whether it is local real-time obstacle avoidance or global planning, it is necessary to accurately know the current state and position of the robot or obstacle to complete tasks...

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): G01S17/02G01S17/06G01C11/00
CPCG01C11/00G01S17/06G01S17/86
Inventor 郭剑辉周贝贝蔡球球吴轶凡牟升钟钎钎
Owner 南京理工大学工程技术研究院有限公司
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