A robot positioning method combining camera, imu and lidar

A technology of robot positioning and laser radar, applied in the direction of instruments, electromagnetic wave re-radiation, image analysis, etc., can solve the problems of low accuracy and stability, point cloud matching, etc., and achieve the effect of eliminating cumulative errors

Active Publication Date: 2020-05-19
SICHUAN UNIV
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] Most of the existing robot solutions are based on cameras or low-beam laser radars. Camera-based solutions will bring problems of low accuracy and stability, and purely based on laser radars will also bring problems that point cloud matching cannot be performed well.

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 positioning method combining camera, imu and lidar
  • A robot positioning method combining camera, imu and lidar
  • A robot positioning method combining camera, imu and lidar

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0031] The present invention will be further described below in conjunction with accompanying drawing:

[0032] Such as figure 1 As shown, the purpose of the present invention is to provide a robot positioning method combining camera, imu and laser radar in order to solve the above problems, including the following steps:

[0033] S1: Calibrate the lidar and camera so that the laser points and pixels can achieve pixel-level accuracy;

[0034] S2: Set the lidar scanning frequency, scanning angle, camera frame rate and imu frequency and collect data;

[0035] S3: Pre-integrate the imu data, and suppress its error through visual feature points, and obtain inter-frame pose transformation information and feature point information in real time;

[0036] S4: Register feature points and laser point cloud, select feature point ray to be located in the feature point pair of laser point cloud curvature smaller area, interpolate out feature point distance, and assign primary weight to f...

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 positioning method combining a camera, an imu and a laser radar. The depth of the surrounding environment is maintained more accurately through the camera and the laser radar, and an odometer is constructed through continuous tracking of feature points. This method can combine the advantages of camera, imu and lidar to establish an accurate and dense point cloud map for robot path planning. Through the tight coupling of camera and lidar, the accuracy of the inter-frame odometer can be improved, and a higher robustness can be achieved. Stickiness; through the point cloud map maintained by laser and camera in real time, local optimization of the odometer in laser scanning; through the word information and imu data provided by the camera to judge the loop, realize the closed loop on the point cloud map provided by vision and laser optimization.

Description

technical field [0001] The invention relates to the technical field of robot positioning, in particular to a robot positioning method combining a camera, an IMU and a laser radar. Background technique [0002] As technologies such as computing power and sensors continue to increase, the functions of outdoor patrol and security robots are also becoming more and more, and at the same time, the mixed use of multi-sensor data is becoming more and more diverse. The robot is no longer limited to the use of a single sensor, but can obtain more accurate environment and pose information through the cooperation of multi-sensor data. As an important means of robot positioning, the mutual use of multi-sensor data requires strong computing power, and the development of computers now provides a good foundation for this condition. [0003] Most of the existing robot solutions are based on cameras or low-beam laser radars. Camera-based solutions will bring problems of low accuracy and stab...

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): G06T7/73G06T7/33G06T7/246G06T7/521G01S17/02G01S17/89G01S17/93
CPCG01S17/89G01S17/93G06T7/246G06T7/33G06T7/521G06T7/73G06T2207/10028G06T2207/10044
Inventor 张轶黄瑞
Owner SICHUAN 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