Unlock instant, AI-driven research and patent intelligence for your innovation.

Vision-assisted distance SLAM method and apparatus, and robot

A robot and distance sensor technology, applied in the field of robots, readable storage media, and visual aided distance SLA, can solve the problem of global relocation that is difficult to eliminate cumulative errors, achieve fast global relocation, high success rate, and eliminate cumulative errors. Effect

Active Publication Date: 2020-04-24
UBTECH ROBOTICS CORP LTD
View PDF6 Cites 8 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] The technical problem mainly solved by the present invention is to provide a visually assisted distance SLAM method and device, a robot, and a readable storage medium, which can solve the problem that distance SLAM is difficult to eliminate cumulative errors / complete global relocation in the prior art

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
  • Vision-assisted distance SLAM method and apparatus, and robot
  • Vision-assisted distance SLAM method and apparatus, and robot
  • Vision-assisted distance SLAM method and apparatus, and robot

Examples

Experimental program
Comparison scheme
Effect test

no. 1 example

[0023] Such as figure 1 As shown, the first embodiment of the visually assisted distance SLAM method of the present invention includes:

[0024] S1: Obtain multiple distance data frames and multiple visual data frames.

[0025] The distance data frame is obtained by using a distance sensor, and the vision data frame is obtained by using a vision sensor. The distance sensor may be a laser radar, an ultrasonic ranging sensor, an infrared ranging sensor, or the like. Vision sensors may include RGB cameras and / or depth cameras. The RGB camera can obtain image data, and the depth camera can obtain depth data. If the visual sensor only includes RGB cameras, the number of RGB cameras can be greater than one. For example, two RGB cameras form a binocular camera, so that images from at least two RGB cameras can be used Data calculates depth data. The image data and / or depth data obtained by the visual sensor can be directly used as a visual data frame, or feature data can be extrac...

no. 4 example

[0051] Such as Figure 5 As shown, the fourth embodiment of the visually assisted distance SLAM method of the present invention includes:

[0052] S10: Obtain current visual data.

[0053] Current vision data is acquired using vision sensors. Vision sensors may include RGB cameras and / or depth cameras. The RGB camera can obtain image data, and the depth camera can obtain depth data. If the visual sensor only includes RGB cameras, the number of RGB cameras can be greater than one. For example, two RGB cameras form a binocular camera, so that images from at least two RGB cameras can be used Data calculates depth data. The image data and / or depth data obtained by the visual sensor may be directly used as a visual data frame, or feature data extracted from the image data and / or depth data may be used as current visual data.

[0054] S20: Perform loopback detection on the current visual data among the multiple stored visual data frames to locate the visual data frame.

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 vision-assisted distance SLAM method. The method comprises the steps: acquiring a plurality of distance data frames and a plurality of visual data frames, enabling each visual data frame to correspond to one distance data frame, and enabling the corresponding visual data frame and distance data frame to be obtained at the same frame; performing loopback detection by usinga current visual data frame in the plurality of visual data frames to find a matched visual data frame; under the condition that the matched visual data frame is found, calculating a relative pose between the current visual data frame and the matched visual data frame; and performing loopback optimization on the pose data of the frame between the current visual data frame and the matched visual data frame by utilizing the relative pose. The invention further discloses a vision-assisted distance SLAM apparatus, a robot and a readable storage medium. With the mode, the mapping precision can beimproved, and rapid repositioning can be realized.

Description

technical field [0001] The invention relates to the field of motors, in particular to a visual-assisted distance SLAM method and device, a robot, and a readable storage medium. Background technique [0002] Simultaneous localization and map construction (Simultaneous Localization And Mapping, SLAM) refers to the acquisition and calculation of various sensor data on the carrier (such as robots, unmanned aerial vehicles, etc.) Techniques for localization and scene map information. [0003] There are generally two types of common SLAM: distance-based SLAM and vision-based SLAM. Distance-based SLAM (distance SLAM), such as lidar-based SLAM (laser SLAM), uses distance sensors to measure objects around the carrier, and the collected object information presents a series of scattered, accurate angle and distance information The point is called the point cloud. By matching and comparing the two point clouds at different times, the distance from the relative movement of the sensor a...

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): G01C21/20G06T7/73
CPCG01C21/20G06T7/74G06T2207/10016G06T2207/30252G01C21/3848G01C21/32G06T7/579G06T2207/10024G06T2207/30244G05D1/0274G05D1/0248G05D1/0246G05D2201/02G05D1/024
Inventor 熊友军蒋晨晨白龙彪毕占甲刘志超
Owner UBTECH ROBOTICS CORP LTD