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

Method and system for fully automatically exploring unknown space and establishing map

A fully automatic, global map technology, applied in the field of machine learning, can solve problems such as low automation, inaccurate positioning, and low map accuracy, and achieve the effects of simple operation, saving human resources, and high accuracy

Pending Publication Date: 2018-12-25
长春博立电子科技有限公司
View PDF9 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0014] Due to inaccurate positioning, the accuracy of the final map is low, and it is difficult for the robot to determine the boundary points and plan the path independently, so manual intervention is required, and the degree of automation is very low

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
  • Method and system for fully automatically exploring unknown space and establishing map
  • Method and system for fully automatically exploring unknown space and establishing map
  • Method and system for fully automatically exploring unknown space and establishing map

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0036] Such as Figures 1 to 2 As shown, a preferred embodiment of a method for fully automatic exploration of unknown space and building a map of the present invention includes:

[0037] Collect stereoscopic video data using stereoscopic video acquisition tools;

[0038] Use the high-precision positioning algorithm to locate the current position in real time and build a map, and perform verification and closed-loop detection during the process of building the map;

[0039] The sub-maps are stitched together, and the loop detection is performed to obtain the final map.

[0040] In this embodiment, a stereoscopic video acquisition tool is used to collect stereoscopic video data, and then a high-performance embedded computer is used to use a high-precision positioning algorithm to locate the current position in real time and establish a map. Test, and closed-loop detection, improve positioning accuracy and map accuracy.

[0041] Positioning, map building and loop closure dete...

Embodiment 2

[0044] A preferred embodiment of a method for fully automatic exploration of unknown space and establishment of a map of the present invention, comprising:

[0045] LiDAR / stereo video sensor for collecting stereo video data;

[0046] The positioning unit uses a high-precision positioning algorithm to locate the current position in real time and establish a map, and perform verification and closed-loop detection during the process of establishing the map;

[0047] The sub-map splicing unit is used for splicing the sub-maps together for loop detection to obtain the final map.

[0048] Further, the lidar / stereo video sensor is supported by a chassis, the chassis is a drivable driving wheel or a track, and the chassis is powered by a battery.

[0049] Such as image 3 As shown, the system in this embodiment builds a map based on stereoscopic video or lidar data, and autonomous movement is based on a movable chassis. And the algorithm itself needs computer hardware support.

[...

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 method and a system for fully automatically exploring unknown space and establishing a map. The method for fully automatically exploring unknown space and establishing a mapcomprises the steps of: collecting stereoscopic video data by using a stereoscopic video collection tool; positioning current location in real time and establishing a map by using a high-precision positioning algorithm; checking and performing closed-loop detection during process of establishing the map; splicing sub-maps and performing loopback detection to obtain a final map. According to the method and the system for fully automatically exploring unknown space and establishing the map, the fully automatically exploring unknown space is finally realized by combining high-precision positioning, high-precision mapping, boundary point selection and optimal path selection.

Description

technical field [0001] The invention relates to the technical field of machine learning, in particular to a method and system for fully automatic exploration of unknown spaces and establishment of maps. Background technique [0002] Machines understand the environment just like humans, and they also need similar Figure 1 In this kind of map, various environmental information are described, and different map description methods are adopted according to the differences of algorithms and sensors. [0003] In the process of establishing the map, it is necessary to realize the positioning of the robot itself and the planning of the exploration path. In the prior art, the positioning of the robot itself is mostly inaccurate, and there are many irrationalities in the planning of the exploration path. The main disadvantages are as follows: [0004] There are errors in the moving distance returned by the robot and the data obtained by the sensor. It is difficult to accurately esta...

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): G01S17/89
CPCG01S17/89
Inventor 张立华薛长宇张阳焦健
Owner 长春博立电子科技有限公司