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

Semantic map construction and operation method, autonomous mobile device and storage medium

A semantic map and construction method technology, applied in the field of artificial intelligence, can solve problems such as simple semantic information, achieve the effect of improving experience, facilitating interactive control, and meeting needs

Inactive Publication Date: 2021-05-11
ECOVACS ROBOTICS (SUZHOU ) CO LTD
View PDF4 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the semantic information contained in existing semantic maps is relatively simple and cannot meet people's needs

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
  • Semantic map construction and operation method, autonomous mobile device and storage medium
  • Semantic map construction and operation method, autonomous mobile device and storage medium
  • Semantic map construction and operation method, autonomous mobile device and storage medium

Examples

Experimental program
Comparison scheme
Effect test

example 1

[0076] In a home environment, a sweeping robot is required to clean an unknown work area. The unknown work area can be the area where the sweeping robot performs cleaning tasks for the first time, or an area that the sweeping robot cannot understand because the semantic map has not yet been built. When the sweeping robot cleans the unknown operation area, the camera on the robot is used to collect the environmental image of the operation area in real time, and the environmental image is sent to the built-in target detection model of the sweeping robot to perform target detection and semantic recognition on the environmental image to obtain the unknown operation Semantic information of at least one object contained in the region, that is, what kind of object the object is. In addition, the actual position of the at least one object in the work area may also be estimated according to the pixel position of the at least one object in the environment image. In this embodiment, assu...

example 2

[0080] In the home environment, the sweeping robot needs to clean an unknown operation area. The unknown operation area can be the area where the sweeping robot performs the cleaning task for the first time, or the area that the sweeping robot cannot understand because the semantic map has not yet been constructed. In the process of cleaning the unknown operation area by the sweeping robot, the camera on the robot is used to collect the environmental image of the unknown operation area in real time, and the real-time collected environmental image is sent to the server.

[0081] The server receives the environmental image sent by the sweeping robot, uses the target detection model to perform target detection and semantic recognition on the environmental image, and obtains the semantic information of at least one object contained in the unknown operation area, that is, what kind of object the object is. In addition, the server can also estimate the actual position of the object i...

Embodiment approach

[0095] In a possible embodiment, according to the semantic information of multiple objects contained in the working environment, an implementation manner of identifying the scene semantic information of at least one job partition includes: according to the position information of multiple objects and the The boundary is to determine the objects contained in each of the at least one operation partition; and to identify the scene semantic information of the at least one operation partition respectively according to the semantic information of the objects contained in each of the at least one operation partition.

[0096] Optionally, during the process of target detection and semantic recognition of the environment information, position information of multiple objects included in the work environment may also be detected. Combining the position information of the plurality of objects and the boundary of at least one operation area, the objects contained in each of the at least one...

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 embodiment of the invention provides a semantic map construction and operation method, autonomous mobile equipment and a storage medium. According to the embodiment of the invention, the method comprises the steps: collecting the environment information of an operation region of the autonomous mobile equipment, and carrying out the target detection and semantic recognition of the environment information to obtain the semantic information of an object contained in the operation region; and furthermore, according to the semantic information of the object contained in the operation area, identifying the scenarized semantic information of the operation area, and constructing a semantic map containing the scenarized semantic information of the operation area. The semantic map is high in semantic understanding level, interaction control between the user and the autonomous mobile equipment is facilitated, the user experience is improved, and the requirements of people on the semantic map are met.

Description

technical field [0001] This application relates to the technical field of artificial intelligence, and in particular to a semantic map construction and operation method, an autonomous mobile device and a storage medium. Background technique [0002] With the development of artificial intelligence technology, household appliances also tend to be intelligent. For example, sweeping robots can automatically complete the task of cleaning the ground, freeing users from cleaning tasks. Some robots use sensors such as cameras or radars to construct an environmental map in real time, and use the environmental map for autonomous localization and navigation. [0003] However, the information contained in the existing environmental map is only some digital information, which is not intuitive enough and not easy to understand for users. Semantic maps can integrate "semantic information" that is easy for users to understand into environmental maps, and have attracted extensive attention...

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): G06K9/00G06F16/29
CPCG06F16/29G06V20/10G06V20/56G06V2201/07
Inventor 蔡瑞莹鲍亮
Owner ECOVACS ROBOTICS (SUZHOU ) CO LTD
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com