CN106067191A - The method and system of semantic map set up by a kind of domestic robot - Google Patents
The method and system of semantic map set up by a kind of domestic robot Download PDFInfo
- Publication number
- CN106067191A CN106067191A CN201610353996.3A CN201610353996A CN106067191A CN 106067191 A CN106067191 A CN 106067191A CN 201610353996 A CN201610353996 A CN 201610353996A CN 106067191 A CN106067191 A CN 106067191A
- Authority
- CN
- China
- Prior art keywords
- map
- dimensional
- indoor
- furniture
- type
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T17/00—Three dimensional [3D] modelling, e.g. data description of 3D objects
- G06T17/05—Geographic models
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10024—Color image
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Geometry (AREA)
- Software Systems (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Remote Sensing (AREA)
- Computer Graphics (AREA)
- Multimedia (AREA)
- Manipulator (AREA)
Abstract
The present invention relates to a kind of method that semantic map set up by domestic robot, including: A, the indoor structure two-dimensional grid map that robot is worked；B, RGD D depth transducer is utilized to carry out the indoor structure three-dimensional map of robot movable；C, combine wearable sensor and judge its furniture type contacted according to the behavior characteristics of people；D, carry out the two-dimensional grid map of structure and three-dimensional map being fused into three-dimensional indoor map；E, the attribute assignment of indoor furniture type and other markers is formed three-dimensional indoor semantic map being built into three-dimensional indoor map.The method determines indoor furniture type by the activity of people, and furniture information is joined in three-dimensional map, thus realizes three-dimensional indoor semanteme and build figure.The method simple in construction, be easily achieved, easy to operate, with low cost.
Description
Technical field
The invention belongs to intelligent semantic map structuring field, particularly relate to a kind of domestic robot and set up the side of semantic map
Method and system.
Background technology
The purposes of robot is more and more extensive, and the especially rise of Information Mobile Service robot, robot starts from traditional
Industrial circle is to field infiltrations such as military affairs, medical treatment, family assistants.Along with the continuous aggravation of social senilization's problem, mobile machine
People enters family provides the demand of service more and more urgent for people.
Current SLAM(is relied on to synchronize location and build figure) environmental map that creates of technology has its limitation, built map
Only within a period of time effectively, if environment changes, that is accomplished by again building figure.It addition, existing cartographic model only embodies shifting
The positional information of mobile robot self, and mobile robot wants with the people in environment, and to carry out information mutual, it is achieved anti-theft monitoring,
The function such as cleaning, monitoring patient, control household electrical appliances, time-indicating awaking, children education, that is accomplished by by means of semantic map, i.e.
Need to allow robot oneself know residing particular location, show that room is " bedroom " or " parlor ".
Prior art all be utilize image first-class sensor, use entropy map, come based on order Bayesian frame structure right
Target is identified, and uses bayesian state estimation to update the probability distribution of current state.Also there is employing based on information-theoretical
Synchronous planning location and the method building figure (SPLAM), estimate its appearance while utilizing the mobile target of robot identification one
State is without any kinematic constraint condition.Further, depth transducer i.e. RGB-D image processing techniques can be used to carry out 3D language
The structure of free burial ground for the destitute figure.
Summary of the invention
It is an object of the invention to provide a kind of method that semantic map set up by domestic robot, it is intended to solve above-mentioned skill
Art problem.
The present invention is achieved in that a kind of method that semantic map set up by domestic robot, and described method includes following
Step:
A, the indoor structure two-dimensional grid map that robot is worked；
B, RGD-D depth transducer is utilized to carry out the indoor structure three-dimensional map of robot movable；
C, combine wearable sensor and judge its furniture type contacted according to the behavior characteristics of people；
D, carry out the two-dimensional grid map of structure and three-dimensional map being fused into three-dimensional indoor map；
E, the attribute assignment of indoor furniture type and other markers is formed three-dimensional indoor language being built into three-dimensional indoor map
Free burial ground for the destitute figure.
The further technical scheme of the present invention is: build two-dimensional grid map use in described step A is laser ranging
Instrument completes.
The further technical scheme of the present invention is: in described step E, the type by judging furniture or sign object determines
The type in room or character.
The further technical scheme of the present invention is: described wearable sensor includes Intelligent bracelet, intelligent watch and sets
Sensor in human body waist.
The further technical scheme of the present invention is: by identifying that physical activity obtains position furniture in described step C
The relevant knowledge of type realizes furniture and predefines model of action for determining the type of furniture.
Another object of the present invention is to the system providing a kind of domestic robot to set up semantic map, described system bag
Include:
Two-dimensional grid map structuring module, for the indoor structure two-dimensional grid map to robot work；
Three-dimensional map builds module, for utilizing RGD-D depth transducer to carry out the indoor structure three-dimensional map of robot movable；
Furniture type judging module, judges its furniture contacted for combining wearable sensor according to the behavior characteristics of people
Type；
Three-dimensional indoor map module, indoor for the two-dimensional grid map of structure and three-dimensional map are carried out being fused into three-dimensional
Map；
Semantic map structuring module, for being built into three-dimensional indoor by the attribute assignment of indoor furniture type and other markers
Map forms three-dimensional indoor semantic map.
The further technical scheme of the present invention is: desire to make money or profit with building two-dimensional grid in described two-dimensional grid map structuring module
Be that laser range finder completes.
The further technical scheme of the present invention is: by judging furniture or indicating object in described semantic map structuring module
Type determine type or the character in room.
The further technical scheme of the present invention is: described wearable sensor includes Intelligent bracelet, intelligent watch and sets
Sensor in human body waist.
The further technical scheme of the present invention is: by identifying that physical activity obtains institute in described furniture type judging module
Relevant knowledge in position furniture type realizes furniture and predefines model of action for determining the type of furniture.
The invention has the beneficial effects as follows: the method determines indoor furniture type by the activity of people, and by furniture information
Join in three-dimensional map, thus realize three-dimensional indoor semanteme and build figure, utilize the intelligence such as the Intelligent bracelet on existing market, wrist-watch
Hardware, the vision sensor that robot carries, to judge the behavior characteristics of people, finally defines the type of furniture and dimensionally
Position in figure, the final structure realizing semantic map.The method simple in construction, be easily achieved, easy to operate, with low cost.
Accompanying drawing explanation
Fig. 1 is the flow chart that the method for semantic map set up by the domestic robot that the embodiment of the present invention provides.
Fig. 2 is the structured flowchart that the system of semantic map set up by the domestic robot that the embodiment of the present invention provides.
Detailed description of the invention
Fig. 1 shows that the flow chart of the method for semantic map set up by a kind of domestic robot that the present invention provides, and it describes in detail
As follows:
Step S1, the indoor structure two-dimensional grid map to robot work；When robot being placed in the place of its work, machine
People is unfamiliar to its working space, at this moment needs to make it for robot and can make identification map at yard, is making
In map, robot utilizes laser range finder to make and builds indoor two-dimensional grid map.
Step S2, utilizes RGD-D depth transducer to carry out the indoor structure three-dimensional map of robot movable；In actual fortune
Only could allow under three-dimensional environment in robot know, the concrete position such as window, so needing to utilize the RGD-D degree of depth to pass
Sensor carries out the structure of three-dimensional map to working space, and it is mainly the structure being completed three-dimensional map by Kinect photographic head
Build.
Step S3, judges its furniture type contacted in conjunction with wearable sensor according to the behavior characteristics of people；Moving machine
Device people is during drawing, it is possible to combine the wearable sensor of people and the behavior characteristics identification to people determines and people
There is the furniture feature of contact, finally judge furniture type, such as chair, bed, desk etc..Nowadays Wearable device includes
Intelligent bracelet popular on market, wrist-watch, be also placed on the sensor of human body waist, obtain from as the action message source of people
Take semantic map.Therefore, by identifying that physical activity is obtained with the relevant knowledge of the furniture type of its position, thus
A kind of predefined model of action about furniture will be used for determining the type of furniture.It is to say, by judge furniture or its
He identifies the type of object, thus knows that room is " office ", " kitchen " or " bedroom ".But this kind of semantic information is for complete
It is very important for becoming the task in some daily life.Such as, if owner wants to go to bed, then robot will
The lamp in bedroom can be closed.
Step S4, carries out being fused into three-dimensional indoor map by two-dimensional grid map and the three-dimensional map of structure；At machine
Drawn working space two-dimensional grid map and the three-dimensional map built are carried out overall fusion formation by the system of device people
New working space three-dimensional map.
Step S5, is being built into three-dimensional indoor map formation three by the attribute assignment of indoor furniture type and other markers
The indoor semantic map of dimension.The goods categories feature indication assignment identified by robot is in the three-dimensional indoor map created
Forming new semantic map, the robot being can be capable of identify that the environment of indoor according to the map.
Existing cartographic model only embodies the positional information of mobile robot self, and mobile robot want with in environment
People to carry out information mutual, that is accomplished by by means of semantic map.Such as, present SLAM(synchronizes location and drawing) technology can
To realize the structure of indoor figure two-dimensional or three-dimensional, but not can know which room is " parlor ", " kitchen " or " bedroom ".
And be very important for the task that this kind of semantic information is in robot assisted owner completes some daily life.Such as
Saying, if owner intends to go to bed, robot just can be in conjunction with the data fusion of sensors multiple in upper figure and room property
Select to close the lamp in which room.
Semantic map is to carry out attribute assignment on the basis of the figure two-dimensional or three-dimensional originally built by SLAM, i.e. allows
The particular location in map is known by robot.Compare and utilize the two dimension that laser range finder, sonar and infrared sensor etc. are traditional
Figure mode is built in indoor, utilizes RGB-D sensor to complete three-dimensional indoor and builds figure, it is possible to obtain complete three-dimensional information positions it
Self also estimates the attitude of a six degree of freedom (x, y, z, rolling, pitching, driftage).Robotic vision sensor is used primarily in
The identity of people is demarcated and limbs feature extraction, compared with the recognition method of motion sensor, and the identification side of view-based access control model sensor
Formula is for reality
Testing environment has specific requirement to compare, and the such as factor such as brightness, obstacle and fog obtains view data for video camera to be had
Significantly impact, motion sensor then will not be affected by environmental factors like this, and this is also that system to use can
The data of wearing sensor carry out the reason merged.
The identity of people is demarcated and is mainly by robot in the indoor interaction with people, is gathered by vision sensor
Family's face database, face database is constantly trained and allows after the face of owner family classified to facilitate by robot
Identification, be so contemplated to allow robot system that kinsfolk is had the demarcation of individual identity, be so obtained with room close
The viscosity number of connection kinsfolk, such as corresponding multiple bedrooms and the mapping relations of multiple kinsfolk.
Wearable sensors is the sensor being placed on human body surface directly or indirectly, and wearable sensor can be embedding
Enter to clothes, glasses, belt, shoes, wrist-watch, mobile device or be directly placed on health.When people carries out activity, they can
To be used for gathering the information such as the position of health, motion, pulse and skin temperature, thus the physiological status of real-time monitor or motion
Feature.Obtaining people's positional information in map by the sensor worn on the person, this can be positioned by wifi
Realizing, WLAN wifi is in extensive range in indoor deployment, is suitable for positioning on a large scale, pedestrian carries out absolute fix, no
Deviation accumulation can be produced, be suitable for long-time location.The reckoning method relying on sensor inertial sensor positions meeting for a long time
Cumulative errors, if using the absolute fix of wifi to carry out correcting, can preferably improve the precision of indoor positioning.
The machine learning algorithms such as neutral net, HMM or support vector machine are used to carry out gesture mode knowledge
Not.Time series motion feature storehouse mentioned here is the data base in high in the clouds, and this is the knot being acquired great amount of samples collecting
Really, in general, there are certain relatedness the state of the limb activity of people and time, such as the time common people having a meal are
Being to be seated to have a meal, and the action having a meal also is regular governed, this is intended to be trained in advance certainly.Due to computing capability
Demand, be all put into high in the clouds here by the algorithm of pattern recognition, so can reduce wanting of the operational capability to robot
Ask.
When after the attribute of the limb activity of system acquisition certain member of family, i.e. know that owner in which position and specifically does
Thing, thus can by owner often map area carry out semantic assignment, finally realize the high-level service merit of robot
Energy.Such as when owner is after dish is finished in kitchen, calling robot, robot just can come the position in kitchen, then by regarding
Sense sensor carries out Face datection, and comes owner at one's side, and performs the thing of owner's instruction, such as serves a dish and arrive hall
On dining table.
Fig. 2 shows the system that another object of the present invention is to provide a kind of domestic robot to set up semantic map, institute
The system of stating includes:
Two-dimensional grid map structuring module, for the indoor structure two-dimensional grid map to robot work；
Three-dimensional map builds module, for utilizing RGD-D depth transducer to carry out the indoor structure three-dimensional map of robot movable；
Furniture type judging module, judges its furniture contacted for combining wearable sensor according to the behavior characteristics of people
Type；
Three-dimensional indoor map module, indoor for the two-dimensional grid map of structure and three-dimensional map are carried out being fused into three-dimensional
Map；
Semantic map structuring module, for being built into three-dimensional indoor by the attribute assignment of indoor furniture type and other markers
Map forms three-dimensional indoor semantic map.
The further technical scheme of the present invention is: desire to make money or profit with building two-dimensional grid in described two-dimensional grid map structuring module
Be that laser range finder completes.
Described semantic map structuring module is determined type or the property in room by the type judging furniture or sign object
Matter.
Described wearable sensor includes Intelligent bracelet, intelligent watch and is located at the sensor of human body waist.
By identifying that physical activity obtains the relevant knowledge of position furniture type in described furniture type judging module
Realize furniture and predefine model of action for determining the type of furniture.
This system determines indoor furniture type by the activity of people, and joins in three-dimensional map by furniture information, from
And realize three-dimensional indoor semanteme and build figure, utilize the Intelligent hardware such as the Intelligent bracelet on existing market, wrist-watch, what robot carried regards
Sense sensor judges the behavior characteristics of people, finally defines the type of furniture and the position in three-dimensional map, finally realizes
The structure of semantic map.The method simple in construction, be easily achieved, easy to operate, with low cost.
The foregoing is only presently preferred embodiments of the present invention, not in order to limit the present invention, all essences in the present invention
Any amendment, equivalent and the improvement etc. made within god and principle, should be included within the scope of the present invention.
Claims (10)
1. the method that semantic map set up by a domestic robot, it is characterised in that said method comprising the steps of:
A, the indoor structure two-dimensional grid map that robot is worked；
B, RGD-D depth transducer is utilized to carry out the indoor structure three-dimensional map of robot movable；
C, combine wearable sensor and judge its furniture type contacted according to the behavior characteristics of people；
D, carry out the two-dimensional grid map of structure and three-dimensional map being fused into three-dimensional indoor map；
E, the attribute assignment of indoor furniture type and other markers is formed three-dimensional indoor language being built into three-dimensional indoor map
Free burial ground for the destitute figure.
Method the most according to claim 1, it is characterised in that in described step A, structure two-dimensional grid map use is
Laser range finder completes.
Method the most according to claim 2, it is characterised in that by judging furniture or indicating object in described step E
Type determines type or the character in room.
Method the most according to claim 3, it is characterised in that described wearable sensor includes Intelligent bracelet, intelligence
Wrist-watch and be located at the sensor of human body waist.
Method the most according to claim 4, it is characterised in that by identifying that physical activity obtains place in described step C
The relevant knowledge of position furniture type realizes furniture and predefines model of action for determining the type of furniture.
6. the system of the semantic map of domestic robot foundation, it is characterised in that described system includes:
Two-dimensional grid map structuring module, for the indoor structure two-dimensional grid map to robot work；
Three-dimensional map builds module, for utilizing RGD-D depth transducer to carry out the indoor structure three-dimensional map of robot movable；
Furniture type judging module, judges its furniture contacted for combining wearable sensor according to the behavior characteristics of people
Type；
Three-dimensional indoor map module, indoor for the two-dimensional grid map of structure and three-dimensional map are carried out being fused into three-dimensional
Map；
Semantic map structuring module, for being built into three-dimensional indoor by the attribute assignment of indoor furniture type and other markers
Map forms three-dimensional indoor semantic map.
Method the most according to claim 6, it is characterised in that build two-dimensional grid in described two-dimensional grid map structuring module
Lattice map use is that laser range finder completes.
Method the most according to claim 7, it is characterised in that in described semantic map structuring module by judge furniture or
The type indicating object determines type or the character in room.
Method the most according to claim 8, it is characterised in that described wearable sensor includes Intelligent bracelet, intelligence
Wrist-watch and be located at the sensor of human body waist.
Method the most according to claim 9, it is characterised in that by identifying human body in described furniture type judging module
The movable relevant knowledge obtaining position furniture type realizes furniture and predefines model of action for determining the type of furniture.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610353996.3A CN106067191A (en) | 2016-05-25 | 2016-05-25 | The method and system of semantic map set up by a kind of domestic robot |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610353996.3A CN106067191A (en) | 2016-05-25 | 2016-05-25 | The method and system of semantic map set up by a kind of domestic robot |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106067191A true CN106067191A (en) | 2016-11-02 |
Family
ID=57420156
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610353996.3A Pending CN106067191A (en) | 2016-05-25 | 2016-05-25 | The method and system of semantic map set up by a kind of domestic robot |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106067191A (en) |
Cited By (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2019127102A1 (en) * | 2017-12-27 | 2019-07-04 | 深圳前海达闼云端智能科技有限公司 | Information processing method and apparatus, cloud processing device, and computer program product |
| CN110309346A (en) * | 2018-03-02 | 2019-10-08 | 上海博泰悦臻网络技术服务有限公司 | Song recommendations method, sound system and server based on indoor location positioning |
| CN111476894A (en) * | 2020-05-14 | 2020-07-31 | 小狗电器互联网科技（北京）股份有限公司 | Three-dimensional semantic map construction method and device, storage medium and electronic equipment |
| CN111487980A (en) * | 2020-05-14 | 2020-08-04 | 小狗电器互联网科技（北京）股份有限公司 | Control method of intelligent device, storage medium and electronic device |
| CN111609852A (en) * | 2019-02-25 | 2020-09-01 | 北京奇虎科技有限公司 | Semantic map construction method, sweeping robot and electronic equipment |
| CN111665842A (en) * | 2020-06-09 | 2020-09-15 | 山东大学 | Indoor SLAM mapping method and system based on semantic information fusion |
| CN111679661A (en) * | 2019-02-25 | 2020-09-18 | 北京奇虎科技有限公司 | Semantic map construction method based on depth camera and sweeping robot |
| CN111679663A (en) * | 2019-02-25 | 2020-09-18 | 北京奇虎科技有限公司 | Three-dimensional map construction method, sweeping robot and electronic equipment |
| CN112037325A (en) * | 2020-08-07 | 2020-12-04 | 珠海格力电器股份有限公司 | Method and device for constructing semantic map, computer equipment and storage medium |
| CN112070122A (en) * | 2020-08-14 | 2020-12-11 | 五邑大学 | Classification method and device of slam map and storage medium |
| CN112075879A (en) * | 2019-06-14 | 2020-12-15 | 江苏美的清洁电器股份有限公司 | Information processing method, device and storage medium |
| CN112184904A (en) * | 2020-09-28 | 2021-01-05 | 中国石油集团工程股份有限公司 | Digital integration method and device |
| CN112346449A (en) * | 2019-08-08 | 2021-02-09 | 和硕联合科技股份有限公司 | Semantic map orientation device and method and robot |
| CN112837412A (en) * | 2019-11-25 | 2021-05-25 | 科沃斯机器人股份有限公司 | Three-dimensional map interaction method and device, robot and storage medium |
| CN113269874A (en) * | 2021-04-20 | 2021-08-17 | 达闼机器人有限公司 | Method and device for establishing three-dimensional map |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090226113A1 (en) * | 2008-03-07 | 2009-09-10 | Kosei Matsumoto | Environment Map Generating Apparatus, Environment Map Generating Method, and Environment Map Generating Program |
| CN104732587A (en) * | 2015-04-14 | 2015-06-24 | 中国科学技术大学 | Depth sensor-based method of establishing indoor 3D (three-dimensional) semantic map |
-
2016
- 2016-05-25 CN CN201610353996.3A patent/CN106067191A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090226113A1 (en) * | 2008-03-07 | 2009-09-10 | Kosei Matsumoto | Environment Map Generating Apparatus, Environment Map Generating Method, and Environment Map Generating Program |
| CN104732587A (en) * | 2015-04-14 | 2015-06-24 | 中国科学技术大学 | Depth sensor-based method of establishing indoor 3D (three-dimensional) semantic map |
Non-Patent Citations (1)
| Title |
|---|
| 陶重犇: "未知环境探测及三维室内语义建图研究", 《中国博士学位论文全文数据库信息科技辑》 * |
Cited By (19)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2019127102A1 (en) * | 2017-12-27 | 2019-07-04 | 深圳前海达闼云端智能科技有限公司 | Information processing method and apparatus, cloud processing device, and computer program product |
| CN110309346A (en) * | 2018-03-02 | 2019-10-08 | 上海博泰悦臻网络技术服务有限公司 | Song recommendations method, sound system and server based on indoor location positioning |
| CN111679661A (en) * | 2019-02-25 | 2020-09-18 | 北京奇虎科技有限公司 | Semantic map construction method based on depth camera and sweeping robot |
| CN111609852A (en) * | 2019-02-25 | 2020-09-01 | 北京奇虎科技有限公司 | Semantic map construction method, sweeping robot and electronic equipment |
| CN111679663A (en) * | 2019-02-25 | 2020-09-18 | 北京奇虎科技有限公司 | Three-dimensional map construction method, sweeping robot and electronic equipment |
| CN112075879A (en) * | 2019-06-14 | 2020-12-15 | 江苏美的清洁电器股份有限公司 | Information processing method, device and storage medium |
| CN112346449A (en) * | 2019-08-08 | 2021-02-09 | 和硕联合科技股份有限公司 | Semantic map orientation device and method and robot |
| CN112837412A (en) * | 2019-11-25 | 2021-05-25 | 科沃斯机器人股份有限公司 | Three-dimensional map interaction method and device, robot and storage medium |
| CN112837412B (en) * | 2019-11-25 | 2023-08-04 | 科沃斯家用机器人有限公司 | Three-dimensional map interaction method, three-dimensional map interaction device, robot and storage medium |
| CN111487980A (en) * | 2020-05-14 | 2020-08-04 | 小狗电器互联网科技（北京）股份有限公司 | Control method of intelligent device, storage medium and electronic device |
| CN111476894A (en) * | 2020-05-14 | 2020-07-31 | 小狗电器互联网科技（北京）股份有限公司 | Three-dimensional semantic map construction method and device, storage medium and electronic equipment |
| CN111487980B (en) * | 2020-05-14 | 2024-04-02 | 小狗电器互联网科技（北京）股份有限公司 | Control method of intelligent device, storage medium and electronic device |
| CN111665842A (en) * | 2020-06-09 | 2020-09-15 | 山东大学 | Indoor SLAM mapping method and system based on semantic information fusion |
| CN111665842B (en) * | 2020-06-09 | 2021-09-28 | 山东大学 | Indoor SLAM mapping method and system based on semantic information fusion |
| CN112037325A (en) * | 2020-08-07 | 2020-12-04 | 珠海格力电器股份有限公司 | Method and device for constructing semantic map, computer equipment and storage medium |
| CN112070122A (en) * | 2020-08-14 | 2020-12-11 | 五邑大学 | Classification method and device of slam map and storage medium |
| CN112070122B (en) * | 2020-08-14 | 2023-10-17 | 五邑大学 | Classification method, device and storage medium of slam map |
| CN112184904A (en) * | 2020-09-28 | 2021-01-05 | 中国石油集团工程股份有限公司 | Digital integration method and device |
| CN113269874A (en) * | 2021-04-20 | 2021-08-17 | 达闼机器人有限公司 | Method and device for establishing three-dimensional map |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106067191A (en) | The method and system of semantic map set up by a kind of domestic robot | |
| US11207236B2 (en) | Method and system for providing information to a user | |
| CN110605724B (en) | Intelligence endowment robot that accompanies | |
| EP2923252B1 (en) | Method and apparatus to control hardware in an environment | |
| CN104504623B (en) | It is a kind of that the method, system and device for carrying out scene Recognition are perceived according to action | |
| CN105364915B (en) | Intelligent home service robot based on three-dimensional machine vision | |
| CN104011788A (en) | System And Method For Augmented And Virtual Reality | |
| Sevrin et al. | Characterization of a multi-user indoor positioning system based on low cost depth vision (Kinect) for monitoring human activity in a smart home | |
| US20140140590A1 (en) | Trends and rules compliance with depth video | |
| CN109240279A (en) | A kind of robot navigation method of view-based access control model perception and spatial cognition neuromechanism | |
| CN107943276A (en) | Based on the human body behavioral value of big data platform and early warning | |
| Bock et al. | Ambient Integrated Robotics: Automation and Robotic Technologies for Maintenance, Assistance, and Service | |
| CN105530581A (en) | Smart wearable device based on voice recognition and control method thereof | |
| Behan et al. | The development of an autonomous service robot. Implementation:“Lucas”—The library assistant robot | |
| Silvera-Tawil et al. | Human-robot interaction with humanoid Diamandini using an open experimentation method | |
| Fraccaro et al. | Development and preliminary evaluation of a method for passive, privacy-aware home care monitoring based on 2D LiDAR data | |
| EP3738726B1 (en) | Animal-shaped autonomous moving body, method of operating animal-shaped autonomous moving body, and program | |
| JP2010205015A (en) | Group behavior estimation device and service provision system | |
| Cheng et al. | Application exploring of ubiquitous pressure sensitive matrix as input resource for home-service robots | |
| JP5567725B2 (en) | Group behavior estimation device | |
| CN104266645B (en) | Indoor personnel behavior recognition and position tracking system and method | |
| Abdullahi et al. | A Smart Real-Time Standalone Route Recognition System for Visually Impaired Persons | |
| Liu et al. | Augmented Reality Powers a Cognitive Prosthesis for the Blind | |
| Wang et al. | Indoor localization system based on wearable posture sensors with incomplete observations | |
| Xue et al. | An efficient ambient intelligent–assisted people searching for Internet of Things–based health-care system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20161102 |
|
| RJ01 | Rejection of invention patent application after publication |