CN108733037A - A kind of sweeping robot avoids cleaning method - Google Patents
A kind of sweeping robot avoids cleaning method Download PDFInfo
- Publication number
- CN108733037A CN108733037A CN201710247519.3A CN201710247519A CN108733037A CN 108733037 A CN108733037 A CN 108733037A CN 201710247519 A CN201710247519 A CN 201710247519A CN 108733037 A CN108733037 A CN 108733037A
- Authority
- CN
- China
- Prior art keywords
- region
- sweeping robot
- cleaned
- cleans
- probability
- 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.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course or altitude of land, water, air, or space vehicles, e.g. automatic pilot
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0212—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory
- G05D1/0219—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory ensuring the processing of the whole working surface
Abstract
The present invention relates to a kind of cleaning method that avoids of sweeping robot, the method is related to four kinds of operating modes of sweeping robot:Initial pattern, stochastic model, conceptual schema and conditional probability pattern, sweeping robot with cleaning wheel number increase, the progressive variation of its operating mode, finally variation is conditional probability pattern, each operating mode is obtained in the statistical basis of previous cleaning process, indoor human or animal is avoided most possibly, improves the sweeping efficiency of sweeping robot.
Description
【Technical field】
Cleaning method is avoided the invention belongs to sweeping robot field more particularly to a kind of sweeping robot.
【Background technology】
Now, for sweeping robot as a kind of intelligent electric appliance, application is more and more common, can rely on certain artificial intelligence
Can, complete floor cleaning work in the room automatically.Under normal conditions, sweeping robot is swept in the time reservation of setting, and
Voluntarily charge, front be provided with inductor, can obstruction detection, such as encounter wall or other barriers, can voluntarily turn, and
Room is cleaned according to being set with planning.
In the prior art, the inductor majority passes through both means using built-in camera detection and laser ranging
It carries out indoor environment scanning, draw indoor map, and avoided when encountering barrier.But when purging zone appearance is more
Always when moving, sweeping robot can avoid always personal or animal, hardly clean, and cause sweeping efficiency low, effect
Fruit is poor.
【Invention content】
In order to solve the above problem in the prior art, what the present invention proposed a kind of sweeping robot avoids cleaning side
Method.
The technical solution adopted by the present invention is specific as follows:
A kind of sweeping robot avoids cleaning method, and there are four types of operating modes for the sweeping robot tool:Introductory die
Formula, stochastic model, conceptual schema and conditional probability pattern;This method comprises the following steps:
(1) after sweeping robot enters a new indoor environment, the first round cleans to N1 wheels to clean and all use
Initial pattern, and draw indoor map;
(2) indoor map is divided into multiple regions by the sweeping robot;
(3) from N1+ 1 takes turns to N2Wheel cleans, and the sweeping robot is cleaned using stochastic model;
(4) from N2+ 1 takes turns to N3Wheel cleans, and the sweeping robot is cleaned using conceptual schema;
(5) from N3+ 1 wheel, which cleans, to be started, and the sweeping robot is cleaned using conditional probability pattern;
Wherein N1、N2、N3All it is predefined numerical value.
Further, under the initial pattern, the direction that the sweeping robot random selection is advanced is cleaned,
When encountering barrier, then the random direction for changing advance.
Further, under the stochastic model, the sweeping robot randomly chooses one first from all areas
Region has cleaned one region of random selection in the region that a region also never cleans every time;After selecting a region, institute
It states sweeping robot and real time scan first is carried out to the region, judge whether the region has human or animal, to this if not
Region is cleaned, if there is randomly choosing one again in the region that then never cleans.
Further, under the conceptual schema, before the cleaning of every wheel, the sweeping robot is remembered according to previous cleaning
Record, calculate each region has the probability of human or animal as its movable probability in previous each wheel cleans;
Then a region of sweeping robot selection activity probability minimum from all areas, is cleaning every time
A region of selection activity probability minimum in the region that one region also never cleans;It is described to sweep after selecting a region
Floor-washing robot first carries out real time scan to the region, judges whether the region has human or animal, to the region if not
It is cleaned, if there is the movable probability in the region is then revised as 1 temporarily, then selection activity probability in the region never cleaned
A minimum region.
Further, under the conditional probability pattern, before the cleaning of every wheel starts, the sweeping robot is based on passing
Cleaning record statistical condition probability P (X, Y), X is 0 or a region, and Y is a region and Y ≠ X;
The conditional probability is defined as follows:
P (0, Y) is probability of the region Y as first purging zone in previous each wheel cleans;
When X is not equal to 0, P (X, Y) is the probability that region Y is cleaned after the X of region during previous each wheel cleans;
Under conditional probability pattern, if not having started cleaning, X=0, otherwise the sweeping robot, which obtains, just cleans
Complete region X, selection make the maximum region Y of value of P (X, Y);After selecting a region Y, the sweeping robot
Real time scan first is carried out to region Y, judges whether region Y has human or animal, region Y is carried out if not clear
Sweep, if there is the conditional probability P (X, Y) of region Y is then revised as 0 temporarily, then in the region never cleaned selection so that P
The maximum region Y of value of (X, Y).
Further, N1=10.
Further, N2=100.
Further, N3=300.
This method has the beneficial effect that:In the cleaning process of sweeping robot, indoor people or dynamic can be effectively avoided
Object improves the sweeping efficiency of robot.
【Description of the drawings】
Attached drawing described herein is to be used to provide further understanding of the present invention, and is constituted part of this application, but
It does not constitute improper limitations of the present invention, in the accompanying drawings:
Fig. 1 is four kinds of operating modes of sweeping robot of the present invention.
【Specific implementation mode】
Come that the present invention will be described in detail below in conjunction with attached drawing and specific embodiment, illustrative examples therein and says
It is bright to be only used for explaining the present invention but not as a limitation of the invention.
It is cleaned current invention assumes that sweeping robot is fixed in the same indoor environment, which can have
The indoor environment is all cleaned one time and is known as a wheel cleaning by multiple rooms or region, sweeping robot.
Referring to attached drawing 1, the cleaning of sweeping robot of the present invention is divided into four kinds of operating modes:It is initial pattern, stochastic model, general
Rate pattern, conditional probability pattern.The each round of sweeping robot, which cleans, all uses one of which operating mode, in the same interior
Under environment, sweeping robot can gradually use different operating modes, specific method to be described as follows as time goes by:
(1) after sweeping robot enters a new indoor environment, the first round cleans to N1Wheel is cleaned and is all used
Initial pattern, and draw indoor map.
Under the initial pattern, the direction that the sweeping robot random selection is advanced is cleaned, and obstacle is being encountered
When object, then the random direction for changing advance.The main purpose of this pattern is gradually to draw out indoor ground by cleaning process
Figure.Typically, after the cleaning of several wheels, indoor map will be drawn out.It should be noted that indoor environment is general
Situation does not have too big variation, but if there is variation, in subsequent cleaning process, map may also can be changed.
The N1Value can be set by manufacturer of robot, can also as the case may be set by user, it is preferable that N1
=10.
(2) indoor map is divided into multiple regions by the sweeping robot.
Since indoor map is drawn out, indoor map can be divided into multiple by the sweeping robot
Region.For example, for one family, bedroom region A, parlor region B, kitchen area C, toilet area can be marked off
D, balcony region E etc..
(3) from N1+ 1 takes turns to N2Wheel cleans, and the sweeping robot is cleaned using stochastic model.
Under the stochastic model, the sweeping robot is cleaned according to region, random first from all areas
A region is selected, has cleaned one region of random selection in the region that a region also never cleans every time.In selection one
Behind region, the sweeping robot first carries out real time scan to the region, judges whether the region has human or animal, if do not had
Have, which is cleaned, if there is randomly choosing one again in the region that then never cleans.
The N2Value can be set by manufacturer of robot, can also as the case may be set by user, it is preferable that N2
=100.
(4) from N2+ 1 takes turns to N3Wheel cleans, and the sweeping robot is cleaned using conceptual schema.
Under the conceptual schema, before the cleaning of every wheel, the sweeping robot is recorded according to previous cleaning, is calculated every
A region has the probability of human or animal as its movable probability.Specifically, in each round cleaning, sweeping robot either exists
Scanning before purging zone, or the scanning in cleaning process, all may find that the human or animal in region, it is assumed that before
It has carried out N wheels altogether to clean, wherein in NADuring wheel cleans, it is found that region A has human or animal, then the activity probability P of region AA=NA/
N。
Then a region of sweeping robot selection activity probability minimum from all areas, is cleaning every time
A region of selection activity probability minimum in the region that one region also never cleans.It is described to sweep after selecting a region
Floor-washing robot first carries out real time scan to the region, judges whether the region has human or animal, to the region if not
It is cleaned, if there is the movable probability in the region is then revised as 1 temporarily, then selection activity probability in the region never cleaned
A minimum region.
The N3Value can be set by manufacturer of robot, can also as the case may be set by user, it is preferable that N3
=300.
(5) from N3+ 1 wheel, which cleans, to be started, and the sweeping robot is cleaned using conditional probability pattern.
The conditional probability pattern is recorded based on passing cleaning, before the cleaning of every wheel starts, the sweeping robot base
In passing cleaning record statistics the following conditions probability P (X, Y), X is 0 or a region, and Y is a region and Y ≠ X.
It is probability (at this time X=0) of the region Y as first purging zone in a wheel cleans first, it is assumed that it
Before have been carried out K wheel clean, wherein there is KADuring wheel cleans, region A is used as first purging zone, then region A is as first
Probability P (0, A)=K of a purging zoneA/K。
The probability that followed by a region Y is cleaned after the X of region, it is assumed that K wheels are had been carried out before to be cleaned, wherein
In KABDuring wheel cleans, after region A has been cleaned, region B is and then cleaned, then conditional probability P (A, B)=KAB/K。
Based on above-mentioned condition probability, under conditional probability pattern, the sweeping robot is based on the region X just cleaned
If (not starting also to clean, X=0), selection makes the maximum region Y of value of P (X, Y).Selecting a region Y
Afterwards, the sweeping robot first carries out real time scan to region Y, judges whether region Y has human or animal, if do not had
Then region Y is cleaned, if there is the conditional probability P (X, Y) of region Y is then revised as 0 temporarily, then never clean
Selection makes the maximum region of value of P (X, Y) in region.
Based on above-mentioned cleaning method, sweeping robot of the invention with the increase of cleaning wheel number, is progressive by operating mode
Variation, finally variation is conditional probability pattern, each operating mode is obtained in the statistical basis of previous cleaning process
, the influence of indoor humans and animals can be preferably avoided out, to improve cleaning works efficiency a step by a step.
The above is only the better embodiment of the present invention, therefore all constructions according to described in present patent application range,
The equivalent change or modification that feature and principle are done, is included within the scope of present patent application.
Claims (8)
1. a kind of sweeping robot avoids cleaning method, which is characterized in that there are four types of Working moulds for the sweeping robot tool
Formula:Initial pattern, stochastic model, conceptual schema and conditional probability pattern;This method comprises the following steps:
(1) after sweeping robot enters a new indoor environment, the first round cleans to N1Wheel, which cleans, all uses introductory die
Formula, and draw indoor map;
(2) indoor map is divided into multiple regions by the sweeping robot;
(3) from N1+ 1 takes turns to N2Wheel cleans, and the sweeping robot is cleaned using stochastic model;
(4) from N2+ 1 takes turns to N3Wheel cleans, and the sweeping robot is cleaned using conceptual schema;
(5) from N3+ 1 wheel, which cleans, to be started, and the sweeping robot is cleaned using conditional probability pattern;
Wherein N1、N2、N3All it is predefined numerical value.
2. sweeping robot according to claim 1 avoids cleaning method, which is characterized in that in the initial pattern
Under, the direction that the sweeping robot random selection is advanced is cleaned, when encountering barrier, then the random side for changing advance
To.
3. sweeping robot according to claim 1-2 any one avoids cleaning method, which is characterized in that in institute
It states under stochastic model, the sweeping robot randomly chooses a region first from all areas, cleans the areas Wan Yige every time
A region is randomly choosed in the region that domain also never cleans;After selecting a region, the areas the sweeping robot Xian Duigai
Domain carry out real time scan, judge the region whether have human or animal, the region is cleaned if not, if there is if
Never one is randomly choosed in the region cleaned again.
4. sweeping robot according to claim 1-3 any one avoids cleaning method, which is characterized in that in institute
It states under conceptual schema, before the cleaning of every wheel, the sweeping robot is recorded according to previous cleaning, calculates each region previous
Each wheel has the probability of human or animal as its movable probability in cleaning;
Then a region of sweeping robot selection activity probability minimum from all areas, is cleaning one every time
A region of selection activity probability minimum in the region that region also never cleans;After selecting a region, the sweeper
Device people first carries out real time scan to the region, judges whether the region has human or animal, is carried out to the region if not
It cleans, if there is the movable probability in the region is then revised as 1 temporarily, then selection activity probability is minimum in the region never cleaned
A region.
5. sweeping robot avoids cleaning method according to any one of claims 1-4, which is characterized in that in institute
It states under conditional probability pattern, before the cleaning of every wheel starts, the sweeping robot is general based on passing cleaning record statistical condition
Rate P (X, Y), X are 0 or a region, and Y is a region and Y ≠ X;
The conditional probability is defined as follows:
P (0, Y) is probability of the region Y as first purging zone in previous each wheel cleans;
When X is not equal to 0, P (X, Y) is the probability that region Y is cleaned after the X of region during previous each wheel cleans;
Under conditional probability pattern, if not having started cleaning, X=0, the otherwise sweeping robot acquisition has just cleaned
Region X, selection make the maximum region Y of value of P (X, Y);After selecting a region Y, the sweeping robot is first right
Region Y carries out real time scan, judges whether region Y has human or animal, is cleaned to region Y if not,
If there is the conditional probability P (X, Y) of region Y is then revised as 0 temporarily, then in the region never cleaned selection so that P (X, Y)
The maximum region Y of value.
6. sweeping robot according to claim 1 avoids cleaning method, which is characterized in that N1=10.
7. sweeping robot according to claim 1 avoids cleaning method, which is characterized in that N2=100.
8. sweeping robot according to claim 1 avoids cleaning method, which is characterized in that N3=300.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710247519.3A CN108733037B (en) | 2017-04-17 | 2017-04-17 | Avoidable sweeping method of sweeping robot |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710247519.3A CN108733037B (en) | 2017-04-17 | 2017-04-17 | Avoidable sweeping method of sweeping robot |
Publications (2)
Publication Number | Publication Date |
---|---|
CN108733037A true CN108733037A (en) | 2018-11-02 |
CN108733037B CN108733037B (en) | 2021-03-16 |
Family
ID=63924169
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710247519.3A Active CN108733037B (en) | 2017-04-17 | 2017-04-17 | Avoidable sweeping method of sweeping robot |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108733037B (en) |
Citations (16)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20050182519A1 (en) * | 2003-08-28 | 2005-08-18 | Sony Corporation | Robot apparatus, control method for robot apparatus, and toy for robot apparatus |
US20050182518A1 (en) * | 2004-02-13 | 2005-08-18 | Evolution Robotics, Inc. | Robust sensor fusion for mapping and localization in a simultaneous localization and mapping (SLAM) system |
CN1811644A (en) * | 2006-03-07 | 2006-08-02 | 北京大学 | Automatic positioning method for intelligent robot under complex environment |
CN101920498A (en) * | 2009-06-16 | 2010-12-22 | 泰怡凯电器(苏州)有限公司 | Device for realizing simultaneous positioning and map building of indoor service robot and robot |
US20120265391A1 (en) * | 2009-06-18 | 2012-10-18 | Michael Todd Letsky | Method for establishing a desired area of confinement for an autonomous robot and autonomous robot implementing a control system for executing the same |
CN102866706A (en) * | 2012-09-13 | 2013-01-09 | 深圳市银星智能科技股份有限公司 | Cleaning robot adopting smart phone navigation and navigation cleaning method thereof |
CN103271699A (en) * | 2013-05-29 | 2013-09-04 | 东北师范大学 | Smart home cleaning robot |
CN103823466A (en) * | 2013-05-23 | 2014-05-28 | 电子科技大学 | Path planning method for mobile robot in dynamic environment |
CN104090573A (en) * | 2014-06-27 | 2014-10-08 | 赵希源 | Robot soccer dynamic decision-making device and method based on ant colony algorithm |
CN204203770U (en) * | 2014-10-24 | 2015-03-11 | 艾洛仕股份有限公司 | Cleaning systems and cleaning device |
CN104757909A (en) * | 2015-01-22 | 2015-07-08 | 深圳市银星智能科技股份有限公司 | Cleaning mode for robot cleaner |
CN104825101A (en) * | 2014-02-12 | 2015-08-12 | Lg电子株式会社 | Robot cleaner and controlling method thereof |
CN105320140A (en) * | 2015-12-01 | 2016-02-10 | 浙江宇视科技有限公司 | Robot cleaner and cleaning path planning method thereof |
CN105466421A (en) * | 2015-12-16 | 2016-04-06 | 东南大学 | Mobile robot autonomous cruise method for reliable WIFI connection |
CN105739504A (en) * | 2016-04-13 | 2016-07-06 | 上海物景智能科技有限公司 | Working area ranking method and ranking system for robot |
CN105793790A (en) * | 2013-12-19 | 2016-07-20 | 伊莱克斯公司 | Prioritizing cleaning areas |
-
2017
- 2017-04-17 CN CN201710247519.3A patent/CN108733037B/en active Active
Patent Citations (16)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20050182519A1 (en) * | 2003-08-28 | 2005-08-18 | Sony Corporation | Robot apparatus, control method for robot apparatus, and toy for robot apparatus |
US20050182518A1 (en) * | 2004-02-13 | 2005-08-18 | Evolution Robotics, Inc. | Robust sensor fusion for mapping and localization in a simultaneous localization and mapping (SLAM) system |
CN1811644A (en) * | 2006-03-07 | 2006-08-02 | 北京大学 | Automatic positioning method for intelligent robot under complex environment |
CN101920498A (en) * | 2009-06-16 | 2010-12-22 | 泰怡凯电器(苏州)有限公司 | Device for realizing simultaneous positioning and map building of indoor service robot and robot |
US20120265391A1 (en) * | 2009-06-18 | 2012-10-18 | Michael Todd Letsky | Method for establishing a desired area of confinement for an autonomous robot and autonomous robot implementing a control system for executing the same |
CN102866706A (en) * | 2012-09-13 | 2013-01-09 | 深圳市银星智能科技股份有限公司 | Cleaning robot adopting smart phone navigation and navigation cleaning method thereof |
CN103823466A (en) * | 2013-05-23 | 2014-05-28 | 电子科技大学 | Path planning method for mobile robot in dynamic environment |
CN103271699A (en) * | 2013-05-29 | 2013-09-04 | 东北师范大学 | Smart home cleaning robot |
CN105793790A (en) * | 2013-12-19 | 2016-07-20 | 伊莱克斯公司 | Prioritizing cleaning areas |
CN104825101A (en) * | 2014-02-12 | 2015-08-12 | Lg电子株式会社 | Robot cleaner and controlling method thereof |
CN104090573A (en) * | 2014-06-27 | 2014-10-08 | 赵希源 | Robot soccer dynamic decision-making device and method based on ant colony algorithm |
CN204203770U (en) * | 2014-10-24 | 2015-03-11 | 艾洛仕股份有限公司 | Cleaning systems and cleaning device |
CN104757909A (en) * | 2015-01-22 | 2015-07-08 | 深圳市银星智能科技股份有限公司 | Cleaning mode for robot cleaner |
CN105320140A (en) * | 2015-12-01 | 2016-02-10 | 浙江宇视科技有限公司 | Robot cleaner and cleaning path planning method thereof |
CN105466421A (en) * | 2015-12-16 | 2016-04-06 | 东南大学 | Mobile robot autonomous cruise method for reliable WIFI connection |
CN105739504A (en) * | 2016-04-13 | 2016-07-06 | 上海物景智能科技有限公司 | Working area ranking method and ranking system for robot |
Non-Patent Citations (3)
Title |
---|
ALEKSANDAR TIMCENKO: "Probability - Driven Motion Planning for Mobile Robots", 《PROCEEDINGS OF THE 1994 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION》 * |
KEVIN M. GODBY: "Robot Self-Recognition Using Conditional Probability–Based Contingency", 《NATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE & THE EIGHTEENTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE》 * |
高亚男: "清洁机器人全覆盖导航技术研究", 《中国优秀硕士学位论文全文数据库-信息科技辑》 * |
Also Published As
Publication number | Publication date |
---|---|
CN108733037B (en) | 2021-03-16 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110353579A (en) | A kind of clean robot automatic path planning method | |
CN106983460B (en) | A kind of sweeping robot region cleaning display control method | |
WO2016110097A1 (en) | Walk control method of robot, and robot | |
EP3705010B1 (en) | Suction collecting station, system comprising a suction collecting station and a suction cleaner and method for same | |
CN105411491A (en) | Home intelligent cleaning system and method based on environment monitoring | |
CN110403528B (en) | Method and system for improving cleaning coverage rate based on cleaning robot | |
CN110286669B (en) | Walking operation method of self-moving robot | |
CN107943036B (en) | Purging zone selection method and device | |
JP6542488B2 (en) | System and method for cleaning a floor using a cleaning robot | |
CN201602711U (en) | Ground processing device capable of automatically moving | |
CN112315379B (en) | Mobile robot, control method and device thereof, and computer readable medium | |
CN110251009A (en) | A kind of the cleaning path management method and system of sweeping robot | |
CN107348906A (en) | The system and method for floor cleaning with clean robot | |
CN108319266A (en) | Row method and its control system are swept based on shape recognition sweeping machine | |
CN113180549A (en) | Cleaning control method, device and air conditioner | |
CN107456162A (en) | Robot for cleaning floor and the control method for robot for cleaning floor | |
CN108742363B (en) | Intelligent stair cleaning system based on remote data restoration | |
CN108733037A (en) | A kind of sweeping robot avoids cleaning method | |
CN111374597B (en) | Method and device for avoiding line of cleaning robot, storage medium and cleaning robot | |
CN110967703A (en) | Indoor navigation method and indoor navigation device using laser radar and camera | |
CN116711996A (en) | Operation method, self-mobile device, and storage medium | |
CN110151058A (en) | Smart home sweeping robot | |
CN108261146A (en) | Row method and its control system are swept from record intelligent sweeping | |
CN107252284A (en) | A kind of clean robot | |
CN108523774A (en) | A kind of rebuffed type flusher of sweeping robot |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
CB02 | Change of applicant information | ||
CB02 | Change of applicant information |
Address after: 150000 Heilongjiang Province Harbin Pingfang District Haping Road Concentrated Area Dalian North Road and Xingkai Road Intersection Applicant after: Harbin University of Technology Robot Group Co., Ltd. Address before: 150000 Heilongjiang Province Harbin Pingfang District Haping Road Concentrated Area Dalian North Road and Xingkai Road Intersection Applicant before: HIT ROBOT GROUP CO., LTD. |
|
GR01 | Patent grant | ||
GR01 | Patent grant |