CN111374597B - Method and device for avoiding line of cleaning robot, storage medium and cleaning robot - Google Patents
Method and device for avoiding line of cleaning robot, storage medium and cleaning robot Download PDFInfo
- Publication number
- CN111374597B CN111374597B CN201811617226.0A CN201811617226A CN111374597B CN 111374597 B CN111374597 B CN 111374597B CN 201811617226 A CN201811617226 A CN 201811617226A CN 111374597 B CN111374597 B CN 111374597B
- Authority
- CN
- China
- Prior art keywords
- obstacle
- cleaning robot
- preselected
- image
- linear
- 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.)
- Active
Links
Images
Classifications
-
- A—HUMAN NECESSITIES
- A47—FURNITURE; DOMESTIC ARTICLES OR APPLIANCES; COFFEE MILLS; SPICE MILLS; SUCTION CLEANERS IN GENERAL
- A47L—DOMESTIC WASHING OR CLEANING; SUCTION CLEANERS IN GENERAL
- A47L11/00—Machines for cleaning floors, carpets, furniture, walls, or wall coverings
- A47L11/24—Floor-sweeping machines, motor-driven
-
- A—HUMAN NECESSITIES
- A47—FURNITURE; DOMESTIC ARTICLES OR APPLIANCES; COFFEE MILLS; SPICE MILLS; SUCTION CLEANERS IN GENERAL
- A47L—DOMESTIC WASHING OR CLEANING; SUCTION CLEANERS IN GENERAL
- A47L11/00—Machines for cleaning floors, carpets, furniture, walls, or wall coverings
- A47L11/40—Parts or details of machines not provided for in groups A47L11/02 - A47L11/38, or not restricted to one of these groups, e.g. handles, arrangements of switches, skirts, buffers, levers
-
- A—HUMAN NECESSITIES
- A47—FURNITURE; DOMESTIC ARTICLES OR APPLIANCES; COFFEE MILLS; SPICE MILLS; SUCTION CLEANERS IN GENERAL
- A47L—DOMESTIC WASHING OR CLEANING; SUCTION CLEANERS IN GENERAL
- A47L11/00—Machines for cleaning floors, carpets, furniture, walls, or wall coverings
- A47L11/40—Parts or details of machines not provided for in groups A47L11/02 - A47L11/38, or not restricted to one of these groups, e.g. handles, arrangements of switches, skirts, buffers, levers
- A47L11/4011—Regulation of the cleaning machine by electric means; Control systems and remote control systems therefor
-
- A—HUMAN NECESSITIES
- A47—FURNITURE; DOMESTIC ARTICLES OR APPLIANCES; COFFEE MILLS; SPICE MILLS; SUCTION CLEANERS IN GENERAL
- A47L—DOMESTIC WASHING OR CLEANING; SUCTION CLEANERS IN GENERAL
- A47L11/00—Machines for cleaning floors, carpets, furniture, walls, or wall coverings
- A47L11/40—Parts or details of machines not provided for in groups A47L11/02 - A47L11/38, or not restricted to one of these groups, e.g. handles, arrangements of switches, skirts, buffers, levers
- A47L11/4061—Steering means; Means for avoiding obstacles; Details related to the place where the driver is accommodated
-
- A—HUMAN NECESSITIES
- A47—FURNITURE; DOMESTIC ARTICLES OR APPLIANCES; COFFEE MILLS; SPICE MILLS; SUCTION CLEANERS IN GENERAL
- A47L—DOMESTIC WASHING OR CLEANING; SUCTION CLEANERS IN GENERAL
- A47L2201/00—Robotic cleaning machines, i.e. with automatic control of the travelling movement or the cleaning operation
-
- A—HUMAN NECESSITIES
- A47—FURNITURE; DOMESTIC ARTICLES OR APPLIANCES; COFFEE MILLS; SPICE MILLS; SUCTION CLEANERS IN GENERAL
- A47L—DOMESTIC WASHING OR CLEANING; SUCTION CLEANERS IN GENERAL
- A47L2201/00—Robotic cleaning machines, i.e. with automatic control of the travelling movement or the cleaning operation
- A47L2201/04—Automatic control of the travelling movement; Automatic obstacle detection
Abstract
The invention relates to a method and a device for avoiding lines of a cleaning robot, a storage medium and the cleaning robot, and belongs to the field of intelligent robots. The front end of the cleaning robot is provided with two image acquisition devices, a depth image of the front lower area is generated, the external contour of the flexible linear obstacle is identified, a plurality of point clouds corresponding to the external contour are determined, the average value of the depth values of the point clouds is used as the depth value of the preselected flexible obstacle, the cleaning robot is controlled to drive to the preselected linear flexible obstacle, the cleaning robot is controlled to move in a preset action, the contour of the preselected flexible linear obstacle in the image is identified again and matched, when the matching is unsuccessful, the preselected flexible linear obstacle is determined to be the linear obstacle, and the cleaning robot is controlled to avoid the linear obstacle. Through the technical scheme, the line avoiding effect can be improved.
Description
Technical Field
The invention relates to the field of intelligent robots, in particular to a method and a device for cleaning a robot to avoid a line, a storage medium and a cleaning robot.
Background
The cleaning robot is also called a lazy floor sweeper, and is an intelligent household appliance capable of automatically absorbing dust on the ground. Because it can detect factors such as room size, furniture placement, ground cleanliness and the like, and make a reasonable cleaning route by means of a built-in program, and has certain intelligence, the robot is called as a robot. At present, the intelligent degree of the cleaning robot is not as advanced as the imagination, but the intelligent cleaning robot is used as a catcher of a new concept of intelligent home and injects forward power for the robot to finally walk into thousands of households. At present, the cleaning robot can automatically identify the obstacle, however, the wire avoiding method can only be used for avoiding the wire of a table, a chair, a bed, a sofa and the like, and the wire, the wire and the like are still difficult to avoid.
Disclosure of Invention
To at least partially solve the above problems in the prior art, the present invention provides a method, an apparatus, a storage medium, and a cleaning robot for avoiding lines in the cleaning robot. The specific technical scheme is as follows:
a method of cleaning a robot bypass line, the cleaning robot being equipped at a front end thereof with two image pickup devices mounted in parallel in a front-downward direction for picking up a front-downward area of a forward direction of the cleaning robot, the method comprising: in the working process of the cleaning robot, controlling the two image acquisition devices to acquire multi-frame images of the front lower area at a preset frequency; acquiring a first image and a second image acquired by the two image acquisition devices at the same time, generating a depth image of the front lower area through the first image and the second image, acquiring depth values of a plurality of point cloud data through the depth image, and determining a preselected flexible linear obstacle in the depth image through the depth values of the plurality of point cloud data; identifying an external contour of the preselected flexible linear obstacle, storing the external contour as a basic contour, determining a plurality of point clouds corresponding to the external contour, taking an average value of depth values of the point clouds as a depth value of the preselected flexible linear obstacle, and determining the orientation of the preselected flexible linear obstacle according to the depth value and relative positions of the point clouds corresponding to the external contour; determining the current position of the cleaning robot as a target position, controlling the cleaning robot to travel to the position of the preselected flexible linear obstacle according to the position of the preselected flexible linear obstacle, controlling the cleaning robot to move in a preset motion mode, controlling the cleaning robot to return to the target position, re-acquiring the image of the position of the preselected flexible linear obstacle, re-identifying the contour of the preselected flexible linear obstacle in the image, matching the contour with the basic contour, determining the preselected flexible linear obstacle as the linear obstacle when the matching is unsuccessful, and controlling the cleaning robot to avoid the preselected flexible linear obstacle.
Further, the preset actions include: stopping sweeping at the preselected flexible line-like obstacle.
Further, the preset action further comprises: controlling the cleaning robot to rotate after stopping sweeping at the preselected flexible linear obstruction, thereby changing a shape of a linear object in the preselected flexible linear obstruction.
Further, said step of re-identifying the contour of said preselected flexible line-like obstacle in said image and matching said contour to said base contour further comprises: when the matching is successful, determining that the preselected flexible linear obstacle is an inherent hard object on the ground or a line on the floor, and controlling the cleaning robot to directly clean the preselected flexible linear obstacle.
An apparatus for cleaning a wire evading of a robot equipped with two image pickup devices at a front end thereof, the two image pickup devices being parallelly equipped in a front-downward direction for picking up a front-downward area of a forward direction of the robot, the apparatus comprising: the acquisition module is used for controlling the two image acquisition devices to acquire multi-frame images of the front lower area at a preset frequency in the operation process of the cleaning robot; acquiring a first image and a second image acquired by the two image acquisition devices at the same time, generating a depth image of the front lower area through the first image and the second image, acquiring depth values of a plurality of point cloud data through the depth image, and determining a preselected flexible linear obstacle in the depth image through the depth values of the plurality of point cloud data; an identification module, configured to identify an external contour of the preselected flexible linear obstacle, store the external contour as a base contour, determine a plurality of point clouds corresponding to the external contour, use an average of depth values of the plurality of point clouds as a depth value of the preselected flexible linear obstacle, and determine an orientation of the preselected flexible linear obstacle according to the depth value and a relative position of the plurality of point clouds corresponding to the external contour; and the line avoiding module is used for determining the current position of the cleaning robot as a target position, controlling the cleaning robot to run to the preselected flexible linear obstacle according to the position of the preselected flexible linear obstacle, controlling the cleaning robot to move in a preset action mode, controlling the cleaning robot to return to the target position, re-acquiring the image of the preselected flexible linear obstacle, re-identifying the profile of the preselected flexible linear obstacle in the image, matching the profile with the basic profile, determining the preselected flexible linear obstacle as the linear obstacle when the matching is unsuccessful, and controlling the cleaning robot to avoid the linear obstacle.
Further, the line avoidance module is also for controlling the cleaning robot to stop sweeping at the preselected flexible line-like obstacle.
Further, the wire avoiding module is also used for controlling the cleaning robot to rotate after cleaning is stopped at the preselected flexible linear obstacle, so as to change the shape of a linear object in the preselected flexible linear obstacle.
Further, the wire avoiding module is also used for determining that the preselected flexible wire-shaped barrier is an inherent hard object on the ground or a line on the floor, and controlling the cleaning robot to directly clean the preselected flexible wire-shaped barrier when the matching is successful.
A computer storage medium, on which a computer program is stored, which, when being executed by a processor, implements a method of cleaning a robot for avoiding wires as described above.
A cleaning robot, comprising: one or more processors; storage means for storing one or more programs; when executed by the one or more processors, cause the one or more processors to implement a method of cleaning a robot from a line as described above.
The invention has the beneficial effects that: the robot can identify a real linear object through image identification, path planning and other modes, and can eliminate interference factors on the ground or in the environment; the front end of the cleaning robot is provided with two image acquisition devices which are assembled in a front-downward direction in parallel and used for acquiring a front-lower area of the advancing direction of the cleaning robot, and the image data of the front-lower area can be acquired in a targeted manner by the assembly mode, so that the interference of objects which do not influence the movement is directly filtered; in the operation process of the cleaning robot, the two image acquisition devices are controlled to acquire multi-frame images of the front lower area at a preset frequency, so that accurate data of the front lower area can be acquired in real time, and real-time monitoring is kept; acquiring a first image and a second image acquired by the two image acquisition devices at the same time, and generating a depth image of the front lower area through the first image and the second image to obtain a three-dimensional image with higher precision; the method comprises the steps of obtaining depth values of a plurality of point cloud data through a depth image, determining a preselected flexible linear obstacle in the depth image according to the depth values of the point cloud data, determining the flexible linear obstacle directly according to the depth values, determining a plurality of point clouds corresponding to the external outline when the external outline of the preselected flexible linear obstacle is identified, determining the relative position of the preselected flexible linear obstacle and a cleaning robot according to the depth values of the point clouds, controlling the cleaning robot to the preselected flexible linear obstacle to try to control the preselected flexible linear obstacle to deform in a soft mode, and if the preselected flexible linear obstacle deforms, indicating that the preselected flexible linear obstacle is the linear obstacle, so as to avoid the preselected flexible linear obstacle.
Drawings
The accompanying drawings, which are included to provide a further understanding of the embodiments of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the embodiments of the invention without limiting the embodiments of the invention. In the drawings:
fig. 1 is a schematic flow chart illustrating a method for cleaning a robot to avoid a line according to an embodiment of the present invention;
fig. 2 is a block diagram schematically illustrating a structure of a device for cleaning a robot to avoid a wire according to an embodiment of the present invention.
Detailed Description
The following detailed description of embodiments of the invention refers to the accompanying drawings. It should be understood that the detailed description and specific examples, while indicating embodiments of the invention, are given by way of illustration and explanation only, not limitation.
In the present invention, the front end of the cleaning robot is equipped with two image capturing devices which are mounted in parallel in a front-downward direction for capturing a front-downward area of the forward direction of the cleaning robot.
Fig. 1 is a flowchart of a method for cleaning a robot to avoid a line according to an embodiment of the present invention. As shown in fig. 1, a first aspect of an embodiment of the present invention provides a method of cleaning a robot line evasion, the method including:
step S101, in the working process of the cleaning robot, controlling the two image acquisition devices to acquire multi-frame images of a front lower area at a preset frequency; acquiring a first image and a second image acquired by the two image acquisition devices at the same time, generating a depth image of the front lower area through the first image and the second image, acquiring depth values of a plurality of point cloud data through the depth image, and determining a preselected flexible linear obstacle in the depth image through the depth values of the plurality of point cloud data.
Step S102, identifying the external contour of the preselected flexible linear obstacle, storing the external contour as a basic contour, determining a plurality of point clouds corresponding to the external contour, taking the average value of the depth values of the point clouds as the depth value of the preselected flexible linear obstacle, and determining the orientation of the preselected flexible linear obstacle according to the depth value and the relative positions of the point clouds corresponding to the external contour.
Step S103, determining the current position of the cleaning robot as a target position, controlling the cleaning robot to travel to the position of the preselected flexible linear obstacle according to the position of the preselected flexible linear obstacle, controlling the cleaning robot to move in a preset motion mode, controlling the cleaning robot to return to the target position, re-acquiring the image of the position of the preselected flexible linear obstacle, re-identifying the contour of the preselected flexible linear obstacle in the image, matching the contour with the basic contour, determining the preselected flexible linear obstacle as the linear obstacle when the matching is unsuccessful, and controlling the cleaning robot to avoid the preselected flexible linear obstacle. The linear object in the current image is identified through an image identification algorithm, the linear object in the linear object is screened out through a linear detection algorithm to determine that the nonlinear linear object is a preselected linear object, whether the preselected linear object protrudes from the ground or not is determined according to the depth value of the preselected linear object in the depth image, and the preselected linear object protruding from the ground is determined to be a flexible linear obstacle, wherein the image identification algorithm at least comprises an edge detection algorithm. The edge recognition algorithm, such as canny edge detection algorithm and sobel edge detection algorithm, can recognize lines in the image through the edge detection algorithm, and simultaneously, the image gray scale transformation, binarization processing, sharpening processing and the like can be carried out on the image before the edge detection is carried out. And detecting straight lines in the image through a Hough algorithm. Each pixel coordinate point is transformed into a unified metric that contributes to the straight line trait, such as: a straight line is a set of a series of discrete points in an image, and through a discrete polar coordinate formula of the straight line, a geometric equation of the discrete points of the straight line can be expressed as follows: x cos (theta) + y sin (theta) where angle theta refers to the angle between r and the X axis, and r is the geometric perpendicular distance to the line. Any point on a straight line, x, y, can be expressed where r, theta is constant. In the field of image processing implemented, the pixel coordinates P (x, y) of the image are known, while r, theta are the variables to be found. If we can plot each (r, theta) value according to the pixel point coordinate P (x, y) value, then we convert from the image cartesian coordinate system to the polar hough space system, and this point-to-curve transformation is called the hough transformation of straight lines. The transform equally divides or accumulates the grid for a finite interval of values by quantizing the hough parameter space. When the hough transform algorithm starts, each pixel coordinate point P (x, y) is transformed to the upper side of the curve point of (r, theta), and is accumulated to the corresponding grid data point, and when a peak appears, a straight line exists.
Preferably, the preset action includes: stopping sweeping at the preselected flexible line-like obstacle. The technical means adopted in the embodiment of the invention is that all the preselected linear obstacles determined in the image are possible linear obstacles, but not all the preselected linear obstacles are real linear obstacles, and the preselected linear obstacles may have interference in the environment, for example, the patterns on the ground are limited, and may also be regarded as the preselected linear obstacles, and the main purpose of stopping cleaning is to prevent the real linear obstacles from winding, so that the real linear obstacles are selected.
Preferably, the preset action further comprises: controlling the cleaning robot to rotate after stopping sweeping at the preselected flexible linear obstruction, thereby changing a shape of a linear object in the preselected flexible linear obstruction.
Preferably, the step of re-identifying the contour of the preselected flexible linear obstacle in the image and matching the contour with the base contour further comprises: when the matching is successful, determining that the preselected flexible linear obstacle is an inherent hard object on the ground or a line on the floor, and controlling the cleaning robot to directly clean the preselected flexible linear obstacle.
In a second aspect, an embodiment of the present invention exemplarily provides an apparatus for cleaning a robot bypass line, wherein a front end of the robot cleaner is equipped with two image capturing devices, which are parallelly equipped in a front-downward direction, for capturing a front-downward area of a forward direction of the robot cleaner, as shown in fig. 2, the apparatus includes: the acquisition module 31 is used for controlling the two image acquisition devices to acquire multi-frame images of the front lower area at a preset frequency in the operation process of the cleaning robot; acquiring a first image and a second image acquired by the two image acquisition devices at the same time, generating a depth image of the front lower area through the first image and the second image, acquiring depth values of a plurality of point cloud data through the depth image, and determining a preselected flexible linear obstacle in the depth image through the depth values of the plurality of point cloud data. An identifying module 32, wherein the identifying module 32 is configured to identify an external contour of the preselected flexible linear obstacle, determine a plurality of point clouds corresponding to the external contour, use an average value of depth values of the plurality of point clouds as a depth value of the preselected flexible linear obstacle, and determine an orientation of the preselected flexible linear obstacle according to the depth value and a relative position of the plurality of point clouds corresponding to the external contour. The edge recognition algorithm, such as canny edge detection algorithm and sobel edge detection algorithm, can recognize lines in the image through the edge detection algorithm, and simultaneously, the image gray scale transformation, binarization processing, sharpening processing and the like can be carried out on the image before the edge detection is carried out. And detecting straight lines in the image through a Hough algorithm. Each pixel coordinate point is transformed into a unified metric that contributes to the straight line trait, such as: a straight line is a set of a series of discrete points in an image, and through a discrete polar coordinate formula of the straight line, a geometric equation of the discrete points of the straight line can be expressed as follows: x cos (theta) + y sin (theta) where angle theta refers to the angle between r and the X axis, and r is the geometric perpendicular distance to the line. Any point on a straight line, x, y, can be expressed where r, theta is constant. In the field of image processing implemented, the pixel coordinates P (x, y) of the image are known, while r, theta are the variables to be found. If we can plot each (r, theta) value according to the pixel point coordinate P (x, y) value, then we convert from the image cartesian coordinate system to the polar hough space system, and this point-to-curve transformation is called the hough transformation of straight lines. The transform equally divides or accumulates the grid for a finite interval of values by quantizing the hough parameter space. When the hough transform algorithm starts, each pixel coordinate point P (x, y) is transformed to the upper side of the curve point of (r, theta), and is accumulated to the corresponding grid data point, and when a peak appears, a straight line exists. A line avoiding module 33, wherein the line avoiding module 33 is configured to determine a current position of the cleaning robot as a target position, control the cleaning robot to travel to the preselected flexible linear obstacle according to the position of the preselected flexible linear obstacle, control the cleaning robot to move in a preset motion, control the cleaning robot to return to the target position, re-acquire an image of the preselected flexible linear obstacle, re-identify the profile of the preselected flexible linear obstacle in the image, match the profile with the basic profile, determine that the preselected flexible linear obstacle is a linear obstacle when the matching is unsuccessful, and control the cleaning robot to avoid the linear obstacle.
Preferably, the thread avoiding module 33 is also used for stopping sweeping at the preselected flexible thread-like obstacle. The technical means adopted in the embodiment of the invention is that all the preselected linear obstacles determined in the image are possible linear obstacles, but not all the preselected linear obstacles are real linear obstacles, and the preselected linear obstacles may have interference in the environment, for example, the patterns on the ground are limited, and may also be regarded as the preselected linear obstacles, and the main purpose of stopping cleaning is to prevent the real linear obstacles from winding, so that the real linear obstacles are selected.
Preferably, the wire avoiding module 33 is further configured to control the cleaning robot to rotate after stopping sweeping at the preselected flexible wire-shaped obstacle, so as to change the shape of the linear object in the preselected flexible wire-shaped obstacle.
Preferably, the thread avoiding module 33 is further configured to determine that the preselected flexible thread-like obstacle is an inherent hard object on the ground or a texture on the floor itself when the matching is successful, and control the cleaning robot to directly clean the preselected flexible thread-like obstacle.
In a third aspect, embodiments of the present invention further provide a computer storage medium, on which a computer program is stored, which when executed by a processor, implements the method for avoiding the line of the cleaning robot as described above.
In a fourth aspect, an embodiment of the present invention further provides a cleaning robot, including: one or more processors; storage means for storing one or more programs; when the one or more programs are executed by the one or more processors, the one or more processors implement the method for avoiding the line of the cleaning robot as described above.
According to the technical scheme of the embodiment, the robot can identify a real linear object through image identification, path planning and other modes, and can eliminate interference factors on the ground or in the environment; the front end of the cleaning robot is provided with two image acquisition devices which are assembled in a front-downward direction in parallel and used for acquiring a front-lower area of the advancing direction of the cleaning robot, and the image data of the front-lower area can be acquired in a targeted manner by the assembly mode, so that the interference of objects which do not influence the movement is directly filtered; in the operation process of the cleaning robot, the two image acquisition devices are controlled to acquire multi-frame images of the front lower area at a preset frequency, so that accurate data of the front lower area can be acquired in real time, and real-time monitoring is kept; acquiring a first image and a second image acquired by the two image acquisition devices at the same time, and generating a depth image of the front lower area through the first image and the second image to obtain a three-dimensional image with higher precision; the method comprises the steps of obtaining depth values of a plurality of point cloud data through a depth image, determining a preselected flexible linear obstacle in the depth image according to the depth values of the point cloud data, determining the flexible linear obstacle directly according to the depth values, determining a plurality of point clouds corresponding to the external outline when the external outline of the preselected flexible linear obstacle is identified, determining the relative position of the preselected flexible linear obstacle and a cleaning robot according to the depth values of the point clouds, controlling the cleaning robot to the preselected flexible linear obstacle to try to control the preselected flexible linear obstacle to deform in a soft mode, and if the preselected flexible linear obstacle deforms, indicating that the preselected flexible linear obstacle is the linear obstacle, so as to avoid the preselected flexible linear obstacle.
While the embodiments of the present invention have been described in detail with reference to the accompanying drawings, the embodiments of the present invention are not limited to the details of the above embodiments, and various simple modifications can be made to the technical solution of the embodiments of the present invention within the technical idea of the embodiments of the present invention, and the simple modifications are within the scope of the embodiments of the present invention.
It should be noted that the various features described in the above embodiments may be combined in any suitable manner without departing from the scope of the invention. In order to avoid unnecessary repetition, the embodiments of the present invention will not be described separately for the various possible combinations.
Those skilled in the art will appreciate that all or part of the steps in the method according to the above embodiments may be implemented by a program, which is stored in a storage medium and includes instructions for causing a single chip, a chip, or a processor (processor) to execute all or part of the steps in the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
In the embodiments provided in the present application, it should be understood that the disclosed system, apparatus and method may be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the units is only one logical division, and other divisions may be realized in practice, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form. The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
Claims (10)
1. A method of cleaning a robot bypass line, wherein a front end of the cleaning robot is equipped with two image pickup devices which are parallelly equipped in a front-downward direction for picking up a front-downward area of an advancing direction of the cleaning robot, the method comprising:
in the working process of the cleaning robot, controlling the two image acquisition devices to acquire multi-frame images of the front lower area at a preset frequency; acquiring a first image and a second image acquired by the two image acquisition devices at the same time, generating a depth image of the front lower area through the first image and the second image, acquiring depth values of a plurality of point cloud data through the depth image, and determining a preselected flexible linear obstacle in the depth image through the depth values of the plurality of point cloud data;
identifying an external contour of the preselected flexible linear obstacle, storing the external contour as a basic contour, determining a plurality of point clouds corresponding to the external contour, taking an average value of depth values of the point clouds as a depth value of the preselected flexible linear obstacle, and determining the orientation of the preselected flexible linear obstacle according to the depth value and relative positions of the point clouds corresponding to the external contour;
determining the current position of the cleaning robot as a target position, controlling the cleaning robot to travel to the position of the preselected linear flexible obstacle according to the position of the preselected linear flexible obstacle, controlling the cleaning robot to move in a preset motion mode, controlling the cleaning robot to return to the target position, re-acquiring the image of the preselected linear flexible obstacle, re-identifying the contour of the preselected linear flexible obstacle in the image, matching the contour with the basic contour, determining the preselected linear flexible obstacle as the linear obstacle when the matching is unsuccessful, and controlling the cleaning robot to avoid the preselected linear flexible obstacle.
2. The method of claim 1, wherein the predetermined action comprises: stopping sweeping at the preselected flexible line-like obstacle.
3. The method of claim 2, wherein the act of presetting further comprises: controlling the cleaning robot to rotate after stopping sweeping at the preselected flexible linear obstruction, thereby changing a shape of a linear object in the preselected flexible linear obstruction.
4. The method of claim 1, wherein said step of re-identifying the contour of said preselected flexible line-like obstruction in said image and matching said contour to said base contour further comprises: when the matching is successful, determining that the preselected flexible linear obstacle is an inherent hard object on the ground or a line on the floor, and controlling the cleaning robot to directly clean the preselected flexible linear obstacle.
5. A device for cleaning a thread evading of a robot, the front end of which is equipped with two image pickup devices mounted in parallel in a front-downward direction for picking up a front-downward area of a forward direction of the robot, the device comprising:
the acquisition module is used for controlling the two image acquisition devices to acquire multi-frame images of the front lower area at a preset frequency in the operation process of the cleaning robot; acquiring a first image and a second image acquired by the two image acquisition devices at the same time, generating a depth image of the front lower area through the first image and the second image, acquiring depth values of a plurality of point cloud data through the depth image, and determining a preselected flexible linear obstacle in the depth image through the depth values of the plurality of point cloud data; the identification module is used for identifying the external contour of the preselected flexible linear obstacle, storing the external contour as a basic contour, determining a plurality of point clouds corresponding to the external contour, taking the average value of the depth values of the point clouds as the depth value of the preselected flexible obstacle, and determining the orientation of the preselected linear flexible obstacle according to the depth value and the relative positions of the point clouds corresponding to the external contour;
and the line avoiding module is used for determining the current position of the cleaning robot as a target position, controlling the cleaning robot to run to the preselected flexible linear obstacle according to the position of the preselected flexible linear obstacle, controlling the cleaning robot to move in a preset action mode, controlling the cleaning robot to return to the target position, re-acquiring the image of the preselected flexible linear obstacle, re-identifying the profile of the preselected flexible linear obstacle in the image, matching the profile with the basic profile, determining the preselected flexible linear obstacle as the linear obstacle when the matching is unsuccessful, and controlling the cleaning robot to avoid the linear obstacle.
6. The device of claim 5, wherein the thread avoidance module is further configured to control the cleaning robot to stop sweeping at the preselected flexible thread-like obstacle.
7. The device of claim 6, wherein the thread avoiding module is further configured to control the cleaning robot to rotate after stopping sweeping at the preselected flexible thread-like obstacle, thereby changing a shape of a linear object in the preselected flexible thread-like obstacle.
8. The device of claim 5, wherein the thread avoiding module is further configured to determine that the preselected flexible thread-like obstacle is an inherent hard object on the ground or a natural texture on the floor when the matching is successful, and control the cleaning robot to directly sweep the preselected flexible thread-like obstacle.
9. A computer storage medium on which a computer program is stored, the computer program, when being executed by a processor, implementing a method of cleaning robot evasion of a line as recited in any one of claims 1-4.
10. A cleaning robot, characterized in that the cleaning robot comprises:
one or more processors;
storage means for storing one or more programs;
when executed by the one or more processors, cause the one or more processors to implement a method of cleaning robot bypass as recited in any of claims 1-4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811617226.0A CN111374597B (en) | 2018-12-28 | 2018-12-28 | Method and device for avoiding line of cleaning robot, storage medium and cleaning robot |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811617226.0A CN111374597B (en) | 2018-12-28 | 2018-12-28 | Method and device for avoiding line of cleaning robot, storage medium and cleaning robot |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111374597A CN111374597A (en) | 2020-07-07 |
| CN111374597B true CN111374597B (en) | 2021-08-24 |
Family
ID=71212890
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811617226.0A Active CN111374597B (en) | 2018-12-28 | 2018-12-28 | Method and device for avoiding line of cleaning robot, storage medium and cleaning robot |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111374597B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR102286132B1 (en) * | 2019-07-31 | 2021-08-06 | 엘지전자 주식회사 | Artificial intelligence robot cleaner |
| CN112034837A (en) * | 2020-07-16 | 2020-12-04 | 珊口（深圳）智能科技有限公司 | Method for determining working environment of mobile robot, control system and storage medium |
| CN116058726A (en) * | 2021-10-29 | 2023-05-05 | 追觅创新科技(苏州)有限公司 | Obstacle identification method and device applied to cleaning equipment and cleaning equipment |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103148804A (en) * | 2013-03-04 | 2013-06-12 | 清华大学 | Indoor unknown structure identification method based on laser scanning |
| CN103955920A (en) * | 2014-04-14 | 2014-07-30 | 桂林电子科技大学 | Binocular vision obstacle detection method based on three-dimensional point cloud segmentation |
| CN106737653A (en) * | 2015-11-20 | 2017-05-31 | 哈尔滨工大天才智能科技有限公司 | The method of discrimination of barrier hard and soft in a kind of robot vision |
| CN106997721A (en) * | 2017-04-17 | 2017-08-01 | 深圳奥比中光科技有限公司 | Draw method, device and the storage device of 2D maps |
| CN108170137A (en) * | 2017-12-15 | 2018-06-15 | 珊口（上海）智能科技有限公司 | Mobile robot and its control method and control system |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20180348783A1 (en) * | 2017-05-31 | 2018-12-06 | Neato Robotics, Inc. | Asynchronous image classification |
-
2018
- 2018-12-28 CN CN201811617226.0A patent/CN111374597B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103148804A (en) * | 2013-03-04 | 2013-06-12 | 清华大学 | Indoor unknown structure identification method based on laser scanning |
| CN103955920A (en) * | 2014-04-14 | 2014-07-30 | 桂林电子科技大学 | Binocular vision obstacle detection method based on three-dimensional point cloud segmentation |
| CN106737653A (en) * | 2015-11-20 | 2017-05-31 | 哈尔滨工大天才智能科技有限公司 | The method of discrimination of barrier hard and soft in a kind of robot vision |
| CN106997721A (en) * | 2017-04-17 | 2017-08-01 | 深圳奥比中光科技有限公司 | Draw method, device and the storage device of 2D maps |
| CN108170137A (en) * | 2017-12-15 | 2018-06-15 | 珊口（上海）智能科技有限公司 | Mobile robot and its control method and control system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111374597A (en) | 2020-07-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111374597B (en) | Method and device for avoiding line of cleaning robot, storage medium and cleaning robot | |
| US11042760B2 (en) | Mobile robot, control method and control system thereof | |
| EP3417350B1 (en) | Method for controlling an autonomous mobile robot | |
| CN111528732B (en) | Cleaning robot operation control method, device and system and storage medium | |
| JP2022546289A (en) | CLEANING ROBOT AND AUTOMATIC CONTROL METHOD FOR CLEANING ROBOT | |
| CN111358362A (en) | Cleaning control method and device of visual robot, chip and sweeping robot | |
| CN110680253A (en) | Robot edge cleaning method and robot | |
| CN107518833A (en) | A kind of obstacle recognition method of sweeping robot | |
| CN109213137A (en) | sweeping robot, sweeping robot system and its working method | |
| DE102010000174A1 (en) | Method for cleaning room, involves defining rectangular area to entire area to be cleaned, where driving lines for cleaning device are equidistant in rectangular area parallel to one side of rectangle part and end in partitioned areas | |
| CN111419116A (en) | Climbing control method and device for sweeping robot, storage medium and sweeping robot | |
| CN112806912B (en) | Robot cleaning control method and device and robot | |
| CN111358359B (en) | Line avoiding method and device for robot, chip and sweeping robot | |
| CN111374603A (en) | Control method and chip for partitioned cleaning of vision robot and intelligent sweeping robot | |
| CN112034837A (en) | Method for determining working environment of mobile robot, control system and storage medium | |
| CN111012254A (en) | Intelligent floor sweeping robot | |
| CN112971621A (en) | Indoor intelligent cleaning system and control method | |
| CN111358360B (en) | Method and device for preventing robot from winding wire, chip and sweeping robot | |
| CN113520246B (en) | Mobile robot compensation cleaning method and system | |
| CN112711250B (en) | Self-walking equipment movement control method and self-walking equipment | |
| CN111443695A (en) | Sweeping robot control method and device, storage medium and sweeping robot | |
| CN111358361B (en) | Line avoidance control method and device for sweeping robot and computer storage medium | |
| CN113749562A (en) | Sweeping robot and control method, device, equipment and storage medium thereof | |
| CN111358364B (en) | Dead angle cleaning method and device based on visual robot, chip and robot | |
| CN116250778A (en) | Cleaning control method and system of cleaning robot and cleaning 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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |