WO2019024863A1 - 机器人的控制方法、装置、系统及所适用的机器人 - Google Patents

机器人的控制方法、装置、系统及所适用的机器人 Download PDF

Info

Publication number
WO2019024863A1
WO2019024863A1 PCT/CN2018/097953 CN2018097953W WO2019024863A1 WO 2019024863 A1 WO2019024863 A1 WO 2019024863A1 CN 2018097953 W CN2018097953 W CN 2018097953W WO 2019024863 A1 WO2019024863 A1 WO 2019024863A1
Authority
WO
WIPO (PCT)
Prior art keywords
robot
feature line
image
line segment
room divider
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.)
Ceased
Application number
PCT/CN2018/097953
Other languages
English (en)
French (fr)
Inventor
崔彧玮
候喜茹
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Ankobot Shanghai Smart Technologies Co Ltd
Ankobot Shenzhen Smart Technologies Co Ltd
Original Assignee
Ankobot Shanghai Smart Technologies Co Ltd
Ankobot Shenzhen Smart Technologies Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Ankobot Shanghai Smart Technologies Co Ltd, Ankobot Shenzhen Smart Technologies Co Ltd filed Critical Ankobot Shanghai Smart Technologies Co Ltd
Priority to CN202210205435.4A priority Critical patent/CN114355836A/zh
Priority to CN201880001118.2A priority patent/CN109074084B/zh
Priority to EP18840843.9A priority patent/EP3686703B1/en
Priority to US16/246,180 priority patent/US10437254B2/en
Publication of WO2019024863A1 publication Critical patent/WO2019024863A1/zh
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
    • G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
    • 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
    • G05D1/0231—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means
    • G05D1/0246—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means using a video camera in combination with image processing means
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
    • G05B19/00—Program-control systems
    • G05B19/02—Program-control systems electric
    • G05B19/04—Program control other than numerical control, i.e. in sequence controllers or logic controllers
    • G05B19/05—Programmable logic controllers, e.g. simulating logic interconnections of signals according to ladder diagrams or function charts
    • G05B19/054—Input/output
    • 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
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
    • G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
    • G05D1/02—Control of position or course in two dimensions
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
    • G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
    • 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
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
    • G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
    • 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
    • G05D1/0221—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory involving a learning process
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
    • G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
    • 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
    • G05D1/0223—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory involving speed control of the vehicle
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
    • G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
    • 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
    • G05D1/0231—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means
    • G05D1/0246—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means using a video camera in combination with image processing means
    • G05D1/0253—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means using a video camera in combination with image processing means extracting relative motion information from a plurality of images taken successively, e.g. visual odometry, optical flow
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
    • G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
    • 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
    • G05D1/0276—Control of position or course in two dimensions specially adapted to land vehicles using signals provided by a source external to the vehicle
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/10—Terrestrial scenes
    • 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
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
    • G05B2219/00—Program-control systems
    • G05B2219/10—Plc systems
    • G05B2219/11—Plc I-O input output
    • G05B2219/1103—Special, intelligent I-O processor, also plc can only access via processor

Definitions

  • the present application relates to the field of intelligent robots, and in particular, to a control method, device, system, and applicable robot for a robot.
  • intelligent robots have gradually entered people's lives.
  • intelligent robots can accept human command, run pre-programmed programs, or act according to the principles of artificial intelligence technology.
  • These robots can be used indoors or outdoors, can be used in industry or home, can be used to replace security inspections, replace people to clean the ground, can also be used for family companion, auxiliary office and so on.
  • the cleaning robot in order to achieve high cleaning efficiency, it is desirable to automatically adjust the posture of the robot to move in the main direction before the cleaning robot performs the cleaning operation, that is, the traveling direction of the robot is perpendicular or parallel to the wall direction. Then, the cleaning is performed, so that the cleaning area can be minimized during the cleaning period, and the cleaning efficiency can be improved. Therefore, how to accurately adjust the posture of the robot to move it in the main direction is a key factor for improving the cleaning efficiency.
  • the purpose of the present application is to provide a robot control method, device, system and applicable robot for solving the problem of how to automatically adjust the posture of the robot in the prior art to make it follow the main The problem of moving direction.
  • a first aspect of the present application provides a method for controlling a robot, comprising: acquiring an image taken during movement of a robot and identifying a feature line segment in the image; according to the identified feature line segment Determining an orientation relationship of the robot and the room divider in a physical space; adjusting a posture of the robot according to the orientation relationship such that the robot moves in a physical direction based on a main direction constructed based on the room divider.
  • the determining, according to the identified feature line segment, the relative orientation relationship of the robot and the room divider in physical space comprises: based on the identified plurality of pieces The vanishing point of the feature line segment groups the feature line segments; select at least one set of feature line segments from the grouped feature line segments; and determine the robot and the room according to the position of the vanishing point of the selected feature line segment group in the image coordinate system The relative orientation of the separator in physical space.
  • the step of selecting at least one set of feature line segments from the grouped feature line segments comprises: selecting a set of feature line segments having the largest number of feature line segments.
  • the adjusting the posture of the robot according to an orientation relationship comprises: adjusting a posture of the robot according to the orientation relationship and at a preset angle step; and repeating Each of the above steps up to the predetermined condition for determining the main direction of the robot built along the room divider.
  • the determining the robot along the main direction constructed based on the room divider comprises: determining whether the identified feature line segment in the current image satisfies a preset parallel condition, if Satisfying the parallel condition determines that the posture of the robot coincides with the main direction constructed based on the room divider, and conversely, continues to adjust the posture of the robot and repeats the above steps until the parallel condition is satisfied.
  • the parallel condition comprises at least one of the following: a pitch error between two feature line segments not on the same line is less than or equal to a preset pitch error threshold, the selected The position of the vanishing point of the feature line segment falls within the preset position area.
  • the acquired image is taken by an imaging device disposed perpendicular to a plane of movement of the robot, the determining that the robot and the room divider are in accordance with the identified feature line segment
  • the step of the relative orientation relationship in the physical space includes: counting a tilt angle of the feature line segment identified from the at least one image in the preset image coordinate system; determining the robot and the room divider in the physical according to the calculated tilt angle Relative orientation in space.
  • the step of counting the tilt angle of the feature line segment identified in the at least one image in the preset image coordinate system comprises any one of the following: a statistical single image a tilt angle of the feature line segment in the preset image coordinate system; during a period of the posture adjustment, according to the rotation angle corresponding to the image taken by the robot, the tilt angle of each feature line segment in at least two images taken is performed Regression processing; and the inclination angle of each feature line segment in the preset image coordinate system after statistical regression processing.
  • the determining, according to the calculated tilt angle, the relative orientation relationship of the robot and the room divider in physical space comprises: according to the statistically located peak interval The tilt angle determines the relative orientation of the robot and the room divider in physical space.
  • the adjusting the posture of the robot according to an orientation relationship comprises: adjusting a posture of the robot according to the tilt angle and a current posture of the robot.
  • control method further comprises: planning a navigation route based on the current location when determining that the robot is in a physical direction based on a primary direction constructed based on the room divider.
  • the navigation route includes: a first route that the robot moves to the room divider, and traverses a predetermined area from an end point of the first route The second route.
  • a second aspect of the present application further provides a control device for a robot, comprising: a storage unit for storing at least one program and an image taken by the camera device; and a processing unit connected to the storage unit for performing the At least one program to perform the control method of any of the above.
  • a third aspect of the present application further provides a robot comprising: an image capturing device for taking an image during movement of the robot; and a moving device for adjusting a posture of the robot according to the received control instruction; and the control device,
  • the camera device is connected to the mobile device, and configured to: acquire an image captured by the camera device and identify a feature line segment in the image; and determine the robot and the room divider in a physical space according to the identified feature line segment a relative orientation relationship; controlling the mobile device to adjust the posture of the robot according to the orientation relationship such that the robot moves in a physical direction based on a main direction constructed based on the room divider.
  • an angle between an optical axis of the imaging device and a moving plane of the robot is between 0° and 90°
  • the imaging device takes an image and provides the image during the movement of the robot.
  • the control device performs: determining, according to the identified feature line segment, a relative orientation relationship between the robot and the room divider in a physical space, comprising: a vanishing point pair based on the identified plurality of feature line segments Each feature line segment is grouped; at least one set of feature line segments are selected from the grouped feature line segments; and the robot and the room divider are determined in the physical space according to the position of the vanishing point of the selected feature line segment group in the image coordinate system. Relative orientation relationship.
  • the controlling means performing the step of selecting at least one set of feature line segments from the grouped feature line segments comprises: selecting a set of feature line segments having the largest number of feature line segments.
  • the controlling means performing the step of adjusting the posture of the robot according to the orientation relationship comprises: controlling the movement of the mobile device according to the orientation relationship and by a preset angle step The direction of rotation and the angle of rotation; and repeating the above steps until a predetermined condition for determining the main direction of the robot along the room-based partition is satisfied.
  • the controlling means performing the step of determining the main direction of the robot along the room-based partition comprises: determining whether the identified feature line segment in the current image satisfies a preset parallel Condition, if the parallel condition is satisfied, it is determined that the posture of the robot coincides with the main direction constructed based on the room divider, and conversely, the posture of the robot is continuously adjusted and the above steps are repeated until the parallel condition is satisfied.
  • the parallel condition includes at least one of the following: a pitch error between two feature line segments that are not on the same line is less than or equal to a preset pitch error threshold, selected The position of the vanishing point of the feature line segment falls within the preset position area.
  • the optical axis of the imaging device is perpendicular to a robot moving plane, the imaging device takes an image during the movement of the robot and provides the image to the control device;
  • the step of identifying the plurality of feature line segments determining the relative orientation relationship between the robot and the room divider in the physical space comprises: counting the inclination angle of the feature line segments identified from the at least one image in the preset image coordinate system And determining a relative orientation relationship between the robot and the room divider in physical space according to the calculated tilt angle.
  • the controlling means performing the step of counting the tilt angle of the feature line segment identified in the at least one image in the preset image coordinate system comprises any one of the following: a tilt angle of a feature line segment in a preset image coordinate system in a single image; during a period of posture adjustment, according to a rotation angle corresponding to the image captured by the robot, for each feature line segment of at least two images captured The tilt angle is used for regression processing; and the tilt angle of each feature line segment in the preset image coordinate system after statistical regression processing.
  • the controlling means performing the determining, according to the calculated tilt angle, the relative orientation relationship of the robot and the room divider in physical space comprises: locating according to the statistics The tilt angle of the peak interval determines the relative orientation of the robot and the room divider in physical space.
  • the controlling means performing the adjustment of the posture of the robot according to the orientation relationship comprises: adjusting the posture of the robot according to the tilt angle and the current posture of the robot.
  • control device is further configured to perform the step of: based on the current location when determining the main direction of the robot along the room divider in the physical space Navigation route.
  • the navigation route includes: a first route that the robot moves to the room divider, and traverses a predetermined area from an end point of the first route The second route.
  • the robot is a cleaning robot.
  • a fourth aspect of the present application also provides a computer storage medium storing at least one program, the at least one program, when invoked, performing the control method of any of the above.
  • a fifth aspect of the present application further provides a control system for a robot, comprising: an image processing module, configured to acquire an image captured during movement of the robot and identify a feature line segment in the image; and an orientation calculation module configured to identify The characteristic line segment determines the relative orientation relationship between the robot and the room divider in the physical space; the control module is configured to adjust the posture of the robot according to the orientation relationship, so that the robot is separated along the room in the physical space The main direction of the body is moved.
  • the orientation calculation module includes a first orientation calculation unit, configured to perform the following steps: performing each feature line segment based on the identified vanishing points of the plurality of feature line segments Grouping; selecting at least one set of feature line segments from the grouped feature line segments; determining a relative orientation relationship between the robot and the room divider in the physical space according to the position of the vanishing point of the selected feature line segment group in the image coordinate system.
  • the orientation calculation module includes a second orientation calculation unit configured to perform the step of: counting feature line segments identified from the at least one image in a preset image coordinate system The tilt angle in the medium; the relative orientation relationship between the robot and the room divider in the physical space is determined according to the calculated tilt angle.
  • control module includes a navigation route planning unit for determining a current position based on the main direction of the robot based on the room divider in the physical space Plan your navigation route.
  • control method, apparatus, system, and applicable robot of the present application have the following beneficial effects: determining the orientation relationship between the robot and the room divider by acquiring the feature line segments in the image, so that the robot can be based on The orientation relationship adjusts its attitude to move in the main direction constructed based on the room divider, improving the mobile coverage.
  • FIG. 1 is a schematic flow chart showing a control method of a robot of the present application in an embodiment.
  • FIG. 2 shows a schematic diagram of an image acquired by an image pickup apparatus.
  • Figure 3 shows a schematic diagram of the contour features identified based on the image in Figure 2.
  • FIG. 4 is a flow chart showing another embodiment of the control method of the present application.
  • FIG. 5 shows a flow chart of still another embodiment of the control method of the present application.
  • Figure 6 shows a waveform diagram of the statistical results of the feature line segment and the tilt angle of the present application in one embodiment.
  • Fig. 7 is a waveform diagram showing the statistical result of the characteristic line segment and the tilt angle of the present application in another embodiment.
  • FIG. 8 is a schematic view showing the structure of a control device for a robot of the present application in an embodiment.
  • FIG. 9 shows a schematic structural view of a robot of the present application in an embodiment.
  • FIG. 10 is a schematic structural view showing a control system of the robot of the present application in an embodiment.
  • the robot performs a moving operation based on the navigation control technology.
  • the cleaning robot as an example, generally, two mutually perpendicular main directions in the room where the cleaning robot is located are two directions corresponding to the wall. In order to traverse the entire area to be cleaned, the cleaning robot moves in a bow shape. Wherein, if the cleaning robot moves along or facing or away from the direction in which the room divider such as a wall, window, screen, etc. is constructed, the cleaning operation can be completed in the most efficient manner. This is because the cleaning robot moves in the above direction to cover the area to be cleaned as much as possible during the operation, reducing the replenishing operation and improving the cleaning efficiency.
  • the present application provides a control method of the robot, which can be based on the control method
  • the feature line segments in the image acquired by the robot determine the relative orientation between the robot and the room divider, such as a wall, window, etc., so that the robot can adjust its posture based on the relative orientation, thereby being able to follow the main direction, such as parallel to the wall direction. Or move perpendicular to the wall to improve mobile coverage.
  • FIG. 1 is a schematic flow chart of a control method of a robot of the present application in an embodiment.
  • the control method can be performed by a control device.
  • the control device is located in the robot, and the robot further comprises an imaging device connected to the control device for capturing images.
  • the control device may preset the time interval at which the camera device captures an image, and then the control device acquires a still image at different times captured by the camera device at preset time intervals, and performs steps S110-S130.
  • the camera device can capture a video. Since the video is composed of image frames, the control device can first continuously or discontinuously acquire image frames in the acquired video, and then the control device selects one frame image as the image. One image and steps S110-S130 are performed.
  • step S110 an image taken during the movement of the robot and a feature line segment in the recognition image are acquired.
  • control device of the robot acquires an image taken by the imaging device during the movement of the robot, and then recognizes the feature line segment in the image using an image processing technique.
  • the feature line segment is a straight line segment.
  • the control device can identify feature segments in the image in a manner that first extracts contour features of the object from the acquired image.
  • the contour feature may be extracted by a contour extraction method, including but not limited to: binary, grayscale, canny operator, and the like.
  • Feature line segments are then extracted from the extracted contour features.
  • the feature line segment can be extracted by the Hough transform.
  • the feature line segments include, but are not limited to, the following features: straightness and/or length features, and the like. For example, when the straightness of the adjacent feature point connection line in the image is greater than the preset straightness threshold, and/or the length thereof is greater than the preset length threshold, the connection of the feature point may be determined to be the feature line segment.
  • control device intercepts a plurality of discrete straight line segments as feature line segments based on the contour of the object for subsequent processing.
  • control device segments the contour features extracted based on the contour of the object, and extracts the feature segments from the segmented contour features. This makes it easier to retain more feature segments.
  • FIG. 2 is a schematic diagram showing an image acquired by an imaging device
  • FIG. 3 is a schematic diagram showing contour features recognized based on the image in FIG. 2. As shown in FIG.
  • the thin lines indicate contour features, which are extracted from the image, for example, based on binary, grayscale, canny operators, etc.; the thick lines indicate feature segments, where are identified in the image
  • the connection of the feature point may be determined as the feature line segment.
  • control device may also employ a neural network algorithm to identify feature segments.
  • the manner in which the feature segments are identified is not limited here.
  • step S120 the relative orientation relationship between the robot and the room divider in the physical space is determined according to the identified feature line segments.
  • the room divider refers to the façade used to separate the application space in the application scenario where the robot is located.
  • the room partition refers to a façade for separating the indoor space, such as a wall surface, a partition, a floor to ceiling window, a ceiling, and the like.
  • the relative orientation of the robot and the room divider in physical space can be expressed as the relative orientation relationship between the direction of travel of the robot and the direction in which the wall is constructed.
  • the orientation relationship between the robot and the room divider can be characterized by the angle between the direction of travel of the robot and the plane defined by the room divider. For example, the angle reflects that the relative orientation relationship between the direction of travel of the robot and the wall is parallel, perpendicular or non-perpendicular.
  • the control device determines, based on the identified feature line segments, an orientation relationship in which the robot is currently facing (or facing away from) the wall surface, moving along the wall surface, or having an angle of between 0° and 90° with the wall surface.
  • the indoor objects are basically placed according to the main direction constructed by the room partition. For example, objects such as desks, beds, wardrobes, shoe cabinets, etc., which are not easily moved, are constructed according to the main direction of the room partition.
  • Positioning which allows the placement features in the actual physical space to be reflected by the image, so the control device analyzes the identified feature line segments according to the orientation features presented by the objects in the room, the room isolators, and the like. The relative orientation relationship between the robot and the room divider in the physical space is obtained.
  • step S130 the posture of the robot is adjusted according to the orientation relationship such that the robot moves in the physical direction based on the main direction constructed based on the room divider.
  • the posture of the adjustment robot mainly refers to an angular relationship between the adjustment robot and the main direction constructed based on the room divider, and the robot is determined to be along, facing, or deviated from the room-based partition according to the orientation relationship. In the main direction, the posture adjustment of the robot is completed.
  • control device controls the robot to rotate an angle according to the angle between the identified feature line segment in the actual physical space and the current attitude of the robot to achieve parallel or vertical rotation of the robot with the room divider.
  • the robot rotation may be continuously adjusted according to a preset angle and direction, and the above steps S110-S130 may be repeated during the rotation until the preset condition is met according to the identified feature line segment to confirm that the robot is separated from the room.
  • the body is approximately parallel or perpendicular.
  • the preset condition is set based on an orientation relationship between the robot and the main direction reflected by the feature line segment.
  • the robot moves in a direction generally parallel or perpendicular to the direction of travel of the room divider. For example, after the control device determines that the cleaning robot faces a wall surface, the control cleaning robot moves to the wall edge and moves in a bow shape.
  • the control method of the robot of the present application determines the orientation relationship between the robot and the room divider by acquiring feature line segments in the image, so that the robot can adjust its posture to the main direction constructed along the room partition based on the orientation relationship.
  • Mobile increased mobile coverage.
  • control device may adopt an implementation related to the placement angle of the imaging device to determine the relative orientation relationship between the robot and the room divider in the physical space. And make posture adjustments.
  • a flow chart includes steps S210-S250.
  • step S210 an image taken during the movement of the robot and a feature line segment in the recognition image are acquired.
  • the step S210 is the same as or similar to the above step S110, and will not be described in detail herein.
  • each feature line segment is grouped based on the identified vanishing points of the plurality of feature line segments.
  • the parallel lines in the captured image have a vanishing point linear characteristic.
  • the vanishing point linear feature refers to a point at which two or more lines representing parallel lines extend to the far horizon (HORIZON LINE) until they are aggregated.
  • a line having a common vanishing point in an image corresponds to a parallel line in space, that is, a parallel line in space corresponds to a line intersecting in an image angle of view, and these intersecting lines have a common vanishing point
  • the case represents multiple sets of parallel lines in space.
  • the control device extends the identified feature line segments with the image coordinate system in which the image is located to obtain a vanishing point of each feature line segment. For example, the control device calculates the intersection of any two feature line segments by using the inclination angle of each feature line segment in the image coordinate system, and performs clustering processing on each intersection point to classify the intersections with similar positions as one vanishing point.
  • the number of vanishing points obtained is usually multiple.
  • Feature line segments intersecting at the same vanishing point are grouped together.
  • step S230 at least one set of feature line segments is selected from the grouped feature line segments.
  • the number of feature segments in each group in the image can reflect the main direction constructed based on the room divider. For example, the greater the number of feature segments corresponding to the vanishing point, the greater the likelihood that the direction of the feature segment of the corresponding group in the physical space is based on the main direction constructed by the room divider.
  • a set of feature line segments having the largest number of feature line segments is selected from the grouped feature line segments, the set of feature line segments representing a main direction constructed based on the room divider.
  • the group with the largest number of feature line segments is not necessarily one, and the feature line segments of the plurality of groups that can select the largest number of groups or randomly select one of the feature line segments to perform step S240.
  • step S240 the relative orientation relationship between the robot and the room divider in the physical space is determined according to the position of the vanishing point of the selected feature line segment group in the image coordinate system.
  • the selected feature line segment group represents the main direction constructed based on the room divider.
  • the selected set of characteristic line segments represents a contour line of an object or a boundary line of an object disposed parallel to a wall or perpendicular to a wall.
  • the robot when the robot has a certain off-angle relationship with a certain room separator A to be faced in the physical space, a plurality of straight lines parallel to the room separator A are reflected in the image, that is, having the same vanishing point.
  • the feature line segment is located at the image coordinate according to the orientation relationship including the yaw angle (for example, the robot faces the room divider A counterclockwise, or the robot faces the room divider A clockwise) A quadrant of the system or an area within a preset distance from the preset center point.
  • the control device determines the relative orientation relationship between the robot and the room divider A in the physical space by analyzing the position of the vanishing point in the image coordinate system. For example, an image coordinate system constructed with a plane perpendicular to the optical axis of the imaging device, wherein the position of the optical axis is the coordinate origin, and if the vanishing point of the selected feature segment group is located to the left of the coordinate system, the robot and the to-be-facing The orientation of the room divider A is counterclockwise. Wherein, the orientation relationship is rough, and it is not certain that the precise declination value between the robot and the room divider to be faced is determined.
  • step S250 the posture of the robot is adjusted according to the orientation relationship and at a preset angle step.
  • control device performs stepwise adjustment according to the obtained orientation relationship with a predetermined angle step as a unit angle.
  • the preset condition of the main direction constructed by the body. Wherein, when the robot faces or faces away from a room divider, or when the robot is separated along a room, the characteristic segment of the selected group is considered to be a line parallel or perpendicular to the room divider in the image in the image. Mapping.
  • the preset condition may be preset based on position coordinates of the vanishing point of the feature line segment of the selected group in the image coordinate system; condition parameters for evaluating the parallelism of the feature line segments of the selected group may also be set.
  • the step of determining the main direction of the robot along the room divider comprises: determining whether the identified feature line segment in the current image satisfies a preset parallel condition, and if so, determining the pose of the robot and based on The main direction of the room divider is the same. Otherwise, the posture of the robot is continuously adjusted and the above steps are repeated until the parallel condition is satisfied. Wherein the posture of the robot coincides with the main direction constructed based on the room divider, including the current posture of the robot being facing a certain room partition, facing away from a certain room partition or along a certain room partition.
  • the control device determines that the current pose of the robot is facing a certain room divider.
  • the parallel condition comprises: a pitch error between two feature line segments not on the same straight line in the selected feature line segment group is less than or equal to a preset pitch error threshold.
  • the control device calculates an endpoint distance of any two feature line segments in the selected feature line segment group, and if the calculated error between the endpoint distances is less than the pitch error threshold, determining that the selected feature line segments are parallel to each other, that is, determining In the physical space, the robot faces a room divider, and vice versa, continues to adjust the posture.
  • the parallel condition includes a position of a vanishing point of the selected set of feature line segments falling within a preset location area.
  • the control device calculates whether the vanishing point coordinate of the selected feature line segment group is located in a preset position area in the image coordinate system, and the position area is used to define that the current posture of the robot is substantially perpendicular to a certain room divider, and if so, It is determined that the selected feature line segments are parallel to each other, that is, it is determined that the robot faces a certain room partition in the physical space, and vice versa, the posture is continuously adjusted.
  • controlling the movement of the robot along the main direction of the room partition such as the wall may include controlling the movement of the robot parallel to the wall, controlling the movement of the robot toward the wall, and controlling The robot moves away from the wall.
  • FIG. 5 shows another embodiment of the control method of the present application.
  • the control method includes steps S310-S340.
  • step S310 an image taken during the movement of the robot and a feature line segment in the recognition image are acquired.
  • the step S310 is the same as or similar to the above step S110, and will not be described in detail herein.
  • step S320 the tilt angle of the feature line segment identified from the at least one image in the preset image coordinate system is counted.
  • the top of the robot and the optical axis are disposed.
  • the image taken by the camera device perpendicular to the moving plane of the robot also has feature line segments orthogonal to each other. Therefore, counting the tilt angle of each feature line segment in the image coordinate system can facilitate finding the feature line segments orthogonal to each other and the tilt thereof. angle.
  • the tilt angle of the feature line segments in the preset image coordinate system in a single image is counted.
  • the preset image coordinate system UOV wherein the intersection of the camera optical axis and the imaging plane is taken as the origin O of the image coordinate system, and the two directions orthogonal to each other are used as the U axis of the image coordinate system and the V axis of the image coordinate system.
  • the corresponding coordinates of the feature line segments in the image coordinate system UOV, and the tilt angle of each feature line segment in the image coordinate system UOV can be obtained, and then the obtained tilt angles are counted to obtain
  • the statistical result represents the angular distribution of the feature line segments.
  • the inclination angle is in the range of 0° to 180°.
  • the statistical result may be shown in a waveform diagram, a histogram, or the like.
  • the feature line segment in the image is in the image coordinate system UOV by the X-axis.
  • the value of the tilt angle value, the Y-axis represents the number of feature line segments under the corresponding tilt angle value, and the statistical result is drawn.
  • the control device counts the tilt angle of the feature line segments in the predetermined image coordinate system in the plurality of images.
  • step S320 includes performing a regression process on the tilt angles of the feature line segments in the at least two captured images according to the rotation angle corresponding to the robot when the image is captured during a period of the posture adjustment; and after the statistical regression processing The tilt angle of the feature line segment in the preset image coordinate system.
  • the regression process refers to one of the images captured by the robot as a reference image, and the posture (position and angle) of the robot when the reference image is captured is used as a reference posture, and the inclination angle of the feature line segments in the other images is corrected.
  • the robot takes the first image and counts the inclination angle of the feature line segments in the first image to obtain the first statistical result, and the robot adjusts the posture and takes the second image.
  • the image is statisticed and the tilt angle of the feature line segments in the second image is obtained to obtain a second statistical result.
  • the posture when the robot takes the first image as the reference posture and based on the posture when the robot captures the second image, the rotation angle of the robot with respect to the reference posture can be obtained by means of a gyroscope, VSLAM, or the like.
  • the obtained rotation angle is projected into the image coordinate system to obtain a rotation angle of the second image with respect to the first image, based on which the inclination angle of the feature line segment included in the second statistical result is corrected, so that the second The feature line segment in the image and the feature line segment in the first image are unified in the image coordinate system, and the tilt angle deviation caused by the rotation of the robot is eliminated.
  • the first statistical result and the second statistical result subjected to the regression processing are subjected to overall statistics to obtain statistical results of the inclination angle of each characteristic line segment in the image coordinate system.
  • step S330 the relative orientation relationship between the robot and the room divider in the physical space is determined according to the calculated tilt angle.
  • the control device may obtain at least one statistical peak interval, and use the obtained tilt angle corresponding to the statistical peak interval as the robot and the room separator in the physical space.
  • Relative orientation relationship a peak interval is obtained based on the statistical result, wherein the peak interval indicates that the number of feature segments is the largest under the corresponding tilt angle in the peak interval, and the maximum number of feature segments indicates that the direction in which the feature segments are located represents the construction based on the room divider. Main direction.
  • the relative orientation of the robot to the room divider in physical space is determined based on the calculated tilt angle at the peak interval.
  • the orientation relationship includes an off-angle interval and a rotation direction between the robot and a partition to be faced to a certain room.
  • the statistical peak range is determined to be 41° ⁇ 1° according to the UV axis ray direction of the preset image coordinate system, and the control device determines that the robot is located in a counterclockwise direction to be facing a room divider and is separated from the room.
  • the body has an off-angle range of 41 ° ⁇ 1 °.
  • the corresponding tilt angle in the peak interval may be a tilt angle interval within a certain error range. Based on this, in one example, the average tilt angle in the tilt angle interval is taken as the tilt angle characterizing the orientation relationship.
  • FIG. 6 is a waveform diagram showing the statistical result of the characteristic line segment and the tilt angle of the present application in an embodiment.
  • the X axis represents the inclination angle of the feature line segment in the image
  • the Y axis represents the feature line segment.
  • the number of the figure shows the case where there is a maximum peak interval
  • the characteristic line segment corresponding to the inclination angle of the peak interval represents the main direction constructed based on the room divider, such as parallel to the wall direction or perpendicular to the wall.
  • the body direction, and thus, the relative orientation relationship between the robot and the room divider in the physical space can be characterized by the angle between the robot and the room divider, that is, the inclination angle corresponding to the peak interval.
  • the peak section corresponds to a tilt angle of 45°, which means that the angle between the robot's traveling direction and the wall direction is 45°.
  • FIG. 7 is a waveform diagram showing the statistical result of the characteristic line segment and the tilt angle of the present application in another embodiment.
  • the X axis represents the inclination angle of the feature line segment in the image
  • the Y axis represents the feature.
  • the number of line segments the figure shows the case where there are two maximum peak intervals. According to the actual situation, the two tilt angles corresponding to the two peak intervals should theoretically be 90° with each other, and the corresponding feature line segments respectively represent parallel In the direction of the wall and perpendicular to the wall.
  • the relative orientation relationship between the robot and the room divider in the physical space can be characterized by the angle between the robot and the room divider, that is, the inclination angle corresponding to any peak interval, and on the other hand, Whether the difference between the two tilt angles corresponding to the peak interval is within the range of "90 ° ⁇ ⁇ " (where ⁇ represents the error) to further verify whether the obtained characteristic line segments corresponding to the two peak intervals are respectively characterized parallel to the wall Body and perpendicular to the wall. For example, if the tilt angle corresponding to a peak interval is 30°, the angle corresponding to the other peak interval should be 120° ⁇ , which means that the angle between the traveling direction of the robot and the wall direction is 30° or 120° ⁇ ⁇ .
  • step S340 the posture of the robot is adjusted according to the tilt angle and the current posture of the robot.
  • control device controls the robot to rotate according to the corresponding tilt angle and the rotation direction based on the statistically obtained tilt angle and the current posture of the robot, so that the traveling direction of the robot is parallel or perpendicular to the room divider, thereby controlling the robot along the main direction. Moves toward or away from the room divider.
  • control device also performs the step of planning a navigation route based on the current location when determining the main direction in which the robot is built along the room divider in physical space.
  • the navigation route may include: a first route that the robot moves to the room divider, and a second route that traverses a preset area from the end of the first route.
  • the preset area is, for example, a cleaning area of the cleaning robot, a patrol area of the patrol robot, and the like.
  • the main direction constructed based on the room divider may be the first wall and the second wall perpendicular to each other, and when the cleaning robot is determined along the main direction constructed based on the room divider, Setting the cleaning robot to move in the main direction until contacting the room divider, for example, setting the cleaning robot to face or face away from the first wall surface until contacting the first wall surface or contacting another wall parallel to the first wall surface, or , the cleaning robot is set to move along the first wall surface until it contacts the second wall surface perpendicular to the first wall surface.
  • the cleaning robot moves in the cleaning area by using a route such as a "bow" shape or a zigzag shape, so that the cleaning robot covers the area to be cleaned as much as possible during the operation, thereby improving the cleaning efficiency.
  • FIG. 8 is a schematic structural diagram of a control device for a robot of the present application in an embodiment. As shown, the control device of the robot includes a storage unit 11 and Processing unit 12.
  • the storage unit 11 is for storing at least one program and an image taken by the image pickup device.
  • Storage unit 11 may include high speed random access memory and may also include non-volatile memory, such as one or more magnetic disk storage devices, flash memory devices, or other non-volatile solid state storage devices.
  • the storage unit 11 also includes a memory controller that can control access to the memory by other components of the device, such as the CPU and peripheral interfaces.
  • the program held in the storage unit 11 includes a related program called by the processing unit to execute the control method described later.
  • Processing unit 12 is operatively coupled to a storage unit or the like.
  • the processing unit is operatively coupled to a power source that can provide power to various components in the control board.
  • the power source can include any suitable energy source, such as a rechargeable lithium polymer (Li-poly) battery and/or an alternating current (AC) power converter.
  • the processing unit 12 is configured to invoke the at least one program and perform the control method as described above.
  • the processing unit 12 performs data communication with the storage unit 11.
  • Processing unit 12 may execute instructions stored in the storage unit to perform operations in the robot.
  • a specific implementation manner of the processing unit performing the control method is shown in FIG. 1 to FIG. 7 and its corresponding description, and details are not described herein again.
  • the present application also provides a robot including, but not limited to, a cleaning robot, a patrol robot, a home companion robot, and the like.
  • the robot performs the above control method.
  • FIG. 9 is a schematic structural view of the robot of the present application in an embodiment. As shown, the robot includes an imaging device 21, a mobile device 22, and a control device 23.
  • the imaging device 21 is for taking an image during the movement of the robot.
  • the control device may preset a time interval at which the camera device captures an image, and then the control device acquires a still image at different times captured by the camera device at preset time intervals.
  • the camera device can capture a video. Since the video is composed of image frames, the control device can first continuously or discontinuously acquire image frames in the acquired video, and then the control device selects one frame image as the image.
  • the image pickup apparatus includes, but is not limited to, a camera, a video camera, a camera module integrated with an optical system or a CCD chip, a camera module integrated with an optical system and a CMOS chip, and the like.
  • the power supply system of the camera device can be controlled by a power supply system of the mobile robot, which captures an image of the route traveled during the movement of the mobile robot.
  • the mobile device 22 is operative to adjust the attitude of the robot in accordance with the received control commands. Among them, the mobile device 22 adjusts the moving distance, the moving direction and the moving speed, the moving acceleration, and the like under the control of the control device 23.
  • the mobile device 22 includes a drive unit and at least two roller sets.
  • the at least one of the at least two roller groups is a controlled roller group.
  • the drive unit is coupled to the processing device, and the drive unit is configured to drive the controlled wheel set scrolling based on a movement control command output by the processing device.
  • the drive unit includes a drive motor coupled to the set of rollers for direct drive roller set rolling.
  • the drive unit may include one or more processors (CPUs) or microprocessing units (MCUs) dedicated to controlling the drive motor.
  • the micro processing unit is configured to convert information or data provided by the processing device into an electrical signal for controlling a driving motor, and control a rotation speed, a steering, etc. of the driving motor according to the electrical signal to adjust the movement.
  • the information or data is an off angle determined by the processing device.
  • the processor in the drive unit can be shared with the processor in the processing device or can be set independently.
  • the drive unit functions as a slave processing device, and the processing device functions as a master device, and the drive unit performs motion control based on control of the processing device.
  • the drive unit is shared with a processor in the processing device.
  • the drive unit receives data provided by the processing device through the program interface.
  • the drive unit is configured to control the controlled wheel set scrolling based on a movement control instruction provided by the processing device.
  • the control device 23 performs data communication with the imaging device 21 and the mobile device 22.
  • Control device 23 may include one or more processors.
  • the processor may include one or more general purpose microprocessors, one or more application specific processors (ASICs), one or more digital signal processors (DSPs), one or more field programmable logic arrays (FPGAs) , or any combination of them.
  • the control device is also operatively coupled to an I/O port and an input structure that enables the robot to interact with various other electronic devices that enable the user to interact with the computing device.
  • the input structure can include buttons, keyboards, mice, trackpads, and the like.
  • the other electronic device may be a mobile motor in the mobile device in the robot, or a slave processor in the robot dedicated to controlling the mobile device, such as an MCU (Microcontroller Unit, MCU for short).
  • MCU Microcontroller Unit
  • control device connects the camera device and the mobile device via data lines, respectively.
  • the control device interacts with the camera device and the mobile device through an interface protocol.
  • the data reading and writing technology includes but is not limited to: a high speed/low speed data interface protocol, a database read and write operation, and the like.
  • the interface protocols include, but are not limited to, an HDMI interface protocol, a serial interface protocol, and the like.
  • the control device 23 acquires an image taken by the imaging device 21 and identifies a feature line segment in the image.
  • control device of the robot acquires an image taken by the imaging device during the movement of the robot, and then recognizes the feature line segment in the image using an image processing technique.
  • the feature line segment is a straight line segment.
  • the control device can identify feature segments in the image in a manner that first extracts contour features of the object from the acquired image.
  • the contour feature may be extracted by a contour extraction method, including but not limited to: binary, grayscale, canny operator, and the like.
  • Feature line segments are then extracted from the extracted contour features.
  • the feature line segment can be extracted by the Hough transform.
  • the feature line segments include, but are not limited to, the following features: straightness and/or length features, and the like. For example, when the straightness of the adjacent feature point connection line in the image is greater than the preset straightness threshold, and/or the length thereof is greater than the preset length threshold, the connection of the feature point may be determined to be the feature line segment.
  • control device intercepts a plurality of discrete straight line segments as feature line segments based on the contour of the object for subsequent processing.
  • control device segments the contour features extracted based on the contour of the object, and extracts the feature segments from the segmented contour features. This makes it easier to retain more feature segments.
  • FIG. 2 is a schematic diagram showing an image acquired by an imaging device
  • FIG. 3 is a schematic diagram showing contour features recognized based on the image in FIG. 2.
  • control device may also employ a neural network algorithm to identify feature segments.
  • the manner in which the feature segments are identified is not limited here.
  • control device determines the relative orientation relationship between the robot and the room divider in the physical space according to the identified feature line segments.
  • the room divider refers to the façade used to separate the application space in the application scenario where the robot is located.
  • the room partition refers to a façade for separating the indoor space, such as a wall surface, a partition, a floor to ceiling window, a ceiling, and the like.
  • the relative orientation of the robot and the room divider in physical space can be expressed as the relative orientation relationship between the direction of travel of the robot and the direction in which the wall is constructed.
  • the orientation relationship between the robot and the room divider can be characterized by the angle between the direction of travel of the robot and the plane defined by the room divider. For example, the angle reflects that the relative orientation relationship between the direction of travel of the robot and the wall is parallel, perpendicular or non-perpendicular.
  • the control device determines, based on the identified feature line segments, an orientation relationship in which the robot is currently facing (or facing away from) the wall surface, moving along the wall surface, or having an angle of between 0° and 90° with the wall surface.
  • the indoor objects are basically placed according to the main direction constructed by the room partition. For example, objects such as desks, beds, wardrobes, shoe cabinets, etc., which are not easily moved, are constructed according to the main direction of the room partition.
  • Positioning which allows the placement features in the actual physical space to be reflected by the image, so the control device analyzes the identified feature line segments according to the orientation features presented by the objects in the room, the room isolators, and the like. The relative orientation relationship between the robot and the room divider in the physical space is obtained.
  • control device adjusts the posture of the robot according to the orientation relationship such that the robot moves in the physical direction based on the main direction constructed based on the room divider.
  • the posture of the adjustment robot mainly refers to an angular relationship between the adjustment robot and the main direction constructed based on the room divider, and the robot is determined to be along, facing, or deviated from the room-based partition according to the orientation relationship. In the main direction, the posture adjustment of the robot is completed.
  • control device controls the robot to rotate an angle according to the angle between the identified feature line segment in the actual physical space and the current attitude of the robot to achieve parallel or vertical rotation of the robot with the room divider.
  • the robot rotation can be continuously adjusted according to a preset angle and direction, and the above steps are repeated during the rotation until the preset condition is met according to the identified feature line segment to confirm that the robot is substantially parallel to the room divider. Or vertical.
  • the preset condition is set based on an orientation relationship between the robot and the main direction reflected by the feature line segment.
  • the robot moves in a direction generally parallel or perpendicular to the direction of travel of the room divider. For example, after the control device determines that the cleaning robot faces a wall surface, the control cleaning robot moves to the wall edge and moves in a bow shape.
  • the robot of the present application determines the orientation relationship between the robot and the room divider based on the feature line segments in the acquired image by the control device, so that the robot can adjust its posture to be constructed along the room partition based on the orientation relationship. Moving in the main direction improves mobile coverage.
  • control device may adopt an implementation related to the placement angle of the imaging device to determine the relative orientation relationship between the robot and the room divider in the physical space. And make posture adjustments.
  • the image pickup device 21 is disposed on the robot body side, that is, in the case where the angle between the optical axis of the image pickup device 21 and the robot movement plane is between 0° and 90°, the image pickup device 21 takes an image during the robot movement. And provided to the control device 23, the control device 23 identifies the feature line segments in the image.
  • control device 23 groups the individual feature line segments based on the identified vanishing points of the plurality of feature line segments.
  • the parallel line in the captured image has a vanishing point linear characteristic.
  • the vanishing point linear feature refers to a point at which two or more lines representing parallel lines extend to the far horizon (HORIZON LINE) until they are aggregated.
  • a line having a common vanishing point in an image corresponds to a parallel line in space, that is, a parallel line in space corresponds to a line intersecting in an image angle of view, and these intersecting lines have a common vanishing point
  • the case represents multiple sets of parallel lines in space.
  • the control device extends the identified feature line segments with the image coordinate system in which the image is located to obtain a vanishing point of each feature line segment. For example, the control device calculates the intersection of any two feature line segments by using the inclination angle of each feature line segment in the image coordinate system, and performs clustering processing on each intersection point to classify the intersections with similar positions as one vanishing point.
  • the number of vanishing points obtained is usually multiple.
  • Feature line segments intersecting at the same vanishing point are grouped together.
  • Control device 23 selects at least one set of feature line segments from the grouped feature line segments.
  • the number of feature segments in each group in the image can reflect the main direction constructed based on the room divider. For example, the greater the number of feature segments corresponding to the vanishing point, the greater the likelihood that the direction of the feature segment of the corresponding group in the physical space is based on the main direction constructed by the room divider.
  • a set of feature line segments having the largest number of feature line segments is selected from the grouped feature line segments, the set of feature line segments representing a main direction constructed based on the room divider.
  • the group with the largest number of feature line segments is not necessarily one, and the feature line segments of the plurality of groups that can select the largest number of groups or randomly select one of the feature line segments to perform step S240.
  • control device 23 determines the relative orientation relationship between the robot and the room divider in the physical space based on the position of the vanishing point of the selected feature line segment in the image coordinate system.
  • the selected feature line segment group represents the main direction constructed based on the room divider.
  • the selected set of characteristic line segments represents a contour line of an object or a boundary line of an object disposed parallel to a wall or perpendicular to a wall.
  • the robot when the robot has a certain off-angle relationship with a certain room separator A to be faced in the physical space, a plurality of straight lines parallel to the room separator A are reflected in the image, that is, having the same vanishing point.
  • the feature line segment is located at the image coordinate according to the orientation relationship including the yaw angle (for example, the robot faces the room divider A counterclockwise, or the robot faces the room divider A clockwise) A quadrant of the system or an area within a preset distance from the preset center point.
  • the control device determines the relative orientation relationship between the robot and the room divider A in the physical space by analyzing the position of the vanishing point in the image coordinate system. For example, an image coordinate system constructed with a plane perpendicular to the optical axis of the imaging device, wherein the position of the optical axis is the coordinate origin, and if the vanishing point of the selected feature segment group is located to the left of the coordinate system, the robot and the to-be-facing The orientation of the room divider A is counterclockwise. Wherein, the orientation relationship is rough, and it is not certain that the precise declination value between the robot and the room divider to be faced is determined.
  • control device 23 adjusts the posture of the robot in accordance with the orientation relationship.
  • control device 23 controls the rotation direction and the rotation angle of the mobile device 22 in accordance with the orientation relationship and at a preset angle step to perform the stepwise adjustment.
  • the preset condition may be preset based on position coordinates of the vanishing point of the feature line segment of the selected group in the image coordinate system; condition parameters for evaluating the parallelism of the feature line segments of the selected group may also be set.
  • the step of determining the main direction of the robot along the room divider comprises: determining whether the identified feature line segment in the current image satisfies a preset parallel condition, and if so, determining the pose of the robot and based on The main direction of the room divider is the same. Otherwise, the posture of the robot is continuously adjusted and the above steps are repeated until the parallel condition is satisfied. Wherein the posture of the robot coincides with the main direction constructed based on the room divider, including the current posture of the robot being facing a certain room partition, facing away from a certain room partition or along a certain room partition.
  • the control device determines that the current pose of the robot is facing a certain room divider.
  • the parallel condition comprises: a pitch error between two feature line segments not on the same straight line in the selected feature line segment group is less than or equal to a preset pitch error threshold.
  • the control device calculates an endpoint distance of any two feature line segments in the selected feature line segment group, and if the calculated error between the endpoint distances is less than the pitch error threshold, determining that the selected feature line segments are parallel to each other, that is, determining In the physical space, the robot faces a room divider, and vice versa, continues to adjust the posture.
  • the parallel condition includes a position of a vanishing point of the selected set of feature line segments falling within a preset location area.
  • the control device calculates whether the vanishing point coordinate of the selected feature line segment group is located in a preset position area in the image coordinate system, and the position area is used to define that the current posture of the robot is substantially perpendicular to a certain room divider, and if so, It is determined that the selected feature line segments are parallel to each other, that is, it is determined that the robot faces a certain room partition in the physical space, and vice versa, the posture is continuously adjusted.
  • controlling the movement of the robot along the main direction of the room partition such as the wall may include controlling the movement of the robot parallel to the wall, controlling the movement of the robot toward the wall, and controlling The robot moves away from the wall.
  • the imaging device 21 is vertically disposed on the top of the robot, that is, in the case where the optical axis of the imaging device 21 is perpendicular to the robot moving plane, the imaging device 21 takes an image during the robot movement and supplies it to the control device 23, and controls Device 23 identifies feature line segments in the image.
  • control device 23 counts the tilt angle of the feature line segment identified from the at least one image in the preset image coordinate system.
  • the top of the robot and the optical axis are disposed.
  • the image taken by the camera device perpendicular to the moving plane of the robot also has feature line segments orthogonal to each other. Therefore, counting the tilt angle of each feature line segment in the image coordinate system can facilitate finding the feature line segments orthogonal to each other and the tilt thereof. angle.
  • the tilt angle of the feature line segments in the preset image coordinate system in a single image is counted.
  • the preset image coordinate system UOV wherein the intersection of the camera optical axis and the imaging plane is taken as the origin O of the image coordinate system, and the two directions orthogonal to each other are used as the U axis of the image coordinate system and the V axis of the image coordinate system.
  • the corresponding coordinates of the feature line segments in the image coordinate system UOV, and the tilt angle of each feature line segment in the image coordinate system UOV can be obtained, and then the obtained tilt angles are counted to obtain
  • the statistical result represents the angular distribution of the feature line segments.
  • the inclination angle is in the range of 0° to 180°.
  • the statistical result may be shown in a waveform diagram, a histogram, or the like.
  • the feature line segment in the image is in the image coordinate system UOV by the X-axis.
  • the value of the tilt angle value, the Y-axis represents the number of feature line segments under the corresponding tilt angle value, and the statistical result is drawn.
  • the control device counts the tilt angle of the feature line segments in the predetermined image coordinate system in the plurality of images.
  • the control device acquires the posture change of the robot corresponding to the captured adjacent image during the movement of the robot. Since the image coordinate system is parallel to the moving plane of the robot, the detected posture change can be used to perform regression compensation on the tilt angle of the feature line segment in the corresponding image. Therefore, during a period of posture adjustment, according to the rotation angle corresponding to the image taken by the robot, the robot needs to perform regression processing on the inclination angles of each feature line segment in at least two images taken; and the features after statistical regression processing The tilt angle of the line segment in the preset image coordinate system.
  • the regression process refers to one of the images captured by the robot as a reference image, and the posture (position and angle) of the robot when the reference image is captured is used as a reference posture, and the inclination angle of the feature line segments in the other images is corrected.
  • the robot takes the first image and counts the inclination angle of the feature line segments in the first image to obtain the first statistical result, and the robot adjusts the posture and takes the second image.
  • the image is statisticed and the tilt angle of the feature line segments in the second image is obtained to obtain a second statistical result.
  • the posture when the robot takes the first image as the reference posture and based on the posture when the robot captures the second image, the rotation angle of the robot with respect to the reference posture can be obtained by means of a gyroscope, VSLAM, or the like.
  • the obtained rotation angle is projected into the image coordinate system to obtain a rotation angle of the second image with respect to the first image, based on which the inclination angle of the feature line segment included in the second statistical result is corrected, so that the second The feature line segment in the image and the feature line segment in the first image are unified in the image coordinate system, and the tilt angle deviation caused by the rotation of the robot is eliminated.
  • the first statistical result and the second statistical result subjected to the regression processing are subjected to overall statistics to obtain statistical results of the inclination angle of each characteristic line segment in the image coordinate system.
  • control device 23 determines the relative orientation relationship between the robot and the room divider in the physical space based on the statistical tilt angle.
  • the control device may obtain at least one statistical peak interval, and use the obtained tilt angle corresponding to the statistical peak interval as the robot and the room separator in the physical space.
  • Relative orientation relationship a peak interval is obtained based on the statistical result, wherein the peak interval indicates that the number of feature segments is the largest under the corresponding tilt angle in the peak interval, and the maximum number of feature segments indicates that the direction in which the feature segments are located represents the construction based on the room divider. Main direction.
  • the relative orientation of the robot to the room divider in physical space is determined based on the calculated tilt angle at the peak interval.
  • the orientation relationship includes an off-angle interval and a rotation direction between the robot and a partition to be faced to a certain room.
  • the statistical peak range is determined to be 41° ⁇ 1° according to the UV axis ray direction of the preset image coordinate system, and the control device determines that the robot is located in a counterclockwise direction to be facing a room divider and is separated from the room.
  • the body has an off-angle range of 41 ° ⁇ 1 °.
  • the corresponding tilt angle in the peak interval may be a tilt angle interval within a certain error range. Based on this, in one example, the average tilt angle in the tilt angle interval is taken as the tilt angle characterizing the orientation relationship.
  • FIG. 6 is a waveform diagram showing the statistical result of the characteristic line segment and the tilt angle of the present application in an embodiment.
  • the X axis represents the inclination angle of the feature line segment in the image
  • the Y axis represents the feature line segment.
  • the number of the figure shows the case where there is a maximum peak interval
  • the characteristic line segment corresponding to the inclination angle of the peak interval represents the main direction constructed based on the room divider, such as parallel to the wall direction or perpendicular to the wall.
  • the body direction, and thus, the relative orientation relationship between the robot and the room divider in the physical space can be characterized by the angle between the robot and the room divider, that is, the inclination angle corresponding to the peak interval.
  • the peak section corresponds to a tilt angle of 45°, which means that the angle between the robot's traveling direction and the wall direction is 45°.
  • FIG. 7 is a waveform diagram showing the statistical result of the characteristic line segment and the tilt angle of the present application in another embodiment.
  • the X axis represents the inclination angle of the feature line segment in the image
  • the Y axis represents the feature.
  • the number of line segments the figure shows the case where there are two maximum peak intervals. According to the actual situation, the two tilt angles corresponding to the two peak intervals should theoretically be 90° with each other, and the corresponding feature line segments respectively represent parallel In the direction of the wall and perpendicular to the wall.
  • the relative orientation relationship between the robot and the room divider in the physical space can be characterized by the angle between the robot and the room divider, that is, the inclination angle corresponding to any peak interval, and on the other hand, Whether the difference between the two tilt angles corresponding to the peak interval is within the range of "90 ° ⁇ ⁇ " (where ⁇ represents the error) to further verify whether the obtained characteristic line segments corresponding to the two peak intervals are respectively characterized parallel to the wall Body and perpendicular to the wall. For example, if the tilt angle corresponding to a peak interval is 30°, the angle corresponding to the other peak interval should be 120° ⁇ , which means that the angle between the traveling direction of the robot and the wall direction is 30° or 120° ⁇ ⁇ .
  • control device 23 adjusts the posture of the robot based on the tilt angle and the current posture of the robot.
  • control device controls the robot to rotate according to the corresponding tilt angle and the rotation direction based on the statistically obtained tilt angle and the current posture of the robot, so that the traveling direction of the robot is parallel or perpendicular to the room divider, thereby controlling the robot along the main direction. Moves toward or away from the room divider.
  • control device also performs the step of planning a navigation route based on the current location when determining the main direction in which the robot is built along the room divider in physical space.
  • the navigation route may include: a first route that the robot moves to the room divider, and a second route that traverses a preset area from the end of the first route.
  • the preset area is, for example, a cleaning area of the cleaning robot, a patrol area of the patrol robot, and the like.
  • the main direction constructed based on the room divider may be the first wall and the second wall perpendicular to each other, and when the cleaning robot is determined along the main direction constructed based on the room divider, Setting the cleaning robot to move in the main direction until contacting the room divider, for example, setting the cleaning robot to face or face away from the first wall surface until contacting the first wall surface or contacting another wall parallel to the first wall surface, or , the cleaning robot is set to move along the first wall surface until it contacts the second wall surface perpendicular to the first wall surface.
  • the cleaning robot moves in the cleaning area by using a route such as a "bow" shape or a zigzag shape, so that the cleaning robot covers the area to be cleaned as much as possible during the operation, thereby improving the cleaning efficiency.
  • FIG. 10 is a schematic structural diagram of a control system of a robot of the present application.
  • the control system includes an image processing module 31 and an orientation.
  • the image processing module 31 is configured to acquire an image taken during the movement of the robot and identify a feature line segment in the image.
  • the orientation calculation module 32 is configured to determine a relative orientation relationship between the robot and the room divider in the physical space according to the identified feature line segments.
  • the control module 33 is configured to adjust the posture of the robot according to the orientation relationship such that the robot moves in the physical direction based on the main direction constructed based on the room divider.
  • control device may adopt an implementation related to the placement angle of the imaging device to determine the relative orientation relationship between the robot and the room divider in the physical space. And make posture adjustments.
  • the camera device is disposed on the robot body side, that is, the angle between the optical axis of the camera device and the robot moving plane is between 0° and 90°
  • the orientation calculation module 32 includes a first orientation calculation unit.
  • the first orientation calculation unit is configured to group the feature line segments based on the identified vanishing points of the plurality of feature line segments; select at least one set of feature line segments from the grouped feature line segments; and disappear according to the selected feature line segment group
  • the position of the point in the image coordinate system determines the relative orientation of the robot and the room divider in physical space.
  • the camera device is vertically disposed on the top of the robot, that is, if the optical axis of the camera device is perpendicular to the robot movement plane, the orientation calculation module 32 includes a second orientation calculation unit for counting from at least one image.
  • control module 33 further includes a navigation route planning unit for planning a navigation route based on the current location when determining the main direction in which the robot is built along the room divider in the physical space.
  • each module of the device in the embodiment of FIG. 10 is only a division of a logical function, and may be integrated into one physical entity or physically separated in whole or in part.
  • these modules can all be implemented by software in the form of processing component calls; or all of them can be implemented in hardware form; some modules can be realized by processing component calling software, and some modules are realized by hardware.
  • each module may be a separately set processing element, or may be integrated in one of the above-mentioned devices, or may be stored in the memory of the above device in the form of program code, and processed by one of the above devices.
  • the implementation of other modules is similar.
  • all or part of these modules can be integrated or implemented independently.
  • the processing elements described herein can be an integrated circuit that has signal processing capabilities. In the implementation process, each step of the above method or each of the above modules may be completed by an integrated logic circuit of hardware in the processor element or an instruction in a form of software.
  • the above modules may be one or more integrated circuits configured to implement the above method, for example, one or more specific integrated circuits (ASICs), or one or more microprocessors (digitalsingnal processors, referred to as DSP), or one or more Field Programmable Gate Arrays (FPGAs).
  • ASICs application specific integrated circuits
  • DSP digital signal processors
  • FPGAs Field Programmable Gate Arrays
  • the processing component may be a general-purpose processor, such as a central processing unit (CPU) or other processor that can call the program code.
  • these modules can be integrated and implemented in the form of a system-on-a-chip (SOC).
  • SOC system-on-a-chip
  • the present application also provides a computer storage medium storing at least one program that, when invoked, performs the control method of any of the foregoing.
  • the computer program code may be in a source code form, an object code form, an executable file, or some intermediate form.
  • portions of the technical solution of the present application that contribute in essence or to the prior art may be embodied in the form of a software product, which may include one or more of the executable instructions for storing the machine thereon.
  • a machine-readable medium that, when executed by one or more machines, such as a computer, computer network, or other electronic device, can cause the one or more machines to perform operations in accordance with embodiments of the present application. For example, each step in the positioning method of the robot is executed.
  • a machine-readable medium can include, but is not limited to, any entity or device capable of carrying the computer program code, a recording medium, a USB flash drive, a removable hard drive, a magnetic disk, an optical disk, a computer memory, a floppy disk, an optical disk, a CD-ROM (tight Disk-read only memory), magneto-optical disk, ROM (Read Only Memory), RAM (Random Access Memory), EPROM (Erasable Programmable Read Only Memory), EEPROM (Electrically Erasable Programmable Read Only Memory) , magnetic or optical cards, flash memory, electrical carrier signals, telecommunications signals, and software distribution media or other types of media/machine readable media suitable for storing machine executable instructions.
  • the content contained in the computer readable medium may be appropriately increased or decreased according to the requirements of legislation and patent practice in a jurisdiction, for example, in some jurisdictions, according to legislation and patent practice, computer readable media Does not include electrical carrier signals and telecommunication signals.
  • the storage medium may be located in a robot or in a third-party server, such as in a server that provides an application store. There are no restrictions on the specific application mall, such as Huawei Application Mall, Apple App Store, etc.
  • This application can be used in a variety of general purpose or special purpose computing system environments or configurations.
  • the application can be described in the general context of computer-executable instructions executed by a computer, such as a program module.
  • program modules include routines, programs, objects, components, data structures, and the like that perform particular tasks or implement particular abstract data types.
  • the present application can also be practiced in distributed computing environments where tasks are performed by remote processing devices that are connected through a communication network.
  • program modules can be located in both local and remote computer storage media including storage devices.

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Automation & Control Theory (AREA)
  • Aviation & Aerospace Engineering (AREA)
  • Remote Sensing (AREA)
  • Radar, Positioning & Navigation (AREA)
  • Multimedia (AREA)
  • Electromagnetism (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Theoretical Computer Science (AREA)
  • Manipulator (AREA)
  • Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)
  • Image Analysis (AREA)

Abstract

一种机器人的控制方法、装置、系统及所适用的机器人。控制方法包括获取机器人移动期间所摄取的图像以及识别图像中的特征线段（S110）；根据所识别出的特征线段确定机器人与房间分隔体在物理空间中相对的方位关系(S120)；根据方位关系调整机器人的姿态，使得在物理空间中机器人沿基于房间分隔体所构建的主方向移动(S130)。该方法通过获取图像中的特征线段来确定机器人与房间分隔体之间的方位关系，使得机器人能够基于方位关系将其姿态调整至沿基于房间分隔体所构建的主方向移动，提高了移动覆盖率。

Description

机器人的控制方法、装置、系统及所适用的机器人 技术领域
本申请涉及智能机器人领域，特别是涉及一种机器人的控制方法、装置、系统及所适用的机器人。
背景技术
随着科技的不断发展，智能机器人逐渐走入人们的生活。在实际应用中，智能机器人既可以接受人类指挥，又可以运行预先编排的程序，也可以根据以人工智能技术制定的原则纲领行动。这类机器人可用在室内或室外，可用于工业或家庭，可用于取代保安巡视、取代人们清洁地面，还可用于家庭陪伴、辅助办公等。
以清洁机器人为例，为了达到较高的清扫效率，理想的是在清洁机器人进行清洁作业前自动调整机器人的姿态以使其沿主方向移动，即机器人的行进方向垂直于或平行于墙面方向，然后再进行清扫，进而使得在清扫期间能够尽量减少补扫面积，提高清扫效率。因而，如何准确地调整机器人的姿态以使其沿主方向移动是提高清扫效率的关键因素。
发明内容
鉴于以上所述现有技术的缺点，本申请的目的在于提供一种机器人的控制方法、装置、系统及所适用的机器人，用于解决现有技术中如何自动调整机器人的姿态以使其沿主方向移动的问题。
为实现上述目的及其他相关目的，本申请的第一方面提供一种机器人的控制方法，包括：获取机器人移动期间所摄取的图像以及识别所述图像中的特征线段；根据所识别出的特征线段确定所述机器人与房间分隔体在物理空间中相对的方位关系；根据所述方位关系调整所述机器人的姿态，使得在物理空间中所述机器人沿基于房间分隔体所构建的主方向移动。
在本申请的第一方面的某些实施方式中，所述根据所识别出的特征线段确定所述机器人与房间分隔体在物理空间中相对的方位关系的步骤包括：基于所识别出的多条特征线段的消失点对各条特征线段进行分组；从所分组的特征线段中选取至少一组特征线段；根据所选择的特征线段组的消失点在图像坐标系中的位置确定所述机器人与房间分隔体在物理空间中相对的方位关系。
在本申请的第一方面的某些实施方式中，所述从所分组的特征线段中选取至少一组特征线段的步骤包括：选取特征线段数量最多的一组特征线段。
在本申请的第一方面的某些实施方式中，所述根据方位关系调整所述机器人的姿态的步骤包括：根据所述方位关系并以预设角度步长调整所述机器人的姿态；以及重复上述各步骤直至满足用于确定所述机器人沿基于房间分隔体所构建的主方向的预设条件。
在本申请的第一方面的某些实施方式中，所述确定机器人沿基于房间分隔体所构建的主方向的步骤包括：判断当前图像中识别出的特征线段是否满足预设的平行条件，若满足所述平行条件则确定所述机器人的姿态与基于房间分隔体所构建的主方向一致，反之，则继续调整所述机器人的姿态并重复上述各步骤直至满足所述平行条件为止。
在本申请的第一方面的某些实施方式中，所述平行条件包括以下至少一种：不在同一直线上的两条特征线段之间的间距误差小于等于预设的间距误差阈值，所选择的特征线段组的消失点的位置落入预设的位置区域。
在本申请的第一方面的某些实施方式中，所获取的图像是由与机器人移动平面垂直设置的摄像装置摄取的，所述根据所识别出的特征线段确定所述机器人与房间分隔体在物理空间中相对的方位关系的步骤包括：统计从至少一幅图像中所识别的特征线段在预设图像坐标系中的倾斜角；根据所统计的倾斜角确定所述机器人与房间分隔体在物理空间中相对的方位关系。
在本申请的第一方面的某些实施方式中，所述统计从至少一幅图像中所识别的特征线段在预设图像坐标系中的倾斜角的步骤包括以下任一种：统计单幅图像中特征线段在预设图像坐标系中的倾斜角；在姿态调整的一时间段内，根据机器人摄取图像时所对应的旋转角度，对所摄取的至少两幅图像中各特征线段的倾斜角进行回归处理；以及统计回归处理后各特征线段在预设图像坐标系中的倾斜角。
在本申请的第一方面的某些实施方式中，所述根据所统计的倾斜角确定所述机器人与房间分隔体在物理空间中相对的方位关系的步骤包括：根据所统计的位于峰值区间的倾斜角，确定所述机器人与房间分隔体在物理空间中相对的方位关系。
在本申请的第一方面的某些实施方式中，所述根据方位关系调整所述机器人的姿态的步骤包括：根据所述倾斜角和机器人的当前姿态，调整所述机器人的姿态。
在本申请的第一方面的某些实施方式中，所述控制方法还包括：在确定在物理空间中所述机器人沿基于房间分隔体所构建的主方向时，基于当前位置规划导航路线。
在本申请的第一方面的某些实施方式中，所述导航路线包括：所述机器人向所述房间分隔体移动的第一路线，以及自所述第一路线的终点开始遍历一预设区域的第二路线。
本申请的第二方面还提供一种机器人的控制装置，包括：存储单元，用于存储至少一个程序以及由摄像装置所摄取的图像；处理单元，与所述存储单元相连，用于执行所述至少一 个程序以执行上述中任一所述的控制方法。
本申请的第三方面还提供一种机器人，包括：摄像装置，用于在机器人移动期间摄取图像；移动装置，用于按照所接收的控制指令调整所述机器人的姿态；控制装置，与所述摄像装置和移动装置相连，用于执行以下步骤：获取所述摄像装置所摄取的图像以及识别所述图像中的特征线段；根据所识别出的特征线段确定所述机器人与房间分隔体在物理空间中相对的方位关系；根据所述方位关系控制所述移动装置调整所述机器人的姿态，使得使得在物理空间中所述机器人沿基于房间分隔体所构建的主方向移动。
在本申请的第三方面的某些实施方式中，所述摄像装置的光轴与机器人移动平面的夹角在0°至90°之间，所述摄像装置在机器人移动期间摄取图像并提供给所述控制装置；所述控制装置执行根据所识别出的特征线段确定所述机器人与房间分隔体在物理空间中相对的方位关系的步骤包括：基于所识别出的多条特征线段的消失点对各条特征线段进行分组；从所分组的特征线段中选取至少一组特征线段；根据所选择的特征线段组的消失点在图像坐标系中的位置确定所述机器人与房间分隔体在物理空间中相对的方位关系。
在本申请的第三方面的某些实施方式中，所述控制装置执行从所分组的特征线段中选取至少一组特征线段的步骤包括：选取特征线段数量最多的一组特征线段。
在本申请的第三方面的某些实施方式中，所述控制装置执行根据方位关系调整所述机器人的姿态的步骤包括：根据所述方位关系并以预设角度步长控制所述移动装置的旋转方向和旋转角度；以及重复上述各步骤直至满足用于确定所述机器人沿基于房间分隔体所构建的主方向的预设条件。
在本申请的第三方面的某些实施方式中，所述控制装置执行确定机器人沿基于房间分隔体所构建的主方向的步骤包括：判断当前图像中识别出的特征线段是否满足预设的平行条件，若满足所述平行条件则确定所述机器人的姿态与基于房间分隔体所构建的主方向一致，反之，则继续调整所述机器人的姿态并重复上述各步骤直至满足所述平行条件为止。
在本申请的第三方面的某些实施方式中，所述平行条件包括以下至少一种：不在同一直线上的两条特征线段之间的间距误差小于等于预设的间距误差阈值，所选择的特征线段组的消失点的位置落入预设的位置区域。
在本申请的第三方面的某些实施方式中，所述摄像装置的光轴与机器人移动平面垂直，所述摄像装置在机器人移动期间摄取图像并提供给所述控制装置；所控制装置执行根据所识别出的多条特征线段确定所述机器人与房间分隔体在物理空间中相对的方位关系的步骤包括：统计从至少一幅图像中所识别的特征线段在预设图像坐标系中的倾斜角；以及根据所统计的倾斜角确定所述机器人与房间分隔体在物理空间中相对的方位关系。
在本申请的第三方面的某些实施方式中，所述控制装置执行统计从至少一幅图像中所识别的特征线段在预设图像坐标系中的倾斜角的步骤包括以下任一种：统计单幅图像中特征线段在预设图像坐标系中的倾斜角；在姿态调整的一时间段内，根据机器人摄取图像时所对应的旋转角度，对所摄取的至少两幅图像中各特征线段的倾斜角进行回归处理；以及统计回归处理后各特征线段在预设图像坐标系中的倾斜角。
在本申请的第三方面的某些实施方式中，所述控制装置执行根据所统计的倾斜角确定所述机器人与房间分隔体在物理空间中相对的方位关系的步骤包括：根据所统计的位于峰值区间的倾斜角，确定所述机器人与房间分隔体在物理空间中相对的方位关系。
在本申请的第三方面的某些实施方式中，所述控制装置执行根据方位关系调整所述机器人的姿态的步骤包括：根据所述倾斜角和机器人的当前姿态，调整所述机器人的姿态。
在本申请的第三方面的某些实施方式中，所述控制装置还用于执行以下步骤：在确定在物理空间中所述机器人沿基于房间分隔体所构建的主方向时，基于当前位置规划导航路线。
在本申请的第三方面的某些实施方式中，所述导航路线包括：所述机器人向所述房间分隔体移动的第一路线，以及自所述第一路线的终点开始遍历一预设区域的第二路线。
在本申请的第三方面的某些实施方式中，所述机器人为清洁机器人。
本申请的第四方面还提供一种计算机存储介质，存储至少一种程序，所述至少一种程序在被调用时执行上述中任一所述的控制方法。
本申请的第五方面还提供一种机器人的控制系统，包括：图像处理模块，用于获取机器人移动期间所摄取的图像以及识别所述图像中的特征线段；方位计算模块，用于根据所识别出的特征线段确定所述机器人与房间分隔体在物理空间中相对的方位关系；控制模块，用于根据所述方位关系调整所述机器人的姿态，使得在物理空间中所述机器人沿基于房间分隔体所构建的主方向移动。
在本申请的第五方面的某些实施方式中，所述方位计算模块包括第一方位计算单元，用于执行以下步骤：基于所识别出的多条特征线段的消失点对各条特征线段进行分组；从所分组的特征线段中选取至少一组特征线段；根据所选择的特征线段组的消失点在图像坐标系中的位置确定所述机器人与房间分隔体在物理空间中相对的方位关系。
在本申请的第五方面的某些实施方式中，所述方位计算模块包括第二方位计算单元，用于执行以下步骤：统计从至少一幅图像中所识别的特征线段在预设图像坐标系中的倾斜角；根据所统计的倾斜角确定所述机器人与房间分隔体在物理空间中相对的方位关系。
在本申请的第五方面的某些实施方式中，所述控制模块包括导航路线规划单元，用于在确定在物理空间中所述机器人沿基于房间分隔体所构建的主方向时，基于当前位置规划导航 路线。
如上所述，本申请的机器人的控制方法、装置、系统及所适用的机器人，具有以下有益效果：通过获取图像中的特征线段来确定机器人与房间分隔体之间的方位关系，使得机器人能够基于所述方位关系将其姿态调整至沿基于房间分隔体所构建的主方向移动，提高了移动覆盖率。
附图说明
图1显示为本申请机器人的控制方法在一种实施方式中的流程示意图。
图2显示为通过摄像装置所获取的图像的示意图。
图3显示为基于图2中的图像所识别出的轮廓特征的示意图。
图4显示为本申请控制方法在另一种实施方式中的流程图。
图5显示为本申请控制方法在又一种实施方式中的流程图。
图6显示为本申请特征线段和倾斜角的统计结果在一种实施方式中的波形图.
图7显示为本申请特征线段和倾斜角的统计结果在另一种实施方式中的波形图。
图8显示为本申请机器人的控制装置在一种实施方式中的结构示意图。
图9显示为本申请机器人在一种实施方式中的结构示意图。
图10显示为本申请机器人的控制系统在一种实施方式中的结构示意图。
具体实施方式
以下由特定的具体实施例说明本申请的实施方式，熟悉此技术的人士可由本说明书所揭露的内容轻易地了解本申请的其他优点及功效。
在下述描述中，参考附图，附图描述了本申请的若干实施例。应当理解，还可使用其他实施例，并且可以在不背离本申请的精神和范围的情况下进行机械组成、结构、电气以及操作上的改变。下面的详细描述不应该被认为是限制性的，并且本申请的实施例的范围仅由公布的专利的权利要求书所限定。这里使用的术语仅是为了描述特定实施例，而并非旨在限制本申请。空间相关的术语，例如“上”、“下”、“左”、“右”、“下面”、“下方”、“下部”、“上方”、“上部”等，可在文中使用以便于说明图中所示的一个元件或特征与另一元件或特征的关系。
再者，如同在本文中所使用的，单数形式“一”、“一个”和“该”旨在也包括复数形式，除非上下文中有相反的指示。应当进一步理解，术语“包含”、“包括”表明存在所述的特征、步骤、操作、元件、组件、项目、种类、和/或组，但不排除一个或多个其他特征、步骤、操作、元件、组件、项目、种类、和/或组的存在、出现或添加。此处使用的术 语“或”和“和/或”被解释为包括性的，或意味着任一个或任何组合。因此，“A、B或C”或者“A、B和/或C”意味着“以下任一个：A；B；C；A和B；A和C；B和C；A、B和C”。仅当元件、功能、步骤或操作的组合在某些方式下内在地互相排斥时，才会出现该定义的例外。
机器人基于导航控制技术执行移动操作。以清洁机器人为例，一般地，清洁机器人所处室内两个互相垂直的主方向即对应墙的两个方向。为了遍历整个待清扫区域，清洁机器人按照弓字形移动。其中，若清洁机器人沿着或面向或背离如墙、窗、屏风等房间分隔体所构建的方向移动，则能够以最高效的方式完成清洁操作。这是因为清洁机器人按照上述方向移动能够在作业期间尽可能全面覆盖待清洁区域，减少补扫操作，提高清洁效率。
基于上述清洁机器人的示例并推及至其他移动机器人，为了提高移动机器人的移动覆盖率，以及在移动期间执行相应操作的工作效率，本申请提供一种机器人的控制方法，使用所述控制方法可以基于机器人所获取图像中的特征线段来确定机器人与房间分隔体例如墙面、窗户等之间的相对方位，使得机器人能够基于所述相对方位调整其姿态，进而能够沿主方向如平行于墙面方向或垂直于墙面方向移动，提高移动覆盖率。
请参阅图1，图1显示为本申请机器人的控制方法在一种实施方式中的流程示意图。其中，所述控制方法可由控制装置来执行。其中，所述控制装置位于机器人中，所述机器人还包括与所述控制装置数据相连的摄像装置，用以摄取图像。在一实施例中，控制装置可以预先设定摄像装置拍摄图像的时间间隔，然后控制装置获取经摄像装置以预设时间间隔拍摄的不同时刻下的静态图像，并执行步骤S110-S130。在另一实施例中，摄像装置可以拍摄视频，由于视频是由图像帧构成的，因此控制装置首先可以连续或不连续地采集所获取的视频中的图像帧，然后控制装置选用一帧图像作为一幅图像并执行步骤S110-S130。
在步骤S110中，获取机器人移动期间所摄取的图像以及识别图像中的特征线段。
在此，机器人的控制装置获取摄像装置在机器人移动期间所摄取的图像，然后利用图像处理技术识别图像中的特征线段。其中，所述特征线段为直线线段。
在一些实施例中，所述控制装置可以采用下述方式识别图像中的特征线段：首先，从所获取的图像中提取物体的轮廓特征。其中，可通过轮廓线提取方法提取轮廓特征，所述轮廓线提取方法包括但不限于：二值、灰度、canny算子等方法。然后，从所提取的轮廓特征中提取特征线段。其中，可通过霍夫变换来提取特征线段。其中，所述特征线段包括但不限于以下特征：直度和/或长度特征等。例如，当图像中所识别的相邻特征点连线的直度大于预设直度阈值，和/或其长度大于预设长度阈值时，可判定该特征点的连线为特征线段。在一示例中，所述控制装置基于物体轮廓线截取不连续的多条直线线段作为特征线段以进行后续处 理。在另一示例中，所述控制装置将基于物体轮廓线所提取的轮廓特征进行分段，再从分段后的轮廓特征中提取特征线段。如此便于保留更多的特征线段。
需要说明的是，所述物体轮廓应宽泛理解，其包括但不限于摆放在房间中的物体的轮廓，还包括房间中墙与墙之间、墙与屋顶之间、墙与门窗之间的交界线等。请参阅图2和图3，其中，图2显示为通过摄像装置所获取的图像的示意图，图3显示为基于图2中的图像所识别出的轮廓特征的示意图。如图3所示，其中细线条指示轮廓特征，所述轮廓特征例如是基于二值、灰度、canny算子等方法从图像中提取的；粗线条指示特征线段，在此，当图像中所识别的相邻特征点连线的直度大于预设直度阈值，和/或其长度大于预设长度阈值时，可判定该特征点的连线为特征线段。
还需要说明的是，所述控制装置还可以采用如神经网络算法来识别特征线段。在此不对识别特征线段的方式进行限制。
在步骤S120中，根据所识别出的特征线段确定机器人与房间分隔体在物理空间中相对的方位关系。
其中，房间分隔体是指在机器人所处应用场景中用于分隔应用空间的立面。以清洁机器人为例，在清洁机器人处于室内场景时，所述房间分隔体是指用于分隔室内空间的立面，如墙面、隔断、落地窗、天花板等。因而，例如，机器人与房间分隔体在物理空间中相对的方位关系可以表示为机器人的行进方向与墙面所构建的方向之间相对的方位关系。在某些实施例中，机器人与房间分隔体之间的方位关系可由机器人的行进方向与房间分隔体所限定的平面之间的夹角来表征。例如，所述夹角反映机器人行进方向与墙面的相对方位关系为平行、垂直相交或非垂直相交。
所述控制装置基于所识别的特征线段，来确定机器人当前面向(或背离)墙面移动、沿墙面移动、或与墙面具有0°到90°之间夹角的方位关系。这是由于为充分利用室内空间，室内物体基本根据房间隔离体所构建的主方向进行摆放，例如，书桌、床、衣柜、鞋柜等不易移动的物体均根据房间隔离体所构建的主方向进行摆放，这使得实际物理空间中的摆放特征可藉由图像反映出来，因此根据室内的物体、房间隔离体等所呈现的方位特征，所述控制装置对所识别的特征线段进行分析，得到所述机器人与房间分隔体在物理空间中相对的方位关系。
在步骤S130中，根据方位关系调整机器人的姿态，使得在物理空间中机器人沿基于房间分隔体所构建的主方向移动。
在此，所述调整机器人的姿态主要指调整机器人与基于房间分隔体所构建的主方向之间的角度关系，当根据方位关系确定机器人以沿着、面向、或背离基于房间分隔体所构建的主 方向，则完成机器人的姿态调整。
在某些实施例中，所述控制装置根据所识别特征线段在实际物理空间中的夹角以及机器人的当前姿态，控制机器人旋转一角度，以实现机器人与房间分隔体平行或垂直。在另一些实施例中，可以依据预设的角度和方向不断调整机器人旋转，并在旋转期间重复上述步骤S110-S130，直至根据所识别出的特征线段满足预设条件，以确认机器人与房间分隔体大致平行或垂直为止。其中，所述预设条件是基于特征线段所反映的机器人与主方向的方位关系而设置的。
机器人按照大致平行于或垂直于房间分隔体的行进方向进行移动。例如，控制装置在确定清洁机器人面向一墙面后，控制清洁机器人移动至墙边，并按弓字形移动。
本申请机器人的控制方法，通过获取图像中的特征线段来确定机器人与房间分隔体之间的方位关系，使得机器人能够基于所述方位关系将其姿态调整至沿基于房间分隔体所构建的主方向移动，提高了移动覆盖率。
基于上述技术思想并结合实际摄像装置在机器人的摆放角度，所述控制装置可采用与摄像装置的摆放角度相关的实现方式来确定所述机器人与房间分隔体在物理空间中相对的方位关系以及进行姿态调整。
在一些实施方式中，摄像装置设置在机器人体侧，即摄像装置的光轴与机器人移动平面的夹角在0°至90°之间的情况下，请参阅图4，图4显示为本申请控制方法在另一种实施方式中的流程图，如图所示，所述控制方法包括步骤S210-S250。
在步骤S210中，获取机器人移动期间所摄取的图像以及识别图像中的特征线段。其中，步骤S210与上述步骤S110相同或相似，在此不再详述。
在步骤S220中，基于所识别出的多条特征线段的消失点对各条特征线段进行分组。
在此，由于摄像装置的光轴与主方向具有0°至90°的夹角，因此，所拍摄的图像中平行线条具有消失点线性特征。其中，所述消失点线性特征是指两条或多条代表平行线线条向远处地平线(HORIZON LINE)伸展直至聚合的那一点。在计算机视觉领域中，图像中具有共同消失点的直线对应于空间中的平行线，也就是说，空间中的平行线对应在图像视角中是相交的线，这些相交的线在具有共同消失点的情况下代表空间中的多组平行线。
所述控制装置以图像所在图像坐标系对所识别出的各特征线段延长处理以得到各特征线段的消失点。例如，所述控制装置利用各特征线段在图像坐标系中的倾斜角计算任意两特征线段的交汇点，并对各交汇点进行聚类处理以将位置相近的交汇点归类为一个消失点。
在所识别的多个特征线段中，所得到的消失点的数量通常为多个，本申请中基于所识别出的多条特征线段所对应的消失点在图像坐标系中的不同坐标位置，将相交于同一消失点的 特征线段分为一组。
在步骤S230中，从所分组的特征线段中选取至少一组特征线段。
由于房间内的大部分物体按照房间分隔体所构建的主方向进行摆放，因此，图像中各分组中特征线段的数量能够反映基于房间分隔体所构建的主方向。例如，消失点对应的特征线段数量越多，表示相应分组的特征线段在物理空间中的方向是基于房间分隔体所构建的主方向的可能性越大。鉴于此，在某些实施例中，从所分组的特征线段中选取特征线段数量最多的一组特征线段，该组特征线段代表基于房间分隔体所构建的主方向。
需要说明的是，所得到的特征线段的数量最多的分组并非一定仅为一个，可选择数量最多的多个分组的特征线段或随机选择其中一组特征线段执行步骤S240。
在步骤S240中，根据所选择的特征线段组的消失点在图像坐标系中的位置确定机器人与房间分隔体在物理空间中相对的方位关系。
其中，所选择的特征线段组代表基于房间分隔体所构建的主方向。例如所选择的特征线段组代表沿平行于一墙体或垂直于一墙体方向设置的物体的轮廓线或房间的交界线。
在此，当在物理空间中机器人与待面向的某一房间分隔体A具有一定偏角的方位关系，平行于该房间分隔体A的多条直线反映在图像中，即为具有同一消失点的特征线段，根据包含所述偏角的方位关系(例如机器人逆时针偏转地面向某一房间分隔体A，或者机器人顺时针偏转地面向某一房间分隔体A)，相应的消失点将位于图像坐标系的某一象限或者与预设中心点相距预设距离之内的区域中。基于上述方位关系与消失点在图像坐标系中位置的对应关系，所述控制装置通过分析消失点在图像坐标系中的位置确定机器人与房间分隔体A在物理空间中相对的方位关系。例如，以垂直于摄像装置的光轴的平面构建的图像坐标系，其中，光轴所在位置为坐标原点，若所选择的特征线段组的消失点位于坐标系左侧，则机器人与待面向的房间分隔体A的方位关系为逆时针偏转。其中，所述方位关系为粗略的，并非一定能够确定机器人与待面向的房间分隔体之间的精准偏角值。
在步骤S250中，根据方位关系并以预设角度步长调整机器人的姿态。
在此，所述控制装置以预设角度步长为单位角度并按照所得到的方位关系进行逐步调整。
每控制机器人旋转一单位角度时，获取摄像装置所拍摄的图像，并重复执行上述步骤S210至步骤S250，直至确定机器人与房间分隔体大致平行或垂直，即，满足用于确定机器人沿基于房间分隔体所构建的主方向的预设条件。其中，当机器人面向或背离某一房间分隔体时，或者当机器人沿某一房间分隔体时，所选择分组的特征线段被认为是房间内平行于或垂直于该房间分隔体的直线在图像中的映射。所述预设条件可基于所选择分组的特征线段的消失点在图像坐标系中的位置坐标而预先设置；还可以设置用于评价所选择分组的特征线段的 平行度的条件参数。
在某些实施例中，确定机器人沿基于房间分隔体所构建的主方向的步骤包括：判断当前图像中识别出的特征线段是否满足预设的平行条件，若满足，则确定机器人的姿态与基于房间分隔体所构建的主方向一致，反之，则继续调整所述机器人的姿态并重复上述各步骤直至满足所述平行条件为止。其中，所述机器人的姿态与基于房间分隔体所构建的主方向一致包括机器人的当前姿态为面向某一房间分隔体、背离某一房间分隔体或沿某一房间分隔体。
在一些示例中，当所述控制装置所选择的特征线段组符合预设平行条件时，所述控制装置确定机器人的当前姿态为面向某一房间分隔体。其中，在一种更具体示例中，所述平行条件包括：所选择的特征线段组中的不在同一直线上的两条特征线段之间的间距误差小于等于预设的间距误差阈值。例如，控制装置计算所选择的特征线段组中任意两条特征线段的端点距离，若所计算的端点距离之间的误差小于所述间距误差阈值，则确定所选择的特征线段彼此平行，即确定在物理空间中机器人面向于某一房间分隔体，反之，则继续调整姿态。在另一种更具体示例中，所述平行条件包括所选择的特征线段组的消失点的位置落入预设的位置区域。例如，控制装置计算所选择的特征线段组的消失点坐标是否位于图像坐标系中预设的位置区域，该位置区域用于界定机器人的当前姿态与某一房间分隔体为大致垂直，若是，则确定所选择的特征线段彼此平行，即确定在物理空间中机器人面向于某一房间分隔体，反之，则继续调整姿态。
在确定了机器人沿基于房间分隔体所构建的主方向的情况下，控制机器人沿房间分隔体例如墙体构建的主方向移动可以包括控制机器人平行于墙体移动、控制机器人面向墙体移动、控制机器人背离墙体移动。
在另一些实施方式中，摄像装置垂直向上设置在机器人顶部，即摄像装置的光轴与机器人移动平面垂直的情况下，请参阅图5，图5显示为本申请控制方法在又一种实施方式中的流程图，如图所示，所述控制方法包括步骤S310-S340。
在步骤S310中，获取机器人移动期间所摄取的图像以及识别图像中的特征线段。其中，步骤S310与上述步骤S110相同或相似，在此不再详述。
在步骤S320中，统计从至少一幅图像中所识别的特征线段在预设图像坐标系中的倾斜角。
在此，由于在房间中各物体摆放及房间结构均基于房间分隔体所构建的主方向摆放，并且基于房间分隔体所构建的主方向彼此正交的特点，设置于机器人顶部且光轴与机器人移动平面垂直的摄像装置所摄取的图像也具有彼此正交的特征线段，因此，统计位于所述图像坐标系中各特征线段的倾斜角可便于找出彼此正交的特征线段及其倾斜角。
在一些实施例中，统计单幅图像中特征线段在预设图像坐标系中的倾斜角。例如，预设图像坐标系UOV，其中，以相机光轴与成像平面的交点作为图像坐标系的原点O、以彼此正交的两个方向作为图像坐标系的U轴和图像坐标系的V轴。针对图像中所识别出的特征线段，可获得特征线段在图像坐标系UOV中的相应坐标，以及每条特征线段在图像坐标系UOV中的倾斜角，然后对所获得的倾斜角进行统计以得到统计结果，该统计结果表示特征线段的角度分布。其中，倾斜角在0°至180°范围内。在一示例中，可以以波形图、直方图等方式示出统计结果，例如，在以波形图方式示出统计结果的情况下，假设以X轴表示图像中特征线段在图像坐标系UOV中的倾斜角数值大小，Y轴表示在相应倾斜角数值下特征线段的数量，绘制统计结果。
在另一些实施例中，为了提高对倾斜角统计的准确度，控制装置统计多幅图像中特征线段在预设图像坐标系中的倾斜角。
在此，为了避免因机器人姿态变化而改变特征线段在图像坐标系中的倾斜角，所述控制装置在机器人移动期间获取所摄取的相邻图像所对应的所述机器人的姿态变化。由于所述图像坐标系平行于机器人的移动平面，因此，所检测的姿态变化可用于将对应图像中特征线段的倾斜角进行回归补偿。因而，步骤S320包括在姿态调整的一时间段内，根据机器人摄取图像时所对应的旋转角度，对所摄取的至少两幅图像中各特征线段的倾斜角进行回归处理；以及统计回归处理后各特征线段在预设图像坐标系中的倾斜角。
其中，回归处理是指以机器人拍摄的其中一幅图像作为基准图像，以拍摄该基准图像时机器人的姿态(位置和角度)作为基准姿态，对其他幅图像中特征线段的倾斜角进行修正。以统计两幅图像中特征线段的倾斜角为例，机器人拍摄第一幅图像并对第一幅图像中的特征线段的倾斜角进行统计以获得第一统计结果，机器人调整姿态后拍摄第二幅图像并对第二幅图像中的特征线段的倾斜角进行统计以获得第二统计结果。基于此，以机器人拍摄第一幅图像时的姿态作为基准姿态，基于机器人拍摄第二幅图像时的姿态，可以借助于陀螺仪、VSLAM等方式获得机器人相对于基准姿态的旋转角度。然后，将所获得的旋转角度投影到图像坐标系中得到第二幅图像相对于第一幅图像的旋转角度，基于此对第二统计结果中包括的特征线段的倾斜角进行修正，使得第二幅图像中特征线段与第一幅图像中特征线段在图像坐标系内实现坐标统一，消除机器人旋转所带来的倾斜角偏差。最后，将第一统计结果和经过回归处理的第二统计结果进行整体统计，以获得各特征线段在图像坐标系中的倾斜角的统计结果。
在步骤S330中，根据所统计的倾斜角确定机器人与房间分隔体在物理空间中相对的方位关系。
当控制装置对至少一幅图像中的特征线段进行统计后，所述控制装置可得到至少一个统 计峰值区间，并将所得到的统计峰值区间对应的倾斜角作为机器人与房间分隔体在物理空间中相对的方位关系。在此，基于统计结果可获得峰值区间，所述峰值区间表示峰值区间内对应的倾斜角下特征线段的数量最多，而特征线段数量最多表示这些特征线段所在的方向代表基于房间分隔体所构建的主方向。因而，在某些实施例中，根据所统计的位于峰值区间的倾斜角，确定机器人与房间分隔体在物理空间中相对的方位关系。在此，所述方位关系包括机器人与待面向某一房间分隔体之间的偏角区间和旋转方向。例如，按照预设图像坐标系的UV轴射线方向确定所统计的峰值区间为41°±1°，所述控制装置确定机器人位于待面向某一房间分隔体的逆时针方向，且与该房间分隔体呈41°±1°的偏角区间。
需要说明的是，基于图像识别误差、统计误差等，峰值区间内对应的倾斜角可以是在一定误差范围内的倾斜角区间。基于此，在一种示例中，以倾斜角区间中的平均倾斜角作为表征方位关系的倾斜角。
请参阅图6，图6显示为本申请特征线段和倾斜角的统计结果在一种实施方式中的波形图，如图所示，X轴表示图像中特征线段的倾斜角，Y轴表示特征线段的数量，图中示出存在一最大的峰值区间的情况，由所述峰值区间的倾斜角对应的特征线段即表示基于房间分隔体所构建的主方向，如平行于墙体方向或垂直于墙体方向，因而，机器人与房间分隔体在物理空间中相对的方位关系可由机器人与房间分隔体之间的夹角即峰值区间对应的倾斜角来表征。例如，假设峰值区间对应的倾斜角为45°，即表示机器人行进方向与墙体方向之间的夹角为45°。
请参阅图7，图7显示为本申请特征线段和倾斜角的统计结果在另一种实施方式中的波形图，如图所示，X轴表示图像中特征线段的倾斜角，Y轴表示特征线段的数量，图中示出存在两个最大峰值区间的情况，根据实际情况，所述两个峰值区间对应的两个倾斜角理论上应互成90°，则其对应的特征线段分别表示平行于墙体的方向和垂直于墙体的方向。因而，一方面，机器人与房间分隔体在物理空间中相对的方位关系可由机器人与房间分隔体之间的夹角即任一峰值区间对应的倾斜角来表征，另一方面，还可以通过两个峰值区间对应的两个倾斜角之间的差是否在“90°±σ”的范围内(其中，σ表示误差)来进一步验证所获得的两个峰值区间对应的特征线段是否分别表征平行于墙体和垂直于墙体的方向。例如，假设一峰值区间对应的倾斜角为30°，则另一峰值区间对应的角度应为120°±σ，即表示机器人行进方向与墙体方向之间的夹角为30°或120°±σ。
在步骤S340中，根据倾斜角及机器人的当前姿态，调整机器人的姿态。
在此，控制装置基于统计获得的倾斜角度以及机器人的当前姿态，控制机器人按照相应倾斜角度和旋转方向进行旋转，使得机器人的行进方向平行于或垂直于房间分隔体，进而控 制机器人沿上述主方向面向或背离房间分隔体移动。
按照上述各示例调整机器人姿态的方式，控制装置还执行在确定在物理空间中所述机器人沿基于房间分隔体所构建的主方向时，基于当前位置规划导航路线的步骤。
其中，所述导航路线可以包括：机器人向房间分隔体移动的第一路线，以及自第一路线的终点开始遍历一预设区域的第二路线。其中，所述预设区域例如清洁机器人的清扫区域，巡逻机器人的巡逻区域等。
以清洁机器人为例，则基于房间分隔体所构建的主方向可以为互相垂直的第一墙面和第二墙面，在确定了清洁机器人沿基于房间分隔体所构建的主方向的情况下，设置清洁机器人沿所述主方向移动直至接触房间分隔体，例如，设置清洁机器人面向或背离第一墙面移动，直至接触第一墙面或接触平行于第一墙面的另一墙面，或者，设置清洁机器人沿着第一墙面移动，直至接触与第一墙面垂直的第二墙面。然后，以清洁机器人当前位置作为起点，采用“弓”字形或“之”字形等路线规划清洁机器人在清扫区域移动，使得清洁机器人在作业期间尽可能全面覆盖待清洁区域，提高清洁效率。
本申请还提供一种机器人的控制装置，请参阅图8，图8显示为本申请机器人的控制装置在一种实施方式中的结构示意图，如图所示，机器人的控制装置包括存储单元11和处理单元12。
存储单元11用于存储至少一个程序以及由摄像装置所摄取的图像。存储单元11可包括高速随机存取存储器，并且还可包括非易失性存储器，例如一个或多个磁盘存储设备、闪存设备或其他非易失性固态存储设备。存储单元11还包括存储器控制器可控制设备的诸如CPU和外设接口之类的其他组件对存储器的访问。存储单元11中所保存的程序包括稍后描述的由处理单元调用以执行控制方法的相关程序。
处理单元12可操作地与存储单元等耦接。此外，处理单元还可操作地耦接至电源，该电源可向控制主板中的各种部件提供电力。如此，电源可包括任何合适的能源，诸如可再充电的锂聚合物(Li-poly)电池和/或交流电(AC)电源转换器。
处理单元12用于调用所述至少一个程序并执行如上任一所述的控制方法。其中，处理单元12与存储单元11进行数据通信。处理单元12可执行在存储单元中存储的指令以在机器人中执行操作。处理单元执行控制方法的具体实现方式如图1至图7及其相应描述所示，在此不再赘述。
本申请还提供一种机器人，所述机器人包括但不限于清洁机器人、巡逻机器人、家庭陪伴机器人等。所述机器人执行上述控制方法。请参阅图9，图9显示为本申请机器人在一种实施方式中的结构示意图，如图所示，机器人包括摄像装置21、移动装置22以及控制装置 23。
摄像装置21用于在机器人移动期间摄取图像。在一实施例中，控制装置可以预先设定摄像装置拍摄图像的时间间隔，然后控制装置获取经摄像装置以预设时间间隔拍摄的不同时刻下的静态图像。在另一实施例中，摄像装置可以拍摄视频，由于视频是由图像帧构成的，因此控制装置首先可以连续或不连续地采集所获取的视频中的图像帧，然后控制装置选用一帧图像作为一幅图像。所述摄像装置包括但不限于：照相机、视频摄像机、集成有光学系统或CCD芯片的摄像模块、集成有光学系统和CMOS芯片的摄像模块等。所述摄像装置的供电系统可受移动机器人的供电系统控制，所述摄像装置摄取移动机器人移动期间所途经路线的图像。
移动装置22用于按照所接收的控制指令调整机器人的姿态。其中，移动装置22在控制装置23的控制下调整移动距离、移动方向和移动速度、移动加速度等。
在某些实施例中，移动装置22包括驱动单元和至少两个滚轮组。其中，所述至少两个滚轮组中的至少一个滚轮组为受控滚轮组。所述驱动单元与所述处理装置相连，所述驱动单元用于基于所述处理装置输出的移动控制指令驱动所述受控滚轮组滚动。
所述驱动单元包含驱动电机，所述驱动电机与所述滚轮组相连用于直接驱动滚轮组滚动。所述驱动单元可以包含专用于控制驱动电机的一个或多个处理器(CPU)或微处理单元(MCU)。例如，所述微处理单元用于将所述处理装置所提供的信息或数据转化为对驱动电机进行控制的电信号，并根据所述电信号控制所述驱动电机的转速、转向等以调整移动机器人的移动速度和移动方向。所述信息或数据如所述处理装置所确定的偏角。所述驱动单元中的处理器可以和所述处理装置中的处理器共用或可独立设置。例如，所述驱动单元作为从处理设备，所述处理装置作为主设备，驱动单元基于处理装置的控制进行移动控制。或者所述驱动单元与所述处理装置中的处理器相共用。驱动单元通过程序接口接收处理装置所提供的数据。所述驱动单元用于基于所述处理装置所提供的移动控制指令控制所述受控滚轮组滚动。
控制装置23与摄像装置21和移动装置22进行数据通信。控制装置23可以包括一个或多个处理器。所述处理器可包括一个或多个通用微处理器、一个或多个专用处理器(ASIC)、一个或多个数字信号处理器(DSP)、一个或多个现场可编程逻辑阵列(FPGA)、或它们的任何组合。所述控制装置还与I/O端口和输入结构可操作地耦接，该I/O端口可使得机器人能够与各种其他电子设备进行交互，该输入结构可使得用户能够与计算设备进行交互。因此，输入结构可包括按钮、键盘、鼠标、触控板等。所述其他电子设备可以是所述机器人中移动装置中的移动电机，或机器人中专用于控制移动装置的从处理器，如MCU (Microcontroller Unit，微控制单元，简称MCU)。
在一种示例中，所述控制装置通过数据线分别连接摄像装置和移动装置。所述控制装置通过接口协议与摄像装置、移动装置进行交互。其中，所述数据读写技术包括但不限于：高速/低速数据接口协议、数据库读写操作等。所述接口协议包括但不限于：HDMI接口协议、串行接口协议等。
控制装置23获取摄像装置21所摄取的图像以及识别所述图像中的特征线段。
在此，机器人的控制装置获取摄像装置在机器人移动期间所摄取的图像，然后利用图像处理技术识别图像中的特征线段。其中，所述特征线段为直线线段。
在一些实施例中，所述控制装置可以采用下述方式识别图像中的特征线段：首先，从所获取的图像中提取物体的轮廓特征。其中，可通过轮廓线提取方法提取轮廓特征，所述轮廓线提取方法包括但不限于：二值、灰度、canny算子等方法。然后，从所提取的轮廓特征中提取特征线段。其中，可通过霍夫变换来提取特征线段。其中，所述特征线段包括但不限于以下特征：直度和/或长度特征等。例如，当图像中所识别的相邻特征点连线的直度大于预设直度阈值，和/或其长度大于预设长度阈值时，可判定该特征点的连线为特征线段。在一示例中，所述控制装置基于物体轮廓线截取不连续的多条直线线段作为特征线段以进行后续处理。在另一示例中，所述控制装置将基于物体轮廓线所提取的轮廓特征进行分段，再从分段后的轮廓特征中提取特征线段。如此便于保留更多的特征线段。
需要说明的是，所述物体轮廓应宽泛理解，其包括但不限于摆放在房间中的物体的轮廓，还包括房间中墙与墙之间、墙与屋顶之间、墙与门窗之间的交界线等。请参阅图2和图3，其中，图2显示为通过摄像装置所获取的图像的示意图，图3显示为基于图2中的图像所识别出的轮廓特征的示意图。
还需要说明的是，所述控制装置还可以采用如神经网络算法来识别特征线段。在此不对识别特征线段的方式进行限制。
接着，控制装置根据所识别出的特征线段确定机器人与房间分隔体在物理空间中相对的方位关系。
其中，房间分隔体是指在机器人所处应用场景中用于分隔应用空间的立面。以清洁机器人为例，在清洁机器人处于室内场景时，所述房间分隔体是指用于分隔室内空间的立面，如墙面、隔断、落地窗、天花板等。因而，例如，机器人与房间分隔体在物理空间中相对的方位关系可以表示为机器人的行进方向与墙面所构建的方向之间相对的方位关系。在某些实施例中，机器人与房间分隔体之间的方位关系可由机器人的行进方向与房间分隔体所限定的平面之间的夹角来表征。例如，所述夹角反映机器人行进方向与墙面的相对方位关系为平行、 垂直相交或非垂直相交。
所述控制装置基于所识别的特征线段，来确定机器人当前面向(或背离)墙面移动、沿墙面移动、或与墙面具有0°到90°之间夹角的方位关系。这是由于为充分利用室内空间，室内物体基本根据房间隔离体所构建的主方向进行摆放，例如，书桌、床、衣柜、鞋柜等不易移动的物体均根据房间隔离体所构建的主方向进行摆放，这使得实际物理空间中的摆放特征可藉由图像反映出来，因此根据室内的物体、房间隔离体等所呈现的方位特征，所述控制装置对所识别的特征线段进行分析，得到所述机器人与房间分隔体在物理空间中相对的方位关系。
然后，控制装置根据方位关系调整机器人的姿态，使得在物理空间中机器人沿基于房间分隔体所构建的主方向移动。
在此，所述调整机器人的姿态主要指调整机器人与基于房间分隔体所构建的主方向之间的角度关系，当根据方位关系确定机器人以沿着、面向、或背离基于房间分隔体所构建的主方向，则完成机器人的姿态调整。
在某些实施例中，所述控制装置根据所识别特征线段在实际物理空间中的夹角以及机器人的当前姿态，控制机器人旋转一角度，以实现机器人与房间分隔体平行或垂直。在另一些实施例中，可以依据预设的角度和方向不断调整机器人旋转，并在旋转期间重复上述步骤，直至根据所识别出的特征线段满足预设条件，以确认机器人与房间分隔体大致平行或垂直为止。其中，所述预设条件是基于特征线段所反映的机器人与主方向的方位关系而设置的。
机器人按照大致平行于或垂直于房间分隔体的行进方向进行移动。例如，控制装置在确定清洁机器人面向一墙面后，控制清洁机器人移动至墙边，并按弓字形移动。
本申请的机器人，通过控制装置基于获取的图像中的特征线段来确定机器人与房间分隔体之间的方位关系，使得机器人能够基于所述方位关系将其姿态调整至沿基于房间分隔体所构建的主方向移动，提高了移动覆盖率。
基于上述技术思想并结合实际摄像装置在机器人的摆放角度，所述控制装置可采用与摄像装置的摆放角度相关的实现方式来确定所述机器人与房间分隔体在物理空间中相对的方位关系以及进行姿态调整。
在一些实施方式中，摄像装置21设置在机器人体侧，即摄像装置21的光轴与机器人移动平面的夹角在0°至90°之间的情况下，摄像装置21在机器人移动期间摄取图像并提供给控制装置23，控制装置23识别所述图像中的特征线段。
接着，控制装置23基于所识别出的多条特征线段的消失点对各条特征线段进行分组。
在此，由于摄像装置的光轴与主方向具有0°至90°的夹角，因此，所拍摄的图像中平 行线条具有消失点线性特征。其中，所述消失点线性特征是指两条或多条代表平行线线条向远处地平线(HORIZON LINE)伸展直至聚合的那一点。在计算机视觉领域中，图像中具有共同消失点的直线对应于空间中的平行线，也就是说，空间中的平行线对应在图像视角中是相交的线，这些相交的线在具有共同消失点的情况下代表空间中的多组平行线。
所述控制装置以图像所在图像坐标系对所识别出的各特征线段延长处理以得到各特征线段的消失点。例如，所述控制装置利用各特征线段在图像坐标系中的倾斜角计算任意两特征线段的交汇点，并对各交汇点进行聚类处理以将位置相近的交汇点归类为一个消失点。
在所识别的多个特征线段中，所得到的消失点的数量通常为多个，本申请中基于所识别出的多条特征线段所对应的消失点在图像坐标系中的不同坐标位置，将相交于同一消失点的特征线段分为一组。
然后，控制装置23从所分组的特征线段中选取至少一组特征线段。
由于房间内的大部分物体按照房间分隔体所构建的主方向进行摆放，因此，图像中各分组中特征线段的数量能够反映基于房间分隔体所构建的主方向。例如，消失点对应的特征线段数量越多，表示相应分组的特征线段在物理空间中的方向是基于房间分隔体所构建的主方向的可能性越大。鉴于此，在某些实施例中，从所分组的特征线段中选取特征线段数量最多的一组特征线段，该组特征线段代表基于房间分隔体所构建的主方向。
需要说明的是，所得到的特征线段的数量最多的分组并非一定仅为一个，可选择数量最多的多个分组的特征线段或随机选择其中一组特征线段执行步骤S240。
接下来，控制装置23根据所选择的特征线段组的消失点在图像坐标系中的位置确定机器人与房间分隔体在物理空间中相对的方位关系。
其中，所选择的特征线段组代表基于房间分隔体所构建的主方向。例如所选择的特征线段组代表沿平行于一墙体或垂直于一墙体方向设置的物体的轮廓线或房间的交界线。
在此，当在物理空间中机器人与待面向的某一房间分隔体A具有一定偏角的方位关系，平行于该房间分隔体A的多条直线反映在图像中，即为具有同一消失点的特征线段，根据包含所述偏角的方位关系(例如机器人逆时针偏转地面向某一房间分隔体A，或者机器人顺时针偏转地面向某一房间分隔体A)，相应的消失点将位于图像坐标系的某一象限或者与预设中心点相距预设距离之内的区域中。基于上述方位关系与消失点在图像坐标系中位置的对应关系，所述控制装置通过分析消失点在图像坐标系中的位置确定机器人与房间分隔体A在物理空间中相对的方位关系。例如，以垂直于摄像装置的光轴的平面构建的图像坐标系，其中，光轴所在位置为坐标原点，若所选择的特征线段组的消失点位于坐标系左侧，则机器人与待面向的房间分隔体A的方位关系为逆时针偏转。其中，所述方位关系为粗略的，并非一定能 够确定机器人与待面向的房间分隔体之间的精准偏角值。
最后，控制装置23根据方位关系调整机器人的姿态。
在此，控制装置23根据方位关系并以预设角度步长控制移动装置22的旋转方向和旋转角度以进行逐步调整。
每控制机器人旋转一单位角度时，获取摄像装置所拍摄的图像，并重复执行上述步骤，直至确定机器人与房间分隔体大致平行或垂直，即，满足用于确定机器人沿基于房间分隔体所构建的主方向的预设条件。其中，当机器人面向或背离某一房间分隔体时，或者当机器人沿某一房间分隔体时，所选择分组的特征线段被认为是房间内平行于或垂直于该房间分隔体的直线在图像中的映射。所述预设条件可基于所选择分组的特征线段的消失点在图像坐标系中的位置坐标而预先设置；还可以设置用于评价所选择分组的特征线段的平行度的条件参数。
在某些实施例中，确定机器人沿基于房间分隔体所构建的主方向的步骤包括：判断当前图像中识别出的特征线段是否满足预设的平行条件，若满足，则确定机器人的姿态与基于房间分隔体所构建的主方向一致，反之，则继续调整所述机器人的姿态并重复上述各步骤直至满足所述平行条件为止。其中，所述机器人的姿态与基于房间分隔体所构建的主方向一致包括机器人的当前姿态为面向某一房间分隔体、背离某一房间分隔体或沿某一房间分隔体。
在一些示例中，当所述控制装置所选择的特征线段组符合预设平行条件时，所述控制装置确定机器人的当前姿态为面向某一房间分隔体。其中，在一种更具体示例中，所述平行条件包括：所选择的特征线段组中的不在同一直线上的两条特征线段之间的间距误差小于等于预设的间距误差阈值。例如，控制装置计算所选择的特征线段组中任意两条特征线段的端点距离，若所计算的端点距离之间的误差小于所述间距误差阈值，则确定所选择的特征线段彼此平行，即确定在物理空间中机器人面向于某一房间分隔体，反之，则继续调整姿态。在另一种更具体示例中，所述平行条件包括所选择的特征线段组的消失点的位置落入预设的位置区域。例如，控制装置计算所选择的特征线段组的消失点坐标是否位于图像坐标系中预设的位置区域，该位置区域用于界定机器人的当前姿态与某一房间分隔体为大致垂直，若是，则确定所选择的特征线段彼此平行，即确定在物理空间中机器人面向于某一房间分隔体，反之，则继续调整姿态。
在确定了机器人沿基于房间分隔体所构建的主方向的情况下，控制机器人沿房间分隔体例如墙体构建的主方向移动可以包括控制机器人平行于墙体移动、控制机器人面向墙体移动、控制机器人背离墙体移动。
在另一些实施方式中，摄像装置21垂直向上设置在机器人顶部，即摄像装置21的光轴与机器人移动平面垂直的情况下，摄像装置21在机器人移动期间摄取图像并提供给控制装置 23，控制装置23识别所述图像中的特征线段。
接着，控制装置23统计从至少一幅图像中所识别的特征线段在预设图像坐标系中的倾斜角。
在此，由于在房间中各物体摆放及房间结构均基于房间分隔体所构建的主方向摆放，并且基于房间分隔体所构建的主方向彼此正交的特点，设置于机器人顶部且光轴与机器人移动平面垂直的摄像装置所摄取的图像也具有彼此正交的特征线段，因此，统计位于所述图像坐标系中各特征线段的倾斜角可便于找出彼此正交的特征线段及其倾斜角。
在一些实施例中，统计单幅图像中特征线段在预设图像坐标系中的倾斜角。例如，预设图像坐标系UOV，其中，以相机光轴与成像平面的交点作为图像坐标系的原点O、以彼此正交的两个方向作为图像坐标系的U轴和图像坐标系的V轴。针对图像中所识别出的特征线段，可获得特征线段在图像坐标系UOV中的相应坐标，以及每条特征线段在图像坐标系UOV中的倾斜角，然后对所获得的倾斜角进行统计以得到统计结果，该统计结果表示特征线段的角度分布。其中，倾斜角在0°至180°范围内。在一示例中，可以以波形图、直方图等方式示出统计结果，例如，在以波形图方式示出统计结果的情况下，假设以X轴表示图像中特征线段在图像坐标系UOV中的倾斜角数值大小，Y轴表示在相应倾斜角数值下特征线段的数量，绘制统计结果。
在另一些实施例中，为了提高对倾斜角统计的准确度，控制装置统计多幅图像中特征线段在预设图像坐标系中的倾斜角。
在此，为了避免因机器人姿态变化而改变特征线段在图像坐标系中的倾斜角，所述控制装置在机器人移动期间获取所摄取的相邻图像所对应的所述机器人的姿态变化。由于所述图像坐标系平行于机器人的移动平面，因此，所检测的姿态变化可用于将对应图像中特征线段的倾斜角进行回归补偿。因而，在姿态调整的一时间段内，根据机器人摄取图像时所对应的旋转角度，机器人需对所摄取的至少两幅图像中各特征线段的倾斜角进行回归处理；以及统计回归处理后各特征线段在预设图像坐标系中的倾斜角。
其中，回归处理是指以机器人拍摄的其中一幅图像作为基准图像，以拍摄该基准图像时机器人的姿态(位置和角度)作为基准姿态，对其他幅图像中特征线段的倾斜角进行修正。以统计两幅图像中特征线段的倾斜角为例，机器人拍摄第一幅图像并对第一幅图像中的特征线段的倾斜角进行统计以获得第一统计结果，机器人调整姿态后拍摄第二幅图像并对第二幅图像中的特征线段的倾斜角进行统计以获得第二统计结果。基于此，以机器人拍摄第一幅图像时的姿态作为基准姿态，基于机器人拍摄第二幅图像时的姿态，可以借助于陀螺仪、VSLAM等方式获得机器人相对于基准姿态的旋转角度。然后，将所获得的旋转角度投影到 图像坐标系中得到第二幅图像相对于第一幅图像的旋转角度，基于此对第二统计结果中包括的特征线段的倾斜角进行修正，使得第二幅图像中特征线段与第一幅图像中特征线段在图像坐标系内实现坐标统一，消除机器人旋转所带来的倾斜角偏差。最后，将第一统计结果和经过回归处理的第二统计结果进行整体统计，以获得各特征线段在图像坐标系中的倾斜角的统计结果。
然后，控制装置23根据所统计的倾斜角确定机器人与房间分隔体在物理空间中相对的方位关系。
当控制装置对至少一幅图像中的特征线段进行统计后，所述控制装置可得到至少一个统计峰值区间，并将所得到的统计峰值区间对应的倾斜角作为机器人与房间分隔体在物理空间中相对的方位关系。在此，基于统计结果可获得峰值区间，所述峰值区间表示峰值区间内对应的倾斜角下特征线段的数量最多，而特征线段数量最多表示这些特征线段所在的方向代表基于房间分隔体所构建的主方向。因而，在某些实施例中，根据所统计的位于峰值区间的倾斜角，确定机器人与房间分隔体在物理空间中相对的方位关系。在此，所述方位关系包括机器人与待面向某一房间分隔体之间的偏角区间和旋转方向。例如，按照预设图像坐标系的UV轴射线方向确定所统计的峰值区间为41°±1°，所述控制装置确定机器人位于待面向某一房间分隔体的逆时针方向，且与该房间分隔体呈41°±1°的偏角区间。
需要说明的是，基于图像识别误差、统计误差等，峰值区间内对应的倾斜角可以是在一定误差范围内的倾斜角区间。基于此，在一种示例中，以倾斜角区间中的平均倾斜角作为表征方位关系的倾斜角。
请参阅图6，图6显示为本申请特征线段和倾斜角的统计结果在一种实施方式中的波形图，如图所示，X轴表示图像中特征线段的倾斜角，Y轴表示特征线段的数量，图中示出存在一最大的峰值区间的情况，由所述峰值区间的倾斜角对应的特征线段即表示基于房间分隔体所构建的主方向，如平行于墙体方向或垂直于墙体方向，因而，机器人与房间分隔体在物理空间中相对的方位关系可由机器人与房间分隔体之间的夹角即峰值区间对应的倾斜角来表征。例如，假设峰值区间对应的倾斜角为45°，即表示机器人行进方向与墙体方向之间的夹角为45°。
请参阅图7，图7显示为本申请特征线段和倾斜角的统计结果在另一种实施方式中的波形图，如图所示，X轴表示图像中特征线段的倾斜角，Y轴表示特征线段的数量，图中示出存在两个最大峰值区间的情况，根据实际情况，所述两个峰值区间对应的两个倾斜角理论上应互成90°，则其对应的特征线段分别表示平行于墙体的方向和垂直于墙体的方向。因而，一方面，机器人与房间分隔体在物理空间中相对的方位关系可由机器人与房间分隔体之间的 夹角即任一峰值区间对应的倾斜角来表征，另一方面，还可以通过两个峰值区间对应的两个倾斜角之间的差是否在“90°±σ”的范围内(其中，σ表示误差)来进一步验证所获得的两个峰值区间对应的特征线段是否分别表征平行于墙体和垂直于墙体的方向。例如，假设一峰值区间对应的倾斜角为30°，则另一峰值区间对应的角度应为120°±σ，即表示机器人行进方向与墙体方向之间的夹角为30°或120°±σ。
最后，控制装置23根据倾斜角及机器人的当前姿态，调整机器人的姿态。
在此，控制装置基于统计获得的倾斜角度以及机器人的当前姿态，控制机器人按照相应倾斜角度和旋转方向进行旋转，使得机器人的行进方向平行于或垂直于房间分隔体，进而控制机器人沿上述主方向面向或背离房间分隔体移动。
按照上述各示例调整机器人姿态的方式，控制装置还执行在确定在物理空间中所述机器人沿基于房间分隔体所构建的主方向时，基于当前位置规划导航路线的步骤。
其中，所述导航路线可以包括：机器人向房间分隔体移动的第一路线，以及自第一路线的终点开始遍历一预设区域的第二路线。其中，所述预设区域例如清洁机器人的清扫区域，巡逻机器人的巡逻区域等。
以清洁机器人为例，则基于房间分隔体所构建的主方向可以为互相垂直的第一墙面和第二墙面，在确定了清洁机器人沿基于房间分隔体所构建的主方向的情况下，设置清洁机器人沿所述主方向移动直至接触房间分隔体，例如，设置清洁机器人面向或背离第一墙面移动，直至接触第一墙面或接触平行于第一墙面的另一墙面，或者，设置清洁机器人沿着第一墙面移动，直至接触与第一墙面垂直的第二墙面。然后，以清洁机器人当前位置作为起点，采用“弓”字形或“之”字形等路线规划清洁机器人在清扫区域移动，使得清洁机器人在作业期间尽可能全面覆盖待清洁区域，提高清洁效率。
本申请还提供一种机器人的控制系统，请参阅图10，图10显示为本申请机器人的控制系统在一种实施方式中的结构示意图，如图所示，控制系统包括图像处理模块31、方位计算模块32以及控制模块33。
其中，图像处理模块31用于获取机器人移动期间所摄取的图像以及识别图像中的特征线段。方位计算模块32用于根据所识别出的特征线段确定机器人与房间分隔体在物理空间中相对的方位关系。控制模块33用于根据方位关系调整机器人的姿态，使得在物理空间中机器人沿基于房间分隔体所构建的主方向移动。
基于上述技术思想并结合实际摄像装置在机器人的摆放角度，所述控制装置可采用与摄像装置的摆放角度相关的实现方式来确定所述机器人与房间分隔体在物理空间中相对的方位关系以及进行姿态调整。
在一些实施方式中，摄像装置设置在机器人体侧，即摄像装置的光轴与机器人移动平面的夹角在0°至90°之间的情况下，方位计算模块32包括第一方位计算单元，第一方位计算单元用于基于所识别出的多条特征线段的消失点对各条特征线段进行分组；从所分组的特征线段中选取至少一组特征线段；根据所选择的特征线段组的消失点在图像坐标系中的位置确定机器人与房间分隔体在物理空间中相对的方位关系。
在另一些实施方式中，摄像装置垂直向上设置在机器人顶部，即摄像装置的光轴与机器人移动平面垂直的情况下，方位计算模块32包括第二方位计算单元用于统计从至少一幅图像中所识别的特征线段在预设图像坐标系中的倾斜角；根据所统计的倾斜角确定机器人与房间分隔体在物理空间中相对的方位关系。
此外，控制模块33还包括导航路线规划单元，用于在确定在物理空间中机器人沿基于房间分隔体所构建的主方向时，基于当前位置规划导航路线。
在此，本申请控制系统中各模块的工作方式与上述控制方法中对应步骤相同或相似，在此不再赘述。
需要说明的是，应理解图10实施例中装置的各个模块的划分仅仅是一种逻辑功能的划分，实际实现时可以全部或部分集成到一个物理实体上，也可以物理上分开。且这些模块可以全部以软件通过处理元件调用的形式实现；也可以全部以硬件的形式实现；还可以部分模块通过处理元件调用软件的形式实现，部分模块通过硬件的形式实现。例如，每个模块可以为单独设立的处理元件，也可以集成在上述装置的某一个芯片中实现，此外，也可以以程序代码的形式存储于上述装置的存储器中，由上述装置的某一个处理元件调用并执行以上接收模块的功能。其它模块的实现与之类似。此外这些模块全部或部分可以集成在一起，也可以独立实现。这里所述的处理元件可以是一种集成电路，具有信号的处理能力。在实现过程中，上述方法的各步骤或以上各个模块可以通过处理器元件中的硬件的集成逻辑电路或者软件形式的指令完成。
例如，以上这些模块可以是被配置成实施以上方法的一个或多个集成电路，例如：一个或多个特定集成电路(ApplicationSpecificIntegratedCircuit，简称ASIC)，或，一个或多个微处理器(digitalsingnalprocessor，简称DSP)，或，一个或者多个现场可编程门阵列(FieldProgrammableGateArray，简称FPGA)等。再如，当以上某个模块通过处理元件调度程序代码的形式实现时，该处理元件可以是通用处理器，例如中央处理器(CentralProcessingUnit，简称CPU)或其它可以调用程序代码的处理器。再如，这些模块可以集成在一起，以片上系统(system-on-a-chip，简称SOC)的形式实现。
另外需要说明的是，通过以上的实施方式的描述，本领域的技术人员可以清楚地了解到 本申请的部分或全部可借助软件并结合必需的通用硬件平台来实现。基于这样的理解，本申请还提供一种计算机存储介质，所述存储介质存储有至少一个程序，所述程序在被调用时执行前述的任一所述的控制方法。需说明的是，所述计算机程序代码可以为源代码形式、对象代码形式、可执行文件或某些中间形式等。
基于这样的理解，本申请的技术方案本质上或者说对现有技术做出贡献的部分可以以软件产品的形式体现出来，该计算机软件产品可包括其上存储有机器可执行指令的一个或多个机器可读介质，这些指令在由诸如计算机、计算机网络或其他电子设备等一个或多个机器执行时可使得该一个或多个机器根据本申请的实施例来执行操作。例如执行机器人的定位方法中的各步骤等。机器可读介质可包括，但不限于，能够携带所述计算机程序代码的任何实体或装置、记录介质、U盘、移动硬盘、磁碟、光盘、计算机存储器、软盘、光盘、CD-ROM(紧致盘-只读存储器)、磁光盘、ROM(只读存储器)、RAM(随机存取存储器)、EPROM(可擦除可编程只读存储器)、EEPROM(电可擦除可编程只读存储器)、磁卡或光卡、闪存、电载波信号、电信信号以及软件分发介质或适于存储机器可执行指令的其他类型的介质/机器可读介质。需要说明的是，所述计算机可读介质包含的内容可以根据司法管辖区内立法和专利实践的要求进行适当的增减，例如在某些司法管辖区，根据立法和专利实践，计算机可读介质不包括电载波信号和电信信号。其中，所述存储介质可位于机器人也可位于第三方服务器中，如位于提供某应用商城的服务器中。在此对具体应用商城不做限制，如小米应用商城、华为应用商城、苹果应用商城等。
本申请可用于众多通用或专用的计算系统环境或配置中。例如：个人计算机、服务器计算机、手持设备或便携式设备、平板型设备、多处理器系统、基于微处理器的系统、置顶盒、可编程的消费电子设备、网络PC、小型计算机、大型计算机、包括以上任何系统或设备的分布式计算环境等。
本申请可以在由计算机执行的计算机可执行指令的一般上下文中描述，例如程序模块。一般地，程序模块包括执行特定任务或实现特定抽象数据类型的例程、程序、对象、组件、数据结构等等。也可以在分布式计算环境中实践本申请，在这些分布式计算环境中，由通过通信网络而被连接的远程处理设备来执行任务。在分布式计算环境中，程序模块可以位于包括存储设备在内的本地和远程计算机存储介质中。
上述实施例仅例示性说明本申请的原理及其功效，而非用于限制本申请。任何熟悉此技术的人士皆可在不违背本申请的精神及范畴下，对上述实施例进行修饰或改变。因此，举凡所属技术领域中具有通常知识者在未脱离本申请所揭示的精神与技术思想下所完成的一切等效修饰或改变，仍应由本申请的权利要求所涵盖。

Claims (31)

  1. 一种机器人的控制方法，其特征在于，包括：
    获取机器人移动期间所摄取的图像以及识别所述图像中的特征线段；
    根据所识别出的特征线段确定所述机器人与房间分隔体在物理空间中相对的方位关系；
    根据所述方位关系调整所述机器人的姿态，使得在物理空间中所述机器人沿基于房间分隔体所构建的主方向移动。
  2. 根据权利要求1所述的控制方法，其特征在于，所述根据所识别出的特征线段确定所述机器人与房间分隔体在物理空间中相对的方位关系的步骤包括：
    基于所识别出的多条特征线段的消失点对各条特征线段进行分组；
    从所分组的特征线段中选取至少一组特征线段；
    根据所选择的特征线段组的消失点在图像坐标系中的位置确定所述机器人与房间分隔体在物理空间中相对的方位关系。
  3. 根据权利要求2所述的控制方法，其特征在于，所述从所分组的特征线段中选取至少一组特征线段的步骤包括：选取特征线段数量最多的一组特征线段。
  4. 根据权利要求2所述的控制方法，其特征在于，所述根据方位关系调整所述机器人的姿态的步骤包括：
    根据所述方位关系并以预设角度步长调整所述机器人的姿态；以及
    重复上述各步骤直至满足用于确定所述机器人沿基于房间分隔体所构建的主方向的预设条件。
  5. 根据权利要求4所述的控制方法，其特征在于，所述确定机器人沿基于房间分隔体所构建的主方向的步骤包括：
    判断当前图像中识别出的特征线段是否满足预设的平行条件，若满足所述平行条件则确定所述机器人的姿态与基于房间分隔体所构建的主方向一致，反之，则继续调整所述机器人的姿态并重复上述各步骤直至满足所述平行条件为止。
  6. 根据权利要求5所述的控制方法，其特征在于，所述平行条件包括以下至少一种：不在同一直线上的两条特征线段之间的间距误差小于等于预设的间距误差阈值，所选择的特征线 段组的消失点的位置落入预设的位置区域。
  7. 根据权利要求1所述的控制方法，其特征在于，所获取的图像是由与机器人移动平面垂直设置的摄像装置摄取的，所述根据所识别出的特征线段确定所述机器人与房间分隔体在物理空间中相对的方位关系的步骤包括：
    统计从至少一幅图像中所识别的特征线段在预设图像坐标系中的倾斜角；
    根据所统计的倾斜角确定所述机器人与房间分隔体在物理空间中相对的方位关系。
  8. 根据权利要求7所述的控制方法，其特征在于，所述统计从至少一幅图像中所识别的特征线段在预设图像坐标系中的倾斜角的步骤包括以下任一种：
    统计单幅图像中特征线段在预设图像坐标系中的倾斜角；
    在姿态调整的一时间段内，根据机器人摄取图像时所对应的旋转角度，对所摄取的至少两幅图像中各特征线段的倾斜角进行回归处理；以及统计回归处理后各特征线段在预设图像坐标系中的倾斜角。
  9. 根据权利要求7所述的控制方法，其特征在于，所述根据所统计的倾斜角确定所述机器人与房间分隔体在物理空间中相对的方位关系的步骤包括：
    根据所统计的位于峰值区间的倾斜角，确定所述机器人与房间分隔体在物理空间中相对的方位关系。
  10. 根据权利要求7所述的控制方法，其特征在于，所述根据方位关系调整所述机器人的姿态的步骤包括：
    根据所述倾斜角和机器人的当前姿态，调整所述机器人的姿态。
  11. 根据权利要求1所述的控制方法，其特征在于，还包括：在确定在物理空间中所述机器人沿基于房间分隔体所构建的主方向时，基于当前位置规划导航路线。
  12. 根据权利要求11所述的控制方法，其特征在于，所述导航路线包括：所述机器人向所述房间分隔体移动的第一路线，以及自所述第一路线的终点开始遍历一预设区域的第二路线。
  13. 一种机器人的控制装置，其特征在于，包括：
    存储单元，用于存储至少一个程序以及由摄像装置所摄取的图像；
    处理单元，与所述存储单元相连，用于执行所述至少一个程序以执行如权利要求1-12中任一所述的控制方法。
  14. 一种机器人，其特征在于，包括：
    摄像装置，用于在机器人移动期间摄取图像；
    移动装置，用于按照所接收的控制指令调整所述机器人的姿态；
    控制装置，与所述摄像装置和移动装置相连，用于执行以下步骤：
    获取所述摄像装置所摄取的图像以及识别所述图像中的特征线段；
    根据所识别出的特征线段确定所述机器人与房间分隔体在物理空间中相对的方位关系；
    根据所述方位关系控制所述移动装置调整所述机器人的姿态，使得使得在物理空间中所述机器人沿基于房间分隔体所构建的主方向移动。
  15. 根据权利要求14所述的机器人，其特征在于，所述摄像装置的光轴与机器人移动平面的夹角在0°至90°之间，所述摄像装置在机器人移动期间摄取图像并提供给所述控制装置；
    所述控制装置执行根据所识别出的特征线段确定所述机器人与房间分隔体在物理空间中相对的方位关系的步骤包括：
    基于所识别出的多条特征线段的消失点对各条特征线段进行分组；
    从所分组的特征线段中选取至少一组特征线段；
    根据所选择的特征线段组的消失点在图像坐标系中的位置确定所述机器人与房间分隔体在物理空间中相对的方位关系。
  16. 根据权利要求14所述的机器人，其特征在于，所述控制装置执行从所分组的特征线段中选取至少一组特征线段的步骤包括：选取特征线段数量最多的一组特征线段。
  17. 根据权利要求14所述的机器人，其特征在于，所述控制装置执行根据方位关系调整所述机器人的姿态的步骤包括：
    根据所述方位关系并以预设角度步长控制所述移动装置的旋转方向和旋转角度；以及
    重复上述各步骤直至满足用于确定所述机器人沿基于房间分隔体所构建的主方向的预设条件。
  18. 根据权利要求17所述的机器人，其特征在于，所述控制装置执行确定机器人沿基于房间分隔体所构建的主方向的步骤包括：
    判断当前图像中识别出的特征线段是否满足预设的平行条件，若满足所述平行条件则确定所述机器人的姿态与基于房间分隔体所构建的主方向一致，反之，则继续调整所述机器人的姿态并重复上述各步骤直至满足所述平行条件为止。
  19. 根据权利要求17所述的机器人，其特征在于，所述平行条件包括以下至少一种：不在同一直线上的两条特征线段之间的间距误差小于等于预设的间距误差阈值，所选择的特征线段组的消失点的位置落入预设的位置区域。
  20. 根据权利要求14所述的机器人，其特征在于，所述摄像装置的光轴与机器人移动平面垂直，所述摄像装置在机器人移动期间摄取图像并提供给所述控制装置；
    所控制装置执行根据所识别出的多条特征线段确定所述机器人与房间分隔体在物理空间中相对的方位关系的步骤包括：统计从至少一幅图像中所识别的特征线段在预设图像坐标系中的倾斜角；以及根据所统计的倾斜角确定所述机器人与房间分隔体在物理空间中相对的方位关系。
  21. 根据权利要求20所述的机器人，其特征在于，所述控制装置执行统计从至少一幅图像中所识别的特征线段在预设图像坐标系中的倾斜角的步骤包括以下任一种：
    统计单幅图像中特征线段在预设图像坐标系中的倾斜角；
    在姿态调整的一时间段内，根据机器人摄取图像时所对应的旋转角度，对所摄取的至少两幅图像中各特征线段的倾斜角进行回归处理；以及统计回归处理后各特征线段在预设图像坐标系中的倾斜角。
  22. 根据权利要求20所述的机器人，其特征在于，所述控制装置执行根据所统计的倾斜角确定所述机器人与房间分隔体在物理空间中相对的方位关系的步骤包括：
    根据所统计的位于峰值区间的倾斜角，确定所述机器人与房间分隔体在物理空间中相对的方位关系。
  23. 根据权利要求20所述的机器人，其特征在于，所述控制装置执行根据方位关系调整所述机器人的姿态的步骤包括：根据所述倾斜角和机器人的当前姿态，调整所述机器人的姿态。
  24. 根据权利要求14所述的机器人，其特征在于，所述控制装置还用于执行以下步骤：在确定在物理空间中所述机器人沿基于房间分隔体所构建的主方向时，基于当前位置规划导航路线。
  25. 根据权利要求24所述的机器人，其特征在于，所述导航路线包括：所述机器人向所述房间分隔体移动的第一路线，以及自所述第一路线的终点开始遍历一预设区域的第二路线。
  26. 根据权利要求14所述的机器人，其特征在于，所述机器人为清洁机器人。
  27. 一种计算机存储介质，其特征在于，存储至少一种程序，所述至少一种程序在被调用时执行如权利要求1-12中任一所述的控制方法。
  28. 一种机器人的控制系统，其特征在于，包括：
    图像处理模块，用于获取机器人移动期间所摄取的图像以及识别所述图像中的特征线段；
    方位计算模块，用于根据所识别出的特征线段确定所述机器人与房间分隔体在物理空间中相对的方位关系；
    控制模块，用于根据所述方位关系调整所述机器人的姿态，使得在物理空间中所述机器人沿基于房间分隔体所构建的主方向移动。
  29. 根据权利要求28所述的控制系统，其特征在于，所述方位计算模块包括第一方位计算单元，用于执行以下步骤：
    基于所识别出的多条特征线段的消失点对各条特征线段进行分组；
    从所分组的特征线段中选取至少一组特征线段；
    根据所选择的特征线段组的消失点在图像坐标系中的位置确定所述机器人与房间分隔体在物理空间中相对的方位关系。
  30. 根据权利要求28所述的控制系统，其特征在于，所述方位计算模块包括第二方位计算单元，用于执行以下步骤：
    统计从至少一幅图像中所识别的特征线段在预设图像坐标系中的倾斜角；
    根据所统计的倾斜角确定所述机器人与房间分隔体在物理空间中相对的方位关系。
  31. 根据权利要求28所述的控制系统，其特征在于，所述控制模块包括导航路线规划单元，用于在确定在物理空间中所述机器人沿基于房间分隔体所构建的主方向时，基于当前位置规划导航路线。
PCT/CN2018/097953 2017-08-02 2018-08-01 机器人的控制方法、装置、系统及所适用的机器人 Ceased WO2019024863A1 (zh)

Priority Applications (4)

Application Number Priority Date Filing Date Title
CN202210205435.4A CN114355836A (zh) 2017-08-02 2018-08-01 机器人的控制方法、装置、系统及所适用的机器人
CN201880001118.2A CN109074084B (zh) 2017-08-02 2018-08-01 机器人的控制方法、装置、系统及所适用的机器人
EP18840843.9A EP3686703B1 (en) 2017-08-02 2018-08-01 Control method, apparatus and system for robot, and applicable robot
US16/246,180 US10437254B2 (en) 2017-08-02 2019-01-11 Control method, device and system of robot and robot using the same

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201710652836.3 2017-08-02
CN201710652836.3A CN109388093B (zh) 2017-08-02 2017-08-02 基于线特征识别的机器人姿态控制方法、系统及机器人

Related Child Applications (1)

Application Number Title Priority Date Filing Date
US16/246,180 Continuation US10437254B2 (en) 2017-08-02 2019-01-11 Control method, device and system of robot and robot using the same

Publications (1)

Publication Number Publication Date
WO2019024863A1 true WO2019024863A1 (zh) 2019-02-07

Family

ID=65232265

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2018/097953 Ceased WO2019024863A1 (zh) 2017-08-02 2018-08-01 机器人的控制方法、装置、系统及所适用的机器人

Country Status (4)

Country Link
US (1) US10437254B2 (zh)
EP (1) EP3686703B1 (zh)
CN (3) CN109388093B (zh)
WO (1) WO2019024863A1 (zh)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114415658A (zh) * 2021-12-10 2022-04-29 深圳拓邦股份有限公司 一种房间分区缺口识别方法及室内机器人
US20240411310A1 (en) * 2023-06-08 2024-12-12 Handa Lab Co., Ltd Pick-up system of autonomous charging robot for electric vehicle

Families Citing this family (23)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US10572775B2 (en) 2017-12-05 2020-02-25 X Development Llc Learning and applying empirical knowledge of environments by robots
CN111358364B (zh) * 2018-12-26 2021-09-07 珠海市一微半导体有限公司 基于视觉机器人的死角清扫方法、装置、芯片及机器人
CN109612469B (zh) * 2019-01-14 2020-05-22 深圳乐动机器人有限公司 一种机器人搜索充电基座位置的方法及机器人
CN110268354A (zh) 2019-05-09 2019-09-20 珊口（深圳）智能科技有限公司 更新地图的方法及移动机器人
CN110288650B (zh) * 2019-05-27 2023-02-10 上海盎维信息技术有限公司 用于vslam的数据处理方法及扫描终端
CN112013844B (zh) * 2019-05-31 2022-02-11 北京小米智能科技有限公司 建立室内环境地图的方法及装置
CN112558595A (zh) * 2019-09-06 2021-03-26 苏州科瓴精密机械科技有限公司 自动工作系统、自动行走设备及其控制方法及计算机可读存储介质
CN110851896B (zh) * 2019-09-29 2023-02-21 成都信息工程大学 基于局部邻域信息的cad外墙体识别方法及装置
CN112683266B (zh) * 2019-10-17 2025-02-07 科沃斯机器人股份有限公司 机器人及其导航方法
CN110874101B (zh) * 2019-11-29 2023-04-18 合肥哈工澳汀智能科技有限公司 一种机器人清扫路径的生成方法及装置
CN113116224B (zh) * 2020-01-15 2022-07-05 科沃斯机器人股份有限公司 机器人及其控制方法
CN113552866B (zh) * 2020-04-17 2023-05-05 苏州科瓴精密机械科技有限公司 提升遍历均衡性能的方法、系统，机器人及可读存储介质
CN112034837A (zh) * 2020-07-16 2020-12-04 珊口（深圳）智能科技有限公司 确定移动机器人工作环境的方法、控制系统及存储介质
CN114115212B (zh) * 2020-08-26 2024-12-20 宁波方太厨具有限公司 一种清洁机器人的定位方法及采用该方法的清洁机器人
CN112263188B (zh) * 2020-10-22 2022-04-05 湖南格兰博智能科技有限责任公司 一种移动机器人行进方向的矫正方法及其设备
CN113126628A (zh) * 2021-04-26 2021-07-16 上海联适导航技术股份有限公司 一种农机自动驾驶的方法、系统、设备及可读存储介质
CN115383737A (zh) * 2021-05-21 2022-11-25 灵动科技（北京）有限公司 用于智能移动机器人的调度系统和方法
CN113379850B (zh) * 2021-06-30 2024-01-30 深圳银星智能集团股份有限公司 移动机器人控制方法、装置、移动机器人及存储介质
CN113633221B (zh) * 2021-08-17 2022-11-11 北京智行者科技股份有限公司 自动清洁设备漏扫区域处理方法、装置和系统
CN113768419B (zh) * 2021-09-17 2023-06-23 安克创新科技股份有限公司 确定扫地机清扫方向的方法、装置及扫地机
CN114569004B (zh) * 2022-02-22 2023-12-01 杭州萤石软件有限公司 行进方向调整方法、移动机器人系统及电子设备
CN115553662B (zh) * 2022-09-13 2025-11-04 上海昱开科技有限公司 一种自监督的实时检测室内布局框架的方法
CN115951671B (zh) * 2022-12-14 2026-02-03 上海发电设备成套设计研究院有限责任公司 移动方向的调整方法、装置、设备及存储介质

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1381340A (zh) * 2001-04-18 2002-11-27 三星光州电子株式会社 机器人清洁机,机器人清洁系统以及控制它们的方法
CN104063711A (zh) * 2014-06-23 2014-09-24 西北工业大学 一种基于K-means方法的走廊消失点快速检测算法
CN106541407A (zh) * 2015-09-18 2017-03-29 三星电子株式会社 清洁机器人及其控制方法
US9978149B1 (en) * 2015-04-20 2018-05-22 Hrl Laboratories, Llc System and method for door detection for corridor exploration

Family Cites Families (19)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US6496754B2 (en) * 2000-11-17 2002-12-17 Samsung Kwangju Electronics Co., Ltd. Mobile robot and course adjusting method thereof
CN1569558A (zh) * 2003-07-22 2005-01-26 中国科学院自动化研究所 基于图像表现特征的移动机器人视觉导航方法
JP2005275500A (ja) * 2004-03-23 2005-10-06 Zenrin Co Ltd 消失点決定方法
KR101339449B1 (ko) * 2006-05-08 2013-12-06 삼성전자주식회사 바닥 영상 정보를 이용하여 청소용 로봇 및 로봇의 제어방법
KR100843085B1 (ko) * 2006-06-20 2008-07-02 삼성전자주식회사 이동 로봇의 격자지도 작성 방법 및 장치와 이를 이용한영역 분리 방법 및 장치
KR101121518B1 (ko) * 2009-10-09 2012-02-28 고려대학교 산학협력단 로봇 이동 장치 지도 작성 방법
US9367770B2 (en) * 2011-08-30 2016-06-14 Digimarc Corporation Methods and arrangements for identifying objects
FR2985588B1 (fr) * 2012-01-10 2015-03-20 Jean Paul Sicard Procede de localisation d'un mobile en milieu construit
CN102663737B (zh) * 2012-03-19 2014-07-23 西安交通大学 一种针对富含几何信息的视频信号的消逝点检测方法
JP2012210703A (ja) * 2012-05-02 2012-11-01 Kazuo Hanno 国の全額借金返済と都道府県市町村区の全額借金返済の為の多機能インプット全自動ロボットの著作権原本。コメント２００８年８月３０日ａｍ１時１６分１１秒原本図面幾らかコピー取って眠る美馬牛カンキチ。２００８年９月４日ｐｍ１７時４９分４７秒多機能ロボット図面とロボット原本図を作り終えて、漸く再び書き始める美馬牛カンキチ。
US9595134B2 (en) * 2013-05-11 2017-03-14 Mitsubishi Electric Research Laboratories, Inc. Method for reconstructing 3D scenes from 2D images
KR101776621B1 (ko) * 2014-06-17 2017-09-11 주식회사 유진로봇 에지 기반 재조정을 이용하여 이동 로봇의 위치를 인식하기 위한 장치 및 그 방법
CN104077809B (zh) * 2014-06-24 2017-04-12 上海交通大学 基于结构性线条的视觉slam方法
KR101575597B1 (ko) * 2014-07-30 2015-12-08 엘지전자 주식회사 로봇 청소 시스템 및 로봇 청소기의 제어방법
CN108369420B (zh) * 2015-11-02 2021-11-05 星船科技私人有限公司 用于自主定位的设备和方法
DE102015119865B4 (de) * 2015-11-17 2023-12-21 RobArt GmbH Robotergestützte Bearbeitung einer Oberfläche mittels eines Roboters
US20170329347A1 (en) * 2016-05-11 2017-11-16 Brain Corporation Systems and methods for training a robot to autonomously travel a route
CN106020207B (zh) * 2016-07-26 2019-04-16 广东宝乐机器人股份有限公司 自移动机器人行走方法与装置
CN106970623B (zh) * 2017-04-18 2021-05-25 杭州匠龙机器人科技有限公司 智能清洁装置及其网格路径作业方法

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1381340A (zh) * 2001-04-18 2002-11-27 三星光州电子株式会社 机器人清洁机,机器人清洁系统以及控制它们的方法
CN104063711A (zh) * 2014-06-23 2014-09-24 西北工业大学 一种基于K-means方法的走廊消失点快速检测算法
US9978149B1 (en) * 2015-04-20 2018-05-22 Hrl Laboratories, Llc System and method for door detection for corridor exploration
CN106541407A (zh) * 2015-09-18 2017-03-29 三星电子株式会社 清洁机器人及其控制方法

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
See also references of EP3686703A4 *

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114415658A (zh) * 2021-12-10 2022-04-29 深圳拓邦股份有限公司 一种房间分区缺口识别方法及室内机器人
US20240411310A1 (en) * 2023-06-08 2024-12-12 Handa Lab Co., Ltd Pick-up system of autonomous charging robot for electric vehicle
US12504761B2 (en) * 2023-06-08 2025-12-23 Handa Lab Co., Ltd Pick-up system of autonomous charging robot for electric vehicle

Also Published As

Publication number Publication date
CN109074084A (zh) 2018-12-21
US10437254B2 (en) 2019-10-08
CN109388093B (zh) 2020-09-15
EP3686703A1 (en) 2020-07-29
EP3686703A4 (en) 2020-12-23
CN114355836A (zh) 2022-04-15
EP3686703B1 (en) 2022-12-14
US20190146521A1 (en) 2019-05-16
CN109074084B (zh) 2022-02-22
CN109388093A (zh) 2019-02-26

Similar Documents

Publication Publication Date Title
WO2019024863A1 (zh) 机器人的控制方法、装置、系统及所适用的机器人
CN110874100B (zh) 用于使用视觉稀疏地图进行自主导航的系统和方法
US10055013B2 (en) Dynamic object tracking for user interfaces
WO2019232803A1 (zh) 移动控制方法、移动机器人及计算机存储介质
US8644560B2 (en) Image processing apparatus and method, and program
CN113439275B (zh) 一种平面语义类别的识别方法以及图像数据处理装置
WO2019128109A1 (zh) 一种基于人脸追踪的动向投影方法、装置及电子设备
US20250005853A1 (en) Three-dimensional building model generation based on classification of image elements
WO2015195623A1 (en) Dynamic template selection for object detection and tracking
WO2022022365A1 (zh) 一种应用于指纹识别的图像匹配方法及相关装置
CN105138990A (zh) 一种基于单目摄像头的手势凸包检测与掌心定位方法
WO2017147748A1 (zh) 一种可穿戴式系统的手势控制方法以及可穿戴式系统
CN103577789A (zh) 检测方法和装置
CN114374791A (zh) 一种基于手势识别的摄像头调节方法和系统
CN112446347B (zh) 人脸方向确定方法和装置、存储介质、电子设备
WO2019128504A1 (zh) 一种台球比赛中的图像处理方法、装置及终端设备
CN111986229A (zh) 视频目标检测方法、装置及计算机系统
CN110222651A (zh) 一种人脸姿态检测方法、装置、终端设备及可读存储介质
CN109377518A (zh) 目标追踪方法、装置、目标追踪设备及存储介质
CN103033145B (zh) 用于识别多个物体的形状的方法与系统
CN114170620A (zh) 手掌位置确定方法、装置、电子设备及存储介质
CN112747734B (zh) 环境地图方向调整方法、系统及装置
JP2012181646A (ja) データ処理装置、データ処理システム、及びプログラム
CN109377519A (zh) 目标追踪方法、装置、目标追踪设备及存储介质
CN114529978A (zh) 一种运动趋势识别方法及装置

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 18840843

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

ENP Entry into the national phase

Ref document number: 2018840843

Country of ref document: EP

Effective date: 20200302