WO2021248845A1 - 一种机器人沿边行走的清洁分区规划方法、芯片及机器人 - Google Patents

一种机器人沿边行走的清洁分区规划方法、芯片及机器人 Download PDF

Info

Publication number
WO2021248845A1
WO2021248845A1 PCT/CN2020/131194 CN2020131194W WO2021248845A1 WO 2021248845 A1 WO2021248845 A1 WO 2021248845A1 CN 2020131194 W CN2020131194 W CN 2020131194W WO 2021248845 A1 WO2021248845 A1 WO 2021248845A1
Authority
WO
WIPO (PCT)
Prior art keywords
robot
cleaning
area
line segment
preset
Prior art date
Application number
PCT/CN2020/131194
Other languages
English (en)
French (fr)
Inventor
黄惠保
周和文
陈卓标
Original Assignee
珠海一微半导体股份有限公司
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 珠海一微半导体股份有限公司 filed Critical 珠海一微半导体股份有限公司
Priority to EP20940180.1A priority Critical patent/EP3985469A4/en
Priority to JP2022539045A priority patent/JP7462244B2/ja
Priority to US17/627,697 priority patent/US11914391B2/en
Priority to KR1020227021759A priority patent/KR20220107017A/ko
Publication of WO2021248845A1 publication Critical patent/WO2021248845A1/zh

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
    • G05D1/20—Control system inputs
    • G05D1/24—Arrangements for determining position or orientation
    • G05D1/247—Arrangements for determining position or orientation using signals provided by artificial sources external to the vehicle, e.g. navigation beacons
    • 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
    • G05D1/0268—Control of position or course in two dimensions specially adapted to land vehicles using internal positioning means
    • G05D1/0274—Control of position or course in two dimensions specially adapted to land vehicles using internal positioning means using mapping information stored in a memory device
    • 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
    • G05D1/0234—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means using optical markers or beacons
    • G05D1/0236—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means using optical markers or beacons in combination with a laser
    • A—HUMAN NECESSITIES
    • A47—FURNITURE; DOMESTIC ARTICLES OR APPLIANCES; COFFEE MILLS; SPICE MILLS; SUCTION CLEANERS IN GENERAL
    • A47L—DOMESTIC WASHING OR CLEANING; SUCTION CLEANERS IN GENERAL
    • A47L11/00—Machines for cleaning floors, carpets, furniture, walls, or wall coverings
    • A47L11/24—Floor-sweeping machines, motor-driven
    • A—HUMAN NECESSITIES
    • A47—FURNITURE; DOMESTIC ARTICLES OR APPLIANCES; COFFEE MILLS; SPICE MILLS; SUCTION CLEANERS IN GENERAL
    • A47L—DOMESTIC WASHING OR CLEANING; SUCTION CLEANERS IN GENERAL
    • A47L11/00—Machines for cleaning floors, carpets, furniture, walls, or wall coverings
    • A47L11/40—Parts or details of machines not provided for in groups A47L11/02 - A47L11/38, or not restricted to one of these groups, e.g. handles, arrangements of switches, skirts, buffers, levers
    • A47L11/4011—Regulation of the cleaning machine by electric means; Control systems and remote control systems therefor
    • A—HUMAN NECESSITIES
    • A47—FURNITURE; DOMESTIC ARTICLES OR APPLIANCES; COFFEE MILLS; SPICE MILLS; SUCTION CLEANERS IN GENERAL
    • A47L—DOMESTIC WASHING OR CLEANING; SUCTION CLEANERS IN GENERAL
    • A47L11/00—Machines for cleaning floors, carpets, furniture, walls, or wall coverings
    • A47L11/40—Parts or details of machines not provided for in groups A47L11/02 - A47L11/38, or not restricted to one of these groups, e.g. handles, arrangements of switches, skirts, buffers, levers
    • A47L11/4061—Steering means; Means for avoiding obstacles; Details related to the place where the driver is accommodated
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B62—LAND VEHICLES FOR TRAVELLING OTHERWISE THAN ON RAILS
    • B62D—MOTOR VEHICLES; TRAILERS
    • B62D57/00—Vehicles characterised by having other propulsion or other ground- engaging means than wheels or endless track, alone or in addition to wheels or endless track
    • B62D57/02—Vehicles characterised by having other propulsion or other ground- engaging means than wheels or endless track, alone or in addition to wheels or endless track with ground-engaging propulsion means, e.g. walking members
    • B62D57/032—Vehicles characterised by having other propulsion or other ground- engaging means than wheels or endless track, alone or in addition to wheels or endless track with ground-engaging propulsion means, e.g. walking members with alternately or sequentially lifted supporting base and legs; with alternately or sequentially lifted feet or skid
    • 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
    • G05D1/0238—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means using obstacle or wall sensors
    • G05D1/024—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means using obstacle or wall sensors in combination with a laser
    • 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
    • G05D1/0248—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 in combination with a laser
    • 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
    • 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
    • G05D1/60—Intended control result
    • G05D1/617—Safety or protection, e.g. defining protection zones around obstacles or avoiding hazards
    • 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

Definitions

  • the present invention relates to the technical field of path planning of robot laser data, in particular to a cleaning partition planning method, a chip and a robot for a robot to walk along the edge.
  • the sweeper performs the cleaning operation according to the rectangular frame area of the MxN grid size (usually 4x4 grid size). After cleaning the current framed MxN grid area, The expansion frame defines another MxN grid area, and continues to clean in the newly expanded area until all the working area is covered.
  • the advantage of this working mode is that it does not require a priori map.
  • the disadvantage is that the outline of the area defined by the frame differs greatly from the actual terrain, causing problems such as more navigation paths, too many small areas, and slow sweeping.
  • a cleaning partition planning method for robots walking along the edge is executed during the robot walking along the edge, and specifically includes the following steps: Step 11, starting from the starting point position of the robot along the edge, according to the laser map The pixel statistics of the laser image scanned in each coordinate axis direction, and then locate the contour boundary line segment along the coordinate axis direction of the laser map within the pre-defined clean area currently framed; the laser map is the process of the robot walking along the edge Step 12, select the contour boundary line segment closest to the preset position from each coordinate axis direction, and enclose a rectangular initial room cleaning partition; Step 13, when the initial room cleaning partition does not belong to the preset room cleaning When partitioning, select a coordinate axis direction with priority expansion, delete the non-wall obstacle line segment positioned perpendicular to the coordinate axis direction of priority expansion in the initial room cleaning partition, and then start to expand the initial room cleaning partition along the same coordinate axis direction, and then Proceed to step 14; step 14, judge whether the contour boundary line segment adjacent to
  • this technical solution does not need to pre-store a complete global map, but based on the pixel information of the map image obtained by laser scanning during the edge process, the initial room cleaning of the robot is divided in real time in the predefined cleaning area.
  • the initial room cleaning zone of the robot is expanded by repeatedly iteratively processing the wall boundaries of the uncleaned area, so as to ensure that the predefined cleaning zone is finally formed in the same predefined cleaning area. Setting the outline boundary of the room cleaning zone to be similar to the wall boundary of the indoor home room improves the efficiency of the robot navigating along the boundary of the preset room cleaning zone, and also effectively prevents the robot from repeating cleaning in the preset room cleaning zone.
  • the method further includes: on the laser map constructed by real-time scanning of the robot, first frame a predefined cleaning area with a planned starting point position as the center, and then select a nearest distance within the predefined cleaning area currently framed The starting point position along the edge of the physical boundary, control the robot from the starting point position along the edge to proceed along the path planned in a straight line to the physical boundary, until the robot is configured to walk along the edge along the physical boundary; where the physical boundary includes pre-defined The boundary or wall of the obstacle in the cleaning area; the planned starting position is the starting position of the robot in the pre-defined cleaning area currently framed.
  • This technical solution speeds up the speed at which the robot starts to walk along the edge and reduces the navigation path.
  • the robot is controlled to continue to walk along the edge in the divided preset room cleaning zone, and wait until the robot finishes this cleaning zone.
  • the control robot starts to perform planned cleaning on this preset room cleaning zone; wherein, this preset room cleaning zone surrounds the planned starting point position, and the robot moves from the planned starting point. Plan the starting point to start the walking path along the edge, and the path along the edge that the robot has already walked.
  • this technical solution divides the preset room cleaning zone in real time during the edge-edge process to select a cleaning area that matches the actual room environment boundary to perform edge-edge and then clean-up operations, which can avoid long edge-edge cleaning. Walk without cleaning.
  • the control robot continues to divide the new preset room cleaning partition, and then merges the two preset room cleaning partitions, and then controls the robot to continue to walk along the edges in the two combined preset room cleaning partitions, and wait until the robot After completing a circle and returning to the planned starting point, the control robot starts to perform planned cleaning on the two merged preset room cleaning partitions; wherein, the two merged preset room cleaning partitions surround the planned starting point position , The robot starts from the planned starting point position to start the walking path along the side, and the side path that the robot has walked.
  • This technical solution ensures that the robot divides the preset room cleaning partitions along the edges, improves the smoothness of the robot's walking along the edge and cleaning the planned path, is not prone to machine stalls, and reduces the construction and calculation time of the map area.
  • control robot does not step out of the preset room cleaning zone during the execution of the planned cleaning until the preset room cleaning zone is covered by the planned cleaning path, and then marks the area covered by the robot cleaning as already The area is cleaned, and the scanned area outside the area covered by the robot cleaning is marked as the uncleaned area.
  • the pre-defined cleaning area is a square frame area with the planned starting point position as the diagonal intersection point, used to limit the range of the robot walking along the side, and then surround the preset room cleaning partition that is currently determined , Or the preset room cleaning zone merged in the same predefined cleaning area; wherein the coverage area of the predefined cleaning area is equivalent to the actual physical area of a square, and the side length of the actual physical area of the square is equal to The size of the indoor area to be cleaned is related.
  • This technical solution sets a rectangular area that limits the edge range corresponding to each planned starting position, which is used to frame the area range of the preset room cleaning partition of the robot planning in advance, and also prevents the robot from walking endlessly along the edge.
  • the specific method for determining the preset room cleaning zone includes: when none of the contour boundary line segments surrounding the initial room cleaning zone is a non-wall obstacle line segment, and there are isolated obstacles inside the initial room cleaning zone When the length of the line segment is smaller than the preset ratio of the length of the line segment corresponding to the number of pixels of the wall fitting quantity value to the length of either side of the initial room cleaning zone, it is determined that the initial room cleaning zone belongs to all The preset room cleaning partition; when one of the contour boundary line segments surrounding the initial room cleaning partition is a non-wall obstacle line segment, or the length of the isolated obstacle line segment inside the initial room cleaning partition is greater than or equal to When the length of the line segment corresponding to the number of pixels of the wall fitting quantity value, or the length of the isolated obstacle line segment inside the initial room cleaning zone is greater than or equal to the preset ratio of the length of one side of the initial room cleaning zone, It is determined that the initial room cleaning partition does not belong to the preset room cleaning partition; wherein the contour boundary line segment is divided into a non-
  • the isolated obstacle line segment is marked as the wall obstacle line segment.
  • This technical solution determines the environmental characteristics of the preset room cleaning zone by judging the length of the boundary line segment, eliminates the interference effect of obstacles in other areas, and fits the isolated obstacle line segment of a non-negligible length to the physical wall, The influence of the contour boundary line segment being misjudged as a wall is reduced, so that the preset room cleaning partition is almost surrounded by the wall.
  • step 11 includes: in the predefined clean area, starting from the planned starting point position, counting the image pixels of the currently constructed laser map; and counting up to the ordinate along the X-axis direction
  • the preset boundary threshold mark the contour boundary line segment formed by the connection of these black pixels with the same ordinate, so that the predefined clean area extends along the X-axis direction
  • the area is divided by the corresponding contour boundary line segment; whenever the number of black pixels with the same abscissa exceeds the preset boundary threshold along the Y-axis direction, mark the connection of these black pixels with the same abscissa
  • the contour boundary line segment is formed such that the area extending in the Y-axis direction in the predefined cleaning area is divided by the corresponding contour boundary line segment.
  • an area with a certain degree of passability is selected in the predefined cleaning area to mark a contour boundary line segment to enclose the contour of the preset room cleaning zone
  • the boundary line segments can be aligned with each other to make the room area division more regular and reasonable, and also to ensure that the marked outline boundary line segments can frame a rectangular working area that supports the robot to continuously walk along the side.
  • a chip with a built-in control program for controlling a mobile robot to execute the cleaning partition planning method is provided.
  • a robot is equipped with a laser sensor, and the robot has the built-in chip for configuring the robot to segment the preset room cleaning zone during the process of walking along the edge.
  • This technical solution does not need to pre-store a complete global map, but based on the pixel information of the map image obtained by laser scanning during the edge process, the initial room cleaning zone of the robot is divided in real time in the predefined cleaning area, and the initial room cleaning zone of the robot is divided in the same way.
  • the initial room cleaning zone of the robot is expanded by iteratively processing the wall boundary of the uncleaned area, so as to ensure that the contour boundary of the preset room cleaning zone is finally formed in the same predefined cleaning zone Similar to the wall boundary of an indoor home room, it improves the efficiency of the robot navigating along the boundary of the preset room cleaning zone, and also effectively prevents the robot from repeating cleaning in the preset room cleaning zone.
  • FIG. 1 is an effect diagram of framing a predefined clean area P1 on a gray-scale laser map constructed by scanning when the robot moves to the planned starting point position O.
  • FIG. 2 is an effect diagram of the robot dividing the preset room cleaning zone #1 from the predefined cleaning area P1 during the edge-edge process.
  • FIG. 3 is an effect diagram of framing the predefined clean area P2 on the gray-scale laser map constructed by scanning when the robot moves to the planned starting point position O1.
  • Figure 4 is an effect diagram of the robot dividing the preset room cleaning zone #2 from the predefined cleaning area P2 during the edge-edge process, where the preset room cleaning zone #1 and the preset room cleaning zone #2 are on the laser map Adjacent.
  • Fig. 5 is a flowchart of a cleaning partition planning method for a robot walking along the edge disclosed in an embodiment of the present invention.
  • the technical solutions in the embodiments of the present invention will be described in detail below in conjunction with the drawings in the embodiments of the present invention.
  • the present invention is provided with drawings. These drawings are a part of the disclosure of the present invention, which are mainly used to illustrate the embodiments, and can cooperate with the relevant description in the specification to explain the operation principle of the embodiments. With reference to these contents, those of ordinary skill in the art should be able to understand other possible implementation manners and advantages of the present invention.
  • the image size of the laser map in the figure is not drawn to scale.
  • the main body of execution of the method program in the embodiment of the present invention is a laser navigation robot.
  • the laser navigation robot can be equipped with a laser sensor, which can detect obstacles. In a general scenario, the laser navigation robot can be set in The laser sensor on the laser navigation robot detects whether there are obstacles around and marks it on the laser map immediately.
  • the present invention discloses a cleaning partition planning method for a robot walking along the edge.
  • the cleaning partition planning method is executed during the robot walking along the edge, as shown in FIG. 5, which specifically includes the following steps:
  • Step S11 Starting from the starting point position along the edge of the robot, according to the pixel statistical information of the laser map scanned by the robot in the current bounded pre-defined clean area, locate the contour boundary line segment in each coordinate axis direction of the laser map, and then enter Step S12; wherein the laser map is scanned and constructed by the robot while walking along the edge; the specific method of step S11 includes: starting from the planned starting point within the pre-defined clean area, statistics of the currently constructed laser map For image pixels, contour boundary line segments are located in the coordinate axis directions within the predefined cleaning area, and the respective coordinate axis directions include the X-axis direction and the Y-axis direction shown in the figure.
  • This embodiment uses the histogram of obstacles to count the number of occurrences of various gray-scale pixels in the detection interval that are different from the planned starting point position, and also realizes obstacles to pixels of corresponding gray-levels.
  • the contour boundary line segment formed by the connection of these black pixels with the same ordinate is marked, so that The area extending along the X-axis in the predefined cleaning area is divided by the corresponding contour boundary line segment; in fact, the subsequent steps may determine that the contour boundary line segment is not a wall and be deleted, and then merge the corresponding divided areas to avoid excessive segmentation Area, but it can still describe the contour features of the local area in the X-axis direction; whenever the number of black pixels with the same ordinate along the X-axis direction does not exceed the preset boundary threshold, it will not follow the current direction The contour boundary line segment is marked on the top.
  • the contour boundary line segment formed by the connection of these black pixels with the same abscissa is marked, so that all The area extending in the Y-axis direction in the predefined cleaning area is divided by the corresponding contour boundary line segment, otherwise the contour boundary line segment is not marked along the current direction to realize the description of the local area contour feature in the Y-axis direction.
  • the step may determine that the contour boundary line segment determined in this direction is not a wall and cannot function as a segmentation area. It is necessary to continue to search for the next contour boundary line segment to approximate the size of the wall edge. Framed in the predefined clean area Out to clean the partition.
  • the contour boundary line segment is related to the size of the robot body and the side length of the predefined cleaning area, and can be adjusted according to actual needs.
  • an area with a certain degree of passability is selected in the predefined cleaning area to mark contour boundary line segments, and the contour boundary line segments enclosing the clean area can be mutually connected. Alignment makes the room area division more regular and reasonable, and also ensures that the marked outline boundary line can frame the rectangular working area for the robot to walk along the side continuously.
  • Step S12 Select the contour boundary line segment closest to the preset position from each coordinate axis direction to enclose a rectangular initial room cleaning zone, and then go to step S13; in this embodiment, the initial room cleaning zone belongs to FIG. 2
  • the room cleaning zone #1 is shown as a part of a rectangular area.
  • Step S13 When the initial room cleaning zone does not belong to the preset room cleaning zone, select a coordinate axis direction with priority expansion (for example, the negative direction of the Y axis), and delete the non-aligned axis direction in the initial room cleaning zone that is positioned perpendicularly to the coordinate axis direction with priority expansion.
  • the wall obstacle line segment is then expanded along the same coordinate axis to expand the initial room cleaning zone, and then go to step S14.
  • Step S14 Determine whether the contour boundary line segment adjacent to the non-wall obstacle line segment deleted in step S13 located in the coordinate axis direction of the priority expansion in step S13 is located in the uncleaned area within the pre-defined cleaning area currently framed If yes, go to step S15, otherwise go to step S17. This step is used to limit the expansion range of the contour boundary line segment in the coordinate axis direction of the priority expansion, so as to avoid the clean partition defined by the contour boundary line segment and the cleaned area or the unknown area from having more overlapping areas.
  • Step S15 Determine whether the intersection of the contour boundary line segment located in the coordinate axis direction of the priority expansion in step S13 and the remaining contour boundary line segment of the aforementioned initial room cleaning partition does not form a preset room cleaning partition, if yes, return to step S13, that is It means that the judgment conditions of step S14 and step S15 are satisfied, then return to step S13 to continue the expansion in the currently selected coordinate axis direction; otherwise, go to step S16.
  • Step S16 It is determined that the predefined cleaning area is divided into a preset room cleaning zone by the corresponding contour boundary line segment, and there is no need to continue to expand in the original predefined cleaning area.
  • Step S17 Stop the expansion in the direction of the coordinate axis currently selected in the step S13, and then return to the step S13 to select the coordinate axis direction of the lower expansion priority (such as the negative direction of the X-axis) for expansion, by repeating
  • the foregoing steps enable the predefined cleaning area to be divided into a preset room cleaning zone by the corresponding contour boundary line segment.
  • the non-wall obstacle line segment belongs to the contour boundary line segment but does not represent the wall, and the contour boundary line segment enclosing the preset room cleaning partition and the actual room boundary coincide within the preset error allowable range;
  • the actual room boundary includes the boundary of the obstacle inside the preset room cleaning zone and/or the boundary of the obstacle inside the actual edge area.
  • the box boundary of room cleaning zone #1 as shown in Fig. 2 is close to the wall boundary of the actual environment, that is, the preset room cleaning zone #1 and the predefined cleaning zone P2 divided in the predefined cleaning zone P1
  • the preset room cleaning partition #2 divided within are all close to the terrain of the actual room; among them, the non-wall obstacle line segment is the contour boundary line segment that does not belong to the wall, and the contour boundary line segment enclosing the preset room cleaning partition is consistent with the actual
  • the room boundaries are coincident within the preset tolerance range; where the actual room boundaries include the boundaries of obstacles inside the preset room cleaning zone and/or the boundaries of obstacles inside the actual edge area, and the actual room is Predefine the actual physical area where the clean area is located.
  • this embodiment uses the pixel information of the map image acquired by laser scanning to divide the initial room cleaning zone of the robot in the predefined cleaning area in real time, and in the same predefined cleaning area, pass Iteratively process the wall boundary of the uncleaned area to expand the initial room cleaning zone of the robot, so as to ensure that the contour boundary of the room cleaning zone finally formed in the same predefined cleaning area is similar to the actual room boundary.
  • the initial working area is expanded into closed box areas #1 and #2 with a larger area and wider coverage, so that the robot can navigate to the wall of the actual environment along the continuously revised and expanded contour boundary line.
  • the target position improves the efficiency of the robot navigating along the boundary of the preset room cleaning zone, and also effectively prevents the robot from repeating cleaning in the preset room cleaning zone.
  • the cleaning partition planning method further includes: after starting the robot to start planning the area, on the laser map constructed by the robot real-time scanning, frame a predefined cleaning area with the planned starting point position of the robot as the center, where , The planned starting position is the starting position of the robot in the pre-defined cleaning area currently framed.
  • the currently defined pre-defined cleaning area is a square frame area defined by the robot at the starting position O (the current planned starting point position) with the starting position O as the diagonal intersection, which is used to limit the robot along the edge The range of the contour boundary line segment for walking and construction.
  • This square box area is a square box with an actual side length of 12 meters; it is worth noting that although the pre-defined cleaning area is a closed area, this pre-defined cleaning area is not all It is detected and scanned by the laser sensor on the robot; while the robot is walking along the edge of the current framed predefined cleaning area, it keeps not crossing the currently framed predefined cleaning area, which is equivalent to not stepping out of a square with a side length of 12 meters The actual physical area.
  • step S3 the robot is configured to move along the edge along this physical boundary: controlling the robot to start from the edge starting point closest to the planned starting point within the pre-defined cleaning area currently framed, Start walking along the edge along the physical boundary where the starting point of the edge is located, but the direction along the edge is not limited.
  • the physical boundary includes the boundary or wall of the obstacle in the pre-defined clean area currently framed, so that the robot is moving along the edge. In the process of advancing along the path planned in a straight line, only when the boundary or wall of the obstacle is detected, the mode of walking along the edge can be turned on. Speed up the robot to start walking along the edge and reduce the navigation path.
  • the robot when it is detected that the preset room cleaning zone is divided from the currently framed predefined cleaning area, the robot is controlled to continue to walk along the edge in the divided preset room cleaning zone, and wait until the robot After completing a circle of this preset room cleaning zone and returning to the planned starting point, the control robot starts to perform planned cleaning on this preset room cleaning zone; wherein, this preset room cleaning zone surrounds the planned starting point position and the robot From the planned starting point position to starting the walking path along the edge, and the edge path that the robot has already walked.
  • this preset room cleaning zone surrounds the planned starting point position and the robot From the planned starting point position to starting the walking path along the edge, and the edge path that the robot has already walked.
  • this embodiment divides the preset room cleaning zone in real time during the edge edge process to select a cleaning area that matches the actual room environment boundary to perform edge edge and then clean operation, which can avoid long edge edge cleaning. Walk without cleaning.
  • the coverage area position of the predefined clean area also changes, as shown in FIG. 3
  • the position O1 is shown in the square box area at the intersection of the diagonals.
  • a rectangular area that limits the edge range is correspondingly set, which is used to frame the maximum edge walking range of the robot in advance and to lay out contour boundary line segments in the directions of each coordinate axis.
  • the robot when the robot is walking along the edge, when the robot divides one of the preset room cleaning partitions at the original position, since the robot is walking along the edge faster, it does not stop and wait for the division while walking along the edge.
  • Preset room cleaning partitions and map generation so it is determined that the robot has walked along the original location and the partition conforms to the preset room cleaning partition, then the robot is controlled to continue to divide the new preset room cleaning at the new location Partition, and then merge the two preset room cleaning partitions to support the robot to walk along the edge to return to the planned starting point, especially when the robot walks out of the gap of the preset room cleaning partition that is currently divided.
  • the currently divided preset room cleaning partition continues to walk along the edge and enters the uncleaned area, where the original position in this embodiment may be the edge starting point in the aforementioned step S11, when the robot walks along the edge to a new one that meets the preset When the room is cleaned and partitioned, you can continue to walk along the edge to return to the planned starting point.
  • control the robot to continue walking along the edges in the two merged preset room cleaning partitions, and when the robot completes a circle and returns to the planned starting point, the control robot starts to plan the two merged preset room cleaning partitions Type cleaning; wherein the two merged preset room cleaning partitions surround the planned starting point position, the robot's walking path along the edge from the planned starting point position to the start, and the edge path that the robot has walked.
  • the robot performs the calculation of the division of the room cleaning partition while walking along the edge, so that the robot can perform edge walking and cleaning smoothly in the current pre-defined cleaning area, and the phenomenon of machine stalls is not prone to occur.
  • the passed boundary is consistent with the actual environmental boundary corresponding to the pre-defined cleaning area currently framed, and the environmental adaptability of the room cleaning partition divided by the robot is improved.
  • the control robot does not step out of the preset room cleaning zone during the execution of the planned cleaning until the preset room cleaning zone is covered by the planned cleaning path, and then marks the area covered by the robot cleaning as already The area is cleaned, and the scanned area outside the area covered by the robot cleaning is marked as the uncleaned area.
  • the robot completes the planned cleaning of the preset room cleaning partition that is currently determined, it distinguishes the cleaned area from the uncleaned area according to the position information marked by the robot, that is, the robot uses the planned cleaning path
  • the covered preset room cleaning partitions are all detected as the cleaned area, and other known areas (including the uncleaned areas that have been scanned and marked) are all detected as the uncleaned areas.
  • the robot also scans and maps the preset room cleaning area to mark the cleaned area during the bow-shaped planning and cleaning of the room cleaning area. To remind the robot not to repeat cleaning operations on the cleaned area. Therefore, it is possible to accurately distinguish the cleaned area and the non-cleaned area within the predefined cleaning area, which is beneficial to realize the full coverage of the area to be cleaned.
  • the predefined cleaning area is a square frame area with the planned starting point position as the diagonal intersection, used to limit the range of the robot walking along the side, and then surround the preset preset that is currently determined.
  • the side length is related to the size of the indoor area to be cleaned.
  • the coverage area of the aforementioned pre-defined cleaning area is equivalent to the actual physical area of a square with a side length of 12 meters, and the location of the coverage area of the pre-defined cleaning area changes with the planned starting point of the robot. .
  • the foregoing embodiment correspondingly sets a rectangular area that limits the edge range for each planned starting point position, which is used to frame the maximum edge edge range of the robot in advance, and also prevents the robot from endlessly performing edge walking. 1 and FIG. 2, it can be seen that the robot scans and divides the preset room cleaning zone #1 shown in FIG. 2 at the planned starting point position O in the predefined cleaning area P1 shown in FIG.
  • the planned starting point position O is also located inside the preset room cleaning zone #1, where the predefined cleaning area P1 is a square frame area with the planned starting position O as the diagonal intersection, which is used to surround the preset room cleaning zone #1 to limit the range where the robot can walk along the edge.
  • the robot is controlled to walk along the edge in the matching area. When the robot completes a circle in this matching area and returns to the When planning the starting position, control the robot to perform planned cleaning in this matching area.
  • a new pre-defined cleaning area is defined as the center of the next planned starting point position, and then an edge of the closest physical boundary is selected in this new pre-defined cleaning area Starting point position, control the robot from this starting point position along the edge to proceed along the path planned in a straight line to this physical boundary, until the robot is configured to walk along the edge along this physical boundary; where the physical boundary includes this new pre-defined clean area
  • the boundary or wall of the obstacle inside; the next planned starting position is the starting position of the robot in this new pre-defined cleaning area.
  • the control robot bypasses the already distinguished cleaned area in the process of performing planned cleaning and walking along the edge, including the cleaned area marked in the previous process of walking along the edge; wherein, the next planned starting point position It is the position in the uncleaned area that is closest to the position where the robot currently ends the planned cleaning.
  • the next planned starting point position needs to rely on the robot to plan and navigate straight from the position where the planned cleaning is currently completed.
  • the robot is in the process of walking If an obstacle or a wall is detected, it will continue to walk along the boundary or wall of the currently detected obstacle until it navigates to the next planned starting point.
  • next planned starting point location is used to frame a new predefined cleaning area, so that enough unknown map areas can be scanned in the subsequent edge edge process, more room cleaning partitions or actual edge areas are framed, and the cleaned area is bypassed. Walk along the side to reduce unnecessary navigation paths.
  • FIG. 2 and FIG. 3 it can be seen that after the robot completes the bow-shaped planning cleaning of the preset room cleaning zone #1 divided by scanning in the predefined cleaning area P1 of FIG. 1, the preset room cleaning zone of FIG. 2 #1 is marked as a cleaned area, and the map area outside the box of the preset room cleaning zone #1 in Figures 2 and 3 is marked as an uncleaned area, and the preset room cleaning zone #1 in Figure 2 is marked The information is more than the marked information in the same area in Figure 1.
  • the planned starting point position O1 in Figure 3 is located at the upper left of the planned starting point position O in Figure 1, and the planned starting point position O1 in Figure 3 is still located at the scanned known laser
  • the planned starting point position O1 is closest to the end cleaning position of the preset room cleaning zone #1 in FIG.
  • the predefined cleaning area P2 of FIG. 3 is offset to the upper left with respect to the predefined cleaning area P1 of FIG. 1 of the same size, so that the predefined cleaning area P2 of FIG. 3 scans out that the predefined cleaning area P1 of FIG.
  • the robot will clean and build the map in the preset room cleaning area divided by the pre-defined cleaning area P2, obtain the preset room cleaning area #4 in Figure 4, and plan more for the laser map to be constructed immediately , which fits the actual wall area, but the two predefined cleaning areas distributed in different coverage areas, the predefined cleaning area P2 and the predefined cleaning area P1, are used to limit the range of the robot walking along the side.
  • the predefined cleaning area P2 of FIG. 3 surrounds the preset room cleaning zone #1 marked as the cleaned area in FIG. 3, so that the predefined cleaning area P2 and the predefined cleaning area P1 of FIG. Including the preset room cleaning zone #1; and in the subsequent predefined cleaning area P2, the preset room cleaning zone expanded based on the boundary contour line in the priority expansion direction is not related to the preset room marked as the cleaned area A coincident area appears in clean partition #1.
  • the robot scans and divides the preset room cleaning zone #2 shown in FIG. 4 at the planned starting point position O1 shown in FIG. 3, and the preset room cleaning zone #2 in FIG. 4 is marked
  • the map information of is more than the map information marked in the same area in FIG. 3; the planned starting point position O1 is also located inside the preset room cleaning zone #2, and the predefined cleaning area P2 surrounds the preset room cleaning zone #2 .
  • the preset room cleaning partition #2 in FIG. 4 is just adjacent to the preset room cleaning partition #1 in FIG.
  • the preset room cleaning zone #1 can be bypassed when walking along the edge and bow-shaped planning and cleaning, avoiding repeated cleaning of the cleaned area, reducing cleaning time, and improving the cleaning efficiency of the robot.
  • the preset room cleaning partitions #1 and #2 that are successively divided are in an adjacent relationship, that is, the preset room cleaning partitions that are divided successively are in an adjacent relationship, which is beneficial to improve the coverage of the cleaning area.
  • the specific method for determining the preset room cleaning zone includes: when none of the contour boundary line segments surrounding the initial room cleaning zone are non-wall obstacle line segments, and the initial room cleaning zone When the length of the internal isolated obstacle line segment is smaller than the number of pixels corresponding to the wall fitting quantity value, the predetermined ratio of the line segment length to the length of any side of the initial room cleaning zone is relatively small, the enclosed area is framed If the size of the internal isolated obstacle is not enough to form a wall, it is determined that the initial room cleaning zone is the preset room cleaning zone; when one of the contour boundary line segments surrounding the initial room cleaning zone is a non-wall obstacle Line segment, or the length of the isolated obstacle line segment inside the initial room cleaning zone is greater than or equal to the length of the line segment corresponding to the number of pixels of the wall fitting value value, or the isolated obstacle line segment inside the initial room cleaning zone When the length of is greater than or equal to the preset ratio of the length of one side of the initial room cleaning zone, it is determined that the initial room cleaning
  • the number of white pixels in the non-wall obstacle line segment is greater than or equal to the preset threshold, while the number of wall obstacle line segments is less than the preset threshold.
  • the isolated obstacle line segment is marked as the wall obstacle line segment.
  • This embodiment determines the environmental characteristics of the preset room cleaning zone by framing the line segment length properties of the contour boundary line segment of the initial room cleaning zone and the length of the isolated obstacle line segment inside the initial room cleaning zone, and excludes other areas.
  • the interference effect of the straight line of obstacles, and the non-negligible length of the isolated obstacle line segment is fitted to the physical wall, reducing the influence of the contour boundary line segment being misjudged as the wall, and ensuring the contour boundary of the preset room clean partition built indoors
  • the locations are close to the wall, so that the pre-defined clean room partitions can constitute the room area in the actual home environment, and the accuracy and intelligence of the robot in distinguishing between wall and non-wall obstacles are improved.
  • a "computer-readable medium” can be any device that can contain, store, communicate, propagate, or transmit a program for use by an instruction execution system, device, or device or in combination with these instruction execution systems, devices, or devices.
  • computer-readable media include the following: electrical connections (electronic devices) with one or more wiring, portable computer disk cases (magnetic devices), random access memory (RAM), Read only memory (ROM), erasable and editable read only memory (EPROM or flash memory), fiber optic devices, and portable compact disk read only memory (CDROM).
  • the computer-readable medium may even be paper or other suitable medium on which the program can be printed, because it can be used for example by optically scanning the paper or other medium, followed by editing, interpretation or other suitable media if necessary. The program is processed in a way to obtain the program electronically and then stored in the computer memory.
  • a chip with a built-in control program for controlling a mobile robot to execute the cleaning partition planning method can be implemented by hardware, software, firmware, middleware, microcode, or any combination thereof.
  • the processing unit can be in one or more application-specific integrated circuits (ASIC), digital signal processors (DSP), digital signal processing devices (DSPD), programmable logic devices (PLD), field programmable gate arrays ( FPGA), a processor, a controller, a microcontroller, a microprocessor, other electronic units designed to perform the functions described herein, or a combination thereof.
  • ASIC application-specific integrated circuits
  • DSP digital signal processors
  • DSPD digital signal processing devices
  • PLD programmable logic devices
  • FPGA field programmable gate arrays
  • a processor a controller, a microcontroller, a microprocessor, other electronic units designed to perform the functions described herein, or a combination thereof.
  • a robot is equipped with a laser sensor, and the robot has the built-in chip for configuring the robot to segment the preset room cleaning zone during the process of walking along the edge.
  • This embodiment does not need to pre-store a complete global map, but according to the pixel information of the map image obtained by laser scanning during the edge process, the initial room cleaning zone of the robot is divided in real time in the predefined cleaning area, and the initial room cleaning zone of the robot is divided in the same way.
  • the initial room cleaning zone of the robot is expanded by repeatedly iteratively processing the wall boundary of the uncleaned area, so as to ensure that the contour boundary of the preset room cleaning zone is finally formed in the same predefined cleaning zone Similar to the wall boundary of an indoor home room, it improves the efficiency of the robot navigating along the boundary of the preset room cleaning zone, and also effectively prevents the robot from repeating cleaning in the preset room cleaning zone.

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Radar, Positioning & Navigation (AREA)
  • Automation & Control Theory (AREA)
  • Aviation & Aerospace Engineering (AREA)
  • Remote Sensing (AREA)
  • General Physics & Mathematics (AREA)
  • Electromagnetism (AREA)
  • Optics & Photonics (AREA)
  • Multimedia (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Chemical & Material Sciences (AREA)
  • Combustion & Propulsion (AREA)
  • Transportation (AREA)
  • Mechanical Engineering (AREA)
  • Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)
  • Electric Vacuum Cleaner (AREA)

Abstract

一种机器人沿边行走的清洁分区规划方法、芯片及机器人，清洁分区规划方法不需要预存有完整的全局地图，而是根据沿边过程中激光扫描获取的地图图像像素信息，在预限定清洁区域中实时划分出机器人的初始房间清洁分区，并在同一预限定清洁区域中，通过反复迭代处理未清洁区域的墙体边界来拓展机器人的初始房间清洁分区，从而确保在同一预限定清洁区域中最终形成的预设房间清洁分区的轮廓边界与室内家居房间墙体边界相似，提高机器人沿着所述预设房间清洁分区的边界导航的效率，也有效预防机器人在预设房间清洁分区内重复清扫。

Description

一种机器人沿边行走的清洁分区规划方法、芯片及机器人 技术领域
本发明涉及机器人激光数据的路径规划的技术领域，尤其涉及一种机器人沿边行走的清洁分区规划方法、芯片及机器人。
背景技术
目前市面上激光SLAM扫地机的覆盖清扫工作模式中，扫地机按MxN栅格大小的矩形框区域(一般为4x4栅格大小)进行清扫作业，在清扫完当前框定的MxN栅格区域后，再扩展框定出另一个MxN栅格区域，并继续在新扩展出的区域内清扫，直至全部工作区域被覆盖完。这种工作模式的优点是不需要先验地图，缺点是框定出的区域轮廓与实际地形差异大，造成导航路径较多、存在过多的小区域、扫地机清扫过慢等问题。
发明内容
为了解决上述技术问题，一种机器人沿边行走的清洁分区规划方法，该清洁分区规划方法在机器人沿边行走过程中执行,具体包括以下步骤：步骤11、从机器人的沿边起点位置开始，根据激光地图在各个坐标轴方向上扫描出的激光图像的像素点统计信息，再在当前框定的预限定清洁区域内沿着激光地图的坐标轴方向定位出轮廓边界线段；其中，激光地图是机器人在沿边行走过程中扫描构建的；步骤12、从每个坐标轴方向上选择距离预设位置最近的轮廓边界线段，围成一个矩形的初始房间清洁分区；步骤13、当初始房间清洁分区不属于预设房间清洁分区时，选择一个优先拓展的坐标轴方向，删除初始房间清洁分区中垂直定位于优先拓展的坐标轴方向的非墙体障碍物线段，再沿着同一坐标轴方向开始拓展初始房间清洁分区，然后进入步骤14；步骤14、判断步骤13所述的优先拓展的坐标轴方向上定位出的与步骤13删除的非墙体障碍物线段相邻的轮廓边界线段是否位于当前框定的预限定清洁区域内的未清扫区域，且判断该坐标轴方向上定位出的轮廓边界线段与前述初始房间清洁分区的剩余轮廓边界线段相交是否没有形成预设房间清洁分区，若两者都满足，则返回步骤13继续在当前选择的坐标轴方向上的拓展；否则停止在所述步骤13当前选择的坐标轴方向上的拓展，再返回所述步骤13以选择低一级的拓展优先级的坐标轴方向进行拓展，使得所述预限定清洁区域被相应的轮廓边界线段划分出预设房间清洁分区；其中，非墙体障碍物线段是属于轮廓边界线段但不代表墙体，围成所述预设房间清洁分区的轮廓边界线段与实际房间边界在预设误差允许范围内是重合的；其中，实际房间边界包括所述预设房间清洁分区内部的障碍物的边界和/或所述实际沿边区域内部的障碍物的边界。
与现有技术相比，本技术方案不需要预存有完整的全局地图，而是根据沿边过程中激光扫描获取的地图图像像素信息，在所述预限定清洁区域中实时划分出机器人的初始房间清洁分区，并在同一所述预限定清洁区域中，通过反复迭代处理未清洁区域的墙体边界来拓展机器人的初始房间清洁分区，从而确保在同一所述预限定清洁区域中最终形成的所述预设房间清洁分区的轮廓边界与室内家居房间墙体边界相似，提高机器人沿着所述预设房间清洁分区的边界导航的效率，也有效预防机器人在所述预设房间清洁分区内重复清扫。
进一步地，还包括：在机器人实时扫描构建的激光地图上，先以一个规划起点位置为中心框定一个所述预限定清洁区域，再在当前框定的所述预限定清洁区域内选定一个距离最近的物理边界的沿边起点位置，控制机器人从这个沿边起点位置开始沿着直线规划的路径向这个物理边界前进，直到机器人被配置为沿着这个物理边界作沿边行走；其中，这个物理边界包括预限定清洁区域内的障碍物的边界或墙体；所述规划起点位置是机器人在当前框定的所述预限定清洁区域内的启动位置。该技术方案加快机器人启动沿边行走的速度，减少导航路径。
进一步地，当检测到从当前框定的预限定清洁区域中划分出符合所述预设房间清洁分区时，控制机器人在划分出的所述预设房间清洁分区内继续沿边行走，等到机器人沿完这个预设房间清洁分区一圈并返回所述规划起点位置时，控制机器人开始对这个预设房间清洁分区进行规划式清扫；其中，这个预设房间清洁分区包围所述规划起点位置、机器人从所述规划起点位置到启动沿边的行走路径、以及机器人已行走过的沿边路径。与现有技术相比，本技术方案通过在沿边过程中实时划分所述预设房间清洁分区，来选择与实际房间环境边界相匹配的清洁区域进行先沿边再清扫作业，既可避免长时间沿边行走而不清扫。
进一步地，在机器人沿边行走的过程中，当机器人划分出一个所述预设房间清洁分区时，如果判断到 机器人已经沿边行走出所述沿边起点位置划分出的所述预设房间清洁分区，则控制机器人继续划分出新的所述预设房间清洁分区，再将这两个所述预设房间清洁分区合并，然后控制机器人在这两个合并的预设房间清洁分区内继续沿边行走，等到机器人沿完一圈并返回所述规划起点位置时，控制机器人开始对这两个合并的预设房间清洁分区进行规划式清扫；其中，这两个合并的预设房间清洁分区包围所述规划起点位置、机器人从所述规划起点位置到启动沿边的行走路径、以及机器人已行走过的沿边路径。该技术方案保证机器人边沿边边划分出预设房间清洁分区，提高机器人沿边行走和清扫规划路径的流畅性，不容易出现机器停顿的现象，减少地图区域的构建计算时间。
进一步地，控制机器人在执行规划式清扫的过程中不跨出所述预设房间清洁分区，直到所述预设房间清洁分区都被规划式清扫路径覆盖，然后将机器人清扫覆盖的区域标记为已清扫区域，同时将机器人清扫覆盖的区域之外的已扫描区域标记为所述未清扫区域。该技术方案实现在所述预限定清洁区域内准确区分已清扫区域和非清扫区域，有利于实现待清扫区域的全面覆盖。
进一步地，所述预限定清洁区域是以所述规划起点位置为对角线交点的一个正方形方框区域，用于限制机器人沿边行走的范围，进而包围当前一次确定的所述预设房间清洁分区、或同一所述预限定清洁区域内合并的所述预设房间清洁分区；其中，所述预限定清洁区域的覆盖区域等效于正方形的实际物理区域，这个正方形的实际物理区域的边长与室内待清扫区域的尺寸相关。该技术方案针对每个规划起点位置对应设置一个限制沿边范围的矩形区域，用于提前框定机器人规划预设房间清洁分区的区域范围，也防止机器人无休止地沿边行走。
进一步地，所述预设房间清洁分区的具体判断方法包括：当围成所述初始房间清洁分区的轮廓边界线段都不是非墙体障碍物线段，且所述初始房间清洁分区内部的孤立障碍物线段的长度小于墙体拟合数量值的像素点个数对应的线段长度与所述初始房间清洁分区的任一边长度的预设比值中相对小的数值时，确定所述初始房间清洁分区属于所述预设房间清洁分区；当围成所述初始房间清洁分区的其中一条所述轮廓边界线段是非墙体障碍物线段，或者，所述初始房间清洁分区内部的孤立障碍物线段的长度大于或等于墙体拟合数量值的像素点个数对应的线段长度，或所述初始房间清洁分区内部的孤立障碍物线段的长度大于或等于所述初始房间清洁分区的其中一边长度的预设比值时，确定所述初始房间清洁分区不属于所述预设房间清洁分区；其中，所述轮廓边界线段根据白色像素点的个数划分为非墙体障碍物线段和墙体障碍物线段，非墙体障碍物线段中的白色像素点的个数大于或等于预设门限值，而墙体障碍物线段的则小于预设门限值；其中，激光地图中还存在扫描出的孤立障碍物线段，所述孤立障碍物线段的长度只要大于或等于所述初始房间清洁分区的其中一边长度的预设误差比值和墙体拟合数量值的像素点个数对应的线段长度这两种线段长度的其中一个时，所述孤立障碍物线段被标记为所述墙体障碍物线段。该技术方案通过判断边界线段长度来确定所述预设房间清洁分区的环境特征，排除其他区域的障碍物直线的干扰作用，并将不可忽略的长度的孤立障碍物线段拟合为物理墙体，减小轮廓边界线段误判为墙体的影响，使得所述预设房间清洁分区几乎由墙体围成。
进一步地，所述步骤11的具体方法包括：在所述预限定清洁区域内，从所述规划起点位置开始统计当前构建的激光地图的图像像素点；每当沿着X轴方向统计到纵坐标相同的黑色像素点的个数超过预设边界门限值时，标记出这些纵坐标相同的黑色像素点的连接形成的所述轮廓边界线段，使得所述预限定清洁区域内沿X轴方向延伸的区域被对应的轮廓边界线段划分；每当沿着Y轴方向统计到横坐标相同的黑色像素点的个数超过预设边界门限值时，标记出这些横坐标相同的黑色像素点的连接形成的所述轮廓边界线段，使得所述预限定清洁区域内沿Y轴方向延伸的区域被对应的轮廓边界线段划分。该技术方案根据同一坐标轴方向上分布的黑色像素点的数目在所述预限定清洁区域内选择具备一定程度可通行性的区域标记出轮廓边界线段，围成所述预设房间清洁分区的轮廓边界线段可以相互对齐以使得房间区域划分更为规整合理，也确保标记出的轮廓边界线段能够框定出支持机器人连续沿边行走的矩形工作区域。
一种芯片，内置控制程序，所述控制程序用于控制移动机器人执行所述清洁分区规划方法。
一种机器人，该机器人装配激光传感器，该机器人内置所述的芯片，用于配置所述机器人在沿边行走过程中分割出所述预设房间清洁分区。本技术方案不需要预存有完整的全局地图，而是根据沿边过程中激光扫描获取的地图图像像素信息，在所述预限定清洁区域中实时划分出机器人的初始房间清洁分区，并在同一所述预限定清洁区域中，通过反复迭代处理未清洁区域的墙体边界来拓展机器人的初始房间清洁分区， 从而确保在同一所述预限定清洁区域中最终形成的所述预设房间清洁分区的轮廓边界与室内家居房间墙体边界相似，提高机器人沿着所述预设房间清洁分区的边界导航的效率，也有效预防机器人在所述预设房间清洁分区内重复清扫。
附图说明
图1是机器人移动至规划起点位置O时，在扫描构建的灰度化的激光地图上框定预限定清洁区域P1的效果图。
图2是机器人在沿边过程中从预限定清洁区域P1内划分出预设房间清洁分区#1的效果图。
图3是机器人移动至规划起点位置O1时，在扫描构建的灰度化的激光地图上框定预限定清洁区域P2的效果图。
图4是机器人在沿边过程中从预限定清洁区域P2内划分出预设房间清洁分区#2的效果图，其中，预设房间清洁分区#1和预设房间清洁分区#2在激光地图上是相邻接的。
图5是本发明实施例公开的一种机器人沿边行走的清洁分区规划方法的流程图。
具体实施方式
下面将结合本发明实施例中的附图，对本发明实施例中的技术方案进行详细描述。为进一步说明各实施例，本发明提供有附图。这些附图为本发明揭露内容的一部分，其主要用以说明实施例，并可配合说明书的相关描述来解释实施例的运作原理。配合参考这些内容，本领域普通技术人员应能理解其他可能的实施方式以及本发明的优点。图中的激光地图的图像尺寸并未按比例绘制。本发明实施例的方法程序的执行主体是激光导航机器人，这个激光导航机器人上可以设置激光传感器，该激光传感器可以检测障碍物，一般场景下，激光导航机器人在室内移动过程中，可以通过设置在该激光导航机器人上的激光传感器检测周围是否存在障碍物并即时标记在激光地图上。
作为一种具体的实施例，本发明公开一种机器人沿边行走的清洁分区规划方法，该清洁分区规划方法在机器人沿边行走过程中执行,如图5所示，具体包括以下步骤：
步骤S11、从机器人的沿边起点位置开始，根据机器人在当前框定的预限定清洁区域内扫描出的激光地图的像素点统计信息，定位出激光地图的各个坐标轴方向上的轮廓边界线段，然后进入步骤S12；其中，激光地图是机器人在沿边行走过程中扫描构建的；所述步骤S11的具体方法包括：在所述预限定清洁区域内，从所述规划起点位置开始统计当前构建的激光地图的图像像素点，在所述预限定清洁区域内的坐标轴方向上定位出轮廓边界线段，所述的各个坐标轴方向包括图示的X轴方向和Y轴方向。本实施例利用障碍物的直方图统计与所述规划起点位置距离不同的所述检测区间内的各种灰度级像素点出现的个数，也实现对相应灰度级的像素点形成的障碍物线段在激光地图上的定位。每当沿着X轴方向统计到纵坐标相同的黑色像素点的个数超过预设边界门限值时，标记出这些纵坐标相同的黑色像素点的连接形成的所述轮廓边界线段，使得所述预限定清洁区域内沿X轴方向延伸的区域被对应的轮廓边界线段划分；实际上后续步骤可能判断到所述轮廓边界线段不是墙体而被删除，再合并对应的分割区域，避免过度分割区域，但还是能描述出X轴方向上局部区域轮廓特征；每当沿着X轴方向统计到纵坐标相同的黑色像素点的个数没有超过预设边界门限值时，不沿着当前方向上标记出所述轮廓边界线段。每当沿着Y轴方向统计到横坐标相同的黑色像素点的个数超过预设边界门限值时，标记出这些横坐标相同的黑色像素点的连接形成的所述轮廓边界线段，使得所述预限定清洁区域内沿Y轴方向延伸的区域被对应的轮廓边界线段划分，否则不沿着当前方向上标记出所述轮廓边界线段，实现描述出Y轴方向上的局部区域轮廓特征，后续步骤可能会判断到该方向上确定的轮廓边界线段不是墙体而不能起到分割区域的功能，需要继续搜索下一个轮廓边界线段以逼近墙体边缘的尺寸大小在所述预限定清洁区域内框定出清洁分区。需要说明的是，轮廓边界线段与机器人的机体尺寸大小和预限定清洁区域的边长大小相关，可根据实际需要进行调整。本实施方式根据同一坐标轴方向上分布的黑色像素点的数目，在所述预限定清洁区域内选择具备一定程度可通行性的区域标记出轮廓边界线段，围成清洁分区的轮廓边界线段可以相互对齐以使得房间区域划分更为规整合理，也确保标记出的轮廓边界线段能够框定出用于机器人连续沿边行走的矩形工作区域。
步骤S12、从每个坐标轴方向上选择距离预设位置最近的轮廓边界线段，围成一个矩形的初始房间清洁分区，然后进入步骤S13；在本实施例中所述初始房间清洁分区属于图2所示的房间清洁分区#1的一部分矩形区域。
步骤S13、当初始房间清洁分区不属于预设房间清洁分区时，选择一个优先拓展的坐标轴方向(比如Y轴负方向)，删除初始房间清洁分区中垂直定位于优先拓展的坐标轴方向的非墙体障碍物线段，再沿着同一坐标轴方向拓展初始房间清洁分区，然后进入步骤S14。
步骤S14、判断步骤S13所述的优先拓展的坐标轴方向上定位出的与步骤S13删除的非墙体障碍物线段相邻的轮廓边界线段是否位于当前框定的预限定清洁区域内的未清扫区域，是则进入步骤S15，否则进入步骤S17。该步骤用以限定该优先拓展的坐标轴方向上的轮廓边界线段拓展范围，以避免轮廓边界线段框定的清洁分区与已清扫区域或未知区域有较多的重合区域。
步骤S15、判断步骤S13所述的优先拓展的坐标轴方向上定位出的轮廓边界线段与前述初始房间清洁分区的剩余轮廓边界线段相交是否没有形成预设房间清洁分区，是则返回步骤S13，即意味着步骤S14和步骤S15的判断条件都满足，则返回步骤S13继续在当前选择的坐标轴方向上的拓展；否则进入步骤S16。
步骤S16、确定所述预限定清洁区域被相应的轮廓边界线段划分出预设房间清洁分区，不需要在原来的所述预限定清洁区域内继续拓展。
步骤S17、停止在所述步骤S13当前选择的坐标轴方向上的拓展，再返回所述步骤S13以选择低一级的拓展优先级的坐标轴方向(比如X轴负方向)进行拓展，通过重复前述步骤使得所述预限定清洁区域被相应的轮廓边界线段划分出预设房间清洁分区。在前述步骤中，非墙体障碍物线段是属于轮廓边界线段但不代表墙体，围成所述预设房间清洁分区的轮廓边界线段与实际房间边界在预设误差允许范围内是重合的；实际房间边界包括所述预设房间清洁分区内部的障碍物的边界和/或所述实际沿边区域内部的障碍物的边界。
如图2的房间清洁分区#1的方框边界与实际环境的墙体边界相接近，即所述预限定清洁区域P1内分割出的预设房间清洁分区#1和所述预限定清洁区域P2内分割出的预设房间清洁分区#2都贴近实际房间的地形；其中，非墙体障碍物线段是不属于墙壁的轮廓边界线段，围成所述预设房间清洁分区的轮廓边界线段与实际房间边界在预设误差允许范围内是重合的；其中，实际房间边界包括所述预设房间清洁分区内部的障碍物的边界和/或所述实际沿边区域内部的障碍物的边界，实际房间是预限定清洁区域所处的实际物理区域。与现有技术相比，本实施例利用激光扫描获取的地图图像像素信息，在所述预限定清洁区域中实时划分出机器人的初始房间清洁分区，并在同一所述预限定清洁区域中，通过反复迭代处理未清洁区域的墙体边界来拓展机器人的初始房间清洁分区，从而确保在同一所述预限定清洁区域中最终形成的所述房间清洁分区的轮廓边界与实际房间边界相似。本实施例实现所述初始工作区域拓展成为面积更大且覆盖更广的封闭方框区域#1和#2，使得机器人能够沿着不断修正拓展的轮廓边界线段导航至实际环境的墙体上的目标位置，提高机器人沿着所述预设房间清洁分区的边界导航的效率，也有效预防机器人在所述预设房间清洁分区内重复清扫。
作为一种具体的实施例，所述清洁分区规划方法还包括：启动机器人开始规划区域后，在机器人实时扫描构建的激光地图上，以机器人的规划起点位置为中心框定一个预限定清洁区域，其中，规划起点位置是机器人在当前框定的预限定清洁区域内的启动位置。如图1所示，当前框定的预限定清洁区域是机器人在启动位置O(当前的规划起点位置)处限定一个以启动位置O为对角线交点的一个正方形方框区域，用于限制机器人沿边行走和构建的轮廓边界线段的范围，这个正方形方框区域是实际边长为12米的正方形的方框；值得注意的是，预限定清洁区域虽然是闭合区域，但是这个预限定清洁区域不是全部被机器人上的激光传感器探测扫描到；机器人在当前框定的预限定清洁区域内作沿边行走过程中，保持不跨出当前框定的预限定清洁区域，相当于不跨出边长为12米的正方形的实际物理区域。
再在当前的规划起点位置处框定的预限定清洁区域内选定一个距离最近的物理边界的沿边起点位置，控制机器人从所述规划起点位置开始沿着直线规划的路径向这个物理边界前进，直到机器人被配置为沿着这个物理边界作沿边行走；然后进入步骤S3。在该步骤中，所述机器人被配置为沿着这个物理边界作沿边行走的运动状态为：控制机器人在当前框定的预限定清洁区域内，从距离所述规划起点位置最近的沿边起点位置开始，沿着该沿边起点位置所在的物理边界开始作沿边行走，但是对于沿边的方向不作限定，其中，这个物理边界包括当前框定的预限定清洁区域内的障碍物的边界或墙体，使得机器人在沿着直线规划的路径前进的过程中，只有检测到障碍物的边界或墙体就可以开启沿边行走模式。加快机器人启动沿边行走的速度，减少导航路径。
作为一种实施例，当检测到从当前框定的预限定清洁区域中划分出符合所述预设房间清洁分区时，控制机器人在划分出的所述预设房间清洁分区内继续沿边行走，等到机器人沿完这个预设房间清洁分区一圈并返回所述规划起点位置时，控制机器人开始对这个预设房间清洁分区进行规划式清扫；其中，这个预设房间清洁分区包围所述规划起点位置、机器人从所述规划起点位置到启动沿边的行走路径、以及机器人已行走过的沿边路径。机器人在当前框定的预限定清洁区域内执行沿边行走的过程中，若检测到障碍物或墙体，则沿着当前检测到的障碍物的边界或墙体继续行走，同时标记机器人沿边过的障碍物或墙体的位置以及形状，但机器人没有停止去等待地图生成或划分房间区域。需要说明的是，不管机器人是否执行沿边行走，若在行走过程中检测到障碍物或墙体，都沿着当前检测到的障碍物的边界或墙体继续行走，同时标记机器人沿边过的障碍物或墙体的位置。从而通过沿边确定房间实际边界，使得当前沿边的边界与后续划分出的房间清洁分区的边界是一致的，有利于后续在同一区域内清扫过程中绕开已标记的障碍物。与现有技术相比，本实施例通过在沿边过程中实时划分所述预设房间清洁分区，来选择与实际房间环境边界相匹配的清洁区域进行先沿边再清扫作业，既可避免长时间沿边行走而不清扫。
值得注意的是，当后续规划起点位置发生变化时，如图1的规划起点位置O变为图3的位置O1时，所述预限定清洁区域的覆盖区域位置也发生变化，如图3的以位置O1为对角线交点的正方形方框区域所示。本实施例针对每个规划起点位置对应设置一个限制沿边范围的矩形区域，用于提前框定机器人的最大的沿边行走的范围和布局各个坐标轴方向上的轮廓边界线段。
作为一种实施例，在机器人沿边行走的过程中，当机器人在原位置处划分出一个所述预设房间清洁分区时，由于机器人的沿边行走速度较快，在沿边行走过程中不停下来等待划分预设房间清洁分区和地图生成，所以判断到机器人已经沿边行走出原位置处划分出的符合所述预设房间清洁分区，则控制机器人在新位置处继续划分出新的所述预设房间清洁分区，再将这两个所述预设房间清洁分区合并，支持机器人沿边行走返回所述规划起点位置，特别是机器人从当前划分好的所述预设房间清洁分区的缺口沿边走出，没来得及在当前划分好的预设房间清洁分区继续沿边行走而进入未清扫区域中，其中，本实施例中的原位置可以是前述步骤S11的沿边起点位置，当机器人沿边行走到新的符合所述预设房间清洁分区时，可以继续通过沿边行走返回所述规划起点位置。然后控制机器人在这两个合并的预设房间清洁分区内继续沿边行走，等到机器人沿完一圈并返回所述规划起点位置时，控制机器人开始对这两个合并的预设房间清洁分区进行规划式清扫；其中，这两个合并的预设房间清洁分区包围所述规划起点位置、机器人从所述规划起点位置到启动沿边的行走路径、以及机器人已行走过的沿边路径。需要说明的是，机器人在执行沿边行走的同时执行房间清洁分区的划分计算，使得机器人在当前框定的预限定清洁区域内较为流畅地执行沿边行走和清扫，不容易出现机器停顿的现象，机器人沿边过的边界与当前框定的预限定清洁区域对应的实际环境边界一致，提高机器人划分的房间清洁分区的环境适应性。
优选地，控制机器人在执行规划式清扫的过程中不跨出所述预设房间清洁分区，直到所述预设房间清洁分区都被规划式清扫路径覆盖，然后将机器人清扫覆盖的区域标记为已清扫区域，同时将机器人清扫覆盖的区域之外的已扫描区域标记为所述未清扫区域。具体地，当机器人完成当前一次确定的所述预设房间清洁分区的规划式清扫时，根据机器人标记的位置信息区分出所述已清扫区域和所述未清扫区域，即机器人使用规划式清扫路径覆盖过的所述预设房间清洁分区都检测为所述已清扫区域，而其他的已知区域(包括已经扫描标记过的未清扫区域)都检测为所述未清扫区域。机器人在弓字型规划清扫所述房间清洁分区的过程中也对所述预设房间清洁分区扫描建图以标记为已清扫区域。以提醒机器人不对已清扫区域进行重复清扫作业。从而实现在所述预限定清洁区域内准确区分已清扫区域和非清扫区域，有利于实现待清扫区域的全面覆盖。
在前述实施例中，所述预限定清洁区域是以所述规划起点位置为对角线交点的一个正方形方框区域，用于限制机器人沿边行走的范围，进而包围当前一次确定的所述预设房间清洁分区、或同一所述预限定清洁区域内合并的所述预设房间清洁分区；其中，所述预限定清洁区域的覆盖区域等效于正方形的实际物理区域，这个正方形的实际物理区域的边长与室内待清扫区域的尺寸相关。该技术方案针对每个规划起点位置对应设置一个限制沿边范围的矩形区域，用于提前框定机器人规划预设房间清洁分区的区域范围，也防止机器人无休止地沿边行走。
需要说明的是，前述的预限定清洁区域的覆盖区域等效于边长为12米的正方形的实际物理区域，所 述预限定清洁区域的覆盖区域位置随着机器人的规划起点位置的变化而变化。前述实施例针对每个规划起点位置对应设置一个限制沿边范围的矩形区域，用于提前框定机器人的最大沿边范围，也防止机器人无休止地执行沿边行走。结合图1和图2可知，机器人在图1所示的预限定清洁区域P1内的所述规划起点位置O处扫描划分出图2所示的预设房间清洁分区#1，所述规划起点位置O也位于预设房间清洁分区#1的内部，其中，所述预限定清洁区域P1是以所述规划起点位置O为对角线交点的一个正方形方框区域，用于包围预设房间清洁分区#1以限制机器人沿边行走的范围。本实施例从当前框定的预限定清洁区域内划分出符合预设房间清洁分区后，控制机器人在相匹配的区域内沿边行走，当机器人在这个相匹配的区域内沿完一圈并返回所述规划起点位置时，控制机器人在这个相匹配的区域内执行规划式清扫。
优选地，在机器人实时扫描构建的激光地图上，以下一个规划起点位置为中心框定出一个新的预限定清洁区域，再在这个新的预限定清洁区域内选定一个距离最近的物理边界的沿边起点位置，控制机器人从这个沿边起点位置开始沿着直线规划的路径向这个物理边界前进，直到机器人被配置为沿着这个物理边界作沿边行走；其中，这个物理边界包括这个新的预限定清洁区域内的障碍物的边界或墙体；下一个规划起点位置是机器人在这个新的预限定清洁区域内的启动位置。当机器人在这个新的预限定清洁区域内沿边行走时，执行前述实施例的步骤以在新的预限定清洁区域内规划出新的预设房间清洁分区。其中，控制机器人在执行规划式清扫和沿边行走的过程中绕过已经区分出的所述已清扫区域，包括上一次沿边行走过程中标记出的已清扫区域；其中，所述下一个规划起点位置是所述未清扫区域中与机器人当前结束规划式清扫的位置的距离最近的位置，所述下一个规划起点位置需要依靠机器人从当前结束规划式清扫的位置直线规划导航过去，机器人在行走的过程中，若检测到障碍物或墙体，则沿着当前检测到的障碍物的边界或墙体继续行走，直到导航至所述下一个规划起点位置。本实施例利用下一个规划起点位置框定新的预限定清洁区域，便于后续沿边过程中扫描出足够多的未知地图区域，框定更多的房间清洁分区或实际沿边区域，并绕过已清扫区域作沿边行走，减少不必要的导航路径。
具体地，对比图2和图3可知，机器人完成图1的预限定清洁区域P1内扫描划分出的所述预设房间清洁分区#1的弓字形规划清扫后，图2的预设房间清洁分区#1被标记为已清扫区域，而图2和图3的预设房间清洁分区#1的方框之外的地图区域则被标记为未清扫区域，图2的预设房间清洁分区#1标记的信息比图1的同一区域处标记信息多。然后控制机器人移动至图3所示的属于未清扫区域的规划起点位置O1处(相当于上述实施例的下一个规划起点位置)，再以规划起点位置O1为对角线交点框定一个新的预限定清洁区域，如图3的正方形方框P2所示。
对比图1、图2和图3扫描出的激光地图可知，图3的规划起点位置O1位于图1的规划起点位置O的左上方，图3的规划起点位置O1还是位于扫描出的已知激光地图区域内，且在图3所示的实施例中属于所述未清扫区域，规划起点位置O1距离图3的预设房间清洁分区#1的结束清扫位置最近。图3的预限定清洁区域P2相对于同样大小的图1的预限定清洁区域P1往左上方偏移，使得图3的预限定清洁区域P2中扫描出图1的预限定清洁区域P1所没扫描出的环境区域，然后机器人会在预限定清洁区域P2划分出的预设房间清洁分区内清扫建图，获取图4的预设房间清洁分区#4，,为即时构建的激光地图规划出更多的贴合实际墙体区域，但是，预限定清洁区域P2和预限定清洁区域P1这两个分布于不同区域覆盖范围的预限定清洁区域都用于限制机器人沿边行走的范围。同时，图3的预限定清洁区域P2包围图3中标记为已清扫区域的预设房间清洁分区#1，使得预限定清洁区域P2与图1的预限定清洁区域P1存在重合区域，这个重合区域包括了预设房间清洁分区#1；而后续预限定清洁区域P2内，基于优先拓展方向上的所述边界轮廓线段拓展出的预设房间清洁分区，没有与标记为已清扫区域的预设房间清洁分区#1出现重合区域。
对比图3和图4可知，机器人在图3所示的所述规划起点位置O1处扫描划分出图4所示的预设房间清洁分区#2，图4的预设房间清洁分区#2内标记的地图信息比图3的同一区域处标记的地图信息更多；所述规划起点位置O1也位于预设房间清洁分区#2的内部，所述预限定清洁区域P2包围预设房间清洁分区#2。其中，图4的预设房间清洁分区#2正好与图4的预设房间清洁分区#1相邻接，这两个预设房间清洁分区可以看作不存在重合区域，使得机器人在预设房间清洁分区#2内执行沿边行走和弓字型规划清扫时可以绕过预设房间清洁分区#1，避免重复清扫已清扫区域，减少清扫时间，提高机器人的清扫工作效率。同时，又由于先后划分出的预设房间清洁分区#1和#2是存在邻接关系的，即先后划分出的预设房间清洁分区是存在邻接关系的，有利于提高清扫区域的覆盖率。
在前述实施例的基础上，所述预设房间清洁分区的具体判断方法包括：当围成所述初始房间清洁分区的轮廓边界线段都不是非墙体障碍物线段，且所述初始房间清洁分区内部的孤立障碍物线段的长度小于墙体拟合数量值的像素点个数对应的线段长度与所述初始房间清洁分区的任一边长度的预设比值中相对小的数值时，框定的封闭区域的内部孤立障碍物尺寸不足以构成墙体，确定所述初始房间清洁分区是所述预设房间清洁分区；当围成所述初始房间清洁分区的其中一条所述轮廓边界线段是非墙体障碍物线段，或者，所述初始房间清洁分区内部的孤立障碍物线段的长度大于或等于墙体拟合数量值的像素点个数对应的线段长度，或所述初始房间清洁分区内部的孤立障碍物线段的长度大于或等于所述初始房间清洁分区的其中一边长度的预设比值时，确定所述初始房间清洁分区不属于所述预设房间清洁分区；其中，所述轮廓边界线段根据白色像素点的个数划分为非墙体障碍物线段和墙体障碍物线段，非墙体障碍物线段中的白色像素点的个数大于或等于预设门限值，而墙体障碍物线段的则小于预设门限值；其中，激光地图中还存在扫描出的孤立障碍物线段，所述孤立障碍物线段的长度只要大于或等于所述初始房间清洁分区的其中一边长度的预设误差比值和墙体拟合数量值的像素点个数对应的线段长度这两种线段长度的其中一个时，所述孤立障碍物线段被标记为所述墙体障碍物线段。本实施例通过框定所述初始房间清洁分区的轮廓边界线段的线段长度性质以及所述初始房间清洁分区内部的孤立障碍物线段长度来确定所述预设房间清洁分区的环境特征，排除其他区域的障碍物直线的干扰作用，并将不可忽略的长度的孤立障碍物线段拟合为物理墙体，减小轮廓边界线段误判为墙体的影响，确保室内构建的预设房间清洁分区的轮廓边界位置处都贴近墙体，使得划分出的预设房间清洁分区能够构成实际家居环境中的房间区域，提高机器人区分墙体与非墙体障碍物的准确性和智能化水平。
在流程图中表示或在此以其他方式描述的逻辑和/或步骤，例如，可以被认为是用于实现逻辑功能的可执行指令的定序列表，可以具体实现在任何计算机可读介质中，以供指令执行系统、装置或设备(如基于计算机的系统、包括处理器的系统或其他可以从指令执行系统、装置或设备取指令并执行指令的系统)使用，或结合这些指令执行系统、装置或设备而使用。就本说明书而言，“计算机可读介质”可以是任何可以包含、存储、通信、传播或传输程序以供指令执行系统、装置或设备或结合这些指令执行系统、装置或设备而使用的装置。计算机可读介质的更具体的示例(非穷尽性列表)包括以下：具有一个或多个布线的电连接部(电子装置)，便携式计算机盘盒(磁装置)，随机存取存储器(RAM)，只读存储器(ROM)，可擦除可编辑只读存储器(EPROM或闪速存储器)，光纤装置，以及便携式光盘只读存储器(CDROM)。另外，计算机可读介质甚至可以是可在其上打印所述程序的纸或其他合适的介质，因为可以例如通过对纸或其他介质进行光学扫描，接着进行编辑、解译或必要时以其他合适方式进行处理来以电子方式获得所述程序，然后将其存储在计算机存储器中。
一种芯片，内置控制程序，所述控制程序用于控制移动机器人执行所述清洁分区规划方法。要理解本文所述的清洁分区规划方法实施例可以由硬件、软件、固件、中间件、微代码或其任意组合来实现。对于硬件实现方式，处理单元可以在一个或多个专用集成电路(ASIC)、数字信号处理器(DSP)、数字信号处理器件(DSPD)、可编程逻辑器件(PLD)、现场可编程门阵列(FPGA)、处理器、控制器、微控制器、微处理器、被设计以执行本文所述功能的其他电子单元、或其组合内实现。当以软件、固件、中间件或微代码、程序代码或代码段来实现实施例时，可以将它们存储在诸如存储组件的机器可读介质中。
一种机器人，该机器人装配激光传感器，该机器人内置所述的芯片，用于配置所述机器人在沿边行走过程中分割出所述预设房间清洁分区。本实施例不需要预存有完整的全局地图，而是根据沿边过程中激光扫描获取的地图图像像素信息，在所述预限定清洁区域中实时划分出机器人的初始房间清洁分区，并在同一所述预限定清洁区域中，通过反复迭代处理未清洁区域的墙体边界来拓展机器人的初始房间清洁分区，从而确保在同一所述预限定清洁区域中最终形成的所述预设房间清洁分区的轮廓边界与室内家居房间墙体边界相似，提高机器人沿着所述预设房间清洁分区的边界导航的效率，也有效预防机器人在所述预设房间清洁分区内重复清扫。
上述实施例只为说明本发明的技术构思及特点，其目的是让熟悉该技术领域的技术人员能够了解本发明的内容并据以实施，并不能以此来限制本发明的保护范围。凡根据本发明精神实质所作出的等同变换或修饰，都应涵盖在本发明的保护范围之内。

Claims (10)

  1. 一种机器人沿边行走的清洁分区规划方法，其特征在于，该清洁分区规划方法在机器人沿边行走过程中执行,具体包括以下步骤：
    步骤11、从机器人的沿边起点位置开始，根据机器人在当前框定的预限定清洁区域内扫描出的激光地图的像素点统计信息，定位出激光地图的各个坐标轴方向上的轮廓边界线段；其中，激光地图是机器人在沿边行走过程中扫描构建的；
    步骤12、从每个坐标轴方向上选择距离预设位置最近的轮廓边界线段，围成一个矩形的初始房间清洁分区；
    步骤13、当初始房间清洁分区不属于预设房间清洁分区时，选择一个优先拓展的坐标轴方向，删除初始房间清洁分区中垂直定位于优先拓展的坐标轴方向的非墙体障碍物线段，再沿着同一坐标轴方向拓展初始房间清洁分区，然后进入步骤14；
    步骤14、判断步骤13所述的优先拓展的坐标轴方向上定位出的与步骤13删除的非墙体障碍物线段相邻的轮廓边界线段是否位于当前框定的预限定清洁区域内的未清扫区域，且判断该坐标轴方向上定位出的轮廓边界线段与前述初始房间清洁分区的剩余轮廓边界线段相交是否没有形成预设房间清洁分区，若两者都满足，则返回步骤13继续在当前选择的坐标轴方向上的拓展；
    当步骤13所述的优先拓展的坐标轴方向上定位出的与步骤13删除的非墙体障碍物线段相邻的轮廓边界线段不是位于当前框定的预限定清洁区域内的所述未清扫区域时，停止在所述步骤13当前选择的坐标轴方向上的拓展，再返回所述步骤13以选择低一级的拓展优先级的坐标轴方向进行拓展，使得所述预限定清洁区域被相应的轮廓边界线段划分出预设房间清洁分区；
    其中，非墙体障碍物线段是属于轮廓边界线段但不代表墙体，围成所述预设房间清洁分区的轮廓边界线段与实际房间边界在预设误差允许范围内是重合的；
    其中，实际房间边界包括所述预设房间清洁分区内部的障碍物的边界和/或所述实际沿边区域内部的障碍物的边界。
  2. 根据权利要求1所述清洁分区规划方法，其特征在于，还包括：在机器人实时扫描构建的激光地图上，先以一个规划起点位置为中心框定一个所述预限定清洁区域，再在当前框定的所述预限定清洁区域内选定一个距离最近的物理边界的沿边起点位置，控制机器人从这个沿边起点位置开始沿着直线规划的路径向这个物理边界前进，直到机器人被配置为沿着这个物理边界作沿边行走；
    其中，这个物理边界包括预限定清洁区域内的障碍物的边界或墙体；所述规划起点位置是机器人在当前框定的所述预限定清洁区域内的启动位置。
  3. 根据权利要求2所述清洁分区规划方法，其特征在于，当检测到从当前框定的预限定清洁区域中划分出符合所述预设房间清洁分区时，控制机器人在划分出的所述预设房间清洁分区内继续沿边行走，等到机器人沿完这个预设房间清洁分区一圈并返回所述规划起点位置时，控制机器人开始对这个预设房间清洁分区进行规划式清扫；其中，这个预设房间清洁分区包围所述规划起点位置、机器人从所述规划起点位置到启动沿边的行走路径、以及机器人已行走过的沿边路径。
  4. 根据权利要求2所述清洁分区规划方法，其特征在于，在机器人沿边行走的过程中，当机器人划分出一个所述预设房间清洁分区时，如果判断到机器人已经沿边行走出所述沿边起点位置划分出的所述预设房间清洁分区，则控制机器人继续划分出新的所述预设房间清洁分区，再将这两个所述预设房间清洁分区合并，然后控制机器人在这两个合并的预设房间清洁分区内继续沿边行走，等到机器人沿完一圈并返回所述规划起点位置时，控制机器人开始对这两个合并的预设房间清洁分区进行规划式清扫；其中，这两个合并的预设房间清洁分区包围所述规划起点位置、机器人从所述规划起点位置到启动沿边的行走路径、以及机器人已行走过的沿边路径。
  5. 根据权利要求3或4所述清洁分区规划方法，其特征在于，控制机器人在执行规划式清扫的过程中不跨出所述预设房间清洁分区，直到所述预设房间清洁分区都被规划式清扫路径覆盖，然后将机器人清扫覆盖的区域标记为已清扫区域，同时将机器人清扫覆盖的区域之外的已扫描区域标记为所述未清扫区域。
  6. 根据权利要求3或4所述清洁分区规划方法，其特征在于，所述预限定清洁区域是以所述规划起点位置为对角线交点的一个正方形方框区域，用于限制机器人沿边行走的范围，进而包围当前一次确定的所述预设房间清洁分区、或同一所述预限定清洁区域内合并的所述预设房间清洁分区；
    其中，所述预限定清洁区域的覆盖区域等效于正方形的实际物理区域，这个正方形的实际物理区域的边长与室内待清扫区域的尺寸相关。
  7. 根据权利要求6所述清洁分区规划方法，其特征在于，所述预设房间清洁分区的具体判断方法包括：
    当围成所述初始房间清洁分区的轮廓边界线段都不是非墙体障碍物线段，且所述初始房间清洁分区内部的孤立障碍物线段的长度小于墙体拟合数量值的像素点个数对应的线段长度与所述初始房间清洁分区的任一边长度的预设比值中相对小的数值时，确定所述初始房间清洁分区属于所述预设房间清洁分区；
    当围成所述初始房间清洁分区的其中一条所述轮廓边界线段是非墙体障碍物线段，或者，所述初始房间清洁分区内部的孤立障碍物线段的长度大于或等于墙体拟合数量值的像素点个数对应的线段长度，或所述初始房间清洁分区内部的孤立障碍物线段的长度大于或等于所述初始房间清洁分区的其中一边长度的预设比值时，确定所述初始房间清洁分区不属于所述预设房间清洁分区；
    其中，所述轮廓边界线段根据白色像素点的个数划分为非墙体障碍物线段和墙体障碍物线段，非墙体障碍物线段中的白色像素点的个数大于或等于预设门限值，而墙体障碍物线段的则小于预设门限值；
    其中，激光地图中还存在扫描出的孤立障碍物线段，所述孤立障碍物线段的长度只要大于或等于所述初始房间清洁分区的其中一边长度的预设误差比值和墙体拟合数量值的像素点个数对应的线段长度这两种线段长度的其中一个时，所述孤立障碍物线段被标记为所述墙体障碍物线段。
  8. 根据权利要求1或7所述清洁分区规划方法，其特征在于，所述步骤11的具体方法包括：
    在所述预限定清洁区域内，从所述规划起点位置开始统计当前构建的激光地图的图像像素点；
    每当沿着X轴方向统计到纵坐标相同的黑色像素点的个数超过预设边界门限值时，标记出这些纵坐标相同的黑色像素点的连接形成的所述轮廓边界线段，使得所述预限定清洁区域内沿X轴方向延伸的区域被对应的轮廓边界线段划分；
    每当沿着Y轴方向统计到横坐标相同的黑色像素点的个数超过预设边界门限值时，标记出这些横坐标相同的黑色像素点的连接形成的所述轮廓边界线段，使得所述预限定清洁区域内沿Y轴方向延伸的区域被对应的轮廓边界线段划分。
  9. 一种芯片，内置控制程序，其特征在于，所述控制程序用于控制移动机器人执行权利要求1至8中任一项所述清洁分区规划方法。
  10. 一种机器人，该机器人装配激光传感器，其特征在于，该机器人内置权利要求9所述的芯片，用于配置所述机器人在沿边行走过程中分割出所述预设房间清洁分区。
PCT/CN2020/131194 2020-06-12 2020-11-24 一种机器人沿边行走的清洁分区规划方法、芯片及机器人 WO2021248845A1 (zh)

Priority Applications (4)

Application Number Priority Date Filing Date Title
EP20940180.1A EP3985469A4 (en) 2020-06-12 2020-11-24 METHOD OF PLANNING A CLEANING SUB-AREA FOR ROBOT MOVING ALONG AN EDGE, CHIP AND ROBOT
JP2022539045A JP7462244B2 (ja) 2020-06-12 2020-11-24 ロボットの縁沿い走行中の清掃区画領域の計画方法、チップ及びロボット
US17/627,697 US11914391B2 (en) 2020-06-12 2020-11-24 Cleaning partition planning method for robot walking along boundry, chip and robot
KR1020227021759A KR20220107017A (ko) 2020-06-12 2020-11-24 로봇이 엣지를 따라 워킹하는 청소 분할 영역 계획 방법, 칩 및 로봇

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202010537628.0 2020-06-12
CN202010537628.0A CN111857127B (zh) 2020-06-12 2020-06-12 一种机器人沿边行走的清洁分区规划方法、芯片及机器人

Publications (1)

Publication Number Publication Date
WO2021248845A1 true WO2021248845A1 (zh) 2021-12-16

Family

ID=72986443

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2020/131194 WO2021248845A1 (zh) 2020-06-12 2020-11-24 一种机器人沿边行走的清洁分区规划方法、芯片及机器人

Country Status (6)

Country Link
US (1) US11914391B2 (zh)
EP (1) EP3985469A4 (zh)
JP (1) JP7462244B2 (zh)
KR (1) KR20220107017A (zh)
CN (1) CN111857127B (zh)
WO (1) WO2021248845A1 (zh)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117193278A (zh) * 2022-05-31 2023-12-08 深圳市普渡科技有限公司 动态沿边路径生成的方法、装置、计算机设备和存储介质

Families Citing this family (14)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111857127B (zh) * 2020-06-12 2021-10-01 珠海市一微半导体有限公司 一种机器人沿边行走的清洁分区规划方法、芯片及机器人
CN112484718B (zh) * 2020-11-30 2023-07-28 海之韵(苏州)科技有限公司 一种基于环境地图修正的边沿导航的装置和方法
CN112561927B (zh) * 2020-12-07 2024-03-12 深圳市愚公科技有限公司 图像区域划分方法、系统、电子设备及存储介质
CN112486182B (zh) * 2020-12-08 2022-12-02 南通大学 一种实现未知环境地图构建与路径规划的扫地机器人及其使用方法
CN112631299B (zh) * 2020-12-24 2023-09-26 南京苏美达智能技术有限公司 一种多区域多台割草机控制方法
CN113223019B (zh) * 2021-05-21 2024-03-26 深圳乐居智能电子有限公司 一种清扫区域的分区方法、装置及清扫设备
CN113223020B (zh) * 2021-05-21 2024-03-26 深圳乐居智能电子有限公司 一种清扫区域的分区方法、装置及清扫设备
CN115393372A (zh) * 2021-05-25 2022-11-25 速感科技（北京）有限公司 地图分区方法、装置、自主移动设备和存储介质
CN113503877A (zh) * 2021-06-22 2021-10-15 深圳拓邦股份有限公司 机器人分区地图建立方法、装置及机器人
CN116069005A (zh) * 2021-10-29 2023-05-05 美智纵横科技有限责任公司 一种机器人沿边路径规划方法、装置、机器人及存储介质
CN117193277A (zh) * 2022-05-30 2023-12-08 珠海一微半导体股份有限公司 基于地图区域轮廓的设置方法与机器人沿边结束控制方法
CN114995458A (zh) * 2022-06-27 2022-09-02 苏州澜途科技有限公司 清洁机器人全覆盖实时路径规划方法及装置
CN115268468B (zh) * 2022-09-27 2023-01-24 深圳市云鼠科技开发有限公司 清洁机器人的沿墙坐标修正方法、装置、设备以及介质
CN115500737B (zh) * 2022-09-28 2023-10-17 云鲸智能(深圳)有限公司 一种地面介质探测方法、装置及清洁设备

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP5158808B2 (ja) * 2009-02-23 2013-03-06 独立行政法人科学技術振興機構 ロボット制御システム及びロボット制御方法
US20180224856A1 (en) * 2016-04-11 2018-08-09 Aqua Products, Inc. Method for modifying an onboard control system of a pool cleaner, and power source for a pool cleaner
CN109363585A (zh) * 2018-12-17 2019-02-22 深圳市银星智能科技股份有限公司 分区遍历方法、清扫方法及其扫地机器人
CN109528090A (zh) * 2018-11-24 2019-03-29 珠海市微半导体有限公司 一种机器人的区域遍历方法和芯片以及清洁机器人
CN110597253A (zh) * 2019-09-05 2019-12-20 珠海市一微半导体有限公司 机器人的控制方法和芯片及激光式清洁机器人
CN111857127A (zh) * 2020-06-12 2020-10-30 珠海市一微半导体有限公司 一种机器人沿边行走的清洁分区规划方法、芯片及机器人

Family Cites Families (19)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20120101679A1 (en) * 2010-10-26 2012-04-26 Noel Wayne Anderson Method and system for enhancing operating performance of an autonomic mobile robotic device
TW201305761A (zh) * 2011-07-21 2013-02-01 Ememe Robot Co Ltd 自走機器人及其定位方法
JP5757900B2 (ja) * 2012-03-07 2015-08-05 日立オートモティブシステムズ株式会社 車両走行制御装置
EP2916189B1 (en) * 2014-03-06 2019-05-08 Hexagon Technology Center GmbH Quality assured manufacturing
CN104035444B (zh) * 2014-06-27 2016-08-24 东南大学 机器人地图构建存储方法
US9963155B2 (en) * 2015-05-29 2018-05-08 Clearpath Robotics, Inc. Method, system and apparatus for path control in unmanned vehicles
US9840003B2 (en) * 2015-06-24 2017-12-12 Brain Corporation Apparatus and methods for safe navigation of robotic devices
US9746852B1 (en) * 2015-08-17 2017-08-29 X Development Llc Using laser sensors to augment stereo sensor readings for robotic devices
US10168711B2 (en) * 2015-09-16 2019-01-01 Omron Adept Technologies, Inc. Method and apparatus for autonomous conveyance of transport carts
US9908702B2 (en) * 2016-02-05 2018-03-06 Invia Robotics, Inc. Robotic navigation and mapping
US10108193B2 (en) * 2016-05-27 2018-10-23 Glen C Wernersbach Mover system
KR102568114B1 (ko) * 2016-11-30 2023-08-18 현대오토에버 주식회사 자율 주행 제어 장치 및 방법
US10585440B1 (en) * 2017-01-23 2020-03-10 Clearpath Robotics Inc. Systems and methods for using human-operated material-transport vehicles with fleet-management systems
US10852730B2 (en) * 2017-02-08 2020-12-01 Brain Corporation Systems and methods for robotic mobile platforms
TW201832710A (zh) 2017-03-14 2018-09-16 聯潤科技股份有限公司 自走式清潔裝置分區清潔方法及使用該方法的自走式清潔裝置
CN108196555B (zh) * 2018-03-09 2019-11-05 珠海市一微半导体有限公司 自主移动机器人沿边行走的控制方法
US10982456B2 (en) * 2018-03-16 2021-04-20 Maytronic Ltd. Pool cleaning system
CN108507578B (zh) * 2018-04-03 2021-04-30 珠海市一微半导体有限公司 一种机器人的导航方法
CN109464074B (zh) * 2018-11-29 2021-05-28 深圳市银星智能科技股份有限公司 区域划分方法、分区清扫方法及其机器人

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP5158808B2 (ja) * 2009-02-23 2013-03-06 独立行政法人科学技術振興機構 ロボット制御システム及びロボット制御方法
US20180224856A1 (en) * 2016-04-11 2018-08-09 Aqua Products, Inc. Method for modifying an onboard control system of a pool cleaner, and power source for a pool cleaner
CN109528090A (zh) * 2018-11-24 2019-03-29 珠海市微半导体有限公司 一种机器人的区域遍历方法和芯片以及清洁机器人
CN109363585A (zh) * 2018-12-17 2019-02-22 深圳市银星智能科技股份有限公司 分区遍历方法、清扫方法及其扫地机器人
CN110597253A (zh) * 2019-09-05 2019-12-20 珠海市一微半导体有限公司 机器人的控制方法和芯片及激光式清洁机器人
CN111857127A (zh) * 2020-06-12 2020-10-30 珠海市一微半导体有限公司 一种机器人沿边行走的清洁分区规划方法、芯片及机器人

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
See also references of EP3985469A4 *

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117193278A (zh) * 2022-05-31 2023-12-08 深圳市普渡科技有限公司 动态沿边路径生成的方法、装置、计算机设备和存储介质

Also Published As

Publication number Publication date
US20220244739A1 (en) 2022-08-04
US11914391B2 (en) 2024-02-27
CN111857127A (zh) 2020-10-30
EP3985469A4 (en) 2023-01-18
CN111857127B (zh) 2021-10-01
KR20220107017A (ko) 2022-08-01
JP7462244B2 (ja) 2024-04-05
EP3985469A1 (en) 2022-04-20
JP2023508091A (ja) 2023-02-28

Similar Documents

Publication Publication Date Title
WO2021248845A1 (zh) 一种机器人沿边行走的清洁分区规划方法、芯片及机器人
WO2021248846A1 (zh) 一种机器人沿边行走的区域清扫规划方法、芯片及机器人
US20210041871A1 (en) Along-edge Walking Control Method for Autonomous Mobile Robot
CN112137529B (zh) 一种基于密集障碍物的清扫控制方法
WO2021243978A1 (zh) 一种基于激光地图的工作区域拓展方法、芯片及机器人
WO2022000961A1 (zh) 一种机器人越障的沿边路径选择方法、芯片及机器人
WO2022000960A1 (zh) 一种越障结束判断方法、越障控制方法、芯片及机器人
CN111949017B (zh) 一种机器人越障的沿边路径规划方法、芯片及机器人
CN112180924B (zh) 一种导航至密集障碍物的移动控制方法
WO2021238115A1 (zh) 全局栅格地图的地图遍历块建立方法、芯片及移动机器人
WO2022121745A1 (zh) 自清洁移动机器人返回基站的方法及自清洁移动机器人
WO2024037262A1 (zh) 一种机器人通过窄道的导航方法、芯片及机器人
CN114431771A (zh) 一种扫地机器人清扫方法及相关装置
CN114779777A (zh) 自移动机器人的传感器控制方法、装置、介质及机器人
WO2023231757A1 (zh) 基于地图区域轮廓的设置方法与机器人沿边结束控制方法
CN113064409A (zh) 一种动态分区方法、系统及清洁设备
CN111897336B (zh) 一种机器人沿边行为结束的判断方法、芯片及机器人
CN116449816A (zh) 一种搜寻充电座信号的运动控制方法、芯片及机器人
CN113110473A (zh) 基于连通性的区域判定方法、芯片及机器人
CN117826775A (zh) 一种区域分界线搜索方法及机器人
CN116465404A (zh) 基于预设探测距离范围内的最优碰撞点搜索方法
CN117826776A (zh) 基于地图轮廓的区域分界线搜索方法
CN116501028A (zh) 路径规划方法和机器人
CN116466695A (zh) 一种最优障碍物碰撞点搜索方法
CN116466694A (zh) 基于激光点的最优碰撞点搜索方法、芯片及机器人

Legal Events

Date Code Title Description
ENP Entry into the national phase

Ref document number: 2020940180

Country of ref document: EP

Effective date: 20220117

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

Ref document number: 20940180

Country of ref document: EP

Kind code of ref document: A1

ENP Entry into the national phase

Ref document number: 2022539045

Country of ref document: JP

Kind code of ref document: A

ENP Entry into the national phase

Ref document number: 20227021759

Country of ref document: KR

Kind code of ref document: A

NENP Non-entry into the national phase

Ref country code: DE