Path planning method, device and computer-readable storage medium for disinfection robot

Abstract

The present invention provides a path planning method, device and computer-readable medium for a disinfection robot, which relates to the field of robots, including identifying whether there is a narrow door in the area to be disinfected, measuring the second distance between the disinfection robot and the narrow door; the camera takes a first image of the narrow door at the second distance from the narrow door under the first focal length condition, and identifies the second image corresponding to the narrow door in the first image; identifies the passable area and the ground baseline; identifies the current posture of the disinfection robot, generates a virtual image of the current posture at the second distance from the narrow door under the first focal length condition based on the actual size of the disinfection robot in the current posture, and obtains the bottom baseline of the current posture virtual image; overlaps the ground baseline and the bottom baseline of the passable area, and determines whether the current posture virtual image is within the range of the passable area: if so, passes through the narrow door. This method can enable the disinfection robot to quickly and accurately identify and pass through narrow doors or passages.

Description

Technical Field

[0001] The present invention relates to the field of robotics technology, and in particular to a path planning method, device, and computer-readable storage medium for a disinfection robot. Background Art

[0002] Common disinfection robots currently available are based on sweeping robots, with some modifications to enable movement and rotation. However, due to their significantly larger size than sweeping or service robots, their maneuverability is limited. In particular, identifying and navigating through narrow passages and doors often requires repeated collisions to construct a virtual map. However, due to the robot's unique structure, collisions can easily damage its disinfection arm and spill disinfectant, creating significant inconvenience.

[0003] Therefore, there is an urgent need for a method to improve the technical problem of disinfection robots quickly identifying and passing through narrow doors and passages. Summary of the Invention

[0004] In view of this, an object of the present invention is to provide a path planning method, device and computer-readable storage medium for a disinfection robot to improve the above-mentioned problems.

[0005] In the first aspect, an embodiment of the present invention provides a path planning method for a disinfection robot, comprising: identifying whether there is a narrow door in the area to be disinfected: if not, executing the disinfection task according to a preset path; if so, determining whether the threshold height of the narrow door meets the passable height: if not, replanning the path to avoid the narrow door; if so, continuing to perform the following steps: identifying the center point position of the narrow door, and establishing a vertical line perpendicular to the plane of the narrow door at the center point position; setting the projection of the vertical line on the ground as a first trajectory, driving the disinfection robot to walk a first distance along the first trajectory and then stop, and measuring the second distance between the disinfection robot and the narrow door; under the first focal length condition, the camera is located at the second distance from the narrow door to capture a first image of the narrow door, and identifying a second image corresponding to the narrow door in the first image; identifying a passable area in the area corresponding to the second image, and identifying the ground baseline of the passable area; identifying the current posture of the disinfection robot, and according to the actual posture of the disinfection robot The size is generated under the first focal length condition, and a virtual image of the current posture is located at the second distance from the narrow door, and the bottom baseline of the virtual image of the current posture is obtained; the ground baseline of the passable area and the bottom baseline of the virtual image of the current posture are overlapped, and it is judged whether the virtual image of the current posture is within the range of the passable area: if so, the disinfection robot is driven to pass through the narrow door; if not, the following steps are performed: the preset postures are selected in sequence from the preset posture database of the disinfection robot, and according to the actual size of the disinfection robot in the preset posture, a virtual image of the preset posture is generated under the first focal length condition, and the second distance from the narrow door is obtained according to the actual size of the disinfection robot in the preset posture, and the bottom baseline of the virtual image of the preset posture is obtained; the ground baseline of the passable area and the bottom baseline of the virtual image of the preset posture are overlapped, and it is judged whether the virtual image of the preset posture is within the range of the passable area: if so, the disinfection robot is driven to adjust to the preset posture corresponding to the preset posture virtual image, and then pass through the narrow door; if not, the path is re-planned to avoid the narrow door.

[0006] Preferably, an embodiment of the present invention provides a first possible implementation method of the first aspect, wherein identifying whether there is a narrow door in the area to be disinfected includes: presetting a narrow door database, detecting environmental data in the area to be disinfected, and obtaining detection information; comparing the narrow door data in the narrow door database with the detection information to identify whether there is a narrow door in the area to be disinfected.

[0007] Preferably, the method of "identifying the center point position of the narrow door and establishing a vertical line perpendicular to the plane of the narrow door at the center point position" includes: obtaining the positions of the door frames on the left and right sides of the narrow door, projecting ranging light to the same horizontal height positions of the door frames on both sides, measuring the third distance and the fourth distance of the door frames on both sides at the same horizontal height from the disinfection robot, and judging whether the third distance and the fourth distance are equal: if they are not equal, driving the disinfection robot to move in the direction of the door frame on the farther side, and re-obtaining the positions of the door frames on the left and right sides of the narrow door to judge the third distance and the fourth distance until the third distance and the fourth distance are equal; if they are equal, performing the following steps: shooting the narrow door image at the current moment, extracting the geometric information of the narrow door image, the geometric information including shape, side length, and corner points, calculating the center point of the narrow door image through the geometric information, projecting the center point to the narrow door, and identifying the center point position of the narrow door; establishing a vertical line perpendicular to the narrow door image at the center point of the narrow door image, and obtaining a vertical line perpendicular to the plane of the narrow door. Preferably, the method for judging whether the threshold height of a narrow door meets the passable height includes the following steps: using radar to identify whether there is an obstacle in the narrow door: if no obstacle is identified, the threshold height of the narrow door meets the passable height of the disinfection robot; if an obstacle is identified, the following steps are executed: obtaining the position information and geometric information of the obstacle in the narrow door, the position information including the distance from the narrow door in the horizontal direction and the distance from the ground in the height direction; the geometric information including shape, side length, and corner points; combining the position information and geometric information to judge whether the obstacle is a threshold: if it is judged not to be a threshold, replanning the route to avoid the narrow door; if it is judged to be a threshold, measuring the threshold height; and comparing the measured threshold height with the obstacle crossing height of the disinfection robot: if the measured threshold height is less than or equal to the obstacle crossing height, judging that the threshold height of the narrow door meets the passable height; if the measured threshold height is greater than the obstacle crossing height, judging that the threshold height of the narrow door does not meet the passable height.

[0008] Preferably, the method for setting the first focal length includes: using machine vision to gradually adjust the focal length to identify the narrow door, stopping adjusting the focal length when the complete narrow door is identified, recording the focal length at this time as the first focal length, and measuring the second distance between the current disinfection robot and the narrow door.

[0009] Preferably, the method for identifying the passable area includes identifying the narrow door image, the narrow door frame image, the threshold image and the ground baseline in the second image, removing the door frame edge area and the threshold image area in the closed area formed by the narrow door frame and the bottom baseline to obtain the passable area.

[0010] Preferably, the method for generating a virtual image of the current posture includes identifying the current posture of the disinfection robot, obtaining the actual size of the disinfection robot corresponding to the current posture from a preset posture database; and generating a virtual image of the current posture according to the actual size of the disinfection robot according to the scaling ratio under the conditions of a first focal length and a second distance from the narrow door.

[0011] Preferably, the method for overlapping the ground baseline of the passable area with the bottom baseline of the current posture virtual image includes covering the ground baseline with the bottom baseline and determining the number of straight lines after covering: if it is equal to 1, the ground baseline coincides with the bottom baseline; if it is not equal to 1, rotating the angle of the current posture virtual image and / or adjusting the height of the current posture virtual image until the bottom baseline covers the ground baseline.

[0012] Preferably, the method for determining whether the current posture virtual image is within the range of the passable area includes: projecting the current posture virtual image on the second image, repeatedly moving the projection position of the current posture virtual image within the second image, and determining whether the projected image of the current posture virtual image is completely within the passable area: if so, determining that the current posture virtual image is within the range of the passable area; if not, determining that the current posture virtual image is not within the range of the passable area.

[0013] Preferably, the actual size of the disinfection robot includes the length, width, height and angle of each component in various posture states of the disinfection robot.

[0014] Preferably, the method for identifying whether there is a narrow door in the area to be disinfected includes: when there are multiple narrow doors in the area to be disinfected, measuring the straight-line distance between the disinfection robot and each narrow door respectively, and giving priority to passing through the nearest narrow door.

[0015] Preferably, the posture database includes actual size data of the disinfection robot in multiple posture states and at multiple angles.

[0016] Preferably, the posture database includes transition time data between multiple postures.

[0017] Preferably, the disinfection robot is driven to adjust to a preset posture corresponding to the preset posture virtual image. The method includes obtaining the time required for the current posture to be adjusted to the preset posture according to the time data, and calculating the required moving speed of the disinfection robot toward the narrow door according to the required time and the second distance: if the required moving speed is greater than or equal to the maximum moving speed of the disinfection robot, the disinfection robot is controlled to move toward the narrow door at the maximum moving speed, and at the same time, the disinfection robot is driven to adjust to the preset posture corresponding to the preset posture virtual image; if the required moving speed is less than the maximum moving speed of the disinfection robot, the disinfection robot is driven to adjust to the preset posture corresponding to the preset posture virtual image, and then moves toward the narrow door at the maximum moving speed.

[0018] Preferably, the narrow gate database includes a narrow gate waveform database; the method for detecting environmental data in the area to be disinfected and obtaining detection information includes detecting the area to be disinfected by radar to form an echo signal, analyzing the echo signal and extracting waveform feature data, comparing the waveform feature data with the narrow gate waveform database of the narrow gate database, and identifying whether there is a narrow gate in the area to be disinfected.

[0019] Preferably, the narrow door database includes a narrow door image database; the method for detecting environmental data in the area to be disinfected and obtaining detection information includes photographing the area to be disinfected with a camera to generate an image of the area to be disinfected, performing image processing on the image of the area to be disinfected and extracting image feature data, comparing the image feature data with the narrow door image database of the narrow door database, and identifying whether there is a narrow door in the area to be disinfected.

[0020] Preferably, the method for measuring the second distance between the disinfection robot and the narrow door includes: measuring the second distance between the disinfection robot and the narrow door using a radar acoustic wave ranging method.

[0021] Preferably, the method for measuring the second distance between the disinfection robot and the narrow door includes: measuring the second distance between the disinfection robot and the narrow door using a binocular distance measuring device.

[0022] In the second aspect, an embodiment of the invention provides a path planning device for a disinfection robot, comprising a processor, a memory, a camera and a drive device; the memory is used to store program instructions, and the processor is used to execute the program instructions to implement the path planning method for the disinfection robot as described in the first aspect above.

[0023] In a third aspect, an embodiment of the invention provides a computer-readable storage medium, which stores computer instructions. When the instructions are executed by a processor, the path planning method of the disinfection robot as described in the first aspect above is implemented.

[0024] The present invention brings the following beneficial effects: the path planning method of the disinfection robot provided by the present invention can identify narrow doors, and determine whether the narrow door has obstacles such as thresholds, and determine whether obstacles such as thresholds can be passed through; the method identifies the center point position of the narrow door, establishes a vertical line perpendicular to the plane of the narrow door at the center point position to achieve the centering of the narrow door, and takes an image of the narrow door, and then identifies the passable area and the ground baseline in the narrow door image, and identifies the current posture of the disinfection robot, generates a current posture virtual image at a second distance from the narrow door under the first focal length condition according to the actual size of the disinfection robot in the current posture, and obtains the bottom baseline of the current posture virtual image; overlaps the ground baseline of the passable area with the bottom baseline of the current posture virtual image, and determines whether the current posture virtual image is within the range of the passable area; thereby determines whether the narrow door or passage can be passed through; in addition, the posture of the disinfection robot can be adjusted to adapt to the passable area to facilitate passing through the narrow door.

[0025] The path planning method for the disinfection robot provided by the present invention has the ability to quickly and easily identify narrow doors or passages. It uses calculation and image processing to determine whether it can pass through the narrow door or passage, which greatly simplifies the calculation data and improves the accuracy. At the same time, compared with traditional collision detection, it avoids damage to the equipment.

[0026] Other features and advantages of the present invention will be described in the following description, and in part will become apparent from the description, or understood by practicing the present invention. The purposes and other advantages of the present invention are realized and obtained by the structures particularly pointed out in the description, claims and drawings.

[0027] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, preferred embodiments are given below and described in detail with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] In order to more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the specific embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without paying any creative work.

[0029] Figure 1 A logical flow chart of a path planning method for a disinfection robot provided in an embodiment of the present invention;

[0030] Figure 2 A schematic diagram of the structure of a path planning device for a disinfection robot provided in the second embodiment of the present invention;

[0031] Figure 3This is a structural block diagram of the disinfection robot path planning device provided in Example 2 of the present invention. DETAILED DESCRIPTION

[0032] To make the objectives, technical solutions, and advantages of the embodiments of the present invention more clear, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the embodiments described are only part of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work shall fall within the scope of protection of the present invention.

[0033] Example 1

[0034] In order to facilitate understanding of this embodiment, the path planning method of the disinfection robot disclosed in the embodiment of the present invention is first introduced in detail.

[0035] The first embodiment of the present invention provides a path planning method for a disinfection robot, see Figure 1 The logical flow chart of the path planning method of the disinfection robot is shown.

[0036] The path planning method of the disinfection robot includes identifying whether there is a narrow door in the area to be disinfected: if not, executing the disinfection task according to the preset path; if it exists, judging whether the threshold height of the narrow door meets the passable height: if not, replanning the path to avoid the narrow door; if it meets, continuing to perform the following steps: identifying the center point position of the narrow door, and establishing a vertical line perpendicular to the plane of the narrow door at the center point; setting the projection of the vertical line on the ground as the first trajectory, driving the disinfection robot to walk a first distance along the first trajectory and then stop, and measuring the second distance between the disinfection robot and the narrow door; under the first focal length condition, the camera is located at the second distance from the narrow door to capture the first image of the narrow door, and identifies the second image corresponding to the narrow door in the first image; identifying the passable area in the area corresponding to the second image, and identifying the ground baseline of the passable area; identifying the current posture of the disinfection robot, and generating a first focal length at the first focal length according to the actual size of the disinfection robot in the current posture. Under the condition, a virtual image of the current posture is located at the second distance from the narrow door, and the bottom baseline of the virtual image of the current posture is obtained; the ground baseline of the passable area and the bottom baseline of the virtual image of the current posture are overlapped, and it is judged whether the virtual image of the current posture is within the range of the passable area: if so, the disinfection robot is driven to pass through the narrow door; if not, the following steps are performed: preset postures are selected from the preset posture database of the disinfection robot in sequence, and a virtual image of the preset posture is generated at the second distance from the narrow door under the first focal length condition according to the actual size of the disinfection robot in the preset posture, and the bottom baseline of the virtual image of the preset posture is obtained; the ground baseline of the passable area and the bottom baseline of the virtual image of the preset posture are overlapped, and it is judged whether the virtual image of the preset posture is within the range of the passable area: if so, the disinfection robot is driven to adjust to the preset posture corresponding to the preset posture virtual image, and then pass through the narrow door; if not, the path is re-planned to avoid the narrow door.

[0037] The first embodiment of the present invention brings the following beneficial effects: the path planning method of the disinfection robot provided by the embodiment of the present invention can identify narrow doors, and determine whether the narrow door has obstacles such as thresholds, and determine whether obstacles such as thresholds can be passed through; this method identifies the center point position of the narrow door, establishes a vertical line perpendicular to the plane of the narrow door at the center point position to achieve the centering of the narrow door, and takes an image of the narrow door, and then identifies the passable area and the ground baseline in the narrow door image, and identifies the current posture of the disinfection robot, generates a current posture virtual image at a second distance from the narrow door under the first focal length condition according to the actual size of the disinfection robot in the current posture, and obtains the bottom baseline of the current posture virtual image; overlaps the ground baseline of the passable area with the bottom baseline of the current posture virtual image, and determines whether the current posture virtual image is within the range of the passable area; thereby determines whether the narrow door or passage can be passed through; in addition, the posture of the disinfection robot can be adjusted to adapt to the passable area to facilitate passing through the narrow door.

[0038] The path planning method for the disinfection robot provided in the first embodiment of the present invention has the ability to quickly and easily identify narrow doors or passages, and can determine whether it can pass through the narrow door or passage by using calculation and image processing, which greatly simplifies the calculation data and improves the accuracy; at the same time, compared with traditional collision detection, it avoids damage to the equipment.

[0039] Preferably, identifying whether there is a narrow door in the area to be disinfected includes: presetting a narrow door database, detecting environmental data in the area to be disinfected, and obtaining detection information; comparing the narrow door data in the narrow door database with the detection information to identify whether there is a narrow door in the area to be disinfected.

[0040] Furthermore, the method of "identifying the center point position of the narrow door and establishing a vertical line perpendicular to the plane of the narrow door at the center point position" includes: obtaining the positions of the door frames on the left and right sides of the narrow door, projecting ranging light to the same horizontal height positions of the door frames on both sides, measuring the third distance and the fourth distance of the door frames on both sides at the same horizontal height from the disinfection robot, and judging whether the third distance and the fourth distance are equal: if they are not equal, driving the disinfection robot to move in the direction of the door frame on the farther side, and re-obtaining the positions of the door frames on the left and right sides of the narrow door to judge the third distance and the fourth distance until the third distance and the fourth distance are equal; if they are equal, executing the following steps: shooting the image of the narrow door at the current moment, extracting the geometric information of the narrow door image, the geometric information including shape, side length, and corner points, calculating the center point of the narrow door image through the geometric information, projecting the center point to the narrow door, and identifying the center point position of the narrow door.

[0041] It should be noted that the ranging light can be projected and detected by a laser ranging device to measure the distance.

[0042] A vertical line perpendicular to the narrow gate image is established at the center point of the narrow gate image to obtain a vertical line perpendicular to the narrow gate plane. In some embodiments, this can also be achieved by direct recognition through machine vision.

[0043] Furthermore, a method for determining whether the threshold height of a narrow door meets the passable height includes the following steps: using radar to identify whether there is an obstacle in the narrow door: if no obstacle is identified, the threshold height of the narrow door meets the passable height of the disinfection robot; if an obstacle is identified, performing the following steps: obtaining the position information and geometric information of the obstacle in the narrow door, the position information includes the distance from the narrow door in the horizontal direction and the distance from the ground in the height direction; the geometric information includes shape, side length, and corner points.

[0044] Combined with the position information and geometric information, determine whether the obstacle is a threshold: if it is not a threshold, replan the route to avoid the narrow door; if it is a threshold, measure the threshold height; and compare the measured threshold height with the obstacle clearance height of the disinfection robot: if the measured threshold height is less than or equal to the obstacle clearance height, determine that the threshold height of the narrow door meets the passable height; if the measured threshold height is greater than the obstacle clearance height, determine that the threshold height of the narrow door does not meet the passable height.

[0045] In this embodiment, the target obstacle can first be determined based on location information to determine whether it is within a range where a threshold may be located. If not, the target obstacle can be directly determined not to be a threshold. If so, the target obstacle can be determined to be a threshold-like object. If the target obstacle is determined to be a threshold-like object, the geometric information can be further used to determine whether the target obstacle matches the shape characteristics of a threshold. If so, the target obstacle can be determined to be a threshold. If not, the target obstacle can be determined not to be a threshold.

[0046] It should be noted that the method for setting the first focal length includes: using machine vision to gradually adjust the focal length to identify the narrow door, stopping adjusting the focal length when the complete narrow door is identified, recording the focal length at this time as the first focal length, and measuring the second distance between the current disinfection robot and the narrow door.

[0047] Furthermore, the method for identifying the passable area includes identifying the narrow door image, the narrow door frame image, the threshold image and the ground baseline in the second image, removing the door frame edge area and the threshold image area in the closed area formed by the narrow door frame and the bottom baseline to obtain the passable area.

[0048] Furthermore, the method for generating a virtual image of the current posture includes identifying the current posture of the disinfection robot, obtaining the actual size of the disinfection robot corresponding to the current posture from a preset posture database; and generating a virtual image of the current posture according to the actual size of the disinfection robot according to the scaling ratio under the conditions of a first focal length and a second distance from the narrow door.

[0049] It should be noted that the scaling relationship between the actual size of the object and the size of the virtual figure in the current pose depends on the focal length of the camera at the time of capture, as well as the distance between the actual object and the camera at the time of capture. In some embodiments, the scaling relationship can also be directly obtained from a pre-set scaling database, which includes scales of the actual size of the object and the virtual figure in the current pose, generated based on scaling relationships at different focal lengths and distances.

[0050] Furthermore, in the path planning method for the disinfection robot provided in this embodiment, the scaling relationship between the actual size of the object and the size of the virtual figure in the current pose depends on the focal length of the camera at the time of capture and the distance between the actual object and the camera at the time of capture. Specifically, the calculation method disclosed in patent CN106643518A or patent CN102607423A may be used.

[0051] Furthermore, the method for overlapping the ground baseline of the passable area with the bottom baseline of the current posture virtual image includes covering the ground baseline with the bottom baseline and determining the number of straight lines after the coverage: if it is equal to 1, the ground baseline and the bottom baseline overlap; if it is not equal to 1, rotating the angle of the current posture virtual image and / or adjusting the height of the current posture virtual image until the bottom baseline covers the ground baseline.

[0052] Furthermore, the method for determining whether the current posture virtual image is within the scope of the passable area includes: projecting the current posture virtual image on the second image, repeatedly moving the projection position of the current posture virtual image in the second image, and determining whether the projected image of the current posture virtual image is completely within the passable area: if so, determining that the current posture virtual image is within the scope of the passable area; if not, determining that the current posture virtual image is not within the scope of the passable area.

[0053] In this embodiment, the actual size of the disinfection robot includes the length, width, height and angle of each component of the disinfection robot in various posture states.

[0054] Preferably, the method for identifying whether there is a narrow door in the area to be disinfected includes: when there are multiple narrow doors in the area to be disinfected, measuring the straight-line distance between the disinfection robot and each narrow door respectively, and giving priority to passing through the nearest narrow door.

[0055] Furthermore, the posture database includes actual size data of the disinfection robot in various posture states and at various angles. The posture states may include upright posture, side posture, disinfection posture, and posture after being rotated at a certain angle.

[0056] The changed posture is the morphological change from the starting position to the ending posture.

[0057] It should be noted that the posture database includes transition time data between multiple postures.

[0058] It is worth mentioning that the method for driving the disinfection robot to adjust to the preset posture corresponding to the preset posture virtual image includes: obtaining the time required for the current posture to adjust to the preset posture according to the time data, and calculating the required moving speed of the disinfection robot to move toward the narrow door according to the required time and the second distance: if the required moving speed is greater than or equal to the maximum moving speed of the disinfection robot, the disinfection robot is controlled to move toward the narrow door at the maximum moving speed, and at the same time, the disinfection robot is driven to adjust to the preset posture corresponding to the preset posture virtual image; if the required moving speed is less than the maximum moving speed of the disinfection robot, the disinfection robot is driven to adjust to the preset posture corresponding to the preset posture virtual image, and then moves toward the narrow door at the maximum moving speed.

[0059] Preferably, the narrow gate database includes a narrow gate waveform database; the method for detecting environmental data in the area to be disinfected and obtaining detection information includes detecting the area to be disinfected by radar to form an echo signal, analyzing the echo signal and extracting waveform feature data, comparing the waveform feature data with the narrow gate waveform database of the narrow gate database, and identifying whether there is a narrow gate in the area to be disinfected.

[0060] In some embodiments, the narrow gate database includes a narrow gate image database; the method for detecting environmental data in the area to be disinfected and obtaining detection information includes photographing the area to be disinfected with a camera to generate an image of the area to be disinfected, performing image processing on the image of the area to be disinfected and extracting image feature data, comparing the image feature data with the narrow gate image database of the narrow gate database, and identifying whether there is a narrow gate in the area to be disinfected.

[0061] In addition, the method of detecting environmental data in the area to be disinfected and obtaining detection information can also be achieved by combining images with radar to achieve accurate detection.

[0062] Preferably, the method for measuring the second distance between the disinfection robot and the narrow door includes: measuring the second distance between the disinfection robot and the narrow door using a radar acoustic wave ranging method.

[0063] In some embodiments, the method for measuring the second distance between the disinfection robot and the narrow door includes: measuring the second distance between the disinfection robot and the narrow door using a binocular distance measuring device.

[0064] In addition, the method of measuring the second distance between the disinfection robot and the narrow door can also use laser ranging.

[0065] Example 2

[0066] Figure 2 A schematic diagram of the structure of a path planning device for a disinfection robot provided in the second embodiment of the present invention; Figure 3 This is a structural block diagram of the path planning device for the disinfection robot provided in the second embodiment of the present invention. Figure 2-3 , a path planning device for a disinfection robot provided in the second embodiment of the present invention

[0067] , including: a processor, a memory, a camera and a driving device; the memory is used to store program instructions, and the processor is used to execute the program instructions to implement the path planning method of the disinfection robot as described in Example 1.

[0068] Among them, the path planning method of the disinfection robot includes identifying whether there is a narrow door in the area to be disinfected: if not, executing the disinfection task according to the preset path; if it exists, judging whether the threshold height of the narrow door meets the passable height: if not, replanning the path to avoid the narrow door; if it meets, continuing to perform the following steps: identifying the center point position of the narrow door, and establishing a vertical line perpendicular to the plane of the narrow door at the center point position; setting the projection of the vertical line on the ground as the first trajectory, driving the disinfection robot to walk a first distance along the first trajectory and then stop, and measuring the second distance between the disinfection robot and the narrow door; under the first focal length condition, the camera is located at the second distance from the narrow door to shoot the first image of the narrow door, and identify the second image corresponding to the narrow door in the first image; identifying the passable area in the area corresponding to the second image, and identifying the ground baseline of the passable area; identifying the current posture of the disinfection robot, and generating a first focal length according to the actual size of the disinfection robot in the current posture. Under the distance condition, a virtual image of the current posture is located at the second distance from the narrow door, and the bottom baseline of the virtual image of the current posture is obtained; the ground baseline of the passable area and the bottom baseline of the virtual image of the current posture are overlapped, and it is judged whether the virtual image of the current posture is within the range of the passable area: if so, the disinfection robot is driven to pass through the narrow door; if not, the following steps are performed: preset postures are selected from the preset posture database of the disinfection robot in sequence, and according to the actual size of the disinfection robot in the preset posture, a virtual image of the preset posture is generated at the second distance from the narrow door under the first focal length condition, and the bottom baseline of the virtual image of the preset posture is obtained; the ground baseline of the passable area and the bottom baseline of the virtual image of the preset posture are overlapped, and it is judged whether the virtual image of the preset posture is within the range of the passable area: if so, the disinfection robot is driven to adjust to the preset posture corresponding to the preset posture virtual image, and then pass through the narrow door; if not, the path is re-planned to avoid the narrow door.

[0069] Example 3

[0070] The third embodiment of the present invention further provides a computer-readable storage medium, which stores computer instructions. When the instructions are executed by a processor, the path planning method of the disinfection robot as described in the first embodiment above is implemented.

[0071] Among them, the path planning method of the disinfection robot includes identifying whether there is a narrow door in the area to be disinfected: if not, executing the disinfection task according to the preset path; if it exists, judging whether the threshold height of the narrow door meets the passable height: if not, replanning the path to avoid the narrow door; if it meets, continuing to perform the following steps: identifying the center point position of the narrow door, and establishing a vertical line perpendicular to the plane of the narrow door at the center point position; setting the projection of the vertical line on the ground as the first trajectory, driving the disinfection robot to walk a first distance along the first trajectory and then stop, and measuring the second distance between the disinfection robot and the narrow door; under the first focal length condition, the camera is located at the second distance from the narrow door to shoot the first image of the narrow door, and identify the second image corresponding to the narrow door in the first image; identifying the passable area in the area corresponding to the second image, and identifying the ground baseline of the passable area; identifying the current posture of the disinfection robot, and generating a first focal length according to the actual size of the disinfection robot in the current posture. Under the distance condition, a virtual image of the current posture is located at the second distance from the narrow door, and the bottom baseline of the virtual image of the current posture is obtained; the ground baseline of the passable area and the bottom baseline of the virtual image of the current posture are overlapped, and it is judged whether the virtual image of the current posture is within the range of the passable area: if so, the disinfection robot is driven to pass through the narrow door; if not, the following steps are performed: preset postures are selected from the preset posture database of the disinfection robot in sequence, and according to the actual size of the disinfection robot in the preset posture, a virtual image of the preset posture is generated at the second distance from the narrow door under the first focal length condition, and the bottom baseline of the virtual image of the preset posture is obtained; the ground baseline of the passable area and the bottom baseline of the virtual image of the preset posture are overlapped, and it is judged whether the virtual image of the preset posture is within the range of the passable area: if so, the disinfection robot is driven to adjust to the preset posture corresponding to the preset posture virtual image, and then pass through the narrow door; if not, the path is re-planned to avoid the narrow door.

[0072] In addition, in the description of the embodiments of the present invention, unless otherwise expressly specified or limited, the terms "mounted," "connected," and "connected" should be understood in a broad sense. For example, they may refer to fixed connections, detachable connections, or integral connections; they may refer to mechanical connections or electrical connections; they may refer to direct connections or indirect connections through an intermediate medium; and they may refer to internal communication between two components. Those skilled in the art will understand the specific meanings of the above terms in the present invention based on the specific circumstances.

[0073] In the description of the present invention, it should be noted that the terms "center," "upper," "lower," "left," "right," "vertical," "horizontal," "inner," and "outer," etc., indicating orientations or positional relationships, are based on the orientations or positional relationships shown in the accompanying drawings and are intended solely to facilitate and simplify the description of the present invention. They are not intended to indicate or imply that the devices or components referred to must have, be constructed, or operate in a specific orientation, and therefore should not be construed as limitations on the present invention. Furthermore, the terms "first," "second," and "third" are used for descriptive purposes only and should not be construed as indicating or implying relative importance.

[0074] Finally, it should be noted that the above embodiments are only specific implementation methods of the present invention, which are used to illustrate the technical solutions of the present invention, rather than to limit them. The scope of protection of the present invention is not limited thereto. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that any person skilled in the art can modify or easily conceive of changes to the technical solutions described in the above embodiments within the technical scope disclosed by the present invention, or replace some of the technical features therein with equivalents. Such modifications, changes or replacements do not deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should be included in the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be based on the scope of protection of the claims.

Claims

1. A path planning method for a disinfection robot, characterized in that: include: Identify whether there is a narrow door in the area to be disinfected. If not, perform the disinfection task according to the preset path. If so, determine whether the threshold height of the narrow door meets the passable height. If not, replan the path to avoid the narrow door. If yes, continue with the following steps: Identify the center point of the narrow door and establish a vertical line perpendicular to the plane of the narrow door at the center point; Set the projection of the vertical line on the ground as a first trajectory, drive the disinfection robot to walk a first distance along the first trajectory and then stop, and measure a second distance between the disinfection robot and the narrow door; The camera captures a first image of the narrow door at a second distance from the narrow door under a first focal length condition, and identifies a second image corresponding to the narrow door in the first image; Identifying a traversable area within the area corresponding to the second image, and identifying a ground baseline of the traversable area; Identify the current posture of the disinfection robot, generate a virtual image of the current posture at a second distance from the narrow door under a first focal length condition based on the actual size of the disinfection robot in the current posture, and obtain a bottom baseline of the virtual image of the current posture; Overlap the ground baseline of the passable area with the bottom baseline of the current pose virtual image, and determine whether the current pose virtual image is within the range of the passable area: if so, drive the disinfection robot through the narrow door; if not, perform the following steps: Selecting preset poses from a preset pose database of the disinfection robot in sequence, generating a virtual image of the preset pose at a second distance from the narrow door under a first focal length condition according to the actual size of the disinfection robot in the preset pose, and obtaining a bottom baseline of the virtual image of the preset pose; Overlap the ground baseline of the passable area with the bottom baseline of the preset posture virtual image, and determine whether the preset posture virtual image is within the range of the passable area: if so, drive the disinfection robot to adjust to the preset posture corresponding to the preset posture virtual image, and then pass through the narrow door; if not, replan the path to avoid the narrow door.

2. The path planning method for a disinfection robot according to claim 1, characterized in that: The method for identifying whether a narrow door exists in the area to be disinfected includes: presetting a narrow door database, detecting environmental data in the area to be disinfected, and obtaining detection information; and comparing the narrow door data in the narrow door database with the detection information to identify whether a narrow door exists in the area to be disinfected.

3. The path planning method for a disinfection robot according to claim 1, characterized in that: The method of "identifying the center point position of the narrow door and establishing a vertical line perpendicular to the plane of the narrow door at the center point position" includes: obtaining the positions of the door frames on the left and right sides of the narrow door, projecting ranging light to the same horizontal height positions of the door frames on both sides, respectively measuring the third distance and the fourth distance of the door frames on both sides at the same horizontal height from the disinfection robot, and determining whether the third distance and the fourth distance are equal: if they are not equal, driving the disinfection robot to move in the direction of the door frame on the farther side, and re-obtaining the positions of the door frames on the left and right sides of the narrow door to determine the third distance and the fourth distance until the third distance and the fourth distance are equal; if they are equal, executing the following steps: Capture the current narrow gate image and extract its geometric information, including shape, side length, and corner points. Calculate the center point of the narrow gate image based on this geometric information, project the center point onto the narrow gate, and identify its center point. A vertical line perpendicular to the narrow gate image is established at the center point of the narrow gate image to obtain a vertical line perpendicular to the narrow gate plane.

4. The path planning method for a disinfection robot according to claim 1, characterized in that: The method for determining whether the threshold height of a narrow door meets the passable height includes the following steps: Use radar to identify whether there is an obstacle in the narrow door. If no obstacle is identified, the threshold height of the narrow door meets the passable height of the disinfection robot. If an obstacle is identified, perform the following steps: Obtain the location and geometric information of the obstacle inside the narrow door. The location information includes the horizontal distance from the narrow door and the height distance from the ground. The geometric information includes the shape, side length, and corner points. Combined with the position information and geometric information, determine whether the obstacle is a threshold: if it is not a threshold, replan the route to avoid the narrow door; if it is a threshold, measure the threshold height; and compare the measured threshold height with the obstacle clearance height of the disinfection robot: if the measured threshold height is less than or equal to the obstacle clearance height, determine that the threshold height of the narrow door meets the passable height; if the measured threshold height is greater than the obstacle clearance height, determine that the threshold height of the narrow door does not meet the passable height.

5. The path planning method for a disinfection robot according to claim 1, characterized in that: The method for setting the first focal length includes: using machine vision to gradually adjust the focal length to identify the narrow door, stopping adjusting the focal length when the complete narrow door is identified, recording the focal length at this time as the first focal length, and measuring the second distance between the current disinfection robot and the narrow door.

6. The path planning method for a disinfection robot according to claim 1, characterized in that: The method for identifying a passable area includes identifying a narrow door image, a narrow door frame image, a threshold image and a ground baseline in a second image, and removing a door frame edge area and a threshold image area within a closed area formed by the narrow door frame and the bottom baseline to obtain a passable area.

7. The path planning method for a disinfection robot according to claim 1, characterized in that: The method for generating the virtual image of the current posture includes identifying the current posture of the disinfection robot and obtaining the actual size of the disinfection robot corresponding to the current posture from a preset posture database; A virtual image of the current posture is generated according to the actual size of the disinfection robot and the scaling ratio under the conditions of a first focal length and a second distance from the narrow door.

8. The path planning method for a disinfection robot according to claim 1, characterized in that: A method for overlapping the ground baseline of a passable area with the bottom baseline of a current posture virtual image includes covering the ground baseline with the bottom baseline and determining the number of straight lines after the covering: if it is equal to 1, the ground baseline and the bottom baseline overlap; if it is not equal to 1, rotating the angle of the current posture virtual image and / or adjusting the height of the current posture virtual image until the bottom baseline covers the ground baseline.

9. The path planning method for a disinfection robot according to claim 1, characterized in that: A method for determining whether a virtual image in a current posture is within the range of a passable area includes: projecting the virtual image in the current posture on a second image, repeatedly moving the projection position of the virtual image in the current posture within the second image, and determining whether the projected image of the virtual image in the current posture is completely within the passable area: if so, determining that the virtual image in the current posture is within the range of the passable area; if not, determining that the virtual image in the current posture is not within the range of the passable area.

10. The path planning method for a disinfection robot according to claim 1, characterized in that: The actual size of the disinfection robot includes the length, width, height and angle of each component in various posture states of the disinfection robot.

11. The path planning method for a disinfection robot according to claim 1, characterized in that: The method for identifying whether there is a narrow door in the area to be disinfected includes: when there are multiple narrow doors in the area to be disinfected, measuring the straight-line distance between the disinfection robot and each narrow door respectively, and preferentially selecting the narrow door closest to pass through.

12. The path planning method for a disinfection robot according to claim 1, characterized in that: The posture database includes actual size data of the disinfection robot in multiple posture states and at multiple angles.

13. The path planning method for a disinfection robot according to claim 1, characterized in that: The posture database includes transition time data between multiple postures.

14. The path planning method for a disinfection robot according to claim 13, characterized in that: The method of driving the disinfection robot to adjust to the preset posture corresponding to the preset posture virtual image includes: obtaining the time required for the current posture to adjust to the preset posture according to the time data, and calculating the required moving speed of the disinfection robot to move toward the narrow door according to the required time and the second distance: if the required moving speed is greater than or equal to the maximum moving speed of the disinfection robot, the disinfection robot is controlled to move toward the narrow door at the maximum moving speed, and at the same time, the disinfection robot is driven to adjust to the preset posture corresponding to the preset posture virtual image; if the required moving speed is less than the maximum moving speed of the disinfection robot, the disinfection robot is driven to adjust to the preset posture corresponding to the preset posture virtual image, and then moves toward the narrow door at the maximum moving speed.

15. The path planning method for a disinfection robot according to claim 2, characterized in that: The narrow gate database includes a narrow gate waveform database; The method for detecting environmental data in the area to be disinfected and obtaining detection information includes detecting the area to be disinfected by radar to form an echo signal, analyzing the echo signal and extracting waveform feature data, comparing the waveform feature data with a narrow gate waveform database in a narrow gate database, and identifying whether there is a narrow gate in the area to be disinfected.

16. The path planning method for a disinfection robot according to claim 2, characterized in that: The narrow gate database includes a narrow gate image database; The method for detecting environmental data in the area to be disinfected and obtaining detection information includes photographing the area to be disinfected with a camera to generate an image of the area to be disinfected, performing image processing on the image of the area to be disinfected and extracting image feature data, comparing the image feature data with a narrow door image database of a narrow door database, and identifying whether a narrow door exists in the area to be disinfected.

17. The path planning method for a disinfection robot according to claim 1, characterized in that: The method for measuring the second distance between the disinfection robot and the narrow door includes: measuring the second distance between the disinfection robot and the narrow door by using a radar sound wave ranging method.

18. The path planning method for a disinfection robot according to claim 1, characterized in that: The method for measuring the second distance between the disinfection robot and the narrow door includes: using a binocular distance measuring device to measure the second distance between the disinfection robot and the narrow door.

19. A path planning device for a disinfection robot, characterized in that: include: Processor, memory, camera and drive device; The memory is used to store program instructions, and the processor is used to execute the program instructions to implement the path planning method of the disinfection robot as described in any one of claims 1 to 18.

20. A computer-readable storage medium, characterized in that The computer-readable storage medium stores computer instructions, which, when executed by a processor, implement the path planning method for the disinfection robot according to any one of claims 1 to 18.

Images