Door opening and closing detection method and mobile robot

Abstract

The application provides a door opening and closing detection method, a mobile robot and a computer readable storage medium. The door opening and closing detection method comprises the following steps: acquiring a specified position point of a target room and a distance between the target room, as a door detection distance of the target room; acquiring a door detection width of the target room; determining a point cloud limit angle of the target room according to the door detection distance and the door detection width; acquiring each point cloud of interest of the target room according to the point cloud limit angle when a mobile robot navigates to the specified position point; and detecting an opening and closing state of the door of the target room based on the robot navigation pose of each point cloud of interest and the specified position point. The application can improve the detection accuracy of the opening and closing state of the door.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of robots, in particular to a door opening and closing detection method, a mobile robot and a computer readable storage medium. BACKGROUND

[0002] With the further maturity of robot technology and the increasing demand of consumers for automated services, robots are applied to more and more scenarios, such as hotels, retail, warehouse logistics, etc.

[0003] In the related art, in order to improve the use efficiency of the mobile robot, the mobile robot needs to determine whether the door is open so as to perform the next operation. For example, when the mobile robot delivers goods to a designated room and detects that the door of the room is in an open state, the hatch door is automatically opened. For another example, when the mobile robot passes through the fire access door, it needs to detect that the fire access door is in an open state before continuing to drive forward. However, the present inventors have found in actual research and development that in the related art, the detection accuracy of the opening and closing state of the door is low. SUMMARY

[0004] The present application provides a door opening and closing detection method, a mobile robot and a computer readable storage medium, which can improve the detection accuracy of the opening and closing state of the door.

[0005] In a first aspect, the present application provides a door opening and closing detection method, which comprises:

[0006] obtaining a specified position point of a target room and a distance between the target room as a door detection distance of the target room;

[0007] obtaining a door detection width of the target room;

[0008] determining a point cloud limit angle of the target room according to the door detection distance and the door detection width;

[0009] obtaining each point cloud of interest of the target room according to the point cloud limit angle after the mobile robot navigates to the specified position point;

[0010] detecting the opening and closing state of the door of the target room based on each point cloud of interest and the robot navigation pose of the specified position point.

[0011] In a second aspect, the present application also provides a mobile robot, which comprises a processor and a memory, and the memory stores a computer program, and the processor invokes the computer program in the memory to execute any of the door opening and closing detection methods provided by the present application.

[0012] In a third aspect, the present application also provides a computer readable storage medium, which stores a computer program, and the computer program is loaded by a processor to execute the door opening and closing detection method.

[0013] In the present application, in a first aspect, by determining the point cloud limit angle of the target room according to the door detection distance and the door detection width of the target room, the point cloud data of interest can be dynamically determined for judging the opening and closing state of the room door, so that the point cloud detection range can be dynamically adjusted according to the actual delivery situation of different rooms (such as the room width, the distance between the mobile robot and the room door), and the detection accuracy of the opening and closing state of the room door is improved. In a second aspect, by dynamically determining the point cloud data of interest in combination with the door detection width, the problem of low detection accuracy of the opening and closing state of the room door caused by the room being too large or too small is avoided when a uniform point cloud detection range is used for detecting the opening and closing state of the room door in different rooms. In a third aspect, by dynamically determining the point cloud data of interest in combination with the door detection distance, the problem of low detection accuracy of the opening and closing state of the room door caused by the door detection distance being too large or too small is avoided when a uniform point cloud detection range is used for detecting the opening and closing state of the room door in different rooms. BRIEF DESCRIPTION OF DRAWINGS

[0014] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed in the embodiment description will be briefly introduced as follows. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can also be obtained by those skilled in the art without creative labor.

[0015] Figure 1 is a structural schematic block diagram of a mobile robot provided by an embodiment of the present application;

[0016] Figure 2 is a flowchart of a door opening and closing detection method provided by an embodiment of the present application;

[0017] Figure 3 is an explanatory schematic diagram of a point cloud limit angle in an embodiment of the present application;

[0018] Figure 4 is an explanatory schematic diagram of a navigation coordinate system and a robot coordinate system in an embodiment of the present application;

[0019] Figure 5 is an explanatory schematic diagram of determining the opening and closing indication information of the point cloud of interest in an embodiment of the present application;

[0020] Figure 6 is an embodiment schematic diagram of a door opening and closing detection process provided by an embodiment of the present application. DETAILED DESCRIPTION

[0021] With reference to the drawings and the embodiments of the present application, the technical solutions in the embodiments of the present application will be described clearly and completely. Obviously, the described embodiments are only some of the embodiments of the present application, but not all of the embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without creative efforts are within the scope of the present application.

[0022] The flowcharts shown in the drawings are only illustrative, and do not necessarily include all the contents and operations / steps, nor are they necessarily executed in the order described. For example, some operations / steps can be further decomposed, combined or partially merged, so the actual execution order may be changed according to actual situations.

[0023] In the description of the embodiments of the present application, it should be understood that the terms "first", "second" are used only for the purpose of description, and cannot be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined with "first", "second" can explicitly or implicitly include one or more of the features. In the description of the embodiments of the present application, the meaning of "multiple" is two or more, unless otherwise explicitly specified.

[0024] The following description is given in order to enable any person skilled in the art to practice and use the present application. In the following description, details are set forth in order to explain the application. It will be apparent to those skilled in the art that the application can be practiced without using these specific details. In other instances, well-known processes have not been described in detail in order to avoid unnecessarily obscuring the description of the embodiments of the present application. Therefore, the present application is not intended to be limited to the embodiments shown, but is to be accorded the widest scope consistent with the principles and features disclosed herein.

[0025] The embodiments of the present application provide a door opening and closing detection method, a mobile robot and a computer readable storage medium. The door opening and closing detection method can be applied to a mobile robot, which can be a cleaning robot, a meal delivery robot, etc.

[0026] Some embodiments of the present application will be described in detail below with reference to the accompanying drawings. The following embodiments and features in the embodiments can be combined with each other without conflict.

[0027] Figure 1 is a structural schematic block diagram of a mobile robot provided by the embodiments of the present application.

[0028] As Figure 1As shown, the mobile robot 100 comprises a processor 101 and a memory 102, which are connected through a bus 103, such as a PCIe (Peripheral Component Interconnect Express) bus.

[0029] Specifically, the processor 101 is configured to provide computing and control capabilities to support the operation of the entire mobile robot 100. The processor 101 can be a central processing unit (CPU), and can also be other general-purpose processors, digital signal processors (DSPs), application specific integrated circuits (ASICs), field programmable gate arrays (FPGAs) or other programmable logic devices, discrete gates or transistor logic components, discrete hardware components, etc. The general-purpose processor can be a microprocessor or any conventional processor.

[0030] Specifically, the memory 102 can be a Flash chip, a read-only memory (ROM) disk, an optical disk, a U disk or a mobile hard disk, etc.

[0031] Those skilled in the art can understand that, Figure 1 The structure shown in the figure is only a block diagram of part of the structure related to the embodiment of the present application, and does not constitute a limitation on the mobile robot to which the embodiment of the present application is applied. The specific mobile robot can include more or less components than those shown in the figure, or combine certain components, or have a different component arrangement.

[0032] The processor 101 is configured to run a computer program stored in the memory 102, and implement any one of the door opening and closing detection methods provided by the embodiments of the present application when executing the computer program. For example, the processor 101 is configured to run a computer program stored in the memory 102, and when executing the computer program, the following steps can be implemented:

[0033] acquire a specified position point of a target room and a distance between the target room, as a door detection distance of the target room; acquire a door detection width of the target room; determine a point cloud limit angle of the target room according to the door detection distance and the door detection width; acquire each point cloud of interest of the target room according to the point cloud limit angle when a mobile robot navigates to the specified position point; and detect an opening and closing state of a door of the target room based on the robot navigation pose of each point cloud of interest and the specified position point.

[0034] In some embodiments, the processor 101 is configured to run a computer program stored in the memory 102, and when the computer program is executed, the following steps can be implemented:

[0035] When the mobile robot navigates to the specified position point, the mobile robot is controlled to collect according to the point cloud limit angle to obtain first collection point cloud data of the target room; and each point cloud of the first collection point cloud data is taken as a point cloud of interest of the target room.

[0036] In some embodiments, the processor 101 is configured to run a computer program stored in the memory 102, and when the computer program is executed, the following steps can be implemented:

[0037] When the mobile robot navigates to the specified position point, the mobile robot is controlled to collect according to a preset collection angle to obtain second collection point cloud data of the target room; the included angle between a current iteration point cloud and the specified position point is taken as a discrimination included angle of the current iteration point cloud by iterating each point cloud in the second collection point cloud data; and if the discrimination included angle is less than or equal to the point cloud limit angle, the current iteration point cloud is taken as a point cloud of interest.

[0038] In some embodiments, the processor 101 is configured to run a computer program stored in the memory 102, and when the computer program is executed, the following steps can be implemented:

[0039] A first direction vector of the specified position point is acquired based on the robot navigation pose of the specified position point; a projection length of each point cloud of interest on a straight line corresponding to the first direction vector is taken as a projection length of each point cloud of interest based on the navigation coordinate system coordinates of each point cloud of interest; and a door opening and closing state of the target room is determined according to the projection length of each point cloud of interest and the door detection distance.

[0040] In some embodiments, the processor 101 is configured to run a computer program stored in the memory 102, and when the computer program is executed, the following steps can be implemented:

[0041] According to the projection length of the point cloud of the interest point and the door detection distance, the number of open state point clouds of the target room is obtained; when the number of open state point clouds is greater than a first preset point cloud number threshold, it is determined that the target room is in a door open state; or, when the number of open state point clouds is less than or equal to the first preset point cloud number threshold, it is determined that the target room is in a door closed state.

[0042] In some embodiments, the processor 101 is configured to run a computer program stored in the memory 102, and when the computer program is executed, the following steps can be implemented:

[0043] The difference between the projection length of each point cloud of interest and the door detection distance is obtained as the distance difference of each point cloud of interest; according to the distance difference of each point cloud of interest and a preset distance difference threshold, the state of each point cloud of interest is determined to obtain the opening and closing indication information of each point cloud of interest; and according to the opening and closing indication information of each point cloud of interest, the number of open state point clouds of the target room is obtained.

[0044] In some embodiments, the processor 101 is configured to run a computer program stored in the memory 102, and when the computer program is executed, the following steps can be implemented:

[0045] According to the projection length of the point cloud of the interest point and the door detection distance, the number of open state point clouds of the target room is obtained; when the number of open state point clouds is greater than a first preset point cloud number threshold, it is determined that the target room is in a door open state; or, when the number of open state point clouds is less than or equal to the first preset point cloud number threshold, it is determined that the target room is in a door closed state.

[0046] In some embodiments, the processor 101 is configured to run a computer program stored in the memory 102, and when the computer program is executed, the following steps can be implemented:

[0047] Based on the navigation coordinate system coordinates of each point cloud of interest and the navigation coordinate system coordinates of the specified position point, the second direction vector of each point cloud of interest is obtained; the included angle between the second direction vector of each point cloud of interest and the second direction vector is obtained as the projection angle of each point cloud of interest; and according to the projection angle of each point cloud of interest, the first direction vector and the second direction vector of each point cloud of interest, the projection length of each point cloud of interest is determined.

[0048] In some embodiments, the processor 101 is configured to run a computer program stored in the memory 102, and when the computer program is executed, the following steps can be implemented:

[0049] When it is detected that the target room is in the open state, the cabin door of the mobile robot is controlled to be opened.

[0050] It should be noted that, for the convenience and brevity of description, the specific working process of the mobile robot described above can refer to the corresponding process in the following house door opening and closing detection method embodiments, which will not be described here.

[0051] It should be noted that, Figure 1 The scenario in the foregoing is only used to explain the house door opening and closing detection method provided by the embodiments of the present application, but does not constitute a limitation on the application scenarios of the house door opening and closing detection method provided by the embodiments of the present application.

[0052] Please refer to Figure 2 , Figure 2 is a flowchart of a house door opening and closing detection method provided by the embodiments of the present application. The house door opening and closing detection method comprises steps 201-205, wherein:

[0053] 201, obtain a specified position point of a target room and a distance between the target room, as a house door detection distance of the target room.

[0054] Among them, the mobile robot can be a delivery robot, a meal delivery robot, etc.

[0055] Among them, the target room is a room that needs to be detected for the opening and closing state of the house door. For example, in the mobile robot hotel meal delivery scenario, the target room can be a hotel room to be delivered. For another example, in the mobile robot post station express distribution scenario, the target room can be a post station store.

[0056] Among them, the specified position point (denoted as p) can be a navigation position point of the target room. For example, in the mobile robot hotel goods distribution scenario, a navigation position point (for example, a position point 0.5 meters in front of the door of the target room) is set for each room, so that the mobile robot can navigate to the front of the door of the target room according to the navigation position point to complete the goods distribution of the target room.

[0057] Among them, the house door detection distance (denoted as L) is the distance between the room j and the specified position point of the room j.

[0058] In some embodiments, the house door detection distance of the target room can be pre-set according to the actual business scenario, for example, it can be determined by the deployment engineer of the mobile robot, and the house door detection distance is used to represent how far the position point of the mobile robot is stopped in front of the door of the target room.

[0059] 202, obtain the house door detection width of the target room.

[0060] The door detection width (denoted as W) is used to indicate the detection width of the point cloud of the room j when determining the open / close state of the door of the room j. For example, the door detection width of the room j can be set to be greater than or equal to the actual width of the room j, for example, the door detection width of the room j is greater than the actual width of the room j by about 10%.

[0061] There are various ways to determine the door detection width in step 202, for example, including:

[0062] (1) In some embodiments, the door detection width is a preset value. At this time, different door detection widths can be set for different rooms, and the room identifier of each room is associated with the door detection width and stored in a preset database; in step 202, the door detection width associated with the room identifier of the target room can be queried from the preset database based on the room identifier of the target room, to serve as the aspect detection width of the target room. For example, different door detection widths can be set for different room types, such as room 101 being a suite with a relatively large width, and the door detection width of room 101 can be set to 10 meters; room 102 is a single room with a relatively small width, and the door detection width of room 102 can be set to 5 meters; and the room identifier of room 101 can be associated with the door detection width of 10 meters and stored in the preset database, and the room identifier of room 102 can be associated with the door detection width of 5 meters and stored in the preset database.

[0063] (2) In some embodiments, the door detection width is dynamically determined according to the actual door width. At this time, the room identifier of each room can be associated with the actual door width and stored in a preset database; in step 202, first, the actual door width associated with the room identifier of the target room can be queried from the preset database based on the room identifier of the target room; then, according to a preset detection ratio (for example, the door detection width is greater than the actual width by about 10%, and the preset detection ratio can be set to 110%) and the actual door width, the aspect detection width of the target room is calculated.

[0064] 203. Determine the point cloud limit angle of the target room according to the door detection distance and the door detection width.

[0065] The point cloud limit angle is used to indicate an angle range of the point cloud of the point of interest of the room j. The point cloud limit angle is dynamically determined according to the door detection distance and the door detection width, and the point cloud limit angle is inversely related to the door detection distance and is positively related to the door detection width. Therefore, by dynamically determining the point cloud limit angle according to the door detection distance and the door detection width of the target room, the point cloud limit angle can be dynamically adjusted for different rooms, so that the detection range can be dynamically adjusted for the actual delivery situation of different rooms, and the detection accuracy of the door opening and closing is improved. On the one hand, by setting the point cloud limit angle of different rooms as a unified fixed value, the problem that the point cloud limit angle is set too small and the door cannot be completely detected is avoided. On the other hand, by setting the point cloud limit angle of different rooms as a unified fixed value, the problem that the point cloud limit angle is set too large and the point cloud data processing amount of the door opening and closing state detection is too large is avoided.

[0066] For example, please refer to Figure 3 , Figure 3 is a schematic diagram of the point cloud limit angle in the embodiment of the present application. For example, the door detection distance and the door detection width of the target room can be substituted into the following formula 1, and the point cloud limit angle φ is calculated according to the following formula 1:

[0067]

[0068] In formula 1, L represents the door detection distance of the target room, W represents the door detection width of the target room, and φ represents the point cloud limit angle of the target room.

[0069] 204, when the mobile robot navigates to the specified position point, each point cloud of interest of the target room is obtained according to the point cloud limit angle.

[0070] For easy understanding, please refer to Figure 4 , the following will first introduce some names involved in the embodiment:

[0071] 1, navigation map: the navigation map can be constructed by a mobile robot moving in an unknown environment (for example, a navigation map can be constructed for each floor in a hotel scene) by using a map construction technology (such as SLAM technology) to construct a map while moving, so as to obtain a navigation map of the unknown environment. The navigation map can be a three-dimensional map or a two-dimensional map, and the embodiment is described by taking the navigation map as a two-dimensional map.

[0072] 2, navigation coordinate system (i.e. global coordinate system): the reference coordinate system of the navigation map, used to describe the entire environment or background. For example, as Figure 4As shown in FIG. 1, assuming that the rectangular frame is the area range of the navigation map, the lower left corner of the navigation map can be taken as the origin O, the direction from the lower left corner of the navigation map to the lower right corner can be taken as the x-axis direction, and the direction from the lower left corner of the navigation map to the upper left corner can be taken as the y-axis direction, so as to construct the navigation coordinate system oxy. Thus, any point on the navigation map can be represented by using the navigation coordinate system.

[0073] In the embodiment, the navigation coordinate system coordinate refers to the coordinate obtained by using the navigation coordinate system. For example, as shown in FIG. 1, the navigation coordinate system coordinate can be represented by using two-dimensional coordinates (x, y). Figure 4

[0074] 3. Robot coordinate system (i.e., local coordinate system): The coordinate system connected with the mobile robot, which moves and rotates with the mobile robot. For example, as shown in FIG. 2, the center point of the mobile robot can be taken as the origin o', the front direction of the mobile robot can be taken as the x'-axis direction, and the front direction of the mobile robot can be taken as the y'-axis direction, so as to construct the navigation coordinate system o'x'y'. Figure 4

[0075] 4. Angle between the robot coordinate system and the navigation coordinate system: In the embodiment, when the x'-axis direction is parallel to the x-axis direction and the y'-axis direction is parallel to the y-axis direction, the angle θ between the robot coordinate system and the navigation coordinate system is 0°. Taking this as a reference point, the orientation angle of the mobile robot at a certain time point (i.e., the angle θ between the robot coordinate system and the navigation coordinate system) is equal to the cumulative angle of the clockwise rotation of the robot coordinate system relative to the navigation coordinate system xoy plane until the x'-axis direction is parallel to the x-axis direction and the y'-axis direction is parallel to the y-axis direction.

[0076] 5. Robot navigation pose: including the position representation and the attitude representation of the mobile robot.

[0077] 5.1. Position representation (i.e., navigation coordinate system coordinate): In the embodiment, the navigation coordinate system coordinate of the position point p (such as the projection point of the center point o' of the mobile robot in the navigation map) of the mobile robot in the navigation map is taken as the position representation.

[0078] 5.2. Attitude representation (i.e., orientation angle): In the embodiment, the angle between the robot coordinate system and the navigation coordinate system is taken as the attitude representation.

[0079] In the embodiment, the navigation coordinate system and the robot coordinate system are taken as two-dimensional coordinate systems for illustration. It can be understood that in some cases, the navigation coordinate system and the robot coordinate system can also be three-dimensional coordinate systems. Converting the specific coordinate relationship from two dimensions to three dimensions can also achieve the method of the embodiment.

[0080] ​​For example, since this embodiment uses a two-dimensional coordinate system for both the navigation coordinate system and the robot coordinate system, the robot navigation pose in this embodiment has three degrees of freedom: namely, movement along the x-axis, movement along the y-axis, and rotation perpendicular to the xoy plane of the navigation coordinate system. For example, as shown... Figure 3 As shown, assume the mobile robot follows the robot navigation pose (p) x ,p y When navigating to the designated location point p, the mobile robot's coordinates in the navigation coordinate system (p, θ) on the navigation map are... x ,p y The position of the mobile robot is represented by the coordinate system θ, and the angle θ between the robot coordinate system and the navigation coordinate system is represented by the posture of the mobile robot.

[0081] There are several ways to obtain the point clouds of interest for each target room in step 204. For example, they include:

[0082] (1) The mobile robot collects point clouds according to a preset collection angle. At this time, step 204 may specifically include the following steps 2041A to 2042A:

[0083] 2041A. After the mobile robot navigates to the designated location, the mobile robot is controlled to collect data based on the point cloud limit angle to obtain the first collected point cloud data of the target room.

[0084] The first point cloud data refers to the point cloud data collected by the mobile robot according to the point cloud limit angle.

[0085] 2042A. Each point cloud of the first collected point cloud data is taken as the point cloud of interest of the target room.

[0086] For example, such as Figure 3 As shown, taking the mobile robot collecting point cloud data through a LiDAR sensor as an example, when the mobile robot navigates to a designated location point p, assuming... The direction is the initial direction of the point cloud detection line of the mobile robot, which can be determined based on the point cloud extreme angle φ and the initial position of the point cloud detection line (reference). Figure 3 middle Determine the maximum sampling position on the left (reference). Figure 3 (middle-range radiation, Pa), maximum acquisition location on the right (reference) Figure 3 (mid-ray pb); then, the point cloud detection line of the lidar sensor controlling the mobile robot is from the initial position (reference) Figure 3 middle Rotate the point cloud to the left by the extreme angle φ to the maximum acquisition position on the left (reference). Figure 3 (middle ray pa), and from the initial position (reference) Figure 3 middle ) to rotate the point cloud limit angle φ to the right maximum collection position (refer to Figure 3 The point cloud collected by the point cloud probe line can be used as the first collection point cloud data C1 of the target room (refer to Figure 3 The point cloud in the scanning area formed by the rays pa and pb). Each point cloud in the first collection point cloud data C1 can be used as the point cloud of interest of the target room.

[0087] (2) The mobile robot collects point clouds according to the point cloud limit angle. At this time, step 204 can specifically include the following steps 2041B-2043B:

[0088] 2041B, after the mobile robot navigates to the specified position point, the mobile robot is controlled to collect according to the preset collection angle, to obtain the second collection point cloud data of the target room.

[0089] The second collection point cloud data refers to the point cloud data collected by the mobile robot according to the preset collection angle.

[0090] 2042B, traverse each point cloud in the second collection point cloud data, and obtain the included angle between the current traversed point cloud and the specified position point as the discrimination angle of the current traversed point cloud.

[0091] 2043B, if the discrimination angle is less than or equal to the point cloud limit angle, the current traversed point cloud is taken as the point cloud of interest.

[0092] For example, taking the collection of point cloud data by the mobile robot through the laser radar sensor as an example, assuming that the preset collection angle is the maximum detection angle of the laser radar sensor (such as 180°), the mobile robot can be controlled to collect according to the preset collection angle, to obtain the second collection point cloud data C2 of the target room. Then, the second collection point cloud data C2 can be processed as follows (2.1)-(2.6) to obtain the point cloud of interest of the target room:

[0093] (2.1) for the ith point cloud in the second collection point cloud data C2, the included angle between the ith point cloud and the specified position point p is obtained as the discrimination angle φ i of the ith point cloud; if the discrimination angle φ i of the ith point cloud is less than or equal to the point cloud limit angle φ, step (2.2) is entered; if the discrimination angle φ i of the ith point cloud is greater than the point cloud limit angle φ, step (2.3) is entered.

[0094] (2.2) if the discrimination angle φ i of the ith point cloud is less than or equal to the point cloud limit angle φ, the ith point cloud is taken as the point cloud of interest, and step (2.4) is entered.

[0095] (2.3) If the discriminant angle φi of the i-th point cloud is greater than the point cloud limit angle φ, the i-th point cloud is discarded (i.e., the i-th point cloud is not a point cloud of interest), and step (2.4) is entered. i

[0096] (2.4) It is detected whether i is equal to K. If i is equal to K, it is proved that each point cloud of the second collected point cloud data is traversed, and step (2.6) is entered. If i is less than K, it is proved that each point cloud of the second collected point cloud data is not traversed, and step (2.5) is entered.

[0097] Wherein, K is the total number of point clouds of the second collected point cloud data.

[0098] (2.5) Let i = i + 1, and enter step (2.1).

[0099] (2.6) End the determination process, and filter out all point clouds of interest of the target room from the second collected point cloud data.

[0100] It can be seen that, by controlling the mobile robot to collect point cloud data according to the point cloud limit angle, each point cloud of the first collected point cloud data can be directly taken as a point cloud of interest of the target room, so that the amount of point cloud collection can be reduced, and the process of determining whether the collected point cloud data is a point cloud of interest can be avoided, and the detection speed of the opening and closing state of the door of the target room can be improved.

[0101] It can be understood that, in addition to collecting point cloud data through a laser radar sensor, the mobile robot can also collect point cloud data through an RGBD sensor or other sensors.

[0102] 205. Based on the robot navigation pose of each point cloud of interest and the specified position point, the opening and closing state of the door of the target room is detected.

[0103] There are many implementation manners of step 205, and exemplarily, the following manners (1) to (4) are included:

[0104] (1) The size relationship between the number of opening state point clouds of the point clouds of interest and the first preset point cloud number threshold can be counted, and the opening and closing state of the door of the target room is determined. At this time, step 205 can specifically include the following steps 2051A-2055A:

[0105] 2051A, based on the robot navigation pose of the specified position point, a first direction vector of the specified position point is obtained.

[0106] Wherein, the first direction vector (denoted as ) is a direction vector of the specified position point, and the first direction vector ​According to the robot's navigation pose (p x ,p y Determined by θ).

[0107] For example, robot navigation pose (p x ,p y θ) includes the navigation coordinates of the mobile robot at a specified location point p (p x ,p y The first direction vector of the specified location point can be calculated using the following formula 2, along with the orientation angle θ of the mobile robot.

[0108]

[0109] 2052A. Based on the navigation coordinate system coordinates of each of the points of interest clouds, obtain the projection length of each of the points of interest clouds on the straight line corresponding to the first direction vector, and use it as the projection length of each of the points of interest clouds.

[0110] For example, step 2052A, which determines the projection length of each point of interest cloud, may specifically include: obtaining a second direction vector of each point of interest cloud based on the navigation coordinate system coordinates of each point of interest cloud and the navigation coordinate system coordinates of the specified location point; obtaining the angle between the second direction vector of each point of interest cloud and the second direction vector, as the projection angle of each point of interest cloud; and determining the projection length of each point of interest cloud based on the projection angle of each point of interest cloud, the first direction vector, and the second direction vector of each point of interest cloud.

[0111] Wherein, the second direction vector (denoted as) ) refers to the point cloud of interest c i The direction vector, the second direction vector Based on the navigation coordinates (p) of the specified location point x ,p y ) and the navigation coordinate system coordinates of the point cloud of interest And so on.

[0112] Please refer to Figure 5 For example, firstly, the point cloud of interest c can be... i navigation coordinate system coordinates and the navigation coordinate system coordinates of the specified location point (p) x ,p y Substituting into Formula 3 below, and referring to Formula 3 below, we can calculate the point cloud of interest c. i The second direction vector Then, the point cloud of interest c is calculated by referring to Formula 4 below. i projection angle φ iFinally, the point cloud of interest c i The second direction vector First direction vector And point cloud of interest c i projection angle φ i Substituting into Formula 5 below, the projection length dist of the point cloud of interest can be calculated with reference to Formula 5 below. i .

[0113]

[0114]

[0115] 2053A. Based on the projection length of the point cloud of interest and the door detection distance, obtain the number of open state point clouds of the target room.

[0116] There are multiple ways to implement step 2053A, including, for example, the following methods ① to ②:

[0117] ① In some embodiments, due to measurement errors of the lidar sensor and positioning errors of the mobile robot, in order to improve the detection accuracy of the door's open / closed state, if (point cloud of interest c) i projection length dist i If the door detection distance L) is greater than the preset distance difference threshold δ, then the point cloud of interest c will be... i As an open state point cloud, the number of open state point clouds in the target room is obtained. At this time, step 2053A specifically includes: obtaining the difference between the projection length of each of the point clouds of interest and the detection distance of the door, as the distance difference of each of the point clouds of interest; determining the state of each point cloud of interest according to the distance difference of each point cloud of interest and a preset distance difference threshold, and obtaining the opening and closing indication information of each point cloud of interest; obtaining the number of open state point clouds in the target room according to the opening and closing indication information of each point cloud of interest.

[0118] Among them, the opening and closing indication information is used to indicate the point cloud of interest c. i Is the point cloud in an enabled state?

[0119] For example, refer to Figure 5 Following Formula 6, first, obtain the point cloud of interest c. i projection length dist i The difference between the detection distance L and the door is taken as the point cloud of interest c. i The distance difference (i.e., dist) i -L); then, determine the point cloud of interest c i The distance difference (i.e., dist) i Is -L) greater than the preset distance difference threshold δ, such as Figure 5As shown in (b) above, if the point cloud of interest is c i The distance difference (i.e., dist) i If -L) is greater than the preset distance difference threshold δ, then the point cloud of interest c i As the open state point cloud, the timer N for the number of open state point clouds is incremented by 1, i.e., N = N + 1; otherwise, as Figure 5 As shown in (a), if the point cloud of interest c i The distance difference (i.e., dist) i If -L) is less than or equal to the preset distance difference threshold δ, then the point cloud of interest c i As the point cloud in the closed state, continue to determine the next point cloud of interest, c. i+1 Whether to treat it as an open point cloud. The value of timer N is the number of open point clouds in the target room when all point clouds of interest have been determined.

[0120] dist i -L>δ Formula 6

[0121] ② In some embodiments, if the point cloud of interest c i projection length dist i If the detection distance is greater than L (the distance to the door), then the point cloud of interest c will be... i As the open state point cloud, the number of open state point clouds in the target room is obtained. At this point, step 2053A specifically includes: determining the point cloud of interest c. i projection length dist i Is it greater than the door detection distance L? Figure 5 As shown in (b) above, if the point cloud of interest is c i projection length dist i If the detection distance L is greater than the door detection distance, then the point cloud of interest c i As the open state point cloud, the timer N for the number of open state point clouds is incremented by 1, i.e., N = N + 1; otherwise, as Figure 5 As shown in (a), if the point cloud of interest c i projection length dist i If the detection distance L is less than or equal to the door, the point cloud of interest c will be... i As the point cloud in the closed state, continue to determine the next point cloud of interest, c. i+1 Whether to treat it as an open point cloud. The value of timer N is the number of open point clouds in the target room when all point clouds of interest have been determined.

[0122] 2054A. When the number of point clouds in the open state is greater than the first preset point cloud number threshold, it is determined that the target room is in the open state.

[0123] 2055A, when the number of open state point clouds is less than or equal to a first preset point cloud number threshold, it is determined that the target room is in a closed door state.

[0124] The specific value of the first preset point cloud number threshold (denoted as Nt) can be set according to actual business scene requirements, and the specific value of the first preset point cloud number threshold is not limited here. For example, in order to reduce the point cloud noise caused by the laser radar sensor, the first preset point cloud number threshold Nt can be set to about 5-10.

[0125] (2) The size relationship between the number of closed state point clouds of the point cloud of interest and the second preset point cloud number threshold can be counted to determine the opening and closing state of the door of the target room. At this time, step 205 can specifically include the following steps 2051B-2055B:

[0126] 2051B, based on the robot navigation pose of the specified position point, a first direction vector of the specified position point is obtained.

[0127] 2052B, based on the navigation coordinate system coordinates of each point cloud of interest, the projection length of each point cloud of interest on the straight line corresponding to the first direction vector is obtained as the projection length of each point cloud of interest.

[0128] The implementation of steps 2051B-2052B is similar to steps 2051A-2052A, and specific reference can be made to the related description in the foregoing, which will not be repeated here.

[0129] 2053B, according to the projection length of the point cloud of interest and the door detection distance, the number of closed state point clouds of the target room is obtained.

[0130] There are many implementation ways of step 2053B, exemplarily including the following ways ①-②:

[0131] ①In some embodiments, due to the measurement error of the laser radar sensor and the positioning error of the mobile robot, in order to improve the detection accuracy of the opening and closing state of the door, if the projection length dist i of the point cloud of interest c i -door detection distance L)≤preset distance difference threshold δ, the point cloud of interest c iAs the closing state point cloud, the number of the closing state point clouds of the target room is obtained. At this time, step 2053B specifically comprises: obtaining the difference between the projection length of each of the point clouds of interest and the door detection distance as the distance difference of each of the point clouds of interest; performing state determination on each of the point clouds of interest according to the distance difference of each of the point clouds of interest and the preset distance difference threshold, to obtain the opening and closing indication information of each of the point clouds of interest; and obtaining the number of the closing state point clouds of the target room according to the opening and closing indication information of each of the point clouds of interest.

[0132] Wherein, the opening and closing indication information is used to indicate whether the point cloud of interest c i is a closing state point cloud.

[0133] For example, referring to Figure 5 and formula 7 as follows, first, the difference between the projection length dist i of the point cloud of interest c i and the door detection distance L is obtained as the distance difference (i.e. dist i -L) of the point cloud of interest c i ; then, it is determined whether the distance difference (i.e. dist i -L) of the point cloud of interest c i is less than or equal to the preset distance difference threshold δ, as shown in (a) of Figure 5 , if the distance difference (i.e. dist i -L) of the point cloud of interest c i is less than or equal to the preset distance difference threshold δ, the point cloud of interest c i is a closing state point cloud, and the counter N of the number of closing state point clouds is increased by 1, i.e. M=M+1; otherwise, as shown in (b) of Figure 5 , if the distance difference (i.e. dist i -L) of the point cloud of interest c i is greater than the preset distance difference threshold δ, the point cloud of interest c i is an opening state point cloud, and it is determined whether the next point cloud of interest c i+1 is a closing state point cloud. Until all point clouds of interest are determined, the value of the counter M is obtained as the number of the closing state point clouds of the target room.

[0134] dist i -L≤δ formula 7

[0135] ②In some embodiments, if the projection length dist i of the point cloud of interest c i is less than or equal to the door detection distance L, the point cloud of interest c iAs the closed point cloud, the number of closed point clouds in the target room is obtained. At this point, step 2053B specifically includes: determining the point cloud of interest c. i projection length dist i Is it less than or equal to the door detection distance L? Figure 5 As shown in (a), if the point cloud of interest c i projection length dist i If the detection distance L is less than or equal to the door distance, then the point cloud of interest c i As the point cloud in the closed state, the timer M for the number of closed point clouds is incremented by 1, i.e., M = N + 1; otherwise, as Figure 5 As shown in (b) above, if the point cloud c is of interest i projection length dist i If the detection distance L is greater than the door distance, then the point cloud of interest c will be... i As the point cloud in the active state, continue to determine the next point cloud of interest, c. i+1 Whether to classify it as a closed point cloud. The value of timer M is the number of closed point clouds in the target room when all point clouds of interest have been identified.

[0136] 2054B. When the number of point clouds in the closed state is less than or equal to the second preset point cloud number threshold, it is determined that the target room is in the open state.

[0137] 2055B. When the number of point clouds in the closed state is greater than the second preset point cloud number threshold, it is determined that the target room is in the closed state.

[0138] The specific value of the second preset point cloud quantity threshold can be set according to the actual business scenario requirements, and there is no restriction on the specific value of the second preset point cloud quantity threshold here.

[0139] (3) The relationship between the proportion of open point clouds in the point cloud of interest and a first preset proportion threshold can be statistically analyzed to determine the open / closed status of the door in the target room. In this case, step 205 may specifically include the following steps 2051C to 2056C:

[0140] 2051C. Based on the robot navigation pose at the specified location point, obtain the first direction vector of the specified location point.

[0141] 2052C. Based on the navigation coordinate system coordinates of each of the points of interest clouds, obtain the projection length of each of the points of interest clouds on the straight line corresponding to the first direction vector, and use it as the projection length of each of the points of interest clouds.

[0142] 2053C. Based on the projection length of the point cloud of interest and the door detection distance, obtain the number of open state point clouds of the target room.

[0143] Steps 2051C-2053C are similar to steps 2051A-2053A, and details are not repeated here.

[0144] 2054C, determining an open state point cloud proportion of the target room according to the open state point cloud quantity and the total number of the point clouds of interest.

[0145] For example, a ratio between the open state point cloud quantity and the total number of the point clouds of interest can be taken as the open state point cloud proportion of the target room.

[0146] 2055C, determining that the target room is in a door open state when the open state point cloud proportion is greater than or equal to a first preset proportion threshold.

[0147] 2056C, determining that the target room is in a door closed state when the open state point cloud proportion is less than the first preset proportion threshold.

[0148] (4) The size relationship between the closed point cloud proportion of the point clouds of interest and the second preset proportion threshold can be determined to determine the door opening and closing state of the target room. At this time, step 205 can specifically include steps 2051D-2055D as follows:

[0149] 2051D, obtaining a first direction vector of the specified position point based on the robot navigation pose of the specified position point.

[0150] 2052D, obtaining a projection length of each point cloud of interest on a straight line corresponding to the first direction vector as a projection length of each point cloud of interest based on the navigation coordinate system coordinates of each point cloud of interest.

[0151] 2053D, obtaining a closed state point cloud quantity of the target room according to the projection length of the point cloud of interest and the door detection distance.

[0152] Steps 2051D-2053D are similar to steps 2051B-2053B, and details are not repeated here.

[0153] 2054D, determining a closed state point cloud proportion of the target room according to the closed state point cloud quantity and the total number of the point clouds of interest.

[0154] For example, a ratio between the closed state point cloud quantity and the total number of the point clouds of interest can be taken as the closed state point cloud proportion of the target room.

[0155] ​2055D. When the proportion of the closed state point cloud is greater than or equal to the second preset proportion threshold, it is determined that the target room is in the closed state.

[0156] 2056D. When the proportion of the closed point cloud is less than the second preset proportion threshold, it is determined that the target room is in the open door state.

[0157] Please refer to Figure 3 , Figure 5 and Figure 6 To better understand the embodiments of this application, the following example illustrates the door opening / closing detection process in this application, using the example of "a hotel delivery robot's workflow where the mobile robot delivers goods to the room door and autonomously determines the robot's door status by detecting the door's opening / closing state." Assume the mobile robot includes a navigation module (for controlling the robot to reach a designated location in the target room according to its navigation pose), a door status detection module (for detecting the door's opening / closing state using LiDAR), and a door control module (for controlling the robot's door opening / closing). In this case, as follows... Figure 6 As shown, the door opening and closing detection process can be as follows:

[0158] 1. Through the navigation module of the mobile robot, control the mobile robot to follow the robot's navigation pose (p x ,p y ,θ) to reach the designated location point in the target room.

[0159] 2. After the mobile robot arrives at the target room via the navigation module, the door status detection module of the mobile robot is activated; the door status detection module detects the open / closed status of the door in the target room. The implementation process of the door status detection module can be as follows (corresponding to steps 203-205):

[0160] 2.1) Obtain the point cloud data C2 from the lidar; for detailed implementation, refer to step 2041B.

[0161] 2.2) Set counter N to 0, and calculate the limiting angle of the point cloud within the region of interest (i.e., the limiting angle of the point cloud) based on the door detection width W and the door detection distance L. Calculate the direction vector at a specified location.

[0162] 2.3) Point cloud c in C2 i Calculate point cloud c i Direction vector And calculate the point cloud c i Direction vector Direction vector of the specified location point The included angle φ i ;

[0163] 2.4), if φ i <φ, the point cloud c i The projection length on the straight line corresponding to the direction vector

[0164]

[0165] 2.5), if dist i If L > δ, add 1 to the counter, i.e. N = N + 1;

[0166] 2.6), repeat steps 2.3), 2.4) and 2.5) until step 2.7) is entered when the statistics for all point clouds in C2 are completed;

[0167] 2.7), if N is greater than a set threshold Nt, return that the target room is in the open door state, otherwise return that the target room is in the closed door state.

[0168] 3, if the door state detection module detects that the target room is in the open door state, the cabin door control module of the mobile robot is controlled to open the cabin door; if the door state detection module detects that the target room is in the closed door state, the opening and closing state of the door is continuously detected until the target room is detected in the open door state to complete the opening of the cabin door.

[0169] From the above, in a first aspect, by determining the point cloud limit angle of the target room according to the door detection distance and the door detection width of the target room, the point cloud data of interest can be dynamically determined for judging the opening and closing state of the room door, so that the point cloud detection range can be dynamically adjusted according to the actual distribution situation of different rooms (such as room width, distance between mobile robot and door), and the detection accuracy of the opening and closing state of the room door is improved. In a second aspect, by dynamically determining the point cloud data of interest in combination with the door detection width, the problem of low detection accuracy of the opening and closing state of the room door caused by excessively large or small room is avoided when a uniform point cloud detection range is used for detecting the opening and closing state of the room door in different rooms. In a third aspect, by dynamically determining the point cloud data of interest in combination with the door detection distance, the problem of low detection accuracy of the opening and closing state of the room door caused by excessively large or small door detection distance is avoided when a uniform point cloud detection range is used for detecting the opening and closing state of the room door in different rooms.

[0170] Those skilled in the art can understand that all or part of the steps in the above door opening and closing detection method can be completed by instructions, or by related hardware controlled by instructions, which can be stored in a computer readable storage medium and loaded and executed by a processor.

[0171] To this end, an embodiment of the present application provides a computer readable storage medium, wherein a plurality of computer programs are stored, the computer programs being capable of being loaded by a processor to execute any of the door opening and closing detection methods provided by the embodiments of the present application. For example, the computer programs are capable of being loaded by the processor to execute the following steps:

[0172] obtaining a specified position point of a target room and a distance between the target room, as a door detection distance of the target room; obtaining a door detection width of the target room; determining a point cloud limit angle of the target room according to the door detection distance and the door detection width; obtaining each point cloud of interest of the target room according to the point cloud limit angle when a mobile robot navigates to the specified position point; and detecting a door opening and closing state of the target room based on each point cloud of interest and a robot navigation pose of the specified position point.

[0173] In some embodiments, the computer programs are capable of being loaded by the processor to execute the following steps:

[0174] obtaining first acquisition point cloud data of the target room by controlling the mobile robot to collect according to the point cloud limit angle when the mobile robot navigates to the specified position point; and taking each point cloud of the first acquisition point cloud data as a point cloud of interest of the target room.

[0175] In some embodiments, the computer programs are capable of being loaded by the processor to execute the following steps:

[0176] obtaining second acquisition point cloud data of the target room by controlling the mobile robot to collect according to a preset collection angle when the mobile robot navigates to the specified position point; obtaining an included angle between a current traversed point cloud and the specified position point as a discrimination included angle of the current traversed point cloud by traversing each point cloud in the second acquisition point cloud data; and taking the current traversed point cloud as a point cloud of interest if the discrimination included angle is less than or equal to the point cloud limit angle.

[0177] In some embodiments, the computer programs are capable of being loaded by the processor to execute the following steps:

[0178] obtaining a first direction vector of the specified position point based on a robot navigation pose of the specified position point; obtaining a projection length of each point cloud of interest on a straight line corresponding to the first direction vector as a projection length of each point cloud of interest based on navigation coordinate system coordinates of each point cloud of interest; and determining a door opening and closing state of the target room according to the projection length of each point cloud of interest and the door detection distance.

[0179] In some embodiments, the computer program is loadable into the working memory of a processor to cause the processor to perform the steps of:

[0180] According to the projection length of the point cloud of interest and the door detection distance, the number of open state point clouds of the target room is obtained; when the number of open state point clouds is greater than a first preset point cloud number threshold, it is determined that the target room is in a door open state; or, when the number of open state point clouds is less than or equal to the first preset point cloud number threshold, it is determined that the target room is in a door closed state.

[0181] In some embodiments, the computer program is loadable into the working memory of a processor to cause the processor to perform the steps of:

[0182] The difference between the projection length of each point cloud of interest and the door detection distance is obtained as the distance difference of each point cloud of interest; according to the distance difference of each point cloud of interest and a preset distance difference threshold, the state of each point cloud of interest is determined to obtain the opening and closing indication information of each point cloud of interest; and according to the opening and closing indication information of each point cloud of interest, the number of open state point clouds of the target room is obtained.

[0183] In some embodiments, the computer program is loadable into the working memory of a processor to cause the processor to perform the steps of:

[0184] According to the projection length of the point cloud of interest and the door detection distance, the number of open state point clouds of the target room is obtained; when the number of open state point clouds is greater than a first preset point cloud number threshold, it is determined that the target room is in a door open state; or, when the number of open state point clouds is less than or equal to the first preset point cloud number threshold, it is determined that the target room is in a door closed state.

[0185] In some embodiments, the computer program is loadable into the working memory of a processor to cause the processor to perform the steps of:

[0186] Based on the navigation coordinate system coordinates of each point cloud of interest and the navigation coordinate system coordinates of the specified position point, the second direction vector of each point cloud of interest is obtained; the included angle between the second direction vector of each point cloud of interest and the second direction vector is obtained as the projection angle of each point cloud of interest; and according to the projection angle of each point cloud of interest, the first direction vector and the second direction vector of each point cloud of interest, the projection length of each point cloud of interest is determined.

[0187] In some embodiments, the computer program is loadable into the working memory of a processor to cause the processor to perform the steps of:

[0188] When it is detected that the target room is in a door open state, the cabin door of the mobile robot is controlled to be opened.

[0189] The computer readable storage medium can include a read only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc.

[0190] In the above-mentioned door opening and closing detection method, computer readable storage medium and mobile robot embodiments, the description of each embodiment has its own focus. The parts not described in detail in a certain embodiment can be referred to the relevant description of other embodiments. Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the computer readable storage medium, the mobile robot and its corresponding units described above and the beneficial effects brought by them can be referred to the description of the door opening and closing detection method in the above embodiments, which will not be described here in detail.

[0191] The above describes in detail a door opening and closing detection method, a mobile robot and a computer readable storage medium provided by the embodiments of the present application. The principle and implementation manner of the present application are described by applying specific examples. The above embodiment description is only used to help understand the method and its core idea of the present application. Meanwhile, for those skilled in the art, according to the idea of the present application, the specific implementation manner and application range will be changed. In summary, the content of the specification should not be understood as a limitation of the present application.

Claims

1. A method of detecting opening and closing of a door, characterized by, The method comprises: acquiring a specified position point of a target room and a distance between the target room, as a door detection distance of the target room; acquiring a door detection width of the target room; determining a point cloud limit angle of the target room according to the door detection distance and the door detection width; after a mobile robot navigates to the specified position point, acquiring each point cloud of interest of the target room according to the point cloud limit angle; detecting an open-close state of a door of the target room based on a robot navigation pose of each point cloud of interest and the specified position point, wherein a size relationship between an open state point cloud quantity of the point cloud of interest and a first preset point cloud quantity threshold is counted to determine the open-close state of the door of the target room; the open state point cloud quantity is determined by: acquiring a difference between a projection length of each point cloud of interest and the door detection distance as a distance difference of each point cloud of interest; according to the distance difference of each point cloud of interest and a preset distance difference threshold, performing state determination on each point cloud of interest to obtain open-close indication information of each point cloud of interest; according to the open-close indication information of each point cloud of interest, acquiring the open state point cloud quantity of the target room.

2. The door opening and closing detection method according to claim 1, characterized by, after the mobile robot navigates to the specified position point, acquiring each point cloud of interest of the target room according to the point cloud limit angle, comprising: after the mobile robot navigates to the specified position point, controlling the mobile robot to collect according to the point cloud limit angle to obtain first collection point cloud data of the target room; each point cloud of the first collection point cloud data is taken as a point cloud of interest of the target room.

3. The door opening and closing detection method according to claim 1, characterized by, after the mobile robot navigates to the specified position point, acquiring each point cloud of interest of the target room according to the point cloud limit angle, comprising: after the mobile robot navigates to the specified position point, controlling the mobile robot to collect according to a preset collection angle to obtain second collection point cloud data of the target room; iterating each point cloud in the second collection point cloud data to acquire an included angle between a current iteration point cloud and the specified position point as a discrimination included angle of the current iteration point cloud; if the discrimination included angle is less than or equal to the point cloud limit angle, the current iteration point cloud is taken as a point cloud of interest.

4. The door opening and closing detection method according to claim 1, characterized by, based on the robot navigation pose of each point cloud of interest and the specified position point, detecting the open-close state of the door of the target room, comprising: based on the robot navigation pose of the specified position point, acquiring a first direction vector of the specified position point; based on navigation coordinate system coordinates of each point cloud of interest, acquiring a projection length of each point cloud of interest on a straight line corresponding to the first direction vector as a projection length of each point cloud of interest; determining the open-close state of the door of the target room according to the projection length of each point cloud of interest and the door detection distance.

5. The door opening and closing detection method according to claim 4, characterized by, determining the open-close state of the door of the target room according to the projection length of each point cloud of interest and the door detection distance, comprising: According to the projection length of the point cloud of the interest point and the door detection distance, an open state point cloud quantity of the target room is obtained; When the open state point cloud quantity is greater than a first preset point cloud quantity threshold, it is determined that the target room is in a door open state; Or, when the open state point cloud quantity is less than or equal to the first preset point cloud quantity threshold, it is determined that the target room is in a door closed state.

6. The door opening and closing detection method according to claim 4, characterized by, The method further comprises: According to the projection length of the point cloud of the interest point and the door detection distance, a closed state point cloud quantity of the target room is obtained; When the closed state point cloud quantity is less than or equal to a second preset point cloud quantity threshold, it is determined that the target room is in a door open state; Or, when the closed state point cloud quantity is greater than the second preset point cloud quantity threshold, it is determined that the target room is in a door closed state.

7. The door opening and closing detection method according to claim 4, characterized by, The method further comprises: Based on the navigation coordinate system coordinates of each point cloud of the interest point and the navigation coordinate system coordinates of the specified position point, a second direction vector of each point cloud of the interest point is obtained; An included angle between the second direction vector of each point cloud of the interest point and the second direction vector is obtained as a projection angle of each point cloud of the interest point; According to the projection angle of each point cloud of the interest point, the first direction vector and the second direction vector of each point cloud of the interest point, the projection length of each point cloud of the interest point is determined.

8. The door opening and closing detection method according to claim 1, characterized by, The method further comprises: When it is detected that the target room is in a door open state, the mobile robot is controlled to open a hatch.

9. A mobile robot, characterized by The mobile robot comprises a processor and a memory, and the memory stores a computer program. When the processor calls the computer program in the memory, the door opening and closing detection method according to any one of claims 1 to 8 is executed.

Images