Elevator entering control method and device, robot and computer program product

Abstract

The invention is suitable for the technical field of robots, and provides an elevator entering control method and device, a robot and a computer program product. The elevator entering control method comprises the steps that point cloud classification is conducted on an area in front of a door of an elevator, and a fixed obstacle point cloud and a movable obstacle point cloud are obtained; according to the density of the point cloud of the fixed obstacle, the density of the point cloud of the moving obstacle and the change condition of the point cloud of the moving obstacle along with time, determining the overall obstacle density of the area in front of the door; when the overall obstacle density is smaller than or equal to the density threshold value, a robot is controlled to take the elevator; and when the overall obstacle density is larger than the density threshold value, the robot is controlled to give up to take the elevator. According to the embodiment of the invention, the robot can enter the elevator more reasonably, and the safety of the robot is improved.

Description

Technical Field

[0001] The present application belongs to the field of robotics technology, and in particular, relates to an elevator control method, device, robot and computer program product. Background Art

[0002] A robot is an intelligent machine that can work semi-autonomously or fully autonomously. Robots working in office buildings, shopping malls and other areas usually have the ability to take the elevator autonomously. The robot's elevator control in an elevator environment usually relies on sensors, but the sensor information is mostly used for obstacle avoidance and elevator door recognition during the elevator process. In some situations where it is not suitable to take the elevator, the robot may still perform the elevator operation, affecting the safety of the robot. Summary of the invention

[0003] The embodiments of the present application provide an elevator entry control method, device, robot and computer program product, which can make the robot's elevator entry timing more reasonable and improve the robot's safety.

[0004] A first aspect of an embodiment of the present application provides an elevator access control method, comprising: performing point cloud classification on the area in front of an elevator door to obtain a fixed obstacle point cloud and a mobile obstacle point cloud; determining the overall obstacle density of the area in front of the door according to the density of the fixed obstacle point cloud, the density of the mobile obstacle point cloud, and the change of the mobile obstacle point cloud over time; when the overall obstacle density is less than or equal to the density threshold, controlling the robot to take the elevator; when the overall obstacle density is greater than the density threshold, controlling the robot to give up taking the elevator.

[0005] In some embodiments of the first aspect, determining the overall obstacle density of the area in front of the door according to the density of the fixed obstacle point cloud, the density of the mobile obstacle point cloud, and the change of the mobile obstacle point cloud over time includes: acquiring a preset time window; counting the movement change of the mobile obstacle point cloud within the time window; if the movement change is less than or equal to a change threshold, determining the overall obstacle density according to the density of the fixed obstacle point cloud and the density of the mobile obstacle point cloud; if the movement change is greater than the change threshold, correcting the density of the mobile obstacle point cloud according to the change of the mobile obstacle point cloud over time, and determining the overall obstacle density of the area in front of the door according to the density of the corrected mobile obstacle point cloud and the density of the fixed obstacle point cloud.

[0006] In some embodiments of the first aspect, the density of the mobile obstacle point cloud is corrected according to the change of the mobile obstacle point cloud over time, including: determining the movement probability and the real-time movement influence range of the mobile obstacle point cloud within the time window; and correcting the density of the mobile obstacle point cloud according to the movement probability and the real-time movement influence range.

[0007] In some embodiments of the first aspect, the controlling the robot to take the elevator includes: generating an initial path for the robot to enter the elevator based on layout information of the elevator and obstacle locations; controlling the robot to move toward the elevator along the initial path, and during the movement, adjusting the initial path in real time based on real-time obstacle information until the robot enters the elevator or the time spent in the elevator is greater than a preset time.

[0008] In some embodiments of the first aspect, before the real-time adjustment of the initial path based on the real-time obstacle information is performed, the method includes: determining a scanning frequency and an angular resolution of the laser radar according to the distance between the robot and the elevator door of the elevator, and the overall obstacle density; and controlling the laser radar to perform point cloud scanning according to the scanning frequency and the angular resolution to obtain the real-time obstacle information.

[0009] In some embodiments of the first aspect, during the process of controlling the robot to take the elevator, it also includes: determining an estimated posture of the elevator door of the elevator based on the point cloud scanned by the laser radar; determining the deviation between the preset posture of the elevator door and the estimated posture; if the deviation exceeds a preset threshold, performing posture correction on the estimated posture to obtain a target posture; if the deviation does not exceed the preset threshold, using the estimated posture as the target posture; and controlling the robot to align with the elevator door according to the estimated posture.

[0010] In some embodiments of the first aspect, controlling the robot to take the elevator includes: obtaining historical elevator riding feedback data; determining an elevator riding strategy for the robot when taking the elevator based on the historical elevator riding feedback data; and controlling the robot to take the elevator based on the elevator riding strategy.

[0011] A second aspect of an embodiment of the present application provides an elevator control device, comprising: a point cloud classification unit, used to perform point cloud classification on the area in front of the elevator door to obtain a fixed obstacle point cloud and a mobile obstacle point cloud; a density determination unit, used to determine the overall obstacle density of the area in front of the door according to the density of the fixed obstacle point cloud, the density of the mobile obstacle point cloud, and the change of the mobile obstacle point cloud over time; an elevator control unit, used to control the robot to take the elevator when the overall obstacle density is less than or equal to the density threshold; the elevator control unit is also used to control the robot to give up taking the elevator when the overall obstacle density is greater than the density threshold.

[0012] A third aspect of an embodiment of the present application provides a robot, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the above-mentioned elevator control method when executing the computer program.

[0013] A fourth aspect of an embodiment of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the above-mentioned elevator control method are implemented.

[0014] A fifth aspect of an embodiment of the present application provides a computer program product, which, when executed on a robot, enables the robot to execute the steps of the above-mentioned elevator control method.

[0015] In an embodiment of the present application, by classifying the point cloud of the area in front of the elevator door, fixed obstacle point cloud and mobile obstacle point cloud are obtained, and the overall obstacle density of the area in front of the door is determined according to the density of the fixed obstacle point cloud, the density of the mobile obstacle point cloud, and the change of the mobile obstacle point cloud over time. When the overall obstacle density is less than or equal to the corrected density threshold, the robot is controlled to take the elevator, otherwise, the robot is controlled to give up taking the elevator. On the one hand, it is possible to decide whether to let the robot take the elevator with reference to the obstacle situation in the area in front of the door. On the other hand, the overall obstacle density used for the elevator decision is obtained based on the change of the mobile obstacle point cloud over time, so that the decision to enter the elevator fully considers the dynamic changes of the mobile obstacles, thereby making the timing of the robot entering the elevator more reasonable, thereby improving the safety of the robot. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0017] Figure 1 It is a schematic diagram of an implementation flow of an elevator entry control method provided in an embodiment of the present application;

[0018] Figure 2 It is a schematic diagram of a specific implementation process of determining the overall obstacle density provided in an embodiment of the present application;

[0019] Figure 3 This is a schematic diagram of a specific implementation process of controlling a robot to take an elevator provided in an embodiment of the present application;

[0020] Figure 4 It is a structural schematic diagram of an elevator access control device provided in an embodiment of the present application;

[0021] Figure 5 It is a schematic diagram of the structure of the robot provided in the embodiment of the present application. DETAILED DESCRIPTION

[0022] In order to make the purpose, technical solutions and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not intended to limit the present application. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without making creative work are protected by the present application.

[0023] It should be understood that when used in the present specification and the appended claims, the term "comprising" indicates the presence of described features, wholes, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or combinations thereof.

[0024] In the description of the present application specification and the appended claims, the terms "first", "second", "third", etc. are only used to distinguish the descriptions and should not be understood as indicating or implying relative importance.

[0025] References to "one embodiment" or "some embodiments" etc. described in the specification of this application mean that one or more embodiments of the present application include specific features, structures or characteristics described in conjunction with the embodiment. Therefore, the statements "in one embodiment", "in some embodiments", "in some other embodiments", "in some other embodiments", etc. that appear in different places in this specification do not necessarily refer to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized in other ways. The terms "including", "comprising", "having" and their variations all mean "including but not limited to", unless otherwise specifically emphasized in other ways.

[0026] A robot is an intelligent machine that can work semi-autonomously or fully autonomously. Robots working in office buildings, shopping malls and other areas usually have the ability to take the elevator autonomously. The robot's elevator control in an elevator environment usually relies on sensors, but the sensor information is mostly used for obstacle avoidance and elevator door recognition during the elevator process. In some situations where it is not suitable to take the elevator, the robot may still perform the elevator operation, affecting the safety of the robot.

[0027] In view of this, the present application proposes a method for controlling entering an elevator. On the one hand, the obstacle situation in the area in front of the door can be used to decide whether to let the robot take the elevator. On the other hand, the overall obstacle density used for the elevator taking judgment is obtained based on the change of the moving obstacle point cloud over time, so that the elevator entry decision fully considers the dynamic changes of the moving obstacles, thereby making the timing of the robot entering the elevator more reasonable and improving the safety of the robot.

[0028] In order to illustrate the technical solution of the present application, a specific embodiment is provided below for illustration.

[0029] Figure 1 The present invention provides a schematic diagram of the implementation process of a control method for entering an elevator provided in an embodiment of the present invention, which can be applied to a robot. The robot can be a welcoming robot, a food delivery robot, a cleaning robot or other types of robots, which are not limited in the present invention.

[0030] Specifically, the above elevator entry control method may include the following steps S101 to S104.

[0031] Step S101, classify the point cloud of the area in front of the elevator door to obtain the fixed obstacle point cloud and the mobile obstacle point cloud.

[0032] The door front area of ​​the elevator is the area in front of the elevator door, which is the area that the robot needs to pass through to enter the elevator.

[0033] In the implementation of the present application, the robot can be controlled to perform point cloud scanning around the area in front of the door to obtain a point cloud of the area in front of the door. The main radar can be set above the robot to continuously perform an all-round scan of the area in front of the elevator door to collect high-resolution radar point cloud data. In other implementations, external point cloud data can also be obtained, for example, by setting a depth sensor around the elevator door to obtain a point cloud of the area in front of the door, which is not limited by the present application.

[0034] The point cloud of the area in front of the door can be classified into fixed obstacle point cloud and mobile obstacle point cloud. Fixed obstacle point cloud means that the obstacle to which the point cloud belongs is not mobile, such as boxes, fences, etc.; mobile obstacle point cloud means that the obstacle to which the point cloud belongs is mobile, such as people, cars, robots, etc. This application can use deep learning algorithms (such as convolutional neural networks), clustering-based classification methods, etc., without limiting this application.

[0035] Step S102, determining the overall obstacle density of the area in front of the door according to the density of the fixed obstacle point cloud, the density of the mobile obstacle point cloud, and the change of the mobile obstacle point cloud over time.

[0036] In the implementation manner of the present application, both fixed obstacles and mobile obstacles are objects that the robot needs to avoid. The position of a fixed obstacle does not change over time, and its density is relatively stable. For a mobile obstacle, its position may change over time, so it should not be simply determined by a fixed density. For the detected mobile obstacle point cloud, it is necessary to introduce time and behavior as a reference to determine the dynamic density value based on the change of the mobile obstacle point cloud over time. In this way, the overall obstacle density of the area in front of the door can be determined based on the density of the fixed obstacle point cloud, the density of the mobile obstacle point cloud, and the change of the mobile obstacle point cloud over time. The overall obstacle density can reflect the blockage level of the area in front of the door.

[0037] The density of the fixed obstacle point cloud and the density of the mobile obstacle point cloud can be obtained by calculating the ratio of the corresponding point cloud quantity to the total point cloud quantity.

[0038] Step S103, when the overall obstacle density is less than or equal to the density threshold, control the robot to take the elevator.

[0039] Step S104: When the overall obstacle density is greater than the density threshold, the robot is controlled to give up taking the elevator.

[0040] That is to say, if the overall obstacle density is less than or equal to the density threshold, it means that there is a safe space for the robot to enter the elevator in the area in front of the door. At this time, the robot can be controlled to take the elevator.

[0041] If the overall obstacle density is less than or equal to the density threshold, it means that there is no safe space for the robot to enter the elevator in the area in front of the door. The robot may collide or fall into an infinite loop when taking the elevator. At this time, the robot can be controlled to give up taking the elevator. Giving up taking the elevator specifically means controlling the robot to choose another elevator, or it can mean controlling the robot to wait until the overall obstacle density is less than or equal to the density threshold before taking the elevator. This application does not limit this.

[0042] In an embodiment of the present application, by classifying the point cloud of the area in front of the elevator door, fixed obstacle point cloud and mobile obstacle point cloud are obtained, and the overall obstacle density of the area in front of the door is determined according to the density of the fixed obstacle point cloud, the density of the mobile obstacle point cloud, and the change of the mobile obstacle point cloud over time. When the overall obstacle density is less than or equal to the corrected density threshold, the robot is controlled to take the elevator, otherwise, the robot is controlled to give up taking the elevator. On the one hand, it is possible to decide whether to let the robot take the elevator with reference to the obstacle situation in the area in front of the door. On the other hand, the overall obstacle density used for the elevator decision is obtained based on the change of the mobile obstacle point cloud over time, so that the decision to enter the elevator fully considers the dynamic changes of the mobile obstacles, thereby making the timing of the robot entering the elevator more reasonable, thereby improving the safety of the robot.

[0043] In some embodiments of the present application, Figure 2 As shown, determining the overall obstacle density of the area in front of the door according to the density of the fixed obstacle point cloud, the density of the mobile obstacle point cloud, and the change of the mobile obstacle point cloud over time may include: steps S201 to S204.

[0044] Step S201, obtaining a preset time window.

[0045] Specifically, the time window refers to a period of time, which can be set according to the determination requirements, and can include the current time, historical time period, and future time period. For example, the time window can be set to a period of time consisting of n (n>0, such as 1, 2, etc.) seconds before and after the current time.

[0046] Step S202: Count the movement change of the moving obstacle point cloud within the time window.

[0047] Specifically, the movement change can reflect the motion performance of the moving obstacle point cloud. From the start time of the time window to the current time, based on the position of the moving obstacle point cloud between each two adjacent sampling times, the movement change between each two adjacent sampling times can be calculated, and the movement change of the moving obstacle point cloud in the time window can be obtained by accumulating the movement change.

[0048] Step S203: If the movement variation is less than or equal to the variation threshold, the overall obstacle density is determined according to the density of the fixed obstacle point cloud and the density of the moving obstacle point cloud.

[0049] Step S204: If the movement change is greater than the change threshold, the density of the moving obstacle point cloud is corrected according to the change of the moving obstacle point cloud over time, and the overall obstacle density of the area in front of the door is determined based on the density of the corrected moving obstacle point cloud and the density of the fixed obstacle point cloud.

[0050] Specifically, if the movement change is less than or equal to the change threshold, it can be considered that the mobile obstacle point cloud is in a stationary state, and the mobile obstacle point cloud can be regarded as a fixed obstacle point cloud. Therefore, the overall obstacle density can be determined based on the density of the fixed obstacle point cloud and the density of the mobile obstacle point cloud. For example, the overall obstacle density is obtained by adding the density of the fixed obstacle point cloud and the density of the mobile obstacle point cloud.

[0051] If the movement change is greater than the change threshold, it can be considered that the moving obstacle point cloud is in a moving state, and the density of the moving obstacle point cloud can be corrected according to the change of the moving obstacle point cloud over time, so that the density of the corrected moving obstacle point cloud fully considers the change of the moving obstacle point cloud over time. At this time, the overall obstacle density of the area in front of the door can be determined based on the density of the corrected moving obstacle point cloud and the density of the fixed obstacle point cloud.

[0052] Specifically, in step S204, the density of the mobile obstacle point cloud is corrected according to the change of the mobile obstacle point cloud over time, which may include: determining the movement probability and real-time movement influence range of the mobile obstacle point cloud within the time window, and correcting the density of the mobile obstacle point cloud according to the movement probability and the real-time movement influence range.

[0053] Specifically, the motion parameters (such as speed, acceleration, etc.) of the moving obstacle point cloud in the historical time period in the time window can be used to estimate the movement probability of the moving obstacle point cloud in the future time period in the time window. The real-time moving influence range refers to the range covered by the moving obstacle point cloud during the movement process, which can be determined based on the obstacle data in the historical time period and the current moment.

[0054] If the movement probability and the real-time movement influence range are small, the density of the moving obstacle point cloud can be appropriately reduced, and it is considered safer to enter the elevator. If the movement probability and the real-time movement influence range are large, the density of the moving obstacle point cloud can be appropriately increased, and then the robot will give up taking the elevator.

[0055] In some embodiments of the present application, the overall obstacle density P total It can be expressed as:

[0056] P total =P static +αP dynamic *(1-e -βt ).

[0057] Among them, P static is the density of static obstacles. dynamic is the density of the moving obstacle. α is the preset weight coefficient, β is the attenuation coefficient, and t is the time. It can be understood that as time goes by,

[0058] (1-e -βt ) is closer to 1, the correction effect on the density of moving obstacles gradually weakens.

[0059] In some embodiments of the present application, Figure 3 As shown, controlling the robot to take the elevator may include: step S301 to step S302.

[0060] Step S301, generating an initial path for the robot to enter the elevator according to the layout information of the elevator and the position of obstacles.

[0061] Specifically, the layout information of the elevator is a priori information, which can be pre-stored in the robot or obtained through the Internet. The obstacle position can be obtained by controlling the robot to collect information around the elevator through sensors, such as based on the point cloud of the aforementioned area in front of the door. According to the layout information of the elevator and the position of the obstacle, path planning can be performed to generate an initial path from the robot's starting position to the elevator.

[0062] Step S302, control the robot to move toward the elevator along the initial path, and during the movement, adjust the initial path in real time based on real-time obstacle information until the robot enters the elevator or the time it takes to enter the elevator is greater than a preset time.

[0063] Specifically, after the robot is controlled to move toward the elevator along the initial path from the starting position, real-time obstacle information can be collected. Real-time obstacle information may include but is not limited to real-time obstacle position, obstacle type, obstacle movement speed, acceleration, etc. Real-time obstacle information can be used to predict obstacle changes through the simulation system, such as obstacle movement, personnel entry and exit, etc., so as to adjust the robot path in real time until the robot enters the elevator or the elevator entry time is longer than the preset time, ensuring that obstacles are avoided and safe entry into the elevator is maintained. Among them, the preset time can be set according to actual conditions.

[0064] Specifically, when a temporary obstacle is detected, the initial path can be fine-tuned locally to avoid collision. When a large-scale environmental change is detected (for example, multiple obstacles are moving, the obstacle movement speed is greater than the speed threshold, etc.), the global path can be recalculated to replace the initial path to ensure that the robot enters the elevator safely and smoothly.

[0065] In some embodiments of the present application, before making real-time adjustments to the initial path based on real-time obstacle information, it can include: determining the scanning frequency and angular resolution of the lidar based on the distance between the robot and the elevator door, and the overall obstacle density; and controlling the lidar to perform point cloud scanning based on the scanning frequency and angular resolution to obtain real-time obstacle information.

[0066] Specifically, when the distance between the robot and the elevator door is smaller, more detailed real-time obstacle information is needed. At this time, the scanning frequency and angular resolution can be increased to distinguish the boundaries and precise positions of different objects, and help identify the shape of the elevator door and the specific positions of surrounding obstacles. When the distance between the robot and the elevator door is larger, the real-time obstacle information does not need to be too detailed. At this time, the scanning frequency and angular resolution can be reduced to meet the needs of roughly estimating objects, thereby reducing the computing burden and improving the processing speed of the system.

[0067] When the overall obstacle density is high, the robot needs to quickly update environmental information and accurately identify the boundaries between different objects. At this time, the scanning frequency and angular resolution can be increased to distinguish the boundaries and precise positions of different objects and ensure that the robot's path planning is adjusted in time. When the overall obstacle density is low, the scanning frequency and angular resolution can be reduced to reduce the computing burden and power consumption.

[0068] For the distance between the robot and the elevator door and the overall obstacle density, weighted fusion or adaptive switching can be used, and the scanning frequency and angular resolution can be adjusted by referring to the two types of information to adapt to the actual operating environment.

[0069] In some embodiments of the present application, in the process of controlling the robot to take the elevator, it may also include: determining the estimated posture of the elevator door of the elevator based on the point cloud scanned by the laser radar. Determining the deviation between the preset posture and the estimated posture of the elevator door. If the deviation exceeds the preset threshold, the estimated posture is corrected to obtain the target posture; if the deviation does not exceed the preset threshold, the estimated posture is used as the target posture. According to the estimated posture, the robot is controlled to align with the elevator door.

[0070] Specifically, using the point cloud scanned by the lidar in real time, the shape, position and posture of the elevator door can be identified through feature matching and point cloud registration methods, so as to calculate the center point posture of the elevator door as the estimated posture.

[0071] Preferably, the point cloud scanned by the laser radar can be combined with the angular velocity and acceleration data of the inertial measurement unit (IMU) to estimate the relative position of the robot and the elevator door using a weighted average or Kalman filter method to obtain an estimated posture. The inertial measurement unit can compensate for the errors that may occur in the laser radar in a dynamic environment.

[0072] When the robot approaches the elevator door, it determines whether to trigger the self-correction mechanism by comparing the deviation between the preset pose and the actual estimated pose. If the deviation exceeds the preset threshold, the self-correction mechanism can be activated to obtain additional elevator door pose data using an external calibration device (such as a high-precision laser scanner or visual sensor) to help correct the deviation caused by sensor error or environmental changes. If the deviation does not exceed the preset threshold, the estimated pose can be directly used as the target pose. The target pose can be used to adjust the robot's direction of travel to ensure that the robot can accurately align with the elevator door.

[0073] It is understandable that, in the process of controlling the robot to take the elevator, the estimated posture can be obtained in real time, and the target posture can be continuously determined until the robot enters the elevator door.

[0074] In some embodiments of the present application, controlling the robot to take the elevator may also include: obtaining historical elevator riding feedback data; determining the robot's elevator riding strategy when taking the elevator based on the historical elevator riding feedback data, and controlling the robot to take the elevator based on the elevator riding strategy.

[0075] The historical elevator riding feedback data can be user feedback data or data recorded during the robot's historical elevator riding process, such as whether a collision or emergency stop occurred. The adjusted elevator riding strategy can include but is not limited to: motion parameters (such as speed and acceleration when entering the elevator), obstacle avoidance parameters, the aforementioned density threshold, positioning accuracy, path planning strategy (such as the number of path corrections, etc.), etc.

[0076] Specifically, historical elevator riding feedback data can be input into the machine learning model to obtain elevator riding strategies to ensure the continuity and safety of operations.

[0077] In the implementation of the present application, by intelligently detecting the density of obstacles, the safe operation of the robot in front of the elevator door can be improved, the damage caused by collision with obstacles can be reduced, and the long-term maintenance and repair costs of the robot can be reduced. At the same time, through path planning and posture correction, the navigation efficiency can be optimized, the collision risk can be reduced, and the robot can adapt to complex working environments, quickly make decisions based on real-time environmental conditions, reduce waiting and stagnation time, and significantly improve operational efficiency.

[0078] It should be noted that, for the sake of simplicity of description, the aforementioned method embodiments are all expressed as a series of action combinations, but those skilled in the art should know that the present application is not limited to the described order of actions, because according to the present application, certain steps can be performed in other orders.

[0079] like Figure 4 Shown is a schematic structural diagram of an elevator control device 400 provided in an embodiment of the present application, wherein the elevator control device 400 is configured on a robot.

[0080] Specifically, the elevator control device 400 may include:

[0081] The point cloud classification unit 401 is used to classify the point cloud of the area in front of the elevator door to obtain a fixed obstacle point cloud and a mobile obstacle point cloud;

[0082] A density determination unit 402, configured to determine the overall obstacle density of the area in front of the door according to the density of the fixed obstacle point cloud, the density of the mobile obstacle point cloud, and the change of the mobile obstacle point cloud over time;

[0083] An elevator control unit 403 is used to control the robot to take the elevator when the overall obstacle density is less than or equal to the density threshold;

[0084] The elevator control unit 403 is also used to control the robot to give up taking the elevator when the overall obstacle density is greater than the density threshold.

[0085] In some embodiments of the present application, the density determination unit 402 is specifically used to: obtain a preset time window; count the movement change of the mobile obstacle point cloud within the time window; if the movement change is less than or equal to the change threshold, determine the overall obstacle density according to the density of the fixed obstacle point cloud and the density of the mobile obstacle point cloud; if the movement change is greater than the change threshold, correct the density of the mobile obstacle point cloud according to the change of the mobile obstacle point cloud over time, and determine the overall obstacle density of the area in front of the door according to the corrected density of the mobile obstacle point cloud and the density of the fixed obstacle point cloud.

[0086] In some embodiments of the present application, the density determination unit 402 is specifically used to: determine the movement probability and real-time movement influence range of the mobile obstacle point cloud within the time window; and correct the density of the mobile obstacle point cloud according to the movement probability and the real-time movement influence range.

[0087] In some embodiments of the present application, the elevator control unit 403 is specifically used to: generate an initial path for the robot to enter the elevator based on the layout information of the elevator and the position of obstacles; control the robot to move toward the elevator along the initial path, and during the movement, adjust the initial path in real time based on real-time obstacle information until the robot enters the elevator or the time it takes to enter the elevator is greater than a preset time.

[0088] In some embodiments of the present application, the elevator control unit 403 is specifically used to: determine the scanning frequency and angular resolution of the laser radar based on the distance between the robot and the elevator door of the elevator, and the overall obstacle density; and control the laser radar to perform point cloud scanning based on the scanning frequency and the angular resolution to obtain the real-time obstacle information.

[0089] In some embodiments of the present application, the elevator control unit 403 is specifically used to: determine the estimated posture of the elevator door of the elevator based on the point cloud scanned by the laser radar; determine the deviation between the preset posture of the elevator door and the estimated posture; if the deviation exceeds the preset threshold, perform posture correction on the estimated posture to obtain the target posture; if the deviation does not exceed the preset threshold, use the estimated posture as the target posture; and control the robot to align with the elevator door according to the estimated posture.

[0090] In some embodiments of the present application, the elevator control unit 403 is specifically used to: obtain historical elevator feedback data; determine the elevator strategy of the robot when taking the elevator based on the historical elevator feedback data; and control the robot to take the elevator based on the elevator strategy.

[0091] It should be noted that, for the convenience and simplicity of description, the specific working process of the elevator control device 400 can be referred to Figures 1 to 3 The corresponding process of the method will not be repeated here.

[0092] like Figure 5 , which is a schematic diagram of a robot provided in an embodiment of the present application. Specifically, the robot 5 may include: a processor 50, a memory 51, and a computer program 52 stored in the memory 51 and executable on the processor 50, such as an elevator control program. When the processor 50 executes the computer program 52, the steps in the above-mentioned various elevator control method embodiments are implemented, such as Figure 1 Alternatively, when the processor 50 executes the computer program 52, the functions of each module / unit in the above-mentioned device embodiments are realized, for example Figure 4 The functions of the point cloud classification unit 401, density determination unit 402 and elevator control unit 403 are shown.

[0093] The computer program may be divided into one or more modules / units, which are stored in the memory 51 and executed by the processor 50 to complete the present application. The one or more modules / units may be a series of computer program instruction segments capable of completing specific functions, which are used to describe the execution process of the computer program in the robot.

[0094] For example, the computer program can be divided into: a data acquisition unit, a performance determination unit, a weight adjustment unit, a data fusion unit, and a task execution unit. The specific functions of each unit are as follows: a point cloud classification unit, used to classify the point cloud of the area in front of the elevator door to obtain a fixed obstacle point cloud and a mobile obstacle point cloud; a density determination unit, used to determine the overall obstacle density of the area in front of the door according to the density of the fixed obstacle point cloud, the density of the mobile obstacle point cloud, and the change of the mobile obstacle point cloud over time; an elevator control unit, used to control the robot to take the elevator when the overall obstacle density is less than or equal to the density threshold; and an elevator control unit, also used to control the robot to give up taking the elevator when the overall obstacle density is greater than the density threshold.

[0095] The robot may include, but is not limited to, a processor 50 and a memory 51. Those skilled in the art will appreciate that Figure 5 These are merely examples of robots and do not constitute a limitation of the robot. The robot may include more or fewer components than those shown in the figure, or a combination of certain components, or different components. For example, the robot may also include input and output devices, network access devices, buses, etc.

[0096] The processor 50 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), off-the-shelf programmable gate arrays or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc.

[0097] The memory 51 may be an internal storage unit of the robot, such as a hard disk or memory of the robot. The memory 51 may also be an external storage device of the robot, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the robot. Furthermore, the memory 51 may include both an internal storage unit and an external storage device of the robot. The memory 51 is used to store the computer program and other programs and data required by the robot. The memory 51 may also be used to temporarily store data that has been output or is to be output.

[0098] It should be noted that, for the convenience and brevity of description, the structure of the above robot can also refer to the specific description of the structure in the method embodiment, which will not be repeated here.

[0099] The technicians in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In practical applications, the above-mentioned function allocation can be completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated in a processing unit, or each unit can exist physically separately, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, which will not be repeated here.

[0100] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0101] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0102] In the embodiments provided in the present application, it should be understood that the disclosed devices / robots and methods can be implemented in other ways. For example, the device / robot embodiments described above are merely schematic. For example, the division of the modules or units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0103] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0104] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0105] If the integrated module / unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present application implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal and software distribution medium. It should be noted that the content contained in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media do not include electric carrier signals and telecommunication signals.

[0106] The embodiments described above are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, a person skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

Claims

1. A method for controlling elevator access, characterized in that: include: Classify the point cloud of the area in front of the elevator door to obtain the fixed obstacle point cloud and the mobile obstacle point cloud; Determine the overall obstacle density of the area in front of the door according to the density of the fixed obstacle point cloud, the density of the mobile obstacle point cloud, and the change of the mobile obstacle point cloud over time; When the overall obstacle density is less than or equal to a density threshold, controlling the robot to take the elevator; When the overall obstacle density is greater than the density threshold, the robot is controlled to give up taking the elevator.

2. The elevator control method according to claim 1, characterized in that: Determining the overall obstacle density of the area in front of the door according to the density of the fixed obstacle point cloud, the density of the mobile obstacle point cloud, and the change of the mobile obstacle point cloud over time includes: Get the preset time window; Counting the movement change of the moving obstacle point cloud within the time window; If the movement change is less than or equal to the change threshold, determining the overall obstacle density according to the density of the fixed obstacle point cloud and the density of the moving obstacle point cloud; If the movement change is greater than the change threshold, the density of the moving obstacle point cloud is corrected according to the change of the moving obstacle point cloud over time, and the overall obstacle density of the area in front of the door is determined based on the density of the corrected moving obstacle point cloud and the density of the fixed obstacle point cloud.

3. The elevator control method according to claim 2, characterized in that: The step of correcting the density of the moving obstacle point cloud according to the change of the moving obstacle point cloud over time includes: Determine the movement probability and real-time movement impact range of the moving obstacle point cloud within the time window; The density of the moving obstacle point cloud is modified according to the moving probability and the real-time moving influence range.

4. The elevator control method according to any one of claims 1 to 3, characterized in that: The controlling robot to take the elevator comprises: Generate an initial path for the robot to enter the elevator according to the layout information of the elevator and the position of obstacles; The robot is controlled to move toward the elevator along an initial path, and during the movement, the initial path is adjusted in real time based on real-time obstacle information until the robot enters the elevator or the time spent in the elevator is greater than a preset time.

5. The elevator control method according to claim 4, characterized in that: Before the real-time adjustment of the initial path based on the real-time obstacle information is performed, the method includes: Determining a scanning frequency and an angular resolution of a laser radar according to a distance between the robot and an elevator door of the elevator and the overall obstacle density; According to the scanning frequency and the angular resolution, the laser radar is controlled to perform point cloud scanning to obtain the real-time obstacle information.

6. The elevator control method according to any one of claims 1 to 3, characterized in that: The process of controlling the robot to take the elevator also includes: Determining an estimated position of an elevator door of the elevator based on a point cloud scanned by the laser radar; Determining a deviation between a preset position and the estimated position of the elevator door; If the deviation exceeds a preset threshold, the estimated posture is corrected to obtain a target posture; If the deviation does not exceed the preset threshold, the estimated posture is used as the target posture; The robot is controlled to align with the elevator door according to the estimated posture.

7. The elevator control method according to any one of claims 1 to 3, characterized in that: The controlling robot to take the elevator comprises: Obtain historical elevator feedback data; Determining a strategy for the robot to take the elevator according to the historical elevator riding feedback data; According to the elevator riding strategy, the robot is controlled to take the elevator.

8. An elevator control device, characterized in that: include: A point cloud classification unit is used to classify the point cloud of the area in front of the elevator door to obtain a fixed obstacle point cloud and a moving obstacle point cloud; A density determination unit, configured to determine the overall obstacle density of the area in front of the door according to the density of the fixed obstacle point cloud, the density of the mobile obstacle point cloud, and the change of the mobile obstacle point cloud over time; An elevator control unit, used to control the robot to take the elevator when the overall obstacle density is less than or equal to a density threshold; The elevator control unit is also used to control the robot to give up taking the elevator when the overall obstacle density is greater than the density threshold.

9. A robot comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the steps of the elevator control method according to any one of claims 1 to 7 are implemented.

10. A computer program product, characterized in that It comprises a computer program, which, when executed, implements the steps of the elevator control method according to any one of claims 1 to 7.

Images