Control Method, Control Device and Robot for a Robot Entering an Elevator

Abstract

An embodiment of the present invention relates to a control method, a control device and a robot for a robot to enter an elevator. The method includes: determining a target waiting point among a plurality of preset waiting points directly in front of the elevator entrance, and controlling the robot to reach the target waiting point; obtaining the distances between the robot and the walls on both sides of the elevator entrance respectively, and adjusting the pose of the robot according to the distances so that the forward direction of the robot faces the elevator entrance; then, controlling the robot to drive straight ahead to pass through and enter the elevator entrance according to the inertial navigation system. By setting preset waiting points on the perpendicular bisector of the passable width of the elevator entrance, and adjusting the pose of the robot based on the distances between the robot and the walls on both sides of the elevator entrance, so that the forward direction of the robot faces the elevator entrance, and then controlling the robot to drive straight ahead into the elevator, the robot can enter the elevator at approximately the middle line position of the elevator, reducing the risk of rubbing between the robot and the elevator and improving the safety of the robot entering and exiting the elevator.

Description

Technical Field

[0001] The present invention relates to the technical field of robots, and in particular, to a control method for a robot to enter an elevator, a control device, a robot, and a storage medium.

Background Art

[0002] With the rapid development of the artificial intelligence industry, the application scenarios of robots are becoming more and more extensive. For example, hotels, KTVs, hospitals, enterprises, etc. In these application scenarios, robots often need to take elevators during their work.

[0003] Currently, when a robot takes an elevator, after the elevator door opens, it relies on laser matching outside the elevator to estimate its pose and drive into the elevator. This solution depends on the pose estimation result of the robot. Limited by the positioning accuracy, there may be an error between the actual position of the robot and the positioning result. When the robot is relatively large, that is, when the diameter of the robot is not much different from the elevator door, the robot is prone to rub against the elevator during the driving process.

Summary of the Invention

[0004] The technical problem to be solved by the present invention is to provide a control method for a robot to enter an elevator, a control device, a robot, and a storage medium, which can reduce the situation of the robot rubbing against the elevator during the process of entering the elevator.

[0005] To solve the above technical problem, in a first aspect, an embodiment of the present invention provides a control method for a robot to enter an elevator. The robot is configured with an inertial navigation system, and the method includes:

[0006] Determine a target waiting point among a plurality of preset waiting points directly in front of the elevator entrance, and control the robot to reach the target waiting point, where the plurality of preset waiting points are all located on the perpendicular bisector of the passable width of the elevator entrance;

[0007] Obtain the distances between the robot and the two side walls of the elevator entrance respectively, and adjust the pose of the robot according to the distances between the robot and the two side walls of the elevator entrance respectively, so that the forward direction of the robot faces the elevator entrance;

[0008] When the forward direction of the robot faces the elevator entrance, control the robot to drive straight to enter the elevator entrance according to the inertial navigation system.

[0009] In some embodiments, the determining a target waiting point among a plurality of preset waiting points directly in front of the elevator entrance and controlling the robot to reach the target waiting point includes:

[0010] Control the robot to enter the waiting area for taking the elevator, where the waiting area includes the plurality of preset waiting points;

[0011] Among the multiple preset waiting points, use the preset waiting point that is closest to the elevator entrance and not occupied by obstacles as the target waiting point;

[0012] Control the robot to drive and reach the target waiting point.

[0013] In some embodiments, the robot is further equipped with a lidar;

[0014] The steps of obtaining the distances between the robot and the two side walls of the elevator entrance respectively, and adjusting the pose of the robot according to the distances between the robot and the two side walls of the elevator entrance so that the forward direction of the robot faces the elevator entrance include:

[0015] Scan the area where the elevator entrance is located through the lidar to obtain point cloud data including the two side walls of the elevator entrance;

[0016] Extract the characteristic point clouds of the two side walls of the elevator entrance from the point cloud data, and determine the distances between the robot and the two side walls of the elevator entrance according to the coordinate positions of the characteristic point clouds;

[0017] Adjust the current position of the robot so that the distances between the robot and the two side walls of the elevator entrance are equal;

[0018] Control the robot to drive straight through the first position point. If the distances between the robot at the first position point and the two side walls of the elevator entrance are equal, it is determined that the forward direction of the robot faces the elevator entrance.

[0019] In some embodiments, the steps of extracting the characteristic point clouds of the two side walls of the elevator entrance from the point cloud data, determining the distances between the robot and the two side walls of the elevator entrance according to the coordinate positions of the characteristic point clouds, and adjusting the current position of the robot so that the distances between the robot and the two side walls of the elevator entrance are equal include:

[0020] Extract the characteristic identifiers set at the relative preset positions of the two side walls of the elevator entrance from the characteristic point clouds;

[0021] Calculate the distances between the robot and the two characteristic identifiers respectively. When the distances between the robot and the two characteristic identifiers are not equal, control the robot to move left or right by a preset adjustment distance until the distances between the robot at the current position and the two characteristic identifiers are equal.

[0022] In some embodiments, the two characteristic identifiers are respectively set at the bottom corner positions on both sides of the elevator entrance, or the two characteristic identifiers are respectively set at the top corner positions on both sides of the elevator entrance.

[0023] In some embodiments, when the forward direction of the robot faces the elevator entrance, controlling the robot to drive straight through the elevator entrance according to the inertial navigation system includes:

[0024] When the forward direction of the robot faces the elevator entrance, the robot is linearly driven by controlling the driving wheels to control the robot to travel straight.

[0025] During the straight-line travel of the robot, the inertial navigation system is used to determine the travel distance of the robot's straight-line travel.

[0026] Whether the robot enters the elevator entrance is determined according to the travel distance.

[0027] After the robot passes through and enters the elevator entrance, repositioning is performed inside the elevator car to determine the position of the robot inside the elevator car.

[0028] In some embodiments, the repositioning inside the elevator car to determine the position of the robot inside the elevator car includes:

[0029] Inside the elevator car, based on the laser data currently obtained by the robot as the observation value and the positioning data output by the inertial navigation system as the prediction value;

[0030] The positioning position of the robot inside the elevator car is determined according to the observation value and the prediction value.

[0031] In a second aspect, an embodiment of the present invention provides a control device for a robot to enter an elevator. The robot is configured with an inertial navigation system. The control device includes:

[0032] A determination module, configured to determine a target waiting point among a plurality of preset waiting points directly in front of the elevator entrance, and control the robot to reach the target waiting point, where the plurality of preset waiting points are all located on the perpendicular bisector of the passable width of the elevator entrance;

[0033] An adjustment module, configured to obtain the distances between the robot and the walls on both sides of the elevator entrance respectively, and adjust the pose of the robot according to the distances between the robot and the walls on both sides of the elevator entrance, so that the forward direction of the robot faces the elevator entrance;

[0034] A control module, configured to, when the forward direction of the robot faces the elevator entrance, control the robot to travel straight according to the inertial navigation system to pass through and enter the elevator entrance.

[0035] In a third aspect, an embodiment of the present invention provides a robot, including:

[0036] A processor and a memory communicatively connected to the processor;

[0037] The memory stores computer program instructions, and when the computer program instructions are called by the processor, the processor is caused to execute the above-mentioned control method for a robot to enter an elevator.

[0038] Fourthly, an embodiment of the present invention provides a storage medium storing computer-executable instructions for causing a processor to execute the above-mentioned control method for a robot to enter an elevator.

[0039] Fifthly, an embodiment of the present invention provides a computer program product which, when running on a processor, causes the processor to execute the above-mentioned control method for a robot to enter an elevator.

[0040] In the embodiment of the present invention, a preset waiting point is set on the perpendicular bisector of the passable width at the elevator entrance, and based on the distances between the robot and the walls on both sides of the elevator entrance, the pose of the robot is adjusted so that the forward direction of the robot faces the elevator entrance. Then, according to the inertial navigation system, the robot is controlled to drive straight into the elevator. The positioning by increasing the distances between the robot and the walls on both sides of the elevator entrance improves the positioning accuracy of the robot. Adjusting the pose of the robot according to the distances on both sides makes the robot face the elevator entrance and drive straight, enabling the robot to enter the elevator at approximately the middle line position of the elevator, reducing the risk of rubbing between the robot and the elevator, and enhancing the safety of the robot entering and exiting the elevator.

BRIEF DESCRIPTION OF THE DRAWINGS

[0041] In order to make the objectives, technical solutions and advantages of the present invention clearer, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.

[0042] Figure 1a is a schematic diagram of a robot entering an elevator according to an embodiment of the present invention;

[0043] Figure 1b is a schematic diagram of a robot entering an elevator according to another embodiment of the present invention;

[0044] Figure 2 is a schematic structural diagram of a robot provided by an embodiment of the present invention;

[0045] Figure 3 is a schematic flowchart of a control method for a robot to enter an elevator provided by an embodiment of the present invention;

[0046] Figure 4 is a functional module diagram of a control device for a robot to enter an elevator provided by an embodiment of the present invention.

DETAILED DESCRIPTION OF THE EMBODIMENTS

[0047] In order to make the objectives, technical solutions and advantages of the present invention clearer, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.

[0048] It should be noted that if there is no conflict, the various features in the embodiments of the present invention can be combined with each other, and all are within the protection scope of the present invention. In addition, although the functional modules are divided in the device schematic diagram and the logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in a different module division from that in the device schematic diagram or a different order from that in the flowchart.

[0049] Unless otherwise defined, all technical and scientific terms used in this specification have the same meaning as commonly understood by those skilled in the technical field to which the present invention belongs. The terms used in the specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. The term "and / or" used in this specification includes any and all combinations of one or more of the related listed items.

[0050] Please refer to Figure 1a , Figure 1a , which shows a schematic diagram of the robot 100 entering the elevator 200. Among them, the robot can be a mobile service robot, such as a delivery robot, a food delivery robot, a hotel robot, a shopping mall shopping guide robot, an inspection robot, etc.

[0051] A certain area in front of the elevator 200 is a waiting area, and the robot 100 can wait for the elevator 200 here. Multiple preset waiting points can be preset in the waiting area. The robot can stand on the preset waiting point to wait for the elevator, and after the elevator door opens, enter the elevator from the preset waiting point.

[0052] The preset waiting point can be located at any position in the waiting area. In some embodiments, to reduce the friction between the robot and the elevator, the preset waiting point can be located on the perpendicular bisector 300 of the passable width at the elevator entrance.

[0053] As can be understood by those skilled in the art, Figure 1a and Figure 1b schematically show the waiting area, the preset waiting point and the perpendicular bisector. In other embodiments, the waiting area can also be other positions and shapes, and the preset waiting point can also be located at other positions.

[0054] Figure 2 Shows a hardware structure of the robot. As Figure 2 shown, the robot 100 includes:

[0055] A processor 10 and a memory 20 communicatively connected to the processor 10. The memory 20 stores computer program instructions. When the computer program instructions are called by the processor 10, the processor 10 is caused to execute the control method for the robot to enter the elevator in any of the above embodiments.

[0056] The processor 10 and the memory 20 can be connected by a bus or other means. Figure 2 Taking the bus connection as an example.

[0057] The memory 20 can include a program storage area and a data storage area. Among them, the program storage area can store an operating system and application programs required for at least one function; the data storage area can store data created by executing the control method for the robot to enter the elevator, etc. The memory 20 can include a high-speed random access memory, and can also include a non-volatile memory, such as at least one magnetic disk storage device, a flash memory device, or other non-volatile solid-state storage devices. In some embodiments, the memory 20 optionally includes a memory remotely set relative to the processor 10, and these remote memories can be connected to the robot through a network. Examples of the above network include but are not limited to the Internet, an enterprise intranet, a local area network, a mobile communication network, and combinations thereof.

[0058] One or more modules are stored in the memory 20, and when executed by one or more processors 10, implement the control method for the robot to enter the elevator according to any embodiment of the present invention.

[0059] The robot can have a power device and a moving device. The power device is, for example, a motor (not shown in the figure), and the moving device is, for example, a driving wheel (not shown in the figure). The robot moves by controlling the power device to drive the driving wheel to rotate.

[0060] In some embodiments, the robot 100 can further include an inertial navigation system 30. The inertial navigation system 30 includes sensors such as a gyroscope, an IMU sensor, and an accelerometer, and can be a navigation parameter calculation system with a gyroscope and an accelerometer as sensitive devices. This system establishes a navigation coordinate system according to the output of the gyroscope, and calculates the speed and position of the vehicle in the navigation coordinate system according to the output of the accelerometer. For example, on the premise that the forward direction of the robot faces the elevator, the inertial navigation system configured by the robot calculates through a straight-line trajectory, and calculates the next position information of the robot according to the known position information of the target waiting point, the measured acceleration and angular velocity of the robot.

[0061] In some embodiments, the robot 100 can further include a ranging device, such as Figure 2 the lidar 40 among them. The lidar is a radar system that detects the position, speed and other characteristic quantities of a target by emitting laser beams. Its working principle is to emit a detection signal to the target, and then compare the received signal reflected from the target with the emitted signal. After appropriate processing, relevant information about the target can be obtained, such as target distance, azimuth, altitude, speed, attitude, and even shape and other parameters, so as to detect, track and identify the target. A point cloud is a dataset of points in a certain coordinate system, and the points can contain rich information, including three-dimensional coordinates, colors, classification values, intensity values, and / or time, etc.

[0062] In some embodiments of the present invention, when the robot needs to take the elevator by itself, it can scan the surrounding environment through a lidar to obtain a point cloud image of the surrounding environment, so that the robot can identify the point cloud image with the characteristics of the elevator entrance to obtain the distances between the robot and the two side walls of the elevator, and realize the robot taking the elevator by itself.

[0063] Among them, the lidar can be set at any suitable position of the robot. For example, there can be two lidars, which are respectively set on both sides of the robot (such as the middle part or the lower middle part of both sides of the robot) to respectively obtain the distances between the robot and the two side walls of the elevator. Or, there can be one lidar, which is set on the chest or head of the robot, and the distances between the robot and the two side walls of the elevator are obtained through this one lidar.

[0064] In some embodiments, to more easily identify the two side walls of the elevator, feature identifiers can be set on the two side walls. Please refer to Figure 1b , and the feature identifiers can be respectively set at the bottom corner positions of the two side walls of the elevator entrance, or respectively set at the top corner positions of the two side walls of the elevator entrance, or set at any position between the top corner and the bottom corner.

[0065] In some embodiments, the feature identifiers are set at positions slightly above the bottom corners of the two side walls of the elevator. Correspondingly, lidars can be respectively set on both sides of the robot, and the lidars and the feature identifiers can be on the same horizontal line. The two lidars are respectively used to obtain point cloud data, and the robot identifies the feature identifiers in the point cloud data to obtain the coordinate positions of the feature identifiers, so as to obtain the distances between the robot and the two side walls.

[0066] Please refer to Figure 3 , Figure 3 shows a control method for a robot to enter an elevator according to an embodiment of the present invention. The control method includes the following steps S11 - S13:

[0067] Step S11, determine a target waiting point among multiple preset waiting points directly in front of the elevator entrance, and control the robot to reach the target waiting point, where the multiple preset waiting points are all located on the perpendicular bisector of the passable width of the elevator entrance.

[0068] Among them, the preset waiting point is a position in front of the elevator entrance where the robot can wait for the elevator. As Figure 1a shown, the multiple preset waiting points are set on the perpendicular bisector of the passable area of the elevator entrance. The target waiting point is one of the preset waiting points. In some embodiments, it can be the preset waiting point that is the closest to the elevator entrance and not occupied when waiting for the elevator. The passable width is the passable width when the elevator is in the open state. If the passable width is represented by a line segment, then the perpendicular bisector is the perpendicular bisector of this line segment.

[0069] In some embodiments, step S11 includes the following steps S111 - S113:

[0070] Step S111, control the robot to enter the waiting area for taking the elevator, where the waiting area contains the multiple preset waiting points.

[0071] The preset waiting points can be located within the waiting area, and the waiting area can be the range where the robot can successfully enter the elevator within the time interval when the elevator door is open. In some of these embodiments, the waiting area can be a semi - circular area, please refer to Figure 1a and Figure 1b , the center point of the semi - circular area can be the point on the bottom of the elevator located on the door gap, that is, the mid - point of the line segment representing the passable width.

[0072] Let the time interval from when the elevator opens to when it closes be T0, then the radius R of the semi - circular area can be the distance between the farthest preset waiting point where the robot can enter the elevator within the T0 time and the center point. In other embodiments, the waiting area can also be square or other shapes.

[0073] In practical applications, the robot can identify the elevator entrance features through a lidar or a vision system, and judge whether the waiting area at the elevator entrance is occupied by obtaining the point cloud image around the elevator entrance.

[0074] If the waiting area is occupied, the robot can go to another elevator entrance. If it is not occupied, it can select an unoccupied preset waiting point as the target waiting point and wait for the elevator.

[0075] Step S112, among the multiple preset waiting points, take the preset waiting point that is closest to the elevator entrance and not occupied by an obstacle as the target waiting point.

[0076] Step S113, control the robot to drive and reach the target waiting point.

[0077] The target waiting point can be the preset waiting point that is closest to the elevator among the unoccupied preset waiting points. In some embodiments, when a preset waiting point is the closest to the elevator entrance and this preset waiting point is not occupied, that is, there is no obstacle on this preset waiting point, this preset waiting point can be taken as the target waiting point. If the closest preset waiting point is occupied, it can be judged whether the preset waiting point that is the second closest to the elevator and at a slightly farther distance is not occupied, and so on, until an unoccupied preset waiting point that is the closest to the elevator is found as the target waiting point.

[0078] For example, when there is no one waiting for the elevator in the waiting area, the preset waiting point closest to the elevator entrance is the target waiting point. Or, when there is already someone waiting for the elevator at the preset waiting point closest to the front of the elevator, the robot moves to the preset waiting point behind that preset waiting point, or the preset waiting points on both sides of that preset waiting point.

[0079] Step S12: Obtain the distances between the robot and the walls on both sides of the elevator entrance respectively, and adjust the pose of the robot according to the distances between the robot and the walls on both sides of the elevator entrance, so that the forward direction of the robot faces the elevator entrance.

[0080] When the robot is at the target waiting point, there is a certain distance between its actual position and the walls on both sides of the elevator entrance, and the distances are equal. The robot can obtain the distances between the robot and the walls on both sides of the elevator entrance through a ranging device, and adjust the pose of the robot based on the distances between the walls on both sides of the elevator entrance, so that the forward direction of the robot faces the elevator entrance.

[0081] In some embodiments, the point cloud data of the surrounding environment can be obtained through a lidar set on the robot, and the distances between the robot and the walls on both sides of the elevator entrance can be obtained based on the point cloud data. In this embodiment, step S12 includes the following steps S121 - S124:

[0082] Step S121: Scan the area where the elevator entrance is located through the lidar to obtain the point cloud data including the walls on both sides of the elevator entrance.

[0083] Specifically, the point cloud data can be a point cloud image, including multiple scan points of the surrounding environment of the robot, and each scan point has a relative coordinate to the robot.

[0084] Step S122: Extract the characteristic point clouds of the walls on both sides of the elevator entrance from the point cloud data, and determine the distances between the robot and the walls on both sides of the elevator entrance according to the coordinate positions of the characteristic point clouds.

[0085] Existing feature point extraction methods can be used to extract the characteristic point clouds of the two walls, obtain the coordinate positions corresponding to the characteristic point clouds, and obtain the relative distances between the robot and the two walls through coordinate system conversion.

[0086] In an embodiment where special identifiers are respectively set at corresponding positions on both sides of the elevator walls, the robot can extract the points corresponding to the characteristic identifiers from the characteristic point clouds, obtain the coordinate positions of these points, so as to obtain the distances between the robot and the two characteristic identifiers on both sides, and thus obtain the distances between the robot and the two walls.

[0087] Step S123: Adjust the current position of the robot so that the distances between the robot and the walls on both sides of the elevator entrance are equal.

[0088] In this embodiment, the position of the robot is continuously adjusted. When the distances from the robot to the two side walls obtained from the point cloud data are not equal, the robot can be moved left or right by a preset step length, and the point cloud data is obtained again. Based on the distances obtained again, the position of the robot is adjusted again until the distances from the robot to the two side walls obtained from the point cloud data are equal.

[0089] In the embodiment of obtaining the distances from the robot to the two side walls of the elevator using the feature identifiers, calculate the distances between the robot and the two feature identifiers respectively. When the distances between the robot and the two feature identifiers are not equal, control the robot to move left by a preset adjustment distance or move right by a preset adjustment distance until the distances between the robot at the current position and the two feature identifiers are equal.

[0090] Step S124, control the robot to drive straight through the first position point. If the distances from the robot at the first position point to the two side walls of the elevator entrance are equal, determine that the forward direction of the robot is towards the elevator entrance.

[0091] In some embodiments, to further ensure that the robot travels approximately along the perpendicular bisector of the passable width, it is also determined whether the forward direction of the robot is towards the elevator entrance. Specifically, control the robot to drive straight through the first position point by the inertial navigation system. If, when at the first position point, the distances from the robot to the two side walls obtained by the lidar are equal, it is considered that the forward direction of the robot is towards the elevator entrance.

[0092] Among them, the first position point can be a position point in front of the target waiting point, and is also located on the perpendicular bisector, that is, the first position point is located on the perpendicular bisector, between the target waiting point and the elevator.

[0093] Step S13, when the forward direction of the robot is towards the elevator entrance, control the robot to drive straight through the inertial navigation system to enter the elevator entrance.

[0094] Since the robot is located at the target waiting point, and the target waiting point is located on the perpendicular bisector of the passable width of the elevator entrance, when the forward direction of the robot is towards the elevator entrance, controlling the robot to drive straight can make the robot travel approximately along the perpendicular bisector of the elevator entrance, reducing the risk of the robot rubbing against the two side walls of the elevator entrance.

[0095] Among them, to control the robot to move straight, specifically, the position obtained by positioning with the inertial navigation system can be used as feedback to control the power device (such as a motor, etc.) of the robot. The power device drives the moving device (such as a driving wheel) to drive the robot to walk approximately straight.

[0096] In this application, when adjusting the forward direction of the robot towards the elevator entrance and the robot is located on the perpendicular bisector of the passable width of the elevator entrance, the robot is controlled to drive straight through the inertial navigation system to enter the elevator entrance, avoiding collisions between the robot and the side wall of the elevator entrance caused by using laser matching to estimate the robot's positioning pose. After the robot enters the elevator car, the robot can still estimate the robot's positioning pose based on laser matching. Among them, the robot can realize map construction and positioning based on the Simultaneous Localization and Mapping (SLAM) technology.

[0097] In some embodiments, step S13 includes the following steps S131 - S133:

[0098] Step S131, when the forward direction of the robot is towards the elevator entrance, control the driving wheels to drive straight to control the robot to drive straight.

[0099] Step S132, during the straight driving process of the robot, determine the driving distance of the robot driving straight through the inertial navigation system.

[0100] Step S133, determine whether the robot enters the elevator entrance according to the driving distance.

[0101] Specifically, in practical applications, control the driving wheels arranged at the bottom of the robot to move straight, and determine the distance of the robot driving straight through the inertial navigation system. For example, first, detect the initial information of the robot, including the initial position, initial orientation, initial attitude, etc. Then, use the IMU to detect the change information of the robot's movement at all times. At the same time, the accelerometer measures the acceleration. By measuring the acceleration and speed of the robot, the driving distance can be obtained. Based on the driving distance, it can be finally determined whether the robot enters the elevator. For example, if the driving distance is greater than the distance from the waiting point of the robot to the elevator, it can be considered that the robot has entered the elevator.

[0102] In some other embodiments, the method further includes:

[0103] Step S14, after the robot passes through and enters the elevator entrance, re - locate inside the elevator car to determine the position of the robot inside the elevator car.

[0104] After the robot enters the elevator, the robot can be re - located inside the elevator car to support the subsequent actions of the robot. For example, realize map construction and positioning based on the SLAM technology. Among them, the position of the robot inside the elevator car can be the relative position of the robot with respect to the elevator car, such as the distance from the surrounding side walls of the elevator car, or the absolute position of the robot inside the elevator car.

[0105] In some of these embodiments, step S14 includes the following steps S141 - S142:

[0106] Step S141, inside the elevator car, based on the laser data currently obtained by the robot as the observation value and the positioning data output by the inertial navigation system as the prediction value.

[0107] Step S142, determine the positioning position of the robot inside the elevator car according to the observation value and the prediction value.

[0108] Specifically, after the robot enters the elevator car, based on the SLAM technology, the robot obtains the laser point cloud data as the observation value through the lidar, and uses the positioning data output by the inertial navigation system, that is, the position of the robot inferred by the inertial navigation system based on the dynamic equation, as the prediction value, and fuses the prediction value and the prediction value to estimate the final positioning pose of the robot.

[0109] In this embodiment, a preset waiting point is set on the perpendicular bisector of the passable width of the elevator entrance. The distances between the robot and the two side walls of the elevator entrance are obtained, the pose of the robot is adjusted so that the forward direction of the robot faces the elevator entrance, and then the robot is controlled to drive straight into the elevator according to the inertial navigation system.

[0110] Adding the positioning of the distances between the robot and the two side walls of the elevator entrance improves the positioning accuracy of the robot. Adjusting the pose of the robot according to the distances on both sides so that the robot faces the elevator entrance and driving the robot straight can make the robot enter the elevator at approximately the mid - line position of the elevator, reducing the risk of rubbing between the robot and the elevator and enhancing the safety of the robot entering and exiting the elevator.

[0111] Please refer to Figure 4 , the embodiment of the present invention also proposes a control device 400 for a robot to enter an elevator. The robot is configured with an inertial navigation system. The device 400 includes:

[0112] A determination module 401, used to determine a target waiting point among a plurality of preset waiting points directly in front of the elevator entrance and control the robot to reach the target waiting point. Among them, the plurality of preset waiting points are all located on the perpendicular bisector of the passable width of the elevator entrance;

[0113] An adjustment module 402, used to obtain the distances between the robot and the two side walls of the elevator entrance respectively, and adjust the pose of the robot according to the distances between the robot and the two side walls of the elevator entrance respectively, so that the forward direction of the robot faces the elevator entrance;

[0114] A control module 403, used to control the robot to drive straight to pass through and enter the elevator entrance according to the inertial navigation system when the forward direction of the robot faces the elevator entrance.

[0115] Optionally, the determination module 401 is further configured to control the robot to enter the waiting area for taking the elevator, where the waiting area includes the multiple preset waiting points;

[0116] Among the multiple preset waiting points, a preset waiting point that is the closest to the elevator entrance and not occupied by an obstacle is used as the target waiting point;

[0117] Control the robot to drive and reach the target waiting point.

[0118] Optionally, the adjustment module 402 is further configured to scan the area where the elevator entrance is located through a lidar to obtain point cloud data including the walls on both sides of the elevator entrance;

[0119] Extract the characteristic point clouds of the walls on both sides of the elevator entrance from the point cloud data, and determine the distances between the robot and the walls on both sides of the elevator entrance according to the coordinate positions of the characteristic point clouds;

[0120] Adjust the current position of the robot so that the distances between the robot and the walls on both sides of the elevator entrance are equal;

[0121] Control the robot to drive straight through the first position point. If the distances between the robot at the first position point and the walls on both sides of the elevator entrance are equal, it is determined that the forward direction of the robot is towards the elevator entrance.

[0122] Optionally, the adjustment module 402 is further configured to extract characteristic identifiers set at relative preset positions on the walls on both sides of the elevator entrance from the characteristic point clouds;

[0123] Calculate the distances between the robot and the two characteristic identifiers respectively. When the distances between the robot and the two characteristic identifiers are not equal, control the robot to move left by a preset adjustment distance or move right by a preset adjustment distance until the distances between the robot at the current position and the two characteristic identifiers are equal.

[0124] Optionally, the two characteristic identifiers are respectively set at the bottom corner positions on both sides of the elevator entrance, or the two characteristic identifiers are respectively set at the top corner positions on both sides of the elevator entrance.

[0125] Optionally, when the forward direction of the robot is towards the elevator entrance, the control module 403 is further configured to linearly drive the driving wheels to control the robot to drive straight;

[0126] During the straight driving process of the robot, determine the driving distance of the robot's straight driving through an inertial navigation system;

[0127] Determine whether the robot enters the elevator entrance according to the driving distance;

[0128] After the robot enters the elevator entrance, it is repositioned inside the elevator car to determine the position of the robot inside the elevator car.

[0129] Optionally, the control module 403 is further configured to, inside the elevator car, use the laser data currently obtained by the robot as the observation value and the positioning data output by the inertial navigation system as the prediction value;

[0130] Determine the positioning position of the robot inside the elevator car according to the observation value and the prediction value.

[0131] It can be understood that for the implementation principle and technical effects of the control device 400 in the embodiments of the present invention, reference can be made to the control method for a robot entering an elevator in the embodiments of the present invention, which will not be elaborated here.

[0132] The embodiments of the present invention further provide a storage medium, which stores computer-executable instructions for causing a processor to execute the steps of the control method for a robot entering an elevator as described in the above embodiments.

[0133] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit them; under the concept of the present invention, the technical features in the above embodiments or different embodiments can also be combined, the steps can be implemented in any order, and there are many other variations in different aspects of the present invention as described above. For the sake of brevity, they are not provided in detail; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements on some of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A control method for a robot to enter an elevator, characterized in that, the robot is equipped with an inertial navigation system and a lidar. The method includes: Determine a target waiting point among multiple preset waiting points directly in front of the elevator entrance, and control the robot to reach the target waiting point. Among them, the multiple preset waiting points are all located on the perpendicular bisector of the passable width of the elevator entrance; Scan the area where the elevator entrance is located through the lidar to obtain point cloud data including the walls on both sides of the elevator entrance; Extract the characteristic point clouds of the walls on both sides of the elevator entrance from the point cloud data, and extract the characteristic identifiers set at the relative preset positions on the walls on both sides of the elevator entrance from the characteristic point clouds; Calculate the distances between the robot and the two characteristic identifiers respectively. When the distances between the robot and the two characteristic identifiers are not equal, control the robot to move left or right by a preset adjustment distance until the distances between the robot at the current position and the two characteristic identifiers are equal; Control the robot to drive straight through the first position point. If the distances between the robot at the first position point and the walls on both sides of the elevator entrance are equal, determine that the forward direction of the robot is towards the elevator entrance; When the forward direction of the robot is towards the elevator entrance, control the robot to drive straight through the inertial navigation system to enter the elevator entrance.

2. The control method for a robot to enter an elevator according to claim 1, characterized in that, The step of determining a target waiting point among multiple preset waiting points directly in front of the elevator entrance and controlling the robot to reach the target waiting point includes: Control the robot to enter the waiting area for taking the elevator, where the waiting area includes the multiple preset waiting points; Among the multiple preset waiting points, take the preset waiting point that is closest to the elevator entrance and not occupied by obstacles as the target waiting point; Control the robot to drive and reach the target waiting point.

3. The control method for a robot to enter an elevator according to claim 1, characterized in that, The two characteristic identifiers are respectively set at the bottom vertex positions on both sides of the elevator entrance, or the two characteristic identifiers are respectively set at the top vertex positions on both sides of the elevator entrance.

4. The control method for a robot to enter an elevator according to claim 1, characterized in that, The step of, when the forward direction of the robot is towards the elevator entrance, controlling the robot to drive straight through the inertial navigation system to enter the elevator entrance includes: When the forward direction of the robot is towards the elevator entrance, control the robot to drive straight by controlling the driving wheels; During the straight driving process of the robot, determine the driving distance of the robot's straight driving through the inertial navigation system; Determine whether the robot enters the elevator entrance according to the driving distance; After the robot enters the elevator entrance, reposition inside the elevator car to determine the position of the robot inside the elevator car.

5. The control method for a robot to enter an elevator according to claim 4, characterized in that, The step of repositioning inside the elevator car to determine the position of the robot inside the elevator car includes: Inside the elevator car, based on the laser data currently obtained by the robot as the observation value, and the positioning data output by the inertial navigation system as the prediction value; Determine the positioning position of the robot inside the elevator car according to the observation value and the prediction value.

6. A control device for a robot to enter an elevator, characterized in that, The robot is equipped with an inertial navigation system, and the robot is also equipped with a lidar. The control device includes: A determination module, configured to determine a target waiting point among a plurality of preset waiting points directly in front of the elevator entrance, and control the robot to reach the target waiting point, wherein the plurality of preset waiting points are all located on the perpendicular bisector of the passable width of the elevator entrance; An adjustment module, configured to scan the area where the elevator entrance is located through the lidar to obtain point cloud data including the walls on both sides of the elevator entrance; extract the characteristic point clouds of the walls on both sides of the elevator entrance in the point cloud data, and extract the characteristic identifiers set at the relative preset positions of the walls on both sides of the elevator entrance in the characteristic point clouds; calculate the distances between the robot and the two characteristic identifiers respectively. When the distances between the robot and the two characteristic identifiers are not equal, control the robot to move left by a preset adjustment distance, or move right by a preset adjustment distance until the distances between the robot at the current position and the two characteristic identifiers are equal; control the robot to drive straight through the first position point. If the distances between the robot at the first position point and the walls on both sides of the elevator entrance are equal, determine that the forward direction of the robot is towards the elevator entrance; A control module, configured to, when the forward direction of the robot is towards the elevator entrance, control the robot to drive straight through the inertial navigation system to enter the elevator entrance.

7. A robot, characterized in that, comprising: A processor and a memory communicatively connected to the processor; The memory stores computer program instructions, and when the computer program instructions are called by the processor, the processor is caused to execute the method according to any one of claims 1-5.

8. A storage medium, characterized in that, The storage medium stores computer-executable instructions for causing a processor to execute the method according to any one of claims 1-5.

Images