A system and method for a robot to control an elevator

Abstract

The present invention discloses a system and method for a robot to control an elevator. The robot obtains task information to determine the target floor, obtains image information of the current floor to determine the current floor, obtains the operation control information of each elevator car at the current moment to determine the target elevator with the highest priority, and then calls the target elevator. The robot collects external image information and sound information of the target elevator for automatic elevator entry determination. After entering the elevator, the target floor is directly sent to the elevator control system of the target elevator. The robot collects the internal image information of the elevator car and the elevator floor detection information for automatic elevator exit determination and docking disconnection with the elevator control system, so that the robot can complete automated elevator call and ride control. The present invention enables the robot to complete intelligent and efficient elevator control, realizes elevator call at the current floor with the optimal strategy, and enables information-based precise ride control, which is conducive to popularizing high-quality building services of the robot.

Description

Technical Field

[0001] The present invention belongs to the technical field of intelligent robots, and particularly relates to a system and method for a robot to control an elevator. Background Art

[0002] With the continuous development of artificial intelligence and robot technologies, service robots have begun to be popularized and applied in various industries. Most of the existing service robots are used for guiding in service halls or fixed floors, such as service halls in hotels, hospitals, government agencies, etc., and cannot achieve cross-floor services well. This is because there are still some problems when the existing service robots call and take the elevator, such as: only realizing the Internet of Things with the elevator control system, and still requiring personnel to remotely realize the elevator call, floor control, etc. of the robot through the intelligent terminal APP; the degree of automation is not high enough, and it is impossible to formulate and schedule intelligent multi-elevator call strategies; the determination of the opening and closing state of the elevator door and the floor where the elevator is located is inaccurate, resulting in unreliable automatic entry and exit of the elevator. Therefore, there is an urgent need for an intelligent and efficient means for a robot to call and control the elevator. Summary of the Invention

[0003] The purpose of the present invention is to provide a system and method for a robot to control an elevator to solve the above problems existing in the prior art.

[0004] To achieve the above purpose, the present invention adopts the following technical solutions:

[0005] In a first aspect, a method for a robot to control an elevator is provided, including:

[0006] Obtain task information, image information of the floor where it is located, and operation control information of each elevator car at the current moment;

[0007] Determine the target floor according to the task information, determine the current floor according to the image information of the floor where it is located, and determine the usage priority of each elevator according to the operation control information of each elevator car at the current moment and the current floor;

[0008] Take the elevator with the highest usage priority as the target elevator, and send a corresponding elevator call instruction to the elevator control system of the target elevator;

[0009] Collect the elevator door image and door opening prompt sound of the target elevator on the current floor, and judge whether the elevator door of the target elevator is opened according to the elevator door image and door opening prompt sound;

[0010] After determining that the elevator door of the target elevator is opened, send the target floor to the elevator control system of the target elevator;

[0011] Obtain the car floor detection information from the elevator control system of the target elevator, and collect the car door image and floor display image inside the car of the target elevator;

[0012] Determine the first verification floor based on the car floor detection information, determine whether the car door is open according to the car door image, determine the floor reached by the car according to the floor display image, and use it as the second verification floor;

[0013] When the first verification floor and the second verification floor are the same, both are the target floor, and it is determined that the car door is open, generate a detachment instruction and send the detachment instruction to the elevator control system of the target elevator.

[0014] In a possible design, the operation control information includes the operation state information of the elevator car, the floor information where it is located, and the subsequent stop floor node information. The method for determining the usage priority of each elevator according to the operation control information of each elevator car at the current moment and the current floor includes:

[0015] According to the current floor and the operation state information, floor information, and subsequent stop floor node information of each elevator car, calculate and judge the estimated time for each elevator car to reach the current floor;

[0016] Sort the elevators according to the estimated time for each elevator car to reach the current floor to determine the usage priority of each elevator.

[0017] In a possible design, the method for determining whether the elevator door of the target elevator is open according to the elevator door image and the door opening prompt sound includes importing the elevator door image into a preset image classification model to obtain a first classification result, and then determining whether the elevator door of the target elevator is open according to the first classification result and the door opening prompt sound; the method for determining whether the car door is open according to the car door image includes importing the car door image into a preset image classification model to obtain a second classification result, and determining whether the car door is open according to the second classification result.

[0018] In a possible design, the method for determining the current floor according to the image information of the floor where it is located includes importing the image information of the floor where it is located into a preset image digital recognition network model to obtain a first recognized number, and determining the current floor according to the first recognized number; the method for determining the floor reached by the car according to the floor display image includes importing the floor display image into a preset image digital recognition network model to obtain a second recognized number, and determining the floor reached by the car according to the second recognized number.

[0019] In a possible design, before obtaining the operation control information of each elevator car at the current moment, the method further includes: accessing the elevator control system of each elevator through the local area network, and sending permission authentication information to the elevator control system of each elevator. After receiving the authentication success information feedback by each elevator control system, establish a communication connection with each elevator control system.

[0020] In a possible design, after sending a corresponding elevator call instruction to the elevator control system of the target elevator, the method further includes: after receiving the operation anomaly information fed back by the elevator control system of the target elevator, using an elevator with a usage priority lower than that of the target elevator as an alternative elevator, and sending a corresponding elevator call instruction to the elevator control system of the alternative elevator.

[0021] In a possible design, after determining that the elevator door of the target elevator is opened, the method further includes:

[0022] Collecting an image of the interior scene of the car of the target elevator;

[0023] Judging the remaining floor area in the car of the target elevator according to the image of the interior scene of the car, and when it is determined that the remaining floor area is greater than a set threshold, sending the target floor to the elevator control system of the target elevator.

[0024] In a second aspect, a system for a robot to control an elevator is provided, including a first acquisition unit, a first determination unit, a first sending unit, a second acquisition unit, a second sending unit, a third acquisition unit, a second determination unit, an instruction generation unit, and a third sending unit, where:

[0025] The first acquisition unit is configured to obtain task information, image information of the floor where it is located, and operation control information of each elevator car at the current moment;

[0026] The first determination unit is configured to determine the target floor according to the task information, determine the current floor according to the image information of the floor where it is located, and determine the usage priority of each elevator according to the operation control information of each elevator car at the current moment and the current floor;

[0027] The first sending unit is configured to use the elevator with the highest usage priority as the target elevator, and send a corresponding elevator call instruction to the elevator control system of the target elevator;

[0028] The second acquisition unit is configured to collect an image of the elevator door of the target elevator on the current floor and an opening prompt sound, and judge whether the elevator door of the target elevator is opened according to the image of the elevator door and the opening prompt sound;

[0029] The second sending unit is configured to send the target floor to the elevator control system of the target elevator after determining that the elevator door of the target elevator is opened;

[0030] The third acquisition unit is configured to obtain car floor detection information from the elevator control system of the target elevator, and collect an image of the car door and a floor display image inside the car of the target elevator;

[0031] The second determination unit determines a first verification floor according to the car floor detection information, judges whether the car door is opened according to the image of the car door, determines the floor reached by the car according to the floor display image, and uses it as the second verification floor;

[0032] An instruction generation unit, configured to generate a detachment instruction when the first verification floor and the second verification floor are consistent and both are the target floor, and it is determined that the car door is open;

[0033] A third sending unit, configured to send the detachment instruction to the elevator control system of the target elevator.

[0034] In a possible design, the system further includes a fourth acquisition unit and a third determination unit. The fourth acquisition unit is configured to acquire an image of the interior scene of the car of the target elevator. The third determination unit is configured to determine the remaining floor area in the car of the target elevator according to the image of the interior scene of the car, and determine whether the remaining floor area is greater than a set threshold. The second sending unit is specifically configured to send the target floor to the elevator control system of the target elevator when the third determination unit determines that the remaining floor area is greater than the set threshold.

[0035] In a third aspect, a system for a robot to control an elevator is provided, including:

[0036] A memory, configured to store instructions;

[0037] A processor, configured to read the instructions stored in the memory and execute any one of the methods in the first aspect according to the instructions.

[0038] In a fourth aspect, a computer-readable storage medium is provided. Instructions are stored on the computer-readable storage medium. When the instructions run on a computer, the computer is enabled to execute any one of the methods in the first aspect. At the same time, a computer program product including instructions is also provided. When the instructions run on a computer, the computer is enabled to execute any one of the methods in the first aspect.

[0039] Advantageous effects: The present invention can use a robot to obtain task information to determine the target floor, obtain image information of the current floor to determine the current floor, obtain the operation control information of each elevator car at the current moment to determine the target elevator with the highest priority, and then call the target elevator. The robot collects external image information and sound information of the target elevator for automatic entry elevator determination. After entering the elevator, the target floor is directly sent to the elevator control system of the target elevator. The internal image information of the car of the target elevator and the car floor detection information are collected for automatic exit elevator determination and docking detachment with the elevator control system, so that the robot can complete automatic call and ride control of the elevator. The present invention can enable the robot to complete intelligent and efficient elevator control, realize call for the current floor with the optimal strategy and information-based precise ride control of the elevator, reduce the problem of errors in the robot's call and ride of the elevator, and is conducive to popularizing and realizing high-quality building services of the robot. Description of the Drawings

[0040] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the accompanying drawings required for the description of the embodiments or the prior art. Obviously, the accompanying drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other accompanying drawings can be obtained based on these drawings.

[0041] Figure 1 It is a schematic diagram of the steps of the method in the embodiment of the present invention;

[0042] Figure 2 It is a schematic diagram of the composition of a system in the embodiment of the present invention;

[0043] Figure 3 It is a schematic diagram of the composition of another system in the embodiment of the present invention. Detailed implementation manners

[0044] It should be noted here that the description of these embodiments is used to help understand the present invention, but does not constitute a limitation to the present invention. The specific structural and functional details disclosed herein are only used to describe the exemplary embodiments of the present invention. However, the present invention can be embodied in many alternative forms and should not be construed as limited to the embodiments set forth herein.

[0045] It should be understood that the terms first, second, third, etc. are only used for descriptive distinction and cannot be construed as indicating or implying relative importance. Although the terms first, second, third, etc. can be used herein to describe various features, these features should not be limited by these terms. For example, the first unit can be called the second unit, and similarly, the first, second, and third units can also be the same unit, without departing from the scope of the exemplary embodiments of the present invention.

[0046] Specific details are provided in the following description to facilitate a complete understanding of the exemplary embodiments. However, those of ordinary skill in the art should understand that the exemplary embodiments can be implemented without these specific details. For example, a system can be shown in a block diagram to avoid obscuring the example with unnecessary details. In other embodiments, well-known processes, structures, and technologies can be shown without unnecessary details to avoid obscuring the embodiments.

[0047] Embodiment 1:

[0048] This embodiment provides a system for a robot to control an elevator, which is applied to a corresponding intelligent robot for building service operations, such as Figure 1 As shown, the method includes the following steps:

[0049] S1. Obtain task information, image information of the floor where it is located, and operation control information of each elevator car at the current moment.

[0050] In specific implementation, before the robot performs building service operations, it needs to first obtain the corresponding task information, and collect the image information of the floor where it is located through the image acquisition device. The image of the floor where it is located contains floor numbers. At the same time, the robot can access the elevator control systems of each elevator through the local area network, and send permission authentication information to the elevator control systems of each elevator. After receiving the authentication success information feedback from each elevator control system, a communication connection is established with each elevator control system to obtain the operation control information of each elevator car in the building at the current moment from each elevator control system.

[0051] S2. Determine the target floor according to the task information, determine the current floor according to the image information of the floor where it is located, and determine the usage priority of each elevator according to the operation control information of each elevator car at the current moment and the current floor.

[0052] In specific implementation, after the robot obtains the task information, it extracts the floor of the destination from the task information as the target floor. After obtaining the image information of the floor where it is located, the image of the floor where it is located is imported into the preset image digital recognition network model for digital recognition in the image, and the floor number contained in the floor image is recognized. Then, the floor corresponding to the floor number is used as the current floor. The image digital recognition network model can adopt a convolutional neural network model after test training, or an SVM model and a KNN model after test training, etc. The selection of the corresponding neural network model can be made according to actual needs.

[0053] After obtaining the operation control information and the current floor of each elevator car at the current moment, the robot can formulate a call elevator strategy based on the operation control information of each elevator car at the current moment and the current floor. The operation control information includes the operation state information, the floor information where the elevator car is located, and the subsequent stop floor node information. When formulating the call elevator strategy, first calculate and judge the estimated time for each elevator car to reach the current floor according to the current floor, the operation state information, the floor information where the elevator car is located, and the subsequent stop floor node information of each elevator car. Then, rank the elevators according to the estimated time for each elevator car to reach the current floor to determine the usage priority of each elevator. The elevator with the least estimated time has the highest call elevator priority, and so on. Exemplarily, if the operation state of Elevator No. 1 is ascending, and the current car is on the 10th floor, it is determined that it still needs to stop at the 15th floor and the 25th floor during the ascending process, and it still needs to stop at the 22nd floor and the 11th floor during the descending process. Based on this, the estimated time for it to reach the current floor, the 1st floor, is calculated to be 3 minutes; the operation state of Elevator No. 2 is descending, and the current car is on the 26th floor. During the descending process, it still needs to stop at the 24th floor, the 22nd floor, the 20th floor, the 18th floor, the 16th floor, the 14th floor, the 12th floor, the 10th floor, the 8th floor, the 6th floor, and the 4th floor. Based on this, the estimated time for it to reach the current floor, the 1st floor, is calculated to be 4 minutes. Then, the usage priority of Elevator No. 2 is higher than that of Elevator No. 1.

[0054] S3. Use the elevator with the highest usage priority as the target elevator, and send the corresponding call elevator instruction to the elevator control system of the target elevator.

[0055] During specific implementation, after the robot determines the elevator with the highest usage priority, it uses this elevator as the target elevator and sends the corresponding call elevator instruction to the elevator control system of the target elevator for targeted call elevator. The execution of targeted call elevator is applicable to the situation where the elevators are relatively scattered. At the same time, it prevents the situation of occupying too many elevator resources on the current floor by calling all elevators at once, so that people on other floors or the robot can call the elevator successfully faster.

[0056] After sending the call elevator instruction to the elevator control system of the target elevator, if the operation abnormal information feedback by the elevator control system of the target elevator is received, the robot abandons the call to the target elevator, and then uses the elevator with the usage priority after the target elevator as the alternative elevator, and sends the corresponding call elevator instruction to the elevator control system of the alternative elevator.

[0057] S4. Collect the elevator door image and the door opening prompt sound of the target elevator on the current floor, and judge whether the elevator door of the target elevator is opened according to the elevator door image and the door opening prompt sound.

[0058] In specific implementation, after calling the elevator, the robot waits for the elevator door to open in front of the target elevator. During this process, the robot collects the elevator door image and the door opening prompt sound of the target elevator on the current floor in real time, and determines whether the elevator door of the target elevator is open based on the elevator door image and the door opening prompt sound. The specific determination process includes: the robot imports the elevator door image into a pre-set image classification model to obtain a first classification result, and then determines whether the elevator door of the target elevator is open based on the first classification result; when the robot determines that it has received the door opening prompt sound and the image determines that the elevator door of the target elevator is open, it is finally determined that the elevator door is open. The pre-set image classification model can adopt the AlexNet model after test training, or the VGGNet model, Inception model, ResNet model, etc. after test training, and the corresponding neural network model can be selected according to actual needs.

[0059] S5. After determining that the elevator door of the target elevator is open, send the target floor to the elevator control system of the target elevator.

[0060] In specific implementation, after the robot determines that the elevator door of the target elevator is open, it can move into the car of the target elevator. Before entering the car of the target elevator, the robot needs to collect the internal scene image of the target elevator to judge the remaining floor area in the car of the target elevator based on the internal scene image of the car. If the remaining floor area is greater than the set threshold, it indicates that the degree of crowding in the car is not high. At this time, the robot can move into the car. If the remaining floor area does not exceed the set threshold, it indicates that the car is relatively crowded. At this time, the robot abandons the target elevator and re-performs the priority sorting and elevator calling of the remaining elevators.

[0061] S6. Obtain the car floor detection information from the elevator control system of the target elevator, and collect the car door image and the floor display image inside the car of the target elevator.

[0062] In specific implementation, after the robot takes the target elevator, it obtains the car floor detection information from the elevator control system of the target elevator in real time, and collects the car door image and the floor display image inside the car of the target elevator for subsequent determination of the getting-off floor.

[0063] S7. Determine the first verification floor based on the car floor detection information, judge whether the car door is open according to the car door image, determine the floor reached by the car according to the floor display image, and use it as the second verification floor.

[0064] In specific implementation, after the robot obtains the car floor detection information, it determines the first verification floor according to the car floor detection information, determines the floor reached by the car according to the floor display image, and uses it as the second verification floor, and determines whether the car door is open according to the car door image. When determining the floor reached by the car according to the floor display image, the floor display image is imported into a preset image digital recognition network model for digital recognition in the image, and the floor number included in the floor display image is recognized, and then the floor corresponding to the floor number is used as the second verification floor. The image digital recognition network model can adopt a convolutional neural network model after test training, or an SVM model and a KNN model after test training, etc., and the corresponding neural network model can be selected according to actual needs. When determining whether the car door is open according to the car door image, the car door image is imported into a preset image classification model to obtain a second classification result, and it is determined whether the car door is open according to the second classification result. The preset image classification model can adopt an AlexNet model after test training, or a VGGNet model, an Inception model, a ResNet model, etc. after test training, and the corresponding neural network model can be selected according to actual needs.

[0065] S8. When the first verification floor and the second verification floor are consistent, both are the target floor, and it is determined that the car door is open, a detachment instruction is generated and sent to the elevator control system of the target elevator.

[0066] In specific implementation, if the robot determines that the first verification floor and the second verification floor are consistent, both are the target floor, and it is determined that the car door is open, it indicates that the target floor has been reached. At this time, the robot can move out of the car to perform the operation task of the target floor. After moving out of the car, the robot generates a detachment instruction and sends the detachment instruction to the elevator control system of the target elevator to disconnect the communication connection with the elevator control system of the target elevator, release the channel, and start subsequent operation tasks.

[0067] Embodiment 2:

[0068] This embodiment provides a system for a robot to control an elevator, as Figure 2 shown. The system includes a first acquisition unit, a first determination unit, a first sending unit, a second acquisition unit, a second sending unit, a third acquisition unit, a second determination unit, an instruction generation unit, and a third sending unit, where:

[0069] The first acquisition unit is used to obtain task information, image information of the floor where it is located, and operation control information of each elevator car at the current moment;

[0070] The first determination unit is configured to determine a target floor according to task information, determine the current floor according to the image information of the current floor, and determine the usage priority of each elevator according to the operation control information of each elevator car at the current moment and the current floor;

[0071] The first sending unit is configured to use the elevator with the highest usage priority as the target elevator and send a corresponding call instruction to the elevator control system of the target elevator;

[0072] The second acquisition unit is configured to acquire the elevator door image and the door opening prompt sound of the target elevator on the current floor, and determine whether the elevator door of the target elevator is opened according to the elevator door image and the door opening prompt sound;

[0073] The second sending unit is configured to send the target floor to the elevator control system of the target elevator after determining that the elevator door of the target elevator is opened;

[0074] The third acquisition unit is configured to obtain the car floor detection information from the elevator control system of the target elevator, and acquire the car door image and the floor display image inside the car of the target elevator;

[0075] The second determination unit determines a first verification floor according to the car floor detection information, determines whether the car door is opened according to the car door image, determines the floor reached by the car according to the floor display image, and uses it as the second verification floor;

[0076] The instruction generation unit is configured to generate a detachment instruction when the first verification floor and the second verification floor are consistent, both are the target floor, and it is determined that the car door is opened;

[0077] The third sending unit is configured to send the detachment instruction to the elevator control system of the target elevator.

[0078] Further, the system further includes a fourth acquisition unit and a third determination unit. The fourth acquisition unit is configured to acquire the internal scene image of the car of the target elevator. The third determination unit is configured to determine the remaining floor area inside the car of the target elevator according to the internal scene image of the car, determine whether the remaining floor area is greater than a set threshold. The second sending unit is specifically configured to send the target floor to the elevator control system of the target elevator when the third determination unit determines that the remaining floor area is greater than the set threshold.

[0079] Embodiment 3:

[0080] This embodiment provides another system for a robot to control an elevator, as Figure 3 shown. At the hardware level, it includes:

[0081] A data interface for establishing data docking between a processor and an external data acquisition device;

[0082] A memory for storing instructions;

[0083] A processor for reading instructions stored in the memory and executing the method for a robot to control an elevator in Embodiment 1 according to the instructions.

[0084] Optionally, the computer device further includes an internal bus. The processor, the memory, and the data interface can be interconnected through the internal bus, and the internal bus can be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect) bus, an EISA (Extended Industry Standard Architecture) bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc.

[0085] The memory can include, but is not limited to, a random access memory (RAM), a read only memory (ROM), a flash memory, a first input first output (FIFO) memory, and / or a first in last out (FILO) memory, etc. The processor can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.

[0086] Embodiment 4:

[0087] This embodiment provides a computer-readable storage medium with instructions stored thereon. When the instructions are run on a computer, the computer is caused to execute the method for a robot to control an elevator in Embodiment 1. Among them, the computer-readable storage medium refers to a carrier for storing data, and can include, but is not limited to, a floppy disk, an optical disc, a hard disk, a flash memory, a USB flash drive, and / or a memory stick, etc. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable systems.

[0088] This embodiment also provides a computer program product containing instructions. When the instructions run on a computer, the computer is caused to execute the method for a robot to control an elevator in Embodiment 1. Among them, the computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable systems.

[0089] Finally, it should be noted that the above are only the preferred embodiments of the present invention and are not intended to limit the protection scope of the present invention. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. A method for a robot to control an elevator, characterized in that, it includes: Obtaining task information, image information of the floor where it is located, and operation control information of each elevator car at the current moment; Determining the target floor according to the task information, determining the current floor according to the image information of the floor where it is located, and determining the usage priority of each elevator according to the operation control information of each elevator car at the current moment and the current floor; Taking the elevator with the highest usage priority as the target elevator, and sending a corresponding elevator call instruction to the elevator control system of the target elevator; Collecting the elevator door image and door opening prompt sound of the target elevator on the current floor, and judging whether the elevator door of the target elevator is opened according to the elevator door image and the door opening prompt sound. The judging whether the elevator door of the target elevator is opened according to the elevator door image and the door opening prompt sound includes importing the elevator door image into a preset image classification model to obtain a first classification result, and then judging whether the elevator door of the target elevator is opened according to the first classification result and the door opening prompt sound; After judging that the elevator door of the target elevator is opened, sending the target floor to the elevator control system of the target elevator; Obtaining car floor detection information from the elevator control system of the target elevator, and collecting the car door image and floor display image inside the target elevator car; Judging to obtain a first verification floor according to the car floor detection information, and judging whether the car door is opened according to the car door image. The judging whether the car door is opened according to the car door image includes importing the car door image into a preset image classification model to obtain a second classification result, and judging whether the car door is opened according to the second classification result; Judging the floor reached by the car according to the floor display image, and taking it as the second verification floor; When the first verification floor and the second verification floor are consistent, both are the target floor, and it is judged that the car door is opened, generating a detachment instruction, and sending the detachment instruction to the elevator control system of the target elevator.

2. The method for a robot to control an elevator according to claim 1, characterized in that, the operation control information includes the operation state information, the floor information where it is located, and the subsequent stop floor node information of the elevator car. The determining the usage priority of each elevator according to the operation control information of each elevator car at the current moment and the current floor includes: Calculating and judging the estimated time for each elevator car to reach the current floor according to the current floor and the operation state information, the floor information where it is located, and the subsequent stop floor node information of each elevator car; Performing priority sorting on each elevator according to the estimated time for each elevator car to reach the current floor, and determining the usage priority of each elevator.

3. The method for a robot to control an elevator according to claim 1, characterized in that, the determining the current floor according to the image information of the floor where it is located includes importing the image information of the floor where it is located into a preset image digital recognition network model to obtain a first recognition number, and determining the current floor according to the first recognition number; the judging the floor reached by the car according to the floor display image includes importing the floor display image into a preset image digital recognition network model to obtain a second recognition number, and determining the floor reached by the car according to the second recognition number.

4. The method for a robot to control an elevator according to claim 1, It is characterized in that Before obtaining the operation control information of each elevator car at the current moment, the method further includes: accessing the elevator control system of each elevator through a local area network, and sending permission authentication information to the elevator control system of each elevator. After receiving the authentication success information feedback by each elevator control system, a communication connection is established with each elevator control system.

5. A method for a robot to control an elevator according to claim 1, It is characterized in that After sending a corresponding elevator call instruction to the elevator control system of the target elevator, the method further includes: after receiving the operation abnormality information feedback by the elevator control system of the target elevator, using the elevator with a usage priority lower than that of the target elevator as an alternative elevator, and sending a corresponding elevator call instruction to the elevator control system of the alternative elevator.

6. A method for a robot to control an elevator according to claim 1, It is characterized in that After determining that the elevator door of the target elevator is opened, the method further includes: Collecting an internal scene image of the car of the target elevator; Judging the remaining floor area in the car of the target elevator according to the internal scene image of the car. When it is determined that the remaining floor area is greater than a set threshold, sending the target floor to the elevator control system of the target elevator.

7. A system for a robot to control an elevator, It is characterized in that It includes a first acquisition unit, a first determination unit, a first sending unit, a second acquisition unit, a second sending unit, a third acquisition unit, a second determination unit, an instruction generation unit and a third sending unit, wherein: The first acquisition unit is used to obtain task information, image information of the floor where it is located, and operation control information of each elevator car at the current moment; The first determination unit is used to determine the target floor according to the task information, determine the current floor according to the image information of the floor where it is located, and determine the usage priority of each elevator according to the operation control information of each elevator car at the current moment and the current floor; The first sending unit is used to use the elevator with the highest usage priority as the target elevator, and send a corresponding elevator call instruction to the elevator control system of the target elevator; The second acquisition unit is used to collect an elevator door image and an opening prompt sound of the target elevator on the current floor, and judge whether the elevator door of the target elevator is opened according to the elevator door image and the opening prompt sound. Judging whether the elevator door of the target elevator is opened according to the elevator door image and the opening prompt sound includes importing the elevator door image into a preset image classification model to obtain a first classification result, and then judging whether the elevator door of the target elevator is opened according to the first classification result and the opening prompt sound; The second sending unit is used to send the target floor to the elevator control system of the target elevator after determining that the elevator door of the target elevator is opened; The third acquisition unit is used to obtain car floor detection information from the elevator control system of the target elevator, and collect a car door image and a floor display image inside the car of the target elevator. A second determination unit, configured to determine a first verification floor according to the car floor detection information, and determine whether the car door is open according to the car door image. The determination of whether the car door is open according to the car door image includes importing the car door image into a preset image classification model to obtain a second classification result, and determining whether the car door is open according to the second classification result, determining the floor reached by the car according to the floor display image, and using it as the second verification floor; An instruction generation unit, configured to generate a detachment instruction when the first verification floor and the second verification floor are the same and both are the target floor, and it is determined that the car door is open; A third sending unit, configured to send the detachment instruction to the elevator control system of the target elevator.

8. A system for a robot to control an elevator according to claim 7, wherein, the system further includes a fourth acquisition unit and a third determination unit. The fourth acquisition unit is configured to acquire an internal scene image of the car of the target elevator. The third determination unit is configured to determine the vacant floor area in the car of the target elevator according to the internal scene image of the car, and determine whether the vacant floor area is greater than a set threshold. The second sending unit is specifically configured to send the target floor to the elevator control system of the target elevator when the third determination unit determines that the vacant floor area is greater than the set threshold.

9. A system for a robot to control an elevator, wherein, it includes: a memory, configured to store instructions; a processor, configured to read the instructions stored in the memory and execute the method according to any one of claims 1-6 according to the instructions.

Images