An intelligent switching control method and system for AGV control mode in hospitals

Through the combination of AGV to real-time situation information and task information, the automatic switching of control mode is solved, and the problem of switching between self-walking and following modes is improved by using AGV in hospitals, which is to improve transportation efficiency and adaptability.

CN118534822BActive Publication Date: 2024-11-19HANGZHOU YILIANTONG TECH CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202410908066.4
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-07-08
Publication Date
2024-11-19
Estimated Expiration
2044-07-08

AI Technical Summary

Technical Problem

It is difficult to achieve automatic switching between the self-travel mode and the following mode in existing hospitals, resulting in inefficient transportation efficiency and insufficient adaptability.

Method used

Through AGV, the real-time situation information of the walking area is detected, combined with its own task information, determine whether to switch the control mode, and switch modes at the appropriate time, including determining the initial mode based on the permission configuration in the task information and high-precision map planning, and The mode switching is determined by evaluating the detected real-time situation information through difficulty and duration.

Benefits of technology

It realizes the fast and accurate response of AGV in the walking area, improves adaptability, and significantly improves transportation efficiency and adaptability compared to manual switching.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118534822B_ABST
    Figure CN118534822B_ABST
Patent Text Reader

Abstract

The present invention belongs to the technical field of AGV. An intelligent switching control method and system for AGV control modes for hospitals is provided. The method includes: in the process of AGV walking according to the set control mode, real-time situation information around the walking area is detected; wherein the control mode includes a self-walking mode and a following mode; according to the real-time situation information obtained by the detection and the task information stored by itself, it is determined whether to switch the control mode; when it is determined that the control mode needs to be switched, the switching timing is determined, and the control mode is switched when the switching timing is reached; otherwise, the current control mode is maintained. The AGV in the present invention can respond quickly and accurately to whether the control mode needs to be switched based on the real-time situation information around the walking area and the task information stored by itself, and has significantly stronger adaptability than the manual switching method.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of AGV technology, and in particular to an intelligent switching control method and system for AGV control modes for hospitals. Background Art

[0002] Hospital AGVs (Automated Guided Vehicles) are unmanned automated vehicles with functions such as automatic guidance, automatic navigation, and automatic obstacle avoidance. They can automatically complete the transportation of medicines, consumables, specimens and other materials according to the hospital map and route planning, thereby improving the efficiency of hospital logistics and reducing the workload of medical staff.

[0003] Hospital AGVs can be equipped with self-driving mode and follow-up mode to be used in different activity scenarios. However, how to automatically switch between the two modes more reasonably is a technical problem that needs to be solved urgently. Summary of the invention

[0004] In this regard, the present invention provides an intelligent switching control method, system, electronic device, computer storage medium and computer program product for AGV control modes for hospitals to solve the above technical problems.

[0005] The present invention discloses an intelligent switching control method for an AGV control mode for a hospital, the method comprising the following steps:

[0006] When the AGV is walking according to the set control mode, the real-time situation information around the walking area is detected; wherein the control mode includes a self-walking mode and a following mode;

[0007] Determine whether to switch the control mode according to the real-time situation information obtained by detection and the task information stored in itself;

[0008] When it is determined that the control mode needs to be switched, a switching timing is determined, and the control mode is switched when the switching timing is reached; otherwise, the current control mode is maintained.

[0009] In some embodiments, before the AGV walks according to the set control mode, the method further includes:

[0010] The AGV receives the task information and determines whether the task information includes setting information of the control mode;

[0011] If the task information includes setting information of the control mode, confirming the control mode corresponding to the setting information;

[0012] If the task information does not include setting information of the control mode, the task content in the task information is parsed to obtain the transport starting point information, the transport end point information and the pass authority configuration information, and the control mode is determined based on the transport starting point information, the transport end point information and the pass authority configuration information.

[0013] In some embodiments, the determining of the control mode according to the transport starting point information, the transport end point information and the authority configuration information includes:

[0014] A task route is obtained based on the transport starting point information, the transport end point information and a high-precision map inside the hospital, wherein the task route includes multiple gate areas and corresponding authority requirement information;

[0015] Matching and calculating the permission configuration information with the permission requirement information corresponding to each door area;

[0016] If all the authority requirement information is matched successfully, the control mode is determined to be the self-propelled mode;

[0017] If all the authority requirement information fails to match successfully, the control mode is determined to be a follow mode;

[0018] If only part of the authority requirement information is matched successfully, the control mode is determined to be the self-propelled mode and the following mode.

[0019] In some embodiments, when the current control mode is the self-propelled mode, determining whether to switch the control mode according to the real-time situation information detected and the task information stored by itself includes:

[0020] The difficulty of passing the current area is evaluated according to the real-time situation information obtained by detection, and if the difficulty of passing the current area is less than the difficulty threshold, the self-propelled mode is not switched to the following mode;

[0021] If the passing difficulty is greater than the difficulty threshold, further determining the passing time according to the difficulty type corresponding to the passing difficulty, and predicting the estimated time consumption of the current area according to the task information;

[0022] If the passing time is longer than the estimated time, the self-propelled mode is switched to the following mode; otherwise, the self-propelled mode is not switched to the following mode.

[0023] In some embodiments, determining the passing time according to the difficulty type corresponding to the passing difficulty level includes:

[0024] The real-time situation information obtained by detection includes the position distribution information of each dynamic object in the current area, and the cluster feature value is extracted based on the position distribution information;

[0025] When the clique feature value is higher than the clique feature threshold, the difficulty type corresponding to the passing difficulty is set to the first type, and the first type corresponds to the first passing time; and when the clique feature value is lower than the clique feature threshold, the difficulty type corresponding to the passing difficulty is set to the second type, and the second type corresponds to the second passing time;

[0026] The first passing time is shorter than the second passing time.

[0027] In some embodiments, when the current control mode is the following mode, determining whether to switch the control mode according to the real-time situation information detected and the task information stored in the system includes:

[0028] The passing difficulty of the current area is evaluated according to the real-time situation information obtained by detection. If the passing difficulty is less than the difficulty threshold and the passing time is longer than the estimated time, the following mode is switched to the self-propelled mode.

[0029] The present invention also discloses an intelligent switching control system for hospital AGV control modes, which is applied to hospital AGVs. The system includes a processing module and a storage module; a computer program is stored in the storage module; the processing module calls and executes the computer program stored in the storage module to implement any of the methods described above.

[0030] The present invention also discloses an electronic device, comprising: at least one processor, a memory, and a computer program stored in the memory and executable on the at least one processor, wherein the processor executes the computer program to implement any of the above methods.

[0031] The present invention also discloses a computer storage medium, wherein the computer-readable storage medium stores a computer program, and the computer program is executed by a processor to implement any of the above methods.

[0032] The present invention also discloses a computer program product, which can realize any of the above methods when the computer program product is run on a terminal.

[0033] The beneficial effect of the present invention is that the AGV in the present invention can respond quickly and accurately to whether the control mode needs to be switched according to the real-time situation information around the walking area and the task information stored in itself. Compared with the manual switching method, it has significantly stronger adaptability. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0035] Figure 1 It is a flow chart of an intelligent switching control method of a hospital AGV control mode disclosed in an embodiment of the present invention;

[0036] Figure 2 It is a structural schematic diagram of an intelligent switching control system for an AGV control mode for a hospital disclosed in an embodiment of the present invention. DETAILED DESCRIPTION

[0037] The following is a description of the implementation of the present application by specific specific embodiments. People familiar with the technology can easily understand other advantages and effects of the present application from the contents disclosed in this specification. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in the field without creative work are within the scope of protection of the present application.

[0038] In addition, the technical features involved in the different embodiments of the present application described below can be combined with each other as long as they do not conflict with each other.

[0039] like Figure 1 As shown, an embodiment of the present invention discloses an intelligent switching control method for hospital AGV control mode, the method comprising the following steps:

[0040] When the AGV is walking according to the set control mode, the real-time situation information around the walking area is detected; wherein the control mode includes a self-walking mode and a following mode;

[0041] Determine whether to switch the control mode according to the real-time situation information obtained by detection and the task information stored in itself;

[0042] When it is determined that the control mode needs to be switched, a switching timing is determined, and the control mode is switched when the switching timing is reached; otherwise, the current control mode is maintained.

[0043] The hospital AGV in the present invention is configured with two control modes, namely, self-propelled mode and follow-up mode. Initially, the AGV is set to self-propelled mode or follow-up mode, and the AGV walks in the hospital area according to the self-propelled mode or follow-up mode to perform the transportation task of carrying medicines, consumables, specimens and other materials. In the process of walking according to the set control mode, the AGV detects the real-time situation information around the walking area based on the detection device configured by itself. The detection device can be a binocular camera, a laser radar, a millimeter-wave radar, etc. The AGV conducts an in-depth analysis of the detected real-time situation information and the task information stored by itself, so as to draw a conclusion on whether the control mode needs to be switched. If switching is required, the switching timing is further determined and switched at the switching timing, otherwise the currently set control mode is maintained. Therefore, the AGV in the present invention can respond quickly and accurately to whether the control mode needs to be switched based on the real-time situation information around the walking area and the task information stored by itself, which has significantly stronger adaptability than the manual switching method.

[0044] The AGV in the present invention may be a conventional "car" form, such as a wheeled structure, a crawler structure, etc., or a "person" form. The present invention does not make any limitation to this.

[0045] In some embodiments, before the AGV walks according to the set control mode, the method further includes:

[0046] The AGV receives the task information and determines whether the task information includes setting information of the control mode;

[0047] If the task information includes setting information of the control mode, confirming the control mode corresponding to the setting information;

[0048] If the task information does not include setting information of the control mode, the task content in the task information is parsed to obtain the transport starting point information, the transport end point information and the pass authority configuration information, and the control mode is determined based on the transport starting point information, the transport end point information and the pass authority configuration information.

[0049] In this embodiment, after the AGV is turned on or activated, it receives the task information sent by the task center through communication, and the task information includes the task content and the setting information of the control mode. The AGV first determines whether the task information contains the setting information of the control mode. If so, it directly performs the initial control mode of the handling task according to the set control mode. If the task center does not specify the control mode of this task, the AGV parses the task content of the task information to obtain the handling starting point information, handling end point information and the permission configuration information, and determines the corresponding control mode accordingly.

[0050] The task information can be sent to the AGV by the task center wirelessly, or input by other staff in the same area as the AGV through voice, card swiping, typing, etc.

[0051] In some embodiments, the determining of the control mode according to the transport starting point information, the transport end point information and the authority configuration information includes:

[0052] A task route is obtained based on the transport starting point information, the transport end point information and a high-precision map inside the hospital, wherein the task route includes multiple gate areas and corresponding authority requirement information;

[0053] Matching and calculating the permission configuration information with the permission requirement information corresponding to each door area;

[0054] If all the authority requirement information is matched successfully, the control mode is determined to be the self-propelled mode;

[0055] If all the authority requirement information fails to match successfully, the control mode is determined to be a follow mode;

[0056] If only part of the authority requirement information is matched successfully, the control mode is determined to be the self-propelled mode and the following mode.

[0057] In this embodiment, the AGV stores a high-precision map of the hospital, and the corresponding task route can be planned by combining the transport starting point information and transport end point information obtained by the above analysis. At the same time, certain areas in the hospital require corresponding permissions to pass through. When planning the task route, the high-precision map is used to retrieve the various door areas and their corresponding permission requirements on the task route. The enabled pass permission configuration information in the task information is matched and calculated with each permission requirement information. There are three matching situations: 1) All permission requirement information is matched successfully, that is, the task center has enabled the AGV to have pass permissions for all door areas that require permissions on the task route. At this time, the control mode can be set to self-propelled mode. In self-propelled mode, the AGV has a faster walking speed; 2) All permission requirement information is not matched successfully, that is, the task center has not enabled the AGV to have pass permissions for any door areas that require permissions on the task route. At this time, the control mode needs to be set to follow mode, that is, the AGV needs to follow the corresponding manager who has pass permissions. In follow mode, the AGV has a higher ability to pass smoothly; 3) Only some permission requirement information is matched successfully, that is, the task center has only enabled the AGV to have pass permissions for some door areas on the task route. At this time, the control mode of the AGV needs to be set to self-propelled mode and follow mode, that is, the self-propelled mode is executed on the section with pass permissions, and the follow mode is executed on the section without pass permissions.

[0058] Among them, the manager with the passing authority can be the person who always follows the AGV at the beginning of the mission, or the person who is temporarily required when the AGV reaches the door area without the passing authority. For example, the manager in the area (wearing the specific style of clothing of the hospital) is determined based on image recognition technology, and then the manager is interacted with through text or voice to request him to assist the AGV to pass through the door area, or subsequent door areas without passing authority. After the manager confirms, the AGV can switch from the self-propelled mode to the following mode.

[0059] In some embodiments, when the current control mode is the self-propelled mode, determining whether to switch the control mode according to the real-time situation information detected and the task information stored by itself includes:

[0060] The difficulty of passing the current area is evaluated according to the real-time situation information obtained by detection, and if the difficulty of passing the current area is less than the difficulty threshold, the self-propelled mode is not switched to the following mode;

[0061] If the passing difficulty is greater than the difficulty threshold, further determining the passing time according to the difficulty type corresponding to the passing difficulty, and predicting the estimated time consumption of the current area according to the task information;

[0062] If the passing time is longer than the estimated time, the self-propelled mode is switched to the following mode; otherwise, the self-propelled mode is not switched to the following mode.

[0063] In this embodiment, when the control mode currently set to the AGV is the self-propelled mode, the AGV can evaluate the difficulty of passing the current area based on the real-time situation information. When the difficulty of passing is less than the difficulty threshold, the AGV can pass through the area smoothly in the self-propelled mode, and the self-propelled mode is not switched to the follow-up mode at this time; when the difficulty of passing is greater than the difficulty threshold, the probability of the AGV passing through the area smoothly is low due to the detection ability and computing ability of the AGV (emergency braking, route replanning, etc.), and the self-propelled mode needs to be switched to the follow-up mode at this time. Since the AGV needs to stop and wait each time the control mode is switched, and can continue to walk after the switch is completed, the execution efficiency of the handling task is low. The present invention analyzes the difficulty of passing to decide whether to switch the self-propelled mode to the follow-up mode, which can reduce the number of control mode switching times and thus improve the execution efficiency of the handling task.

[0064] At the same time, when the passing difficulty is greater than the difficulty threshold, the present invention further determines the passing time according to the difficulty type corresponding to the passing difficulty, and predicts the estimated time consumption of the current area according to the task information. The estimated time consumption is the ideal driving time of the AGV in the current area expected by the task center. In other words, in order to improve the execution timeliness of the handling task, the task center configures the corresponding ideal driving time for each section of the task route. If the passing time of the AGV in the current area is higher than the ideal driving time, it may reduce the execution timeliness of the handling task, resulting in the failure to meet medical needs, which is not allowed in the hospital scenario. In this regard, the present invention sets the AGV to switch the self-propelled mode to the following mode when the passing time of the AGV in the current area is higher than the ideal driving time, that is, to pass the current area as soon as possible by timely requesting the management personnel to "lead the way"; otherwise, there is no need to switch the self-propelled mode to the following mode, and the probability of smooth passage can be improved by reducing the speed and other measures, especially when the management personnel who "lead the way" in the current area fail to find is particularly applicable.

[0065] It should be noted that the transport destination information included in the task information corresponds to different departments, and different departments correspond to different "urgency levels". For example, the "urgency level" of the operating room is significantly higher than that of the general outpatient clinic. The corresponding standard time is configured according to the emergency priority of each department. The higher the emergency priority, the shorter the standard time of the department, and the lower the emergency priority, the longer the standard time of the department. Therefore, based on the transport destination information, the standard time of the planned route corresponding to this transport task can be determined, and then the corresponding estimated time can be determined based on the length of each section of the planned route.

[0066] In some embodiments, determining the passing time according to the difficulty type corresponding to the passing difficulty level includes:

[0067] The real-time situation information obtained by detection includes the position distribution information of each dynamic object in the current area, and the cluster feature value is extracted based on the position distribution information;

[0068] When the clique feature value is higher than the clique feature threshold, the difficulty type corresponding to the passing difficulty is set to the first type, and the first type corresponds to the first passing time; and when the clique feature value is lower than the clique feature threshold, the difficulty type corresponding to the passing difficulty is set to the second type, and the second type corresponds to the second passing time;

[0069] The first passing time is shorter than the second passing time.

[0070] In this embodiment, when the AGV finds that the probability of successfully passing through the area is low, it can wait by the side and wait for these dynamic objects to pass through the current area before starting to move. The dynamic objects include people, carts, other AGVs, etc. This requires predicting the predicted time for these dynamic objects to pass through the current area.

[0071] The real-time situation information detected by the AGV contains the location distribution information of dynamic objects, and the cluster characteristic value can be extracted based on the location distribution information of these dynamic objects. The cluster characteristic value in the present invention refers to the degree of aggregation presented by all dynamic objects. When these dynamic objects gather in a small area, that is, they are clustered, the corresponding cluster characteristic value is larger. On the contrary, when these dynamic objects are dispersed, the corresponding cluster characteristic value is smaller. On this basis, when the cluster characteristic value is higher than the cluster characteristic threshold, that is, the more clustered, the shorter the time for these dynamic objects to pass through, the difficulty type corresponding to the passing difficulty is set to the first type, and the first type corresponds to a smaller first passing time; when the cluster characteristic value is lower than the cluster characteristic threshold, that is, the more dispersed, the longer the time for these dynamic objects to pass through will be, and the difficulty type corresponding to the passing difficulty is set to the second type, and the second type corresponds to a larger second passing time.

[0072] In addition, the first type and the second type should also correspond to multiple first passing durations and second passing durations in groups, mainly depending on the number of dynamic objects. The details are shown in the following table:

[0073] It should be noted that the cluster characteristic value can be represented by the degree of aggregation according to the position distribution information. The higher the degree of aggregation, the larger the corresponding cluster characteristic value, and vice versa. The principle for determining the degree of aggregation is: perform a bird's-eye projection on the position distribution information of the dynamic objects in the current area, connect each projection point to obtain multiple connected domains, calculate the number and maximum area of ​​each connected domain, and the smaller the number of connected domains and the larger the maximum area, the larger the corresponding degree of aggregation. The present invention does not limit the specific calculation formula of the degree of aggregation, and it is sufficient to mainly comply with the above determination principle.

[0074] In some embodiments, when the current control mode is the following mode, determining whether to switch the control mode according to the real-time situation information detected and the task information stored in the system includes:

[0075] The passing difficulty of the current area is evaluated according to the real-time situation information obtained by detection. If the passing difficulty is less than the difficulty threshold and the passing time is longer than the estimated time, the following mode is switched to the self-propelled mode.

[0076] In this embodiment, when the control mode currently set to the AGV is the follow mode, the AGV can evaluate the difficulty of passing the current area in the above manner. If the difficulty is less than the difficulty threshold, it means that the conditions for smooth passing are initially met. If the AGV predicts that the time it will take to pass the current area is longer than the estimated time, there is a problem of insufficient timeliness in transportation. At this time, the follow mode can be switched to the self-propelled mode to increase the speed of passing the current area and ensure the timeliness of transportation.

[0077] Among them, after the AGV switches the following mode to the self-propelled mode, it can evaluate the difficulty of passing the area based on the real-time situation information obtained from the new detection, and adjust its own walking speed accordingly to reduce the passing time of subsequent sections, thereby ensuring that the overall passing time of the planned route is no higher than the aforementioned standard time.

[0078] In addition, the aforementioned switching timing may be determined in a manner of: determining the switching timing according to the passing difficulty, and the time difference between the switching timing and the current moment is negatively correlated with the passing difficulty.

[0079] 1) In the self-propelled mode: the switching timing is determined according to the passing difficulty, and the time difference between the switching timing and the current moment is positively correlated with the passing difficulty.

[0080] In the self-propelled mode, when the AGV determines that the difficulty of passing is too great and needs to switch to the following mode, it can determine how long it will take to switch to the following mode based on the difficulty of passing and the corresponding positive correlation function. That is, the greater the difficulty of passing, the longer it will take to switch. At this time, the AGV is closer to the area where the dynamic object is located, and the management personnel who can "lead the way" are also likely to be in the dynamic object, which can increase the execution rate of the following mode; otherwise, the standard time difference is used to determine the switching time, and the marked time difference is, for example, 1s.

[0081] 2) In the follow-up mode: the moment when the passing difficulty is lower than the difficulty threshold is determined as the switching timing.

[0082] In the following mode, the AGV continuously judges the current passing difficulty. When the passing difficulty is lower than the difficulty threshold, the following mode can be directly switched to the self-propelled mode to ensure the timeliness of transportation.

[0083] like Figure 2 As shown, an embodiment of the present invention also discloses an intelligent switching control system for hospital AGV control mode, which is applied to hospital AGV. The system includes a processing module and a storage module; a computer program is stored in the storage module; the processing module calls and executes the computer program stored in the storage module to implement the method described in the above embodiment.

[0084] An embodiment of the present invention further discloses an electronic device, comprising: at least one processor, a memory, and a computer program stored in the memory and executable on the at least one processor, characterized in that: the processor executes the computer program to implement the method described in the above embodiment.

[0085] An embodiment of the present invention further discloses a computer storage medium, wherein the computer storage medium stores a computer program, and the computer program is executed by a processor to implement the method described in the above embodiment.

[0086] The embodiment of the present invention further discloses a computer program product. When the computer program product is run on a terminal, the terminal implements the method described in the above embodiment.

[0087] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in terms of function in the above description. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0088] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0089] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of units is only a logical function division, and there may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, or it can be an electrical, mechanical or other form of connection.

[0090] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the embodiments of the present invention.

[0091] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0092] The above are only specific embodiments of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed by the present invention, and these modifications or replacements should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention shall be based on the protection scope of the claims.

Claims

1. An intelligent switching control method for AGV control mode in a hospital, characterized by: The method comprises the following steps: When the AGV is walking according to the set control mode, the real-time situation information around the walking area is detected; wherein the control mode includes a self-walking mode and a following mode; Determine whether to switch the control mode according to the real-time situation information obtained by detection and the task information stored in itself; When it is determined that the control mode needs to be switched, a switching timing is determined, and the control mode is switched when the switching timing is reached; otherwise, the current control mode is maintained; When the current control mode is the self-propelled mode, determining whether to switch the control mode according to the real-time situation information detected and the task information stored in the self-propelled mode includes: The difficulty of passing the current area is evaluated according to the real-time situation information obtained by detection, and if the difficulty of passing the current area is less than the difficulty threshold, the self-propelled mode is not switched to the following mode; If the passing difficulty is greater than the difficulty threshold, further determining the passing time according to the difficulty type corresponding to the passing difficulty, and predicting the estimated time consumption of the current area according to the task information; If the passing time is longer than the estimated time, the self-propelled mode is switched to the following mode; otherwise, the self-propelled mode is not switched to the following mode.

2. According to claim 1, the intelligent switching control method of the hospital AGV control mode is characterized in that: Before the AGV walks according to the set control mode, the method further includes: The AGV receives the task information and determines whether the task information includes setting information of the control mode; If the task information includes setting information of the control mode, confirming the control mode corresponding to the setting information; If the task information does not include setting information of the control mode, the task content in the task information is parsed to obtain the transport starting point information, the transport end point information and the pass authority configuration information, and the control mode is determined based on the transport starting point information, the transport end point information and the pass authority configuration information.

3. The intelligent switching control method of the hospital AGV control mode according to claim 2 is characterized in that: The control mode is determined according to the transport starting point information, the transport end point information and the authority configuration information, including: A task route is obtained based on the transport starting point information, the transport end point information and a high-precision map inside the hospital, wherein the task route includes multiple gate areas and corresponding authority requirement information; Matching and calculating the permission configuration information with the permission requirement information corresponding to each door area; If all the authority requirement information is matched successfully, the control mode is determined to be the self-propelled mode; If all the authority requirement information fails to match successfully, the control mode is determined to be a follow mode; If only part of the authority requirement information is matched successfully, the control mode is determined to be the self-propelled mode and the following mode.

4. The intelligent switching control method of the hospital AGV control mode according to claim 3 is characterized in that: The determining of the passing time according to the difficulty type corresponding to the passing difficulty includes: The real-time situation information obtained by detection includes the position distribution information of each dynamic object in the current area, and the cluster feature value is extracted based on the position distribution information; When the clique feature value is higher than the clique feature threshold, the difficulty type corresponding to the passing difficulty is set to the first type, and the first type corresponds to the first passing time; and when the clique feature value is lower than the clique feature threshold, the difficulty type corresponding to the passing difficulty is set to the second type, and the second type corresponds to the second passing time; The first passing time is shorter than the second passing time.

5. The intelligent switching control method of the hospital AGV control mode according to claim 1 is characterized in that: When the current control mode is the following mode, determining whether to switch the control mode according to the real-time situation information obtained by detection and the task information stored in itself includes: The passing difficulty of the current area is evaluated according to the real-time situation information obtained by detection. If the passing difficulty is less than the difficulty threshold and the passing time is longer than the estimated time, the following mode is switched to the self-propelled mode.

6. An intelligent switching control system for hospital AGV control mode, applied to hospital AGV, the system comprises a processing module and a storage module; the storage module stores a computer program; the characteristics are: The processing module calls and executes the computer program stored in the storage module to implement the method according to any one of claims 1 to 5.

7. An electronic device comprising: At least one processor, a memory, and a computer program stored in the memory and executable on the at least one processor, wherein the processor executes the computer program to implement the method according to any one of claims 1 to 5.

8. A computer storage medium storing a computer program, characterized in that: The computer program is executed by a processor to implement the method according to any one of claims 1 to 5.

9. A computer program product, characterized in that: When the computer program product is run on a terminal, the method according to any one of claims 1 to 5 is implemented.