Robot floor localization method and apparatus

Abstract

The present disclosure relates to the technical field of robots, and provides a robot floor positioning method and device. The robot floor positioning method comprises: after determining that a robot is in a cross-floor task scenario, acquiring wireless signal sources and corresponding signal strengths in an environment where the robot is currently located, and selecting a first number of initial wireless signal sources with the largest signal strengths from the wireless signal sources; acquiring a modulus of a difference between the signal strengths of the initial wireless signal sources and corresponding signal strengths of a preset KNN model sample set; selecting a second number of reselected wireless signal sources with the smallest modulus of the difference from the initial wireless signal sources; and determining a target floor where the robot is located according to floor information labels corresponding to the reselected wireless signal sources. The above technical means can solve the technical problem that the floor where the robot is located cannot be simply and accurately positioned.

Description

Technical Field

[0001] This disclosure relates to the field of robotics, and more particularly to a robot floor positioning method, apparatus, electronic device, and computer-readable storage medium. Background Technology

[0002] A robot is a machine that performs tasks automatically. It can receive instructions from humans, communicate with humans, run pre-programmed programs, or act according to principles and guidelines customized by artificial intelligence technology.

[0003] The automated execution of a robot's task requires the successful accumulation of each step; if any one step fails, the entire task cannot succeed. In the operating environment of delivery robots in hotels and buildings, many abnormal situations may occur during the crucial elevator riding process in cross-floor tasks. These include situations such as the robot failing to obtain the correct floor information, the robot being moved out of or into the elevator, or being moved into a different elevator during the ride. Generally, elevator companies do not provide communication interfaces with the outside world for safety reasons, preventing the robot from obtaining floor information through the elevator's communication interface.

[0004] In related technologies, floor information can be determined by combining sensor ranging with wireless communication, or by deploying positioning sensors in the elevator shaft. However, these methods suffer from difficulties in ranging or deployment. How to easily and accurately locate the floor where the robot is located is a pressing technical problem that needs to be solved. Summary of the Invention

[0005] In view of this, the present disclosure provides a robot floor positioning method, apparatus, electronic device, and computer-readable storage medium to solve the problem in the prior art that it is impossible to simply and accurately locate the floor where the robot is located.

[0006] A first aspect of this disclosure provides a robot floor localization method, the method comprising: after determining that the robot is in a cross-floor task scenario, acquiring wireless signal sources and their corresponding signal strengths in the environment where the robot is currently located, and selecting a first number of initial wireless signal sources with the largest signal strength from the wireless signal sources, wherein the first number is a constant; acquiring the modulus of the difference between the signal strength of the initial wireless signal sources and the signal strength of the corresponding wireless signal sources in the sample set of a preset KNN model, wherein the sample set includes feature vectors of the signal strengths of the wireless signal sources in the set arranged in order of their physical addresses and corresponding floor information tags; selecting a second number of reselected wireless signal sources with the smallest modulus of the difference from the initial wireless signal sources, wherein the second number is the K value of the trained KNN model; and determining the target floor where the robot is located based on the floor information tags corresponding to the reselected wireless signal sources.

[0007] A second aspect of this disclosure provides a robot floor positioning device, comprising: a signal source initial selection module, configured to, after determining that the robot is in a cross-floor task scenario, acquire wireless signal sources and their corresponding signal strengths in the environment where the robot is currently located, and select a first number of initial wireless signal sources with the largest signal strength from the wireless signal sources, wherein the first number is a constant; a modulus acquisition module, configured to acquire the modulus of the difference between the signal strength of the initial wireless signal sources and the signal strength of the corresponding wireless signal sources in the sample set of a preset KNN model, wherein the sample set includes feature vectors of the signal strengths of the wireless signal sources in the set arranged in order of their physical addresses and corresponding floor information tags; a signal source reselection module, configured to select a second number of reselected wireless signal sources with the smallest modulus of the difference from the initial wireless signal sources, wherein the second number is the K value of the trained KNN model; and a floor determination module, configured to determine the target floor where the robot is located based on the floor information tags corresponding to the reselected wireless signal sources.

[0008] A third aspect of this disclosure provides an electronic device including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the method described above.

[0009] A fourth aspect of this disclosure provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the above-described method.

[0010] The beneficial effects of this disclosed embodiment compared with the prior art are: by selecting an initial wireless signal source, selecting a second wireless signal source based on the sample set of the KNN model, and determining the target floor where the robot is located based on the second wireless signal source and the K nearest neighbor algorithm, the robot floor can be located simply and accurately without the need to deploy sensors. Attached Figure Description

[0011] To more clearly illustrate the technical solutions in the embodiments of this disclosure, the accompanying drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this disclosure. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0012] Figure 1 This is a schematic diagram illustrating an application scenario of an embodiment of this disclosure;

[0013] Figure 2 This is a flowchart illustrating a robot floor positioning method provided in an embodiment of this disclosure;

[0014] Figure 3 This is a flowchart illustrating the method for determining a target floor provided in an embodiment of this disclosure;

[0015] Figure 4 This is a schematic diagram of the structure of a robot floor positioning device provided in an embodiment of this disclosure;

[0016] Figure 5 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this disclosure. Detailed Implementation

[0017] In the following description, specific details such as particular system architectures and techniques are set forth for illustrative purposes and not for limitation, so as to provide a thorough understanding of the embodiments of this disclosure. However, those skilled in the art will understand that this disclosure may also be implemented in other embodiments without these specific details. In other instances, detailed descriptions of well-known systems, apparatuses, circuits, and methods have been omitted so as not to obscure the description of this disclosure with unnecessary detail.

[0018] In related technologies, when obtaining the robot's floor in a robot's cross-floor task, the robot's floor can be obtained by combining infrared laser or ultra-wideband sensor ranging with wireless or network communication. Alternatively, multiple radio frequency identification or infrared sensors can be installed near the elevator's stops at each floor in the elevator shaft to determine whether the elevator has passed the current floor, thereby obtaining the robot's floor. Floors can also be located by deploying wireless access points.

[0019] Among the methods for obtaining robot floor information using infrared laser or ultra-wideband sensor ranging combined with wireless or network communication, both sensor ranging and wireless communication have maximum distance limitations. At higher floors, this can cause ranging to exceed limits, leading to measurement failures and communication breakdowns. Network communication suffers from severe latency within the elevator shaft, resulting in incorrect floor information. Deploying RFID or infrared sensors within the elevator shaft requires sensors to be placed above and below each elevator stop, offering relatively high accuracy but being time-consuming, labor-intensive, and cumbersome to deploy. Both of these methods measure elevator floors, not the robot's floor directly. When the measurement results differ from other robot floor location methods, tracking becomes difficult. Deploying wireless access points for floor location also presents deployment challenges.

[0020] To address the above issues, this disclosure provides a robot floor positioning solution.

[0021] A robot floor positioning method and apparatus according to embodiments of the present disclosure will now be described in detail with reference to the accompanying drawings.

[0022] Figure 1This is a schematic diagram illustrating an application scenario of an embodiment of this disclosure. The application scenario may include terminal devices 101, 102, and 103, server 104, and network 105.

[0023] Terminal devices 101, 102, and 103 can be hardware or software. When terminal devices 101, 102, and 103 are hardware, they can be various electronic devices with displays that support communication with server 104, including but not limited to smartphones, robots, laptops, and desktop computers (for example, 102 can be a robot). When terminal devices 101, 102, and 103 are software, they can be installed in the aforementioned electronic devices. Terminal devices 101, 102, and 103 can be implemented as multiple software programs or software modules, or as a single software program or software module; this disclosure does not limit this. Furthermore, various applications can be installed on terminal devices 101, 102, and 103, such as data processing applications, instant messaging tools, social platform software, search applications, shopping applications, etc.

[0024] Server 104 can be a server that provides various services, such as a backend server that receives requests sent by terminal devices with which it has established communication connections. This backend server can receive and analyze the requests sent by the terminal devices and generate processing results. Server 104 can be a single server, a server cluster consisting of several servers, or a cloud computing service center. This embodiment of the disclosure does not impose any limitations on these aspects.

[0025] It should be noted that server 104 can be either hardware or software. When server 104 is hardware, it can be various electronic devices that provide various services to terminal devices 101, 102, and 103. When server 104 is software, it can be multiple software programs or software modules that provide various services to terminal devices 101, 102, and 103, or it can be a single software program or software module that provides various services to terminal devices 101, 102, and 103. This disclosure does not limit the scope of the embodiments.

[0026] Network 105 can be a wired network using coaxial cable, twisted pair, and fiber optic connection, or it can be a wireless network that enables interconnection of various communication devices without wiring, such as Bluetooth, Near Field Communication (NFC), Infrared, etc. This disclosure does not limit the scope of the network.

[0027] Target users can establish a communication connection with server 104 via network 105 through terminal devices 101, 102, and 103 to receive or send information, etc. It should be noted that the specific types, quantities, and combinations of terminal devices 101, 102, and 103, server 104, and network 105 can be adjusted according to the actual needs of the application scenario, and this disclosure embodiment does not impose any limitations on this.

[0028] Figure 2 This is a flowchart illustrating a robot floor positioning method provided in an embodiment of this disclosure. Figure 2 The robot floor positioning method can be derived from Figure 1 The terminal device or server executes the command. For example... Figure 2 As shown, the robot floor positioning method includes:

[0029] Step S201: After determining that the robot is in a cross-floor task scenario, obtain the wireless signal sources and corresponding signal strengths in the environment where the robot is currently located, and select the first number of initial wireless signal sources with the largest signal strength from the wireless signal sources, where the first number is a constant.

[0030] Specifically, the robot's working scenarios can be single-floor tasks and multi-floor tasks. Multi-floor tasks include, but are not limited to, multi-floor charging tasks and multi-floor item retrieval or delivery tasks. The wireless signal source can be a Wi-Fi router, but is not limited to. The robot's built-in industrial control computer is equipped with a wireless network device. Through this device, the robot can search for wireless network routers in its environment. This search process allows the robot to obtain the signal strength of the wireless network router while it is searching for one. This signal strength can be represented by RSSI (Received Signal Strength Indicator). The first quantity can be a constant set according to actual needs; for example, the first quantity can be set to 6, but is not limited to this. The robot's position when searching for wireless signal sources in its environment can be any position in the multi-floor task scenario.

[0031] Step S202: Obtain the modulus of the difference between the signal strength of the initially selected wireless signal source and the signal strength of the corresponding wireless signal source in the sample set of the preset KNN (K Nearest Neighbors) model. The sample set includes feature vectors of the signal strengths of the wireless signal sources arranged in order of their physical addresses, along with their corresponding floor information tags. Theoretically, the set of wireless signal sources includes all wireless signal sources in cross-floor task scenarios. If the signal strength of a wireless signal source is low during a measurement, it can be considered that the signal strength of the wireless signal source with the low signal strength in that measurement is 0.

[0032] Specifically, the KNN model is a K-nearest neighbor algorithm model. The KNN algorithm determines the category of a sample based on known category samples surrounding it. Further, it determines the category based on the K nearest neighbors. Training the KNN model yields a K value that results in more accurate classification. The initial set of wireless signal sources refers to wireless signal sources with the same physical address as the initial selected wireless signal source. The magnitude of the difference in signal strength between two wireless signal sources is the absolute value of the difference in signal strength.

[0033] Step S203: Select a second number of reselected wireless signal sources from the initial selection of wireless signal sources, where the second number is the K value of the trained KNN model.

[0034] Step S204: Determine the target floor where the robot is located based on the floor information tag corresponding to the selected wireless signal source.

[0035] Specifically, the floor corresponding to the selected wireless signal source can be determined based on the floor information, and the target floor can be determined based on the frequency of the floor's occurrence.

[0036] According to the technical solution provided in this disclosure, by pre-constructing a sampling set of the KNN model and training the KNN model to obtain the K value, and then using the KNN algorithm to select a new wireless signal source based on the currently obtained initial wireless signal source and the KNN model, the target floor where the robot is located is determined based on the new wireless signal source and the K nearest neighbor algorithm. Compared with the prior art, robot floor positioning can be performed more simply and accurately.

[0037] In this embodiment of the disclosure, the training method of the KNN model includes: obtaining the second physical address and corresponding signal strength of the wireless signal source obtained by the robot searching for the wireless signal source on each floor in a cross-floor task scenario; using the signal strength corresponding to the second physical address as a feature vector, and saving the floor where the second physical address is found as a floor information label into the sample set of the KNN model; training the KNN model according to the sample set to obtain the K value.

[0038] Specifically, the feature vector can be formed by arranging the signal strengths of all or part of the strong wireless signal sources in the MAC (Media Access Control) address list of the entire current scene according to their MAC addresses. For example, the feature vector and floor information label can be in the form of [RSSI_1, RSSI_2, RSSI_3, ...: floor], where RSSI_1, RSSI_2, and RSSI_3 are the signal strength values ​​of the wireless signal sources in the set, numbered 1 to 3 after sorting by physical address, and floor is the floor information label. The sorting method can be ascending or descending.

[0039] During the collection of the sample set, the robot's position when searching for wireless signal sources in its environment can be any position in the cross-floor task scenario.

[0040] During the sample collection process, only the signal strength of the third strongest wireless signal source can be saved, while the signal strength of the remaining weaker wireless signal sources is recorded as 0. That is, the signal strength corresponding to the physical address of the weakest wireless signal source is 0. Here, the third strongest signal source is a constant set as needed. If relevant data of wireless signal sources are collected 10 times on different floors, 10 arrays in the form of [RSSI_1, RSSI_2, RSSI_3, ...:floor] can be obtained.

[0041] When determining the value of K, a cross-validation method can be used. The process involves trying multiple K values ​​according to certain rules, recording the number of errors for each K value on the validation set, and selecting the K value with the smallest number of errors as the target K value. Using the CNN algorithm for floor localization eliminates the need for deploying additional sensors; only preliminary data collection and model training are required for simple and accurate robot floor localization.

[0042] Before step S201, it is also necessary to obtain the robot's environmental deployment information and determine the robot's cross-floor task scenario based on the environmental deployment information.

[0043] Specifically, the robot's environmental deployment information can be obtained from the robot's task information. For example, when the robot is performing a task to return to a charging station on a designated floor for charging, it involves a cross-floor task scenario. However, when performing a greeting task in the hotel lobby, it does not involve a cross-floor task scenario.

[0044] In step S202, the first physical address and first signal strength of the currently initially selected wireless signal source are obtained; the wireless signal source with the first physical address and its corresponding second signal strength are searched in the set of wireless signal sources; the modulus of the difference between the first signal strength and the second signal strength is obtained.

[0045] Specifically, when searching for a wireless signal source with a first physical address in the set of wireless signal sources, the order of the first physical address in the sampling set is determined according to the size of the first physical address, thereby finding the signal strength corresponding to the physical address in that order.

[0046] The smaller the magnitude of the difference in signal strength between wireless signal sources at the same physical address, the smaller the distance between the current initial wireless signal source and the corresponding set of wireless signal sources. Thus, the floor where the initial wireless signal source is located can be inferred based on the floor information tag corresponding to the set of wireless signal sources. Furthermore, based on the floors where multiple initial wireless signal sources are located, the floor where the robot is located can be inferred.

[0047] like Figure 2 As shown, in step S204, the process of determining the target floor where the robot is located includes the following steps:

[0048] Step S301: Obtain the floor corresponding to the selected wireless signal source based on the floor information tag corresponding to the selected wireless signal source.

[0049] Specifically, if the value of K is 4, that is, the number of selectable wireless signal sources is 4, the floors corresponding to these 4 selectable wireless signal sources can be obtained according to the floor information labels.

[0050] Step S302: Select the floor with the highest frequency of occurrence as the target floor where the robot is located, based on the frequency of occurrence of the floor corresponding to the selected wireless signal source.

[0051] Specifically, if the floors corresponding to these four selected wireless signal sources are 3, 2, 3 and 3 respectively, and floor 3 appears most frequently, then the target floor can be determined to be floor 3.

[0052] In this embodiment of the disclosure, after step S204, in response to the robot successfully performing the cross-floor task and the target floor where the robot is located being the floor information reported by the robot, the wireless signal source, the corresponding signal strength, and the target floor in the robot's current environment can be updated to the sample set.

[0053] Specifically, the sample set records relevant data of the third strongest wireless signal source on each floor. This relevant data includes physical address, signal strength, and floor information. By updating the sample set with the relevant data of the wireless signal sources and removing the relevant data of the oldest wireless signal sources in the sample set for the current floor, a closed-loop automatic update of the sample set can be achieved to match real-time information.

[0054] Specifically, the floor information reported by the robot can be the current floor information recorded in the task information during the robot's operation.

[0055] In this embodiment of the disclosure, after step S204, in response to the fact that the target floor where the robot is located is not the floor information reported by the robot, the target floor can be obtained again, and an alarm signal can be generated to issue an alarm when the target floor obtained a second time is still not the floor information reported by the robot.

[0056] Specifically, if the target floor differs from the floor information reported by the robot on both occasions, a floor alarm needs to be issued, and the current floor information recorded in the task information during the robot's operation should be replaced with the target floor.

[0057] All of the above-mentioned optional technical solutions can be combined in any way to form the optional embodiments of this application, and will not be described in detail here.

[0058] The robot floor localization method according to the embodiments of this disclosure selects an initial wireless signal source, selects a second wireless signal source based on the sample set of the KNN model, and determines the target floor where the robot is located based on the second wireless signal source and the K nearest neighbor algorithm. This method can locate the robot floor simply and accurately without the need to deploy sensors.

[0059] The following are embodiments of the apparatus disclosed herein, which can be used to execute the embodiments of the method disclosed herein. The robot floor positioning apparatus described below and the robot floor positioning method described above can be referred to each other. For details not disclosed in the embodiments of the apparatus disclosed herein, please refer to the embodiments of the method disclosed herein.

[0060] Figure 4 This is a schematic diagram of a robot floor positioning device provided in an embodiment of this disclosure. Figure 4 As shown, the robot floor positioning device includes:

[0061] The signal source initial selection module 401 can be used to obtain the wireless signal sources and corresponding signal strengths in the current environment of the robot after determining that the robot is in a cross-floor task scenario, and select the first number of wireless signal sources with the largest signal strength from the wireless signal sources, where the first number is a constant.

[0062] The modulus acquisition module 402 can be used to acquire the modulus of the difference between the signal strength of the initially selected wireless signal source and the signal strength of the corresponding wireless signal source in the sample set of the preset KNN model. The sample set includes feature vectors of the signal strength of the wireless signal sources in the set arranged in order according to their physical addresses and corresponding floor information tags.

[0063] The signal source reselection module 403 can be used to select a second number of reselected wireless signal sources with the smallest difference among the initially selected wireless signal sources, wherein the second number is the K value of the trained KNN model.

[0064] The floor determination module 404 can be used to determine the target floor where the robot is located based on the floor information tag corresponding to the selected wireless signal source.

[0065] According to the technical solution provided in this disclosure, by pre-constructing a sampling set of the KNN model and training the KNN model to obtain the K value, and then using the KNN algorithm to select a new wireless signal source based on the currently obtained initial wireless signal source and the KNN model, the target floor where the robot is located is determined based on the new wireless signal source and the K nearest neighbor algorithm. Compared with the prior art, robot floor positioning can be performed more simply and accurately.

[0066] In this embodiment of the disclosure, the floor determination module 404 can also be used to obtain the floor corresponding to the reselected wireless signal source according to the floor information tag corresponding to the reselected wireless signal source, and select the floor with the highest occurrence frequency as the target floor where the robot is located according to the occurrence frequency of the floor corresponding to the reselected wireless signal source.

[0067] In this embodiment of the disclosure, the modulus acquisition module 402 can also be used to acquire the first physical address and the first signal strength of the currently selected wireless signal source, search for the wireless signal source with the first physical address and its corresponding second signal strength in the set of wireless signal sources, and acquire the modulus of the difference between the first signal strength and the second signal strength.

[0068] In this embodiment of the present disclosure, the robot floor localization device may further include a training module for training a KNN model. The training module may be used to: obtain the second physical address and corresponding signal strength of the wireless signal source obtained by the robot searching for wireless signal sources on each floor in a cross-floor task scenario; use the signal strength corresponding to the second physical address as a feature vector, and save the floor where the second physical address is found as a floor information label into the sample set of the KNN model; and train the KNN model according to the sample set to obtain the K value.

[0069] In this embodiment of the disclosure, the robot floor positioning device may further include an update module, which is used to update the wireless signal source, the corresponding signal strength and the target floor in the robot's current environment to the sample set in response to the robot successfully performing a cross-floor task and the target floor where the robot is located is the floor information reported by the robot.

[0070] In this embodiment of the disclosure, the robot floor positioning device may further include an alarm module, which is used to obtain the target floor again in response to the target floor where the robot is located not being the floor information reported by the robot, and to generate an alarm signal to issue an alarm when the target floor obtained a second time is still not the floor information reported by the robot.

[0071] In this embodiment of the disclosure, the signal source initial selection module 401 can also be used to obtain the robot's environmental deployment information; and determine that the robot is in a cross-floor task scenario based on the environmental deployment information.

[0072] Since the functional modules of the robot floor positioning device in the example embodiments of this disclosure correspond to the steps of the robot floor positioning method in the example embodiments described above, for details not disclosed in the device embodiments of this disclosure, please refer to the embodiments of the robot floor positioning method described above.

[0073] The robot floor positioning device according to the embodiments of this disclosure selects an initial wireless signal source, selects a second wireless signal source based on the sample set of the KNN model, and determines the target floor where the robot is located based on the second wireless signal source and the K nearest neighbor algorithm. This device can simply and accurately locate the robot floor without the need to deploy sensors.

[0074] It should be understood that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this disclosure.

[0075] Figure 5 This is a schematic diagram of the electronic device 500 provided in an embodiment of this disclosure. Figure 5 As shown, the electronic device 500 of this embodiment includes: a processor 501, a memory 502, and a computer program 503 stored in the memory 502 and executable on the processor 501. When the processor 501 executes the computer program 503, it implements the steps in the various method embodiments described above. Alternatively, when the processor 501 executes the computer program 503, it implements the functions of each module / unit in the various device embodiments described above.

[0076] For example, computer program 503 may be divided into one or more modules / units, which are stored in memory 502 and executed by processor 501 to perform the present disclosure. The one or more modules / units may be a series of computer program instruction segments capable of performing a specific function, which describe the execution process of computer program 503 in electronic device 500.

[0077] Electronic device 500 can be a desktop computer, laptop, handheld computer, cloud server, or other electronic device. Electronic device 500 may include, but is not limited to, processor 501 and memory 502. Those skilled in the art will understand that... Figure 5 This is merely an example of electronic device 500 and does not constitute a limitation on electronic device 500. It may include more or fewer components than shown, or combine certain components, or different components. For example, electronic device may also include input / output devices, network access devices, buses, etc.

[0078] Processor 501 can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor can be a microprocessor or any conventional processor.

[0079] The memory 502 can be an internal storage unit of the electronic device 500, such as a hard disk or RAM of the electronic device 500. The memory 502 can also be an external storage device of the electronic device 500, such as a plug-in hard disk, Smart Media Card (SMC), Secure Digital (SD) card, or Flash Card equipped on the electronic device 500. Furthermore, the memory 502 can include both internal and external storage units of the electronic device 500. The memory 502 is used to store computer programs and other programs and data required by the electronic device. The memory 502 can also be used to temporarily store data that has been output or will be output.

[0080] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional units and modules is merely an example. In practical applications, the above functions can be assigned to different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiments can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit. Furthermore, the specific names of the functional units and modules are only for easy differentiation and are not intended to limit the scope of protection of this application. The specific working process of the units and modules in the above system can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0081] In the above embodiments, the descriptions of each embodiment have different focuses. For parts that are not described in detail or recorded in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0082] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this disclosure.

[0083] In the embodiments provided in this disclosure, it should be understood that the disclosed devices / electronic devices and methods can be implemented in other ways. For example, the device / electronic device embodiments described above are merely illustrative. For instance, the division of modules or units is only a logical functional division, and in actual implementation, there may be other division methods. Multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces, and the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms.

[0084] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0085] Furthermore, the functional units in the various embodiments of this disclosure can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0086] If an integrated module / unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the methods of the above embodiments can also be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program may include computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. A computer-readable medium may include: any entity or device capable of carrying computer program code, recording media, USB flash drives, portable hard drives, magnetic disks, optical disks, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signals, telecommunication signals, and software distribution media, etc. It should be noted that the content included in a computer-readable medium may be appropriately added to or subtracted according to the requirements of legislation and patent practice in a jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media may not include electrical carrier signals and telecommunication signals.

[0087] The above embodiments are only used to illustrate the technical solutions of this disclosure, and are not intended to limit it. Although this disclosure has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this disclosure, and should all be included within the protection scope of this disclosure.

Claims

1. A robot floor positioning method, characterized in that, The method includes: After determining that the robot is in a cross-floor task scenario, the wireless signal sources and corresponding signal strengths in the robot's current environment are obtained, and a first number of initial wireless signal sources with the largest signal strength are selected from the wireless signal sources, where the first number is a constant. Obtain the modulus of the difference between the signal strength of the initially selected wireless signal source and the signal strength of the corresponding wireless signal source in the sample set of the preset K-nearest neighbor KNN model, wherein the sample set includes feature vectors of the signal strength of the wireless signal sources in the set arranged in order of their physical addresses and corresponding floor information tags. From the initially selected wireless signal sources, a second number of reselected wireless signal sources with the smallest modulus of the difference are selected, wherein the second number is the K value of the trained KNN model; The target floor where the robot is located is determined based on the floor information tag corresponding to the selected wireless signal source. The training method for the KNN model includes: The robot obtains the second physical address and corresponding signal strength of the wireless signal source obtained by searching for wireless signal sources on each floor in the cross-floor task scenario. The signal strength corresponding to the second physical address is used as a feature vector, and the floor where the second physical address is found is saved as a floor information label in the sample set of the KNN model. The KNN model is trained based on the sample set to obtain the K value; Determining the target floor where the robot is located based on the floor information tag corresponding to the selected wireless signal source includes: The floor corresponding to the selected wireless signal source is obtained based on the floor information tag corresponding to the selected wireless signal source. Based on the frequency of occurrence of the floors corresponding to the selected wireless signal sources, the floor with the highest frequency of occurrence is selected as the target floor where the robot is located.

2. The method according to claim 1, characterized in that, Obtaining the modulus of the difference between the signal strength of the initially selected wireless signal source and the signal strength of the corresponding wireless signal source in the sample set of the preset KNN model includes: Obtain the first physical address and first signal strength of the currently selected wireless signal source; The system searches for the wireless signal source in the collection whose physical address is the first physical address and its corresponding second signal strength. Obtain the modulus of the difference between the first signal strength and the second signal strength.

3. The method according to claim 1, characterized in that, After determining the target floor where the robot is located based on the floor information tag corresponding to the selected wireless signal source, the method further includes: In response to the robot successfully performing the cross-floor task, and the target floor where the robot is located is the floor information reported by the robot, the wireless signal source, the corresponding signal strength, and the target floor in the robot's current environment are updated in the sample set.

4. The method according to claim 1, characterized in that, After determining the target floor where the robot is located based on the floor information tag corresponding to the selected wireless signal source, the method further includes: In response to the fact that the target floor where the robot is located is not the floor information reported by the robot, the target floor is obtained again, and if the target floor obtained a second time is still not the floor information reported by the robot, an alarm signal is generated to issue an alarm.

5. The method according to any one of claims 1 to 4, characterized in that, Before obtaining the wireless signal source and corresponding signal strength in the robot's current environment, the method further includes: Obtain the robot's environmental deployment information; Based on the environmental deployment information, it is determined that the robot is in a cross-floor task scenario.

6. A robot floor positioning device, characterized in that, The apparatus for performing the robot floor positioning method according to any one of claims 1 to 5, the apparatus comprising: The signal source initial selection module is used to obtain the wireless signal sources and corresponding signal strengths in the current environment of the robot after determining that the robot is in a cross-floor task scenario, and select a first number of wireless signal sources with the largest signal strength from the wireless signal sources, wherein the first number is a constant. The modulus acquisition module is used to acquire the modulus of the difference between the signal strength of the initially selected wireless signal source and the signal strength of the corresponding wireless signal source in the sample set of the preset KNN model. The sample set includes feature vectors of the signal strength of the wireless signal sources in the set, arranged in order of their physical addresses, and corresponding floor information tags. The signal source reselection module is used to select a second number of reselected wireless signal sources from the initially selected wireless signal sources, where the second number is the K value of the trained KNN model. The floor determination module is used to determine the target floor where the robot is located based on the floor information tag corresponding to the selected wireless signal source.

7. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the method as described in any one of claims 1 to 5.

8. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method as described in any one of claims 1 to 5.

Images