Similar industrial equipment identification method based on robot autonomous position adjustment and equipment signal relation

Abstract

The invention relates to a similar industrial equipment identification method based on robot autonomous position adjustment and equipment signal relationship, and the method comprises the steps: enabling a robot to directly face an industrial equipment group, collecting and processing the RSSI signal of each equipment to construct an RSSI signal sample set, and generating an initial equipment candidate list through a proximity estimation algorithm; when the candidate equipment is not unique, the robot autonomously calculates the direction and distance of position adjustment and executes position adjustment according to the size relation of the RSSI mean values of the equipment in the list, and a candidate list after position adjustment is generated; and if the list is still not unique, further constructing a two-stage screening mechanism by using the RSSI variation before and after the position adjustment and the difference value of the RSSI variation, and iteratively carrying out screening and position adjustment until only unique equipment is left in the candidate list, thereby completing target equipment identification. The method can achieve the precise and efficient recognition of similar industrial equipment, overcomes the limitation of a conventional machine vision method, does not need extra identification, and is suitable for industrial inspection scenes with similar appearances and dense deployment.

Description

Technical Field

[0001] This invention relates to the field of industrial automation and equipment identification technology, specifically to a method for identifying similar industrial equipment based on the relationship between robot autonomous position adjustment and equipment signals. Background Technology

[0002] In autonomous industrial inspections, equipment in industrial settings often shares similarities in appearance and is densely deployed, making it difficult for inspection robots to accurately identify devices using traditional machine vision methods (such as YOLO and Mask R-CNN). These vision methods are highly dependent on differences in the appearance of the equipment and are easily affected by factors such as navigation errors, changes in lighting conditions, and fluctuations in observation distance, leading to unstable recognition accuracy. Furthermore, while technologies such as QR code recognition are also used, they have strict requirements on ambient brightness and scanning distance, making them unsuitable for large equipment or hazardous scenarios requiring safe distances.

[0003] With the development of the Industrial Internet of Things (IIoT), most industrial equipment now possesses wireless communication capabilities. Therefore, proximity estimation methods based on Received Signal Strength Indication (RSSI) have emerged as a potential solution to the aforementioned problems. However, wireless signals in industrial environments are unstable; path loss and multipath effects can cause significant fluctuations in RSSI values. When a robot is far from a densely deployed group of devices, the wireless signal strength received from multiple devices is very similar, leading existing proximity estimation methods to generate multiple candidate devices and failing to arrive at a unique identification result. Furthermore, the number of RSSI samples that inspection robots can collect is limited and susceptible to outlier interference, further reducing the accuracy and efficiency of identification.

[0004] In existing technologies, such as Chinese patent application CN202111544623.1, an attention mechanism is introduced to enhance the network's feature extraction capabilities and solve the problem of recognizing similarly shaped devices. However, for industrial equipment with almost identical image features, its recognition accuracy is still insufficient. Another Chinese patent application, CN202211213736.8, uses QR code scanning to lock onto targets, but this method is limited by environmental brightness and safe distance constraints, limiting its application scenarios. Furthermore, Chinese patent application CN202110818272.2, while considering neighbor device relationships and RSSI frequency distribution to shorten sampling time, still cannot guarantee the uniqueness of the estimation results when faced with densely deployed similar devices.

[0005] Therefore, there is an urgent need in the field for a method for identifying similar industrial equipment that can overcome the above-mentioned defects, is not dependent on appearance features, is environmentally robust, and can guarantee the uniqueness of the identification results. Summary of the Invention

[0006] The purpose of this invention is to overcome the shortcomings of the prior art and provide a method for identifying similar industrial equipment based on the relationship between robot autonomous position adjustment and equipment signals. This method utilizes the relationship between changes in wireless signals of equipment caused by the robot's active position adjustment, combined with spatial constraints between equipment, to achieve accurate and efficient identification of similar industrial equipment.

[0007] To achieve the above-mentioned objectives, the present invention adopts the following technical solution: a method for identifying similar industrial equipment based on the relationship between robot autonomous position adjustment and equipment signals, comprising the following steps:

[0008] Step S1: The robot adjusts its angle through target detection to face the industrial equipment group;

[0009] Step S2: The robot collects RSSI signals from each scanned device N times, removes abnormal RSSI values, calculates the mean RSSI value of each device, and constructs an RSSI signal sample set;

[0010] Step S3: Based on the RSSI signal sample set, perform a preliminary estimation of the target device using the nearest neighbor estimation algorithm to generate an initial candidate device list;

[0011] Step S4: If the number of devices in the current candidate device list is greater than 1, the robot will autonomously calculate the direction and distance for position adjustment based on the ranking of the average RSSI values ​​of the devices in the candidate device list, and then adjust its position accordingly.

[0012] Step S5: After the robot position is adjusted, the nearest neighbor estimation algorithm is executed again to generate a new list of candidate devices. Based on the spatial relationship between the devices, the intersection of the new list of candidate devices and the list of candidate devices before the position adjustment is taken to obtain the list of candidate devices after the position adjustment.

[0013] Step S6: If the number of devices in the device candidate list after the location adjustment is still greater than 1, construct a sample set of device RSSI signal changes, and filter the devices in the device candidate list after the location adjustment based on the relationship between the RSSI signal changes of each device before and after the location adjustment.

[0014] Step S7: If the number of devices in the candidate device list after step S6 is still greater than 1, calculate the difference in RSSI change between each device and its adjacent devices, and perform a second screening based on the relative size of the difference.

[0015] Step S8: Repeat steps S4-S7 until only one device remains in the device candidate list. This device is the target device, thus completing the identification of the target device.

[0016] Furthermore, in step S2, the robot collects the corresponding RSSI signal for each scanned device N times, and records all RSSI values ​​of device i. Calculate the expected value μ and standard deviation σ of all RSSI values ​​for each device, and retain those that meet the conditions. RSSI value , where j represents the j-th retained RSSI value. Abnormal RSSI values ​​that do not meet the criteria are removed, and the average of all retained RSSI values ​​is calculated, denoted as . ;

[0017] An RSSI signal sample set was constructed based on the mean RSSI of all devices. , where p represents the number of devices scanned.

[0018] Furthermore, in step S3, the robot performs a preliminary estimation of the target device based on the RSSI signal sample set using a proximity estimation algorithm, generating an initial candidate device list. ;

[0019] If the device candidate list The result is unique, that is, the number of devices. If the target device is determined, then the corresponding device is the nearest industrial device that the robot faces.

[0020] Furthermore, in step S4, if the robot cannot directly determine the target device from multiple candidate devices, i.e., the current candidate device list... Number of equipment Then, it automatically calculates the direction and distance of the position adjustment, specifically as follows:

[0021] Device candidate list The mean RSSI values ​​of all devices in the dataset are sorted from largest to smallest, i.e.:

[0022]

[0023] in, Represents the device candidate list The RSSI signal sample set obtained by sorting the mean RSSI of all devices in the sample from largest to smallest; These represent the candidate device lists. The first in , , One device;

[0024] make , Calculate the direction D of the position adjustment:

[0025]

[0026] when When, the robot adjusts to the right; when At that moment, the robot adjusted to the left;

[0027] Calculate the distance of position adjustment :

[0028]

[0029] Where m is an intermediate variable. ; Indicates the spacing between industrial equipment;

[0030] Then, the robot calculates the direction. and distance It can autonomously complete the corresponding position adjustment.

[0031] Furthermore, in step S5, after the robot's position is adjusted, the nearest neighbor estimation algorithm is executed again to generate a new list of candidate devices. :

[0032]

[0033] Where n represents the nth position adjustment performed by the robot. This represents the list of candidate devices before the nth position adjustment. Represents the device candidate list The first in One device;

[0034] Based on the spatial relationships of the devices, obtain the candidate list of devices after position adjustment:

[0035]

[0036] in, This represents the list of candidate devices after the nth position adjustment.

[0037] For the device candidate list after location adjustment If the number of devices If the signal is correct, then the corresponding device is the one the robot is facing, and the identification task is complete; otherwise, the robot continues to analyze the signal relationships between the devices.

[0038] Furthermore, in step S6, after the robot position is adjusted, the RSSI value of the device changes. Following the method in step S2, a new RSSI signal sample set is constructed, which is then subtracted from the original RSSI signal sample set to construct a sample set of the RSSI signal change. ;

[0039] if And it satisfies:

[0040]

[0041] If the device is selected, it is retained; if only one device meets the conditions, it is numbered. The corresponding device is the one the robot is facing, and the recognition task is completed; otherwise, the robot... For the device candidate list Update.

[0042] Furthermore, in step S7, after the screening in step S6, the robot utilizes the difference in RSSI changes of the devices. A second screening was conducted, in which... If the following conditions are met:

[0043]

[0044] If the device is selected, it is retained; if only one device meets the conditions, it is numbered. The corresponding device is the one the robot is facing, and the recognition task is completed; otherwise, according to... For the device candidate list Update.

[0045] The present invention also 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 program to implement the above-described method.

[0046] The present invention also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the above-described method.

[0047] Compared with the prior art, the present invention has the following beneficial effects:

[0048] 1) Compared with traditional machine vision methods, this invention utilizes the wireless signal characteristics in the Industrial Internet of Things as distinguishing features of similar industrial equipment. By controlling the position adjustment of the robot to generate changes in equipment signals, a screening mechanism for nearby equipment is constructed. At the same time, the spatial relationship of the equipment is also considered, so that the robot can accurately identify the target industrial equipment to facilitate subsequent inspection work.

[0049] 2) This invention takes into account the signal relationship between candidate devices and designs an optimization strategy for robot autonomous position adjustment, which further improves the efficiency of similar industrial equipment identification while ensuring the uniqueness of the estimation results.

[0050] 3) This invention does not rely on the appearance features of the equipment, does not require the installation of additional identification modules, and has no special requirements for ambient brightness. It can achieve identification by simply utilizing the wireless communication function of industrial IoT devices, resulting in low deployment costs and wide applicability in industrial inspection scenarios. Attached Figure Description

[0051] Figure 1 This is a flowchart illustrating the implementation of a method for identifying similar industrial equipment based on the relationship between robot autonomous position adjustment and equipment signals, provided in an embodiment of the present invention.

[0052] Figure 2 This is a schematic diagram of an application scenario in an embodiment of the present invention. Detailed Implementation

[0053] The present invention will be further described below with reference to the accompanying drawings and embodiments.

[0054] It should be noted that the following detailed descriptions are exemplary and intended to provide further explanation of this application. Unless otherwise specified, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application pertains.

[0055] It should be noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the exemplary embodiments according to this application. As used herein, the singular form is intended to include the plural form as well, unless the context clearly indicates otherwise. Furthermore, it should be understood that when the terms "comprising" and / or "including" are used in this specification, they indicate the presence of features, steps, operations, devices, components, and / or combinations thereof.

[0056] like Figure 1 As shown, this embodiment provides a method for identifying similar industrial equipment based on the relationship between robot autonomous position adjustment and equipment signals, including the following steps:

[0057] Step S1: The robot adjusts its angle through target detection to face the industrial equipment group.

[0058] Step S2: The robot collects RSSI signals from each scanned device N times, removes abnormal RSSI values, calculates the mean RSSI value of each device, and constructs an RSSI signal sample set.

[0059] Specifically, the robot collects the corresponding RSSI signal for each scanned device N times, and records the RSSI values ​​of all devices i. Calculate the expected value μ and standard deviation σ of all RSSI values ​​for each device, and retain those that meet the conditions. RSSI value , where j represents the j-th retained RSSI value. Abnormal RSSI values ​​that do not meet the criteria are removed, and the average of all retained RSSI values ​​is calculated, denoted as . .

[0060] An RSSI signal sample set was constructed based on the mean RSSI of all devices. , where p represents the number of devices scanned.

[0061] Step S3: Based on the RSSI signal sample set, perform a preliminary estimation of the target device using a proximity estimation algorithm to generate an initial candidate device list. .

[0062] If the device candidate list The result is unique, that is, the number of devices. If the corresponding device is the nearest industrial device that the robot is facing, then the target device can be determined.

[0063] In this embodiment, the nearest neighbor estimation algorithm is the FaceME algorithm.

[0064] Step S4: If the number of devices in the current candidate device list is greater than 1, the robot will autonomously calculate the direction and distance for position adjustment based on the ranking of the average RSSI values ​​of the devices in the candidate device list, and then adjust its position accordingly.

[0065] Specifically, if the robot cannot directly determine the target device from multiple candidate devices, i.e., the current candidate device list... Number of equipment The autonomous calculation of the direction and distance for position adjustment is achieved as follows:

[0066] Device candidate list The mean RSSI values ​​of all devices in the dataset are sorted from largest to smallest, i.e.:

[0067]

[0068] in, Represents the device candidate list The RSSI signal sample set obtained by sorting the mean RSSI of all devices in the sample from largest to smallest; These represent the candidate device lists. The first in , , One device.

[0069] make , Calculate the direction D of the position adjustment:

[0070]

[0071] when When, the robot adjusts to the right; when At that moment, the robot adjusted to the left.

[0072] Calculate the distance of position adjustment :

[0073]

[0074] Where m is an intermediate variable. ; Indicates the spacing between industrial equipment.

[0075] Then, the robot calculates the direction. and distance It can autonomously complete the corresponding position adjustment.

[0076] Step S5: After the robot position is adjusted, the nearest neighbor estimation algorithm is executed again to generate a new list of candidate devices. Based on the spatial relationship between the devices, the intersection of the new list of candidate devices and the list of candidate devices before the position adjustment is taken to obtain the list of candidate devices after the position adjustment.

[0077] Specifically, after the robot's position is adjusted, the proximity estimation algorithm is executed again to generate a new list of candidate devices. :

[0078]

[0079] Where n represents the nth position adjustment performed by the robot (for example, n=1 represents the first position adjustment). This represents the list of candidate devices before the nth position adjustment. Represents the device candidate list The first in One device.

[0080] Based on the spatial relationships of the devices, obtain the candidate list of devices after position adjustment:

[0081]

[0082] in, This represents the list of candidate devices after the nth position adjustment.

[0083] For the device candidate list after location adjustment If the number of devices If the signal is correct, then the corresponding device is the one the robot is facing, and the identification task is complete; otherwise, the robot continues to analyze the signal relationships between the devices.

[0084] Step S6: If the number of devices in the device candidate list after the location adjustment is still greater than 1, construct a sample set of device RSSI signal changes, and filter the devices in the device candidate list after the location adjustment based on the relationship between the RSSI signal changes of each device before and after the location adjustment.

[0085] After the robot's position is adjusted, the RSSI value of the device changes. Following the method in step S2, a new RSSI signal sample set is constructed, which is then subtracted from the original RSSI signal sample set to construct a sample set of the RSSI signal change. .

[0086] if And it satisfies:

[0087]

[0088] If the device is selected, it is retained; if only one device meets the conditions, it is numbered. The corresponding device is the one the robot is facing, and the recognition task is completed; otherwise, the robot... For the device candidate list Update.

[0089] Step S7: If the number of devices in the candidate device list after step S6 is still greater than 1, calculate the difference in RSSI change between each device and its neighboring devices, and perform a second screening based on the relative size of the difference.

[0090] After screening in step S6, the robot utilizes the difference in RSSI changes of the equipment. A second screening was conducted, in which... If the following conditions are met:

[0091]

[0092] If the device is selected, it is retained; if only one device meets the conditions, it is numbered. The corresponding device is the one the robot is facing, and the recognition task is completed; otherwise, according to... For the device candidate list Update.

[0093] Step S8: Repeat steps S4-S7 until only one device remains in the device candidate list. This device is the target device, thus completing the identification of the target device.

[0094] The technical solution of the present invention will be further explained below with specific examples from industrial field scenarios.

[0095] In this embodiment, to simulate the deployment of equipment in an industrial field, the experimental platform uses eight industrial IoT modules arranged in... The industrial IoT modules and inspection robots are arranged at equal intervals of 0.6m, forming a wireless communication system. Each network physical address is paired with an industrial equipment number. The inspection robot sets a navigation point before industrial equipment number 4, and the vertical distance between the robot and the equipment is... Set to 1.5m, such as Figure 2 As shown.

[0096] (1) This experiment uses the FaceME algorithm. The robot needs to complete the data collection of the Industrial Internet of Things in offline measurement in advance. The information to be collected in this embodiment includes: the minimum value of the original RSSI of the nearest device in the offline measurement stage is -46dBm; the maximum value of the original RSSI in the set of non-nearest devices is -34dBm; the minimum value of the RSSI of the nearest device after filtering is -40.4dBm; and the maximum value of the RSSI of non-nearest devices after filtering is -39.3dBm.

[0097] (2) After the inspection robot navigates to the front of the industrial equipment, it adjusts the robot angle through the target detection algorithm so that the robot is facing the industrial equipment.

[0098] (3) The robot collects the corresponding RSSI signal of the scanned device 20 times and records the RSSI value of device i. Calculate the expected value μ and standard deviation σ of the RSSI values ​​for all devices, remove outlier RSSIs, and retain the RSSIs that meet the criteria, denoted as σ. ,in The mean RSSI of device i is calculated and denoted as . For example, in this embodiment, the expected RSSI of device 5 is -41.15 dBm, with a standard deviation of 6.26 dBm. The mean value of device 5 was -40.58dBm.

[0099] (4) Construct RSSI signal samples for all devices The robot uses the FaceME algorithm to perform a preliminary estimation and obtain a candidate list of devices. .

[0100] If the result in the device list is unique at this time, that is This means that the result in the list is the nearest industrial equipment facing the robot, thus confirming that the equipment facing the robot is the nearest industrial equipment. (Note: If the robot has not yet adjusted its position, in this embodiment the robot directly identifies the target device as device 4.)

[0101] (5) If the robot cannot directly determine the target device among multiple candidate devices, then the robot will perform autonomous position adjustment. For example If so, autonomous position adjustment is required. The robot will sort the candidate devices in the device candidate list from largest to smallest:

[0102]

[0103] Select and Calculate the adjustment direction Adjust the distance m. Robot based on and It can autonomously adjust its position, specifically by 0.6m to the left.

[0104] (6) After the robot position is adjusted, the FaceME algorithm is executed to generate a new candidate list. Where n represents the sequence number of the robot's position adjustment (e.g., n=1 indicates the 1st adjustment). This is obtained based on the spatial relationships of the equipment.

[0105]

[0106] For the device candidate list If the number of devices A is equal to 1, that is... Then the device number That is, the device that the robot faces, and the corresponding neighboring device number at the initial position is... If the identification task is completed, the robot will be able to identify the signal relationships between the devices; otherwise, the robot will still need to analyze the signal relationships between the devices.

[0107] (7) After the robot adjusts its position, the RSSI of the device changes. Therefore, a sample containing the changes in the device's RSSI is constructed. The sample is still constructed by first removing outliers and then calculating the average. If And it satisfies:

[0108]

[0109] If only one device meets the conditions, that is Then the device number That is, the robot completes the recognition task when it encounters the device; otherwise, it needs to... Candidate list The update is performed. In this embodiment, the changes in device signals after a specific robot position adjustment are recorded as follows:

[0110] Table 1

[0111] 7.1dBm -10.2dBm 1.1dBm -5.3dBm

[0112] have and Requirements are met, therefore updates are being made. .

[0113] (8) The robot will utilize the difference in RSSI changes of the equipment. Further judgment, among which Criteria for judgment:

[0114]

[0115] If only one device meets the conditions, then the device number is... This refers to the equipment the robot interacts with. For example, Table 1... It is 17.3dBm. It is 6.4dBm. Therefore, the robot faces the adjacent device, which is device 3.

[0116] Otherwise, it is necessary to follow the rules. Candidate list The update is performed, and the robot begins the next position adjustment; until the device candidate list contains only one device, the corresponding original neighboring device number is used. For example, in this embodiment, after the robot adjusts once, it identifies the surface as device 3. Then, the neighboring device of the original robot is device 4, thereby completing the task of identifying similar industrial equipment.

[0117] The present invention also 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 program to implement the above-described method.

[0118] The present invention also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the above-described method.

[0119] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0120] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0121] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0122] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0123] The above description is merely a preferred embodiment of the present invention and is not intended to limit the invention in any other way. Any person skilled in the art may make changes or modifications to the above-disclosed technical content to create equivalent embodiments. However, any simple modifications, equivalent changes, and modifications made to the above embodiments based on the technical essence of the present invention without departing from the scope of the present invention shall still fall within the protection scope of the present invention.

Claims

1. A method for identifying similar industrial equipment based on the relationship between the autonomous position adjustment of a robot and the signals of the equipment, characterized by, The method comprises the following steps: Step S1: The robot adjusts its angle by target detection, so that it faces the industrial equipment group; Step S2: The robot collects RSSI signals of each equipment scanned for N times, calculates the RSSI average value of each equipment after eliminating abnormal RSSI values, and constructs an RSSI signal sample set; Step S3: Based on the RSSI signal sample set, the target equipment is preliminarily estimated by a proximity estimation algorithm, and an initial equipment candidate list is generated; Step S4: If the number of equipment in the current equipment candidate list is greater than 1, the robot sorts the equipment in the equipment candidate list according to the size of the RSSI average value, autonomously calculates the direction and distance of position adjustment, and performs position adjustment; Step S5: After the position adjustment of the robot, the proximity estimation algorithm is executed again to generate a new equipment candidate list, and based on the spatial relationship of the equipment, the new equipment candidate list and the equipment candidate list before the position adjustment are intersected to obtain the equipment candidate list after the position adjustment; Step S6: If the number of equipment in the equipment candidate list after the position adjustment is still greater than 1, a device RSSI signal change sample set is constructed, and based on the RSSI signal change relationship of each equipment before and after the position adjustment, the equipment in the equipment candidate list after the position adjustment is screened; Step S7: If the number of equipment in the equipment candidate list screened in step S6 is still greater than 1, the RSSI change difference between each equipment and its adjacent equipment is calculated, and secondary screening is performed based on the relative size relationship of the difference; Step S8: Steps S4-S7 are repeated until only one equipment is left in the equipment candidate list, and the equipment is the target equipment, thereby completing the identification of the target equipment. 2.The method of claim 1, wherein, In step S2, the robot collects the corresponding RSSI signal for each device scanned N times, and records all RSSI values of device i as ; calculates the expectation μ and the standard deviation σ of all RSSI values of each device, retains the RSSI values satisfying the condition , where j represents the jth retained RSSI value, eliminates abnormal RSSI values not satisfying the condition, and calculates the average of all retained RSSI values, denoted as ;​ constructing a set of RSSI signal samples based on the mean of RSSI of all devices where p represents the number of scanned devices. 3.The method of claim 1, wherein, In step S3, the robot performs a preliminary estimation on the target device based on the RSSI signal sample set through a proximity estimation algorithm, and generates an initial device candidate list ; If the device candidate list The result is unique, i.e. the number of devices The corresponding device is the closest industrial device in front of the robot, i.e. the target device is determined. 4.The method of claim 1, wherein, In step S4, if the robot cannot directly determine the target device from the multiple candidate devices, i.e., the current device candidate list the number of devices in the middle the robot autonomously calculates the direction and distance of the position adjustment, specifically: Ranking the list of device candidates The mean RSSI of all devices is sorted in descending order, i.e.: wherein, representing a device candidate list RSSI signal sample set obtained by sorting the RSSI mean values of all devices in the device candidate list in descending order; respectively represent the first devices in the device candidate list , , ; Let , , the direction D of the position adjustment is calculated: When the robot adjusts to the right; when the robot adjusts to the left; calculating the distance of the position adjustment : where m is an intermediate variable, ; denotes the industrial plant spacing; Then, the robot autonomously completes the corresponding position adjustment based on the calculated direction and distance . 5.The method of claim 1, wherein, In step S5, after the robot position adjustment is completed, the proximity estimation algorithm is executed again to generate a new device candidate list : wherein n represents the nth position adjustment by the robot, represents a device candidate list before the nth position adjustment, represents a device candidate list in the nth position adjustment device; Based on the spatial relationship of the equipment, the equipment candidate list after the position adjustment is obtained: wherein, represents the device candidate list after the n-th position adjustment; For the position-adjusted device candidate list , if the number of devices , the corresponding device is the device faced by the robot, and the identification task is completed; otherwise, the robot continues to analyze the device signal relationship. 6.The method of claim 1, wherein, In step S6, after the robot position is adjusted, the RSSI value of the device changes, and the changed RSSI signal sample set is constructed according to the method in step S2, and the RSSI signal sample set before the change is subtracted to construct the RSSI signal change sample set ; If and the following is satisfied: If there is more than one device satisfying the condition, then the device with the lowest number is selected The corresponding device is the one that the robot is facing, and the recognition task is completed. Otherwise, the robot updates the list of device candidates according to the list of device candidates.​ 7.The method of claim 6, wherein, In step S7, the robot uses the RSSI change amount difference of the device after the screening in step S6 A secondary screening is performed, in which if the following is satisfied: If there is more than one device satisfying the condition, then the device with the lowest number is selected The corresponding device is the one that the robot is facing, and the task of recognition is completed. Otherwise, according to The list of device candidates is updated.

8. An electronic device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, The processor implements the method of any one of claims 1-7 when executing the program.

9. A computer-readable storage medium having stored thereon a computer program, characterized in that, The program is executed by the processor to implement the method of any one of claims 1-7.

Images