Control method and device of inspection robot and inspection robot

Abstract

The invention relates to the technical field of robots, and discloses a control method and device of an inspection robot and the inspection robot. The control method comprises the steps that the inspection robot is controlled to detect obstacles in the moving direction; acquiring feature information of an obstacle under the condition that the obstacle exists in the moving direction; determining a target obstacle coping strategy according to the feature information of the obstacle; and according to the target obstacle coping strategy, controlling the inspection robot to perform obstacle handling. According to the method, the consumption of computing resources is reduced, the obstacle coping strategy can be flexibly selected, and the energy consumption is lower.

Description

Technical Field

[0001] The present application relates to the field of robotics technology, and for example, to a control method and device for an inspection robot and an inspection robot. Background Art

[0002] Inspection robots are a type of robotic system that integrates multiple advanced technologies and is used to automatically inspect specific areas or equipment. During the inspection process, inspection robots will inevitably encounter obstacles, so it is crucial to effectively avoid obstacles and ensure that the inspection robots can successfully complete the inspection task.

[0003] The related technology discloses an intelligent obstacle avoidance method for an inspection robot, comprising: collecting the inspection environment of the inspection robot to obtain a first scan data point and a second scan data point; acquiring scan data records and scan data volume according to the first scan data point and the second scan data point; respectively calculating the scan data volume and the scan data record to obtain a scan data standard deviation and a scan data observation difference; calculating the scan data observation difference and the scan data standard deviation to obtain a scan data standard score; screening the scan data standard score to obtain point cloud data; performing point cloud registration and 3D reconstruction on the point cloud data to obtain a 3D model. model; read the three-dimensional model to obtain the Euclidean distance and total potential energy from the current position of the inspection robot to the target node; obtain and calculate the path coordinate set to obtain the total path cost; calculate the total path cost, total potential energy and the Euclidean distance from the current position of the inspection robot to the target node to obtain the cost value; process the cost value, total potential energy and the three-dimensional model to obtain the obstacle avoidance path; collect the three-dimensional data of the inspection robot in real time during operation to obtain the second point cloud data; compare the point cloud data with the second point cloud data to obtain the data change range; correct the obstacle avoidance path according to the data change range to obtain a safe obstacle avoidance route.

[0004] In the process of implementing the above embodiments, it is found that although the related technology can effectively avoid obstacles, the energy consumption is relatively large. Summary of the invention

[0005] In order to provide a basic understanding of some aspects of the disclosed embodiments, a brief summary is given below. The summary is not an extensive review, nor is it intended to identify key / critical components or delineate the scope of protection of these embodiments, but rather serves as a prelude to the detailed description that follows.

[0006] The embodiments of the present disclosure provide a control method and device for an inspection robot, and an inspection robot, which reduce the consumption of computing resources, can flexibly select obstacle response strategies, and have lower energy consumption.

[0007] In some embodiments, a control method for a patrol robot is provided, including: controlling the patrol robot to detect obstacles in the moving direction; if there are obstacles in the moving direction, obtaining characteristic information of the obstacles; determining a target obstacle response strategy based on the characteristic information of the obstacles; and controlling the patrol robot to handle the obstacles based on the target obstacle response strategy.

[0008] Optionally, the inspection robot includes a radar component; the step of obtaining characteristic information of the obstacle includes: controlling the radar component to emit a radar signal; receiving a reflected signal after the radar signal encounters an obstacle and obtaining a round-trip time; determining the position and volume of the obstacle based on the round-trip time; and using the position and volume of the obstacle as the characteristic information of the obstacle.

[0009] Optionally, the characteristic information of the obstacle includes position and volume. The step of determining the target obstacle response strategy based on the characteristic information of the obstacle includes: evaluating the volume of the obstacle to determine the obstruction index of the obstacle to the inspection robot; determining the target obstacle response strategy based on the position and obstruction index of the obstacle.

[0010] Optionally, the step of evaluating the volume of the obstacle and determining the hindrance index of the obstacle to the inspection robot includes: obtaining the type of the obstacle; determining an evaluation coefficient of the obstacle volume according to the type of the obstacle; and determining the hindrance index of the obstacle to the inspection robot according to the evaluation coefficient and the volume of the obstacle.

[0011] Optionally, the obstacle type is obtained in the following manner: obtaining image data of the obstacle; and inputting the image data into a pre-trained target recognition model to obtain the obstacle type.

[0012] Optionally, the obstacle type is obtained in the following manner: image data of the obstacle and environmental parameters of the target inspection area are obtained; the image data and environmental parameters are input into a pre-trained target recognition model to obtain the obstacle type.

[0013] Optionally, the obstacle type is obtained in the following manner: obtaining image data of the obstacle and environmental parameters of the target inspection area; preprocessing the image data of the obstacle according to the environmental parameters; inputting the preprocessed image data into a pre-trained target recognition model to obtain the obstacle type.

[0014] Optionally, the step of determining the obstruction index of the obstacle to the inspection robot based on the evaluation coefficient and the volume of the obstacle includes: obtaining the obstacle avoidance space volume of the inspection robot; and determining the obstruction index of the obstacle to the inspection robot based on the obstacle avoidance space volume, the evaluation coefficient and the volume of the obstacle.

[0015] Optionally, the inspection robot includes walking wheels, and the obstacle response strategy includes an obstacle crossing strategy, an obstacle avoidance strategy and an obstacle clearing strategy. The steps of determining the target obstacle response strategy according to the position of the obstacle and the obstruction index include: when the obstacle is located on the walking route of the walking wheels and the obstruction index is less than an index threshold, the obstacle clearing strategy is used as the target obstacle response strategy; when the obstacle is located between the walking routes of two walking wheels and the obstruction index is less than an index threshold, the obstacle crossing strategy is used as the target obstacle response strategy; when the obstacle is located on the target inspection route of the inspection robot and the obstruction index is greater than or equal to the index threshold, the obstacle avoidance strategy is used as the target obstacle response strategy.

[0016] Optionally, the inspection robot includes a cleaning mechanism and walking wheels; when the target obstacle response strategy is an obstacle clearing strategy, the steps of controlling the inspection robot to handle obstacles according to the target obstacle response strategy include: controlling the cleaning mechanism to clear obstacles on the walking route; after cleaning, controlling the inspection robot to move according to the target inspection route.

[0017] Optionally, when the target obstacle response strategy is an obstacle crossing strategy, the steps of controlling the inspection robot to handle obstacles according to the target obstacle response strategy include: obtaining the height and width of the obstacle; and obtaining the obstacle avoidance height and obstacle avoidance width of the obstacle avoidance space of the inspection robot; when the height of the obstacle is less than the obstacle avoidance height and the width of the obstacle is less than the obstacle avoidance width, controlling the inspection robot to move according to the target inspection route.

[0018] Optionally, the inspection robot includes a knocking component; when the target obstacle response strategy is an obstacle crossing strategy, the step of controlling the inspection robot to perform obstacle handling according to the target obstacle response strategy also includes: when the height of the obstacle is greater than or equal to the obstacle avoidance height, controlling the knocking component to knock on the obstacle so that the height of the obstacle is less than the obstacle avoidance height; after the knocking is completed, controlling the inspection robot to move according to the target inspection route; and / or, when the width of the obstacle is greater than or equal to the obstacle avoidance width, controlling the knocking component to knock on the obstacle so that the width of the obstacle is less than the obstacle avoidance width; after the knocking is completed, controlling the inspection robot to move according to the target inspection route.

[0019] Optionally, when the target obstacle response strategy is an obstacle avoidance strategy, the steps of controlling the inspection robot to handle obstacles according to the target obstacle response strategy include: correcting the target inspection route according to the position and volume of the obstacle; and controlling the inspection robot to move along the corrected target inspection route.

[0020] In some embodiments, a control device for a patrol robot is provided, comprising: a detection module, configured to control the patrol robot to detect obstacles in the moving direction; an acquisition module, configured to acquire characteristic information of the obstacle when there is an obstacle in the moving direction; a determination module, configured to determine a target obstacle coping strategy based on the characteristic information of the obstacle; and a control module, configured to control the patrol robot to handle the obstacle based on the target obstacle coping strategy.

[0021] In some embodiments, a control device for an inspection robot is provided, comprising a processor and a memory storing program instructions, wherein the processor is configured to execute the control method for the inspection robot as described in the above embodiments when running the program instructions.

[0022] In some embodiments, a patrol robot is provided, comprising: a robot body; and a control device of the patrol robot as described in the above embodiments, installed on the robot body.

[0023] The control method, device and inspection robot provided by the embodiments of the present disclosure can achieve the following technical effects:

[0024] The disclosed embodiment can first obtain the obstacle volume when there is an obstacle in the moving direction of the inspection robot. Different obstacle volumes correspond to different obstacle response strategies. The optimal obstacle response strategy, that is, the target obstacle response strategy, is determined based on the obstacle volume, and the inspection robot is controlled to operate according to the target obstacle response strategy to ensure that the inspection robot safely and effectively crosses or avoids obstacles. Compared with the related art that executes a safe obstacle avoidance route after a large amount of calculation, the disclosed embodiment reduces the complexity of the calculation, reduces the consumption of computing resources, and flexibly selects obstacle response strategies to avoid unnecessary energy consumption caused by the single execution of an obstacle avoidance route, thereby lowering energy consumption.

[0025] The above general description and the following description are exemplary and explanatory only and are not intended to limit the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] One or more embodiments are exemplarily described by corresponding drawings, which do not limit the embodiments. Elements with the same reference numerals in the drawings are shown as similar elements, and the drawings do not constitute a scale limitation, and wherein:

[0027] Figure 1 is a schematic diagram of the structure of an inspection robot provided by an embodiment of the present disclosure;

[0028] Figure 2 yes Figure 1A schematic diagram of a portion of the structure of the inspection robot in the illustrated embodiment;

[0029] Figure 3 is a schematic diagram of an inspection robot provided by an embodiment of the present disclosure deployed on a tubular belt transport system and a track;

[0030] Figure 4 This is a front view of an inspection robot provided by an embodiment of the present disclosure deployed on the ground;

[0031] Figure 5 This is a front view of an inspection robot provided by an embodiment of the present disclosure deployed on a track;

[0032] Figure 6 is a schematic diagram of a control method of an inspection robot provided by an embodiment of the present disclosure;

[0033] Figure 7 is a schematic diagram of a control method of an inspection robot provided by another embodiment of the present disclosure;

[0034] Figure 8 is a schematic diagram of a control method of an inspection robot provided by another embodiment of the present disclosure;

[0035] Fig. 9 is a schematic diagram of a control device of an inspection robot provided by an embodiment of the present disclosure;

[0036] Fig.10 It is a schematic diagram of a control device of an inspection robot provided in another embodiment of the present disclosure.

[0037] Reference numerals:

[0038] 10 inspection robot; 100 robot body; 101 box; 410 walking wheel; 513 image acquisition device; 514 positioning antenna; 510 proximity switch; 511 electromagnetic switch; 512 photoelectric switch; 517 radar component; 518 single-point laser radar; 520 ultrasonic radar; 601 chassis bracket; 610 cleaning mechanism; 612 telescopic component; 613 installation pipe; 615 connecting pipe; 617 cleaning parts;

[0039] 70 control device of the inspection robot; 71 detection module; 72 acquisition module; 73 determination module; 74 control module;

[0040] 90 control device of the inspection robot; 900 processor; 901 memory; 902 communication interface; 903 bus;

[0041] 50 tubular belt conveyor; 424 track; 503 positioning piece. DETAILED DESCRIPTION

[0042] In order to be able to understand the features and technical contents of the embodiments of the present disclosure in more detail, the implementation of the embodiments of the present disclosure is described in detail below in conjunction with the accompanying drawings. The attached drawings are for reference only and are not used to limit the embodiments of the present disclosure. In the following technical description, for the convenience of explanation, a full understanding of the disclosed embodiments is provided through multiple details. However, one or more embodiments can still be implemented without these details. In other cases, to simplify the drawings, well-known structures and devices can be simplified for display.

[0043] The terms "first", "second", etc. in the specification and claims of the embodiments of the present disclosure and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the terms used in this way can be interchanged where appropriate, so that the embodiments of the embodiments of the present disclosure described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions.

[0044] Unless otherwise stated, the term "plurality" means two or more.

[0045] In the embodiment of the present disclosure, the character " / " indicates that the preceding and following objects are in an "or" relationship. For example, A / B indicates: A or B.

[0046] The term "and / or" is a description of the association relationship between objects, indicating that three relationships can exist. For example, A and / or B means: A, B, A and B.

[0047] The term "correspondence" may refer to an association relationship or a binding relationship. The correspondence between A and B means that there is an association relationship or a binding relationship between A and B.

[0048] It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present disclosure may be combined with each other.

[0049] Combination Figure 1 As shown, the embodiment of the present disclosure provides an inspection robot 10, including a robot body 100 and a control device 70 (90) of the inspection robot. The control device 70 (90) of the inspection robot is installed on the robot body 100.

[0050] In the disclosed embodiment, the control device 70 (90) of the inspection robot is installed on the robot body 100. The installation relationship described here is not limited to being placed inside the robot body 100, but also includes the installation connection with other components of the inspection robot 10, including but not limited to physical connection, electrical connection or signal transmission connection, etc. It can be understood by those skilled in the art that the control device 70 (90) of the inspection robot can be adapted to a feasible inspection robot 10, thereby realizing other feasible embodiments.

[0051] Optionally, combined Figure 1 , Figure 4 and Figure 5 As shown, the robot body 100 includes a box 101, a walking wheel 410, an image acquisition device 513, a positioning antenna 514, a proximity switch 510 and a radar assembly 517. The walking wheel 410 and the proximity switch 510 are arranged at intervals at the bottom of the box 101 along the height direction of the inspection robot 10. The image acquisition device 513 and the positioning antenna 514 are arranged at intervals at the top of the box 101 along the height direction of the inspection robot 10. The radar assembly 517 is arranged at intervals on the side of the box 101 along the moving direction of the inspection robot 10.

[0052] Optionally, combined Figure 1 , Figure 4 and Figure 5 As shown, the radar assembly 517 includes a single-point laser radar 518 and an ultrasonic radar 520. The single-point laser radar 518 and the ultrasonic radar 520 are arranged at intervals on the side of the box 101.

[0053] Optionally, combined Figure 2 As shown, the proximity switch 510 includes an electromagnetic switch 511 and a photoelectric switch 512. The electromagnetic switch 511 and the photoelectric switch 512 are arranged at a distance from each other at the bottom of the box 101.

[0054] Optionally, combined Figure 1 , Figure 2 , Figure 4 and Figure 5 As shown, the inspection robot 10 further includes a chassis bracket 601. The chassis bracket 601 is arranged at the bottom of the box body 101 along the height direction of the box body 101. The walking wheel 410 and the proximity switch 510 are arranged at intervals on a side of the chassis bracket 601 away from the box body 101.

[0055] Optionally, combined Figure 1 , Figure 2 , Figure 4 and Figure 5 As shown, the inspection robot 10 further includes a cleaning mechanism 610 . The cleaning mechanism 610 is disposed on the chassis bracket 601 and is located in front of the walking wheel 410 along the moving direction of the inspection robot 10 .

[0056] Optionally, combined Figure 1 , Figure 2 , Figure 4 and Figure 5 As shown, the cleaning mechanism 610 includes a first motor (not shown in the figure), a telescopic assembly 612 and a cleaning member 617. The first motor is arranged on the chassis bracket 601. One end of the telescopic assembly 612 is connected to the output end of the first motor, and the first motor can drive the telescopic assembly 612 to move along the cleaning direction. The cleaning member 617 is connected to one end of the telescopic assembly 612 away from the first motor, and the telescopic assembly 612 can drive the cleaning member 617 to move along the height direction of the inspection robot 10. Among them, the cleaning direction is perpendicular to the extension direction of the walking route and perpendicular to the height direction of the inspection robot 10.

[0057] Optionally, combined Figure 1 , Figure 2 , Figure 4 and Figure 5 As shown, the telescopic assembly 612 includes a mounting tube 613, a connecting tube 615, and a second motor (not shown in the figure). One end of the mounting tube 613 is connected to the output end of the first motor. The second motor is arranged at the other end of the mounting tube 613, and the output end of the second motor is connected to one end of the connecting tube 615, and the other end of the connecting tube 615 is connected to the cleaning member 617. The second motor can drive the connecting tube 615 to move along the height direction of the inspection robot 10.

[0058] Optionally, the inspection robot 10 includes a knocking component (not shown in the figure), which is located at the end of the chassis bracket 601 along the moving direction of the inspection robot 10.

[0059] Optionally, the knocking assembly includes a third motor (not shown in the figure), a connecting rod (not shown in the figure) and a knocking piece (not shown in the figure). The third motor is located at the end of the chassis bracket 601 along the moving direction of the inspection robot 10. The connecting rod is connected to the output end of the third motor. The knocking piece is connected to the connecting rod. The third motor can drive the connecting rod to move in the direction where the obstacle is located, thereby driving the knocking piece to move in the direction where the obstacle is located.

[0060] Optionally, the control device 90 of the inspection robot includes a processor 900. The processor 900 can control the inspection robot to detect obstacles in the moving direction; can obtain characteristic information of obstacles when there are obstacles in the moving direction; can determine a target obstacle response strategy based on the characteristic information of the obstacles; can control the inspection robot to handle obstacles based on the target obstacle response strategy.

[0061] Combination Figure 6 As shown, the embodiment of the present disclosure provides a control method of an inspection robot, comprising:

[0062] S601, the processor controls the inspection robot to detect obstacles in the moving direction.

[0063] S602: When there is an obstacle in the moving direction, the processor obtains feature information of the obstacle.

[0064] S603: The processor determines a target obstacle coping strategy based on the characteristic information of the obstacle.

[0065] S604: The processor controls the inspection robot to handle obstacles according to the target obstacle response strategy.

[0066] The control method of the inspection robot provided by the embodiment of the present disclosure can first obtain the obstacle volume when there is an obstacle in the moving direction of the inspection robot. Different obstacle volumes correspond to different obstacle response strategies. The optimal obstacle response strategy, that is, the target obstacle response strategy, is determined according to the obstacle volume, and the inspection robot is controlled to operate according to the target obstacle response strategy to ensure that the inspection robot safely and effectively crosses or avoids obstacles. Compared with the related art that executes a safe obstacle avoidance route after a large amount of calculation, the embodiment of the present disclosure reduces the complexity of the calculation, reduces the consumption of computing resources, and flexibly selects the obstacle response strategy to avoid unnecessary energy consumption caused by the single execution of the obstacle avoidance route. Therefore, energy consumption is lower, and the efficiency and safety of the inspection task are improved, and the probability of task interruption or failure due to obstacles is reduced.

[0067] In some embodiments, in combination Figure 1 , Figure 4 and Figure 5 As shown, the inspection robot 10 includes a radar component 517. The step of controlling the inspection robot to detect obstacles in the moving direction includes: controlling the radar component to transmit a radar signal in the moving direction of the inspection robot; when receiving an effective reflection signal reflected from the radar signal, determining that there is an obstacle in the moving direction of the inspection robot; when not receiving an effective reflection signal reflected from the radar signal, determining that there is no obstacle in the moving direction of the inspection robot.

[0068] In this embodiment, the effective reflected signal reflected by the radar signal refers to a reflected signal that can be successfully received by the radar component and identified as a reflected signal from an obstacle, and the reflected signal has the following characteristics: the intensity of the reflected signal is greater than or equal to the intensity threshold, the direction of the reflected signal matches the receiving direction of the radar component, the frequency of the reflected signal is within the frequency threshold range, and the time delay of the reflected signal is within the duration threshold range. The intensity of the reflected signal is limited to be greater than or equal to the intensity threshold so that the reflected signal can be successfully detected by the radar component. Since the radar signal has a certain directionality, it can only be successfully received by the radar component when the reflected signal returns in the opposite direction of the incident signal. Therefore, the direction of the reflected signal needs to match the receiving direction of the radar component. The frequency of the reflected signal should be within the frequency threshold range so that it can be successfully identified by the radar component. The time delay of the reflected signal should be within the duration threshold range so that the radar component can identify the reflected signal. When an effective reflected signal is received, it can be determined that there is an obstacle in the moving direction of the inspection robot; when no effective reflected signal is received, it means that the obstacle is very small, the distance is very far or there is no obstacle. At this time, it can be considered that there is no obstacle in the moving direction of the inspection robot.

[0069] In this embodiment, radar components are deployed to detect obstacles in the moving direction of the inspection robot, determine whether there are obstacles in the moving direction of the inspection robot, realize obstacle recognition, avoid collision between the inspection robot and obstacles, and improve the safety of the inspection process.

[0070] In some embodiments, in combination Figure 1 , Figure 4 and Figure 5 As shown, the radar component 517 includes a single-point laser radar 518 and an ultrasonic radar 520. The step of controlling the inspection robot to detect obstacles in the moving direction includes: controlling the single-point laser radar and the ultrasonic radar to respectively emit laser signals and ultrasonic signals in the moving direction of the inspection robot; when receiving an effective reflection signal reflected from any one of the laser signal and the ultrasonic signal, determining that there is an obstacle in the moving direction of the inspection robot; when no effective reflection signal reflected from the laser signal and the ultrasonic signal is received, determining that there is no obstacle in the moving direction of the inspection robot.

[0071] In this embodiment, single-point laser radar and ultrasonic radar are deployed simultaneously to identify whether there are obstacles in the moving direction of the inspection robot, thereby improving the accuracy and reliability of obstacle detection and further improving the safety of the inspection process.

[0072] In some embodiments, the characteristic information of the obstacle includes position and volume. Figure 7As shown, the embodiment of the present disclosure provides another control method of the inspection robot, comprising:

[0073] S701, the processor controls the inspection robot to detect obstacles in the moving direction.

[0074] S702: When there is an obstacle in the moving direction, the processor controls the radar component to transmit a radar signal.

[0075] S703: The processor receives a reflected signal of the radar signal after encountering an obstacle, and obtains a round-trip time.

[0076] S704: The processor determines the location and volume of the obstacle based on the round-trip time.

[0077] Optionally, the step of determining the position of the obstacle includes: obtaining the current position of the inspection robot; and obtaining the propagation speed and propagation direction of the radar signal; determining the relative distance between the obstacle and the inspection robot based on the round-trip time and the propagation speed; determining the relative position of the obstacle relative to the inspection robot based on the propagation direction and the relative distance; and determining the position of the obstacle based on the relative position and the current position.

[0078] In this embodiment, the relative distance between the obstacle and the inspection robot can be determined based on the round-trip time and propagation speed of the radar signal, and then the relative position of the obstacle relative to the inspection robot can be determined based on the propagation direction and relative distance of the radar signal. When the current position of the inspection robot and the relative position of the obstacle relative to the inspection robot are known, the position of the obstacle in the target inspection area can be determined through coordinate transformation or geometric calculation, thereby achieving accurate acquisition of the obstacle position.

[0079] Optionally, the step of obtaining the current position of the inspection robot includes: obtaining positioning information of the inspection robot in the target inspection area; and obtaining the moving distance of the inspection robot; and determining the current position of the inspection robot in the target inspection area based on the positioning information and the moving distance.

[0080] In this embodiment, the positioning information of the inspection robot in the target inspection area and the movement distance of the inspection robot can be obtained in real time, and then the current position of the inspection robot in the target inspection area can be determined by combining the positioning information and the movement distance, so as to achieve accurate acquisition of the current position of the inspection robot and improve the positioning accuracy of the inspection robot. By improving the positioning accuracy of the inspection robot, it is possible to determine whether the inspection robot deviates from the target inspection route, and correct it in time when it deviates from the route, so as to ensure that the inspection robot can accurately move along the target inspection route, thereby improving the inspection efficiency and effectiveness.

[0081] In some embodiments, in combination Figure 1, Figure 4 and Figure 5 As shown, a plurality of wireless base stations (not shown in the figure) are arranged in the target inspection area, and the inspection robot 10 includes a positioning antenna 514 which is communicatively connected to the wireless base station. The step of obtaining the positioning information of the inspection robot in the target inspection area includes: controlling the positioning antenna to send a positioning request to the wireless base station; and receiving the positioning information fed back by the wireless base station based on the positioning request.

[0082] In this embodiment, when the inspection robot needs to obtain its own positioning information, the positioning antenna is controlled to send a positioning request to a nearby wireless base station. The positioning request contains the unique identifier of the inspection robot, timestamp and other necessary information so that the wireless base station can correctly identify and respond to the request. After receiving the positioning request, the wireless base station will calculate the location information of the inspection robot based on the location information of the wireless base station, the communication delay with the inspection robot, the signal strength and other parameters, and send the location information as positioning information feedback to the inspection robot, so that the inspection robot can obtain its own position in the target inspection area. In this embodiment, the inspection robot can send a positioning request to the wireless base station in real time and quickly receive the positioning information fed back by the base station. This real-time performance improves the response speed and inspection efficiency of the inspection robot.

[0083] In some embodiments, Figure 1 and Figure 2 As shown, a plurality of positioning members 503 are provided in the target inspection area, and the inspection robot 10 includes a proximity switch 510. The step of obtaining the positioning information of the inspection robot in the target inspection area includes: obtaining feedback information of successful docking with the positioning member fed back by the proximity switch; and generating the positioning information of the inspection robot according to the feedback information.

[0084] In this embodiment, a plurality of positioning members are provided in the target inspection area. When the inspection robot moves to a certain positioning member and the proximity switch docks with the positioning member, the proximity switch detects the presence of the positioning member and triggers the switch, and then outputs feedback information indicating successful docking. The feedback information may be an electrical signal, a digital signal, or a signal in other forms to indicate that the inspection robot has successfully docked with the positioning member. After receiving the feedback information output by the proximity switch, the inspection robot converts the feedback information into specific positioning information to characterize the position information of the inspection robot in the target inspection area. This embodiment, based on the physical docking of the proximity switch and the positioning member, does not require complex communication protocols or algorithm support, is simple and reliable, is not easily affected by environmental interference, and can ensure the accuracy and stability of the positioning information.

[0085] In a specific application, a marker, such as a QR code, an RFID (Radio Frequency Identification) tag, etc., is attached to the positioning member 503, and the QR code or RFID tag records the position information of the positioning member 503 in the target inspection area. The proximity switch 510 includes an encoder, which is used to identify the marker attached to the positioning member 503 when the proximity switch 510 is docked with the positioning member 503, so as to obtain the position information recorded in the marker as the positioning information of the inspection robot 10.

[0086] In a specific application, a plurality of positioning members 503 are arranged at a preset spacing. When the proximity switch 510 is docked with the positioning member 503, a feedback message indicating successful docking is output. The moving distance of the inspection robot 10 is obtained by recording the number of times the feedback message is received and calculating the product of the number of feedback messages and the preset spacing. After obtaining the moving distance of the inspection robot 10, the position coordinates of the inspection robot 10 in the target inspection area can be calculated as the positioning information of the inspection robot 10 according to the moving distance and the target inspection route. The specific steps of calculating the position coordinates of the inspection robot in the target inspection area according to the moving distance and the target inspection route refer to the steps of calculating the second position coordinates of the inspection robot in the target inspection area according to the moving distance and the target inspection route in the following embodiment, which will not be repeated here.

[0087] Alternatively, if Figure 2 As shown, the proximity switch 510 includes an electromagnetic switch 511 and a photoelectric switch 512. The step of determining whether the proximity switch and the positioning member are successfully docked includes: obtaining the current value and current direction fed back by the electromagnetic switch; and obtaining the distance value fed back by the photoelectric switch; when the distance value is less than the distance threshold and the current value is greater than the current threshold, or when the distance value is less than the distance threshold and the current direction changes, determining that the proximity switch and the positioning member are successfully docked.

[0088] In this embodiment, the proximity switch includes an electromagnetic switch and a photoelectric switch. The electromagnetic switch works on the principle of electromagnetic induction. When approaching a metal object (positioning piece), an eddy current effect is generated, thereby triggering the switch action. The photoelectric switch detects the presence and distance of the positioning piece by emitting and receiving light beams.

[0089] When the electromagnetic switch approaches the positioning part and docks with the positioning part, the electromagnetic switch triggers electromagnetic induction and generates current. As the docking area gradually increases, the current value gradually increases. When the docking area is the largest, the current value also reaches the maximum value. Then the electromagnetic switch begins to move away from the positioning part, the docking area begins to decrease, and the direction of the current changes. Therefore, it is possible to determine whether it is close to the positioning part and the degree of docking by obtaining the current value and current direction fed back by the electromagnetic switch. The photoelectric switch emits a light beam and receives the reflected light beam, and calculates the distance value to the positioning part by measuring the round-trip time of the light beam. When the photoelectric switch begins to dock with the positioning part, the distance value fed back by the photoelectric switch becomes smaller.

[0090] In this embodiment, a distance threshold and a current threshold are pre-set as conditions for judging whether the docking is successful. When the distance value is less than the distance threshold and the current value is greater than the current threshold, or the distance value is less than the distance threshold and the current direction changes, it is considered that the proximity switch and the positioning member are successfully docked. In this embodiment, two types of proximity switches, electromagnetic switches and photoelectric switches, are combined to ensure the accuracy of successful docking through double detection. In addition, the embodiment of the present disclosure adopts two independent detection conditions to judge whether the docking is successful, namely, the distance value is less than the distance threshold and the current value is greater than the current threshold, or the distance value is less than the distance threshold and the current direction changes. Such multiple judgment conditions improve the reliability of the judgment and reduce the possibility of misjudgment and missed judgment.

[0091] In some embodiments, the positioning information fed back by the wireless base station based on the positioning request is defined as the first position information, and the positioning information of the inspection robot generated according to the feedback information of successful docking with the positioning member fed back by the proximity switch is defined as the second position information. Then the step of obtaining the positioning information of the inspection robot in the target inspection area includes: determining the positioning information of the inspection robot in the target inspection area according to the first position information and the second position information.

[0092] In this embodiment, the wireless base station and the proximity switch are used simultaneously to obtain the position information of the inspection robot. By combining the positioning information of the wireless base station and the proximity switch to integrate the advantages of both, the positioning accuracy of the inspection robot is improved.

[0093] Optionally, the step of determining the positioning information of the inspection robot in the target inspection area based on the first position information and the second position information includes: converting the first position information into the fourth position coordinates of the inspection robot in the target inspection area; converting the second position information into the fifth position coordinates of the inspection robot in the target inspection area; calculating the average value or weighted average value of the first position coordinates and the second position coordinates to obtain the first position coordinates; and using the first position coordinates as the current position of the inspection robot in the target inspection area.

[0094] In this embodiment, the first position coordinate is obtained by converting the first position information and the second position information into the fourth position coordinate and the fifth position coordinate of the inspection robot in the target inspection area, respectively, and then performing an average value or a weighted average value calculation. The average value calculation is to add the corresponding components of the fourth position coordinate and the fifth position coordinate and divide by 2, and the weighted average value calculation is to assign different weights according to the reliability or importance of the two coordinates, and then perform a weighted average. The first position coordinate obtained after performing the average value or the weighted average value calculation is used as the current position of the inspection robot, which realizes the fusion of the first position information and the second position information and improves the positioning accuracy of the inspection robot.

[0095] In some embodiments, in combination Figure 1 , Figure 4 and Figure 5 As shown, the inspection robot 10 includes a running wheel 410. The step of obtaining the moving distance of the inspection robot includes: obtaining the wheel diameter and the number of rotations of the running wheel; and determining the moving distance of the inspection robot according to the wheel diameter and the number of rotations.

[0096] In this embodiment, the number of rotations can be monitored and recorded by an encoder or sensor that is communicatively connected to the running wheel. After obtaining the wheel diameter and the number of rotations, the moving distance of the inspection robot can be calculated based on the wheel diameter and the number of rotations. Specifically, the moving distance = wheel diameter × π × number of rotations to accurately reflect the actual distance of the inspection robot during movement. The wheel diameter and the number of rotations are stable physical quantities. The method of calculating the moving distance based on the wheel diameter and the number of rotations has high stability, reliability and accuracy. In addition, since the wheel diameter and the number of rotations of the running wheel can be monitored in real time, the real-time performance is better.

[0097] In some embodiments, in combination Figure 1 , Figure 4 and Figure 5 As shown, when there are multiple running wheels 410 and the multiple running wheels 410 are the same, it is sufficient to obtain the wheel diameter and the number of rotations of one of the running wheels 410 .

[0098] Optionally, the step of determining the current position of the inspection robot in the target inspection area based on the positioning information and the moving distance includes: converting the positioning information into the first position coordinates of the inspection robot in the target inspection area; calculating the second position coordinates of the inspection robot in the target inspection area based on the moving distance and the target inspection route; calculating the average or weighted average of the first position coordinates and the second position coordinates to obtain the third position coordinates; and using the third position coordinates as the current position of the inspection robot in the target inspection area.

[0099] In this embodiment, the first position coordinate and the second position coordinate are averaged or weighted averaged to fuse the obtained positioning information and the moving distance, and the third position coordinate is accurately obtained, that is, the current position of the inspection robot in the target inspection area is accurately obtained. By combining the positioning information and the moving distance to calculate the current position of the inspection robot, the accuracy of the positioning of the inspection robot is improved, so as to determine whether the inspection robot deviates from the target inspection route, and correct it in time when it deviates from the route, so as to ensure that the inspection robot can accurately move according to the target inspection route, and improve the inspection efficiency and effectiveness.

[0100] Optionally, the step of calculating the second position coordinates of the inspection robot in the target inspection area based on the moving distance and the target inspection route includes: obtaining the starting position coordinates of the inspection robot; calculating the second position coordinates of the inspection robot in the target inspection area based on the starting position coordinates, the moving distance and the target inspection route.

[0101] In this embodiment, when the starting position coordinates, moving distance and target inspection route of the inspection robot are known, the second position coordinates of the inspection robot in the target inspection area can be calculated through path planning and navigation algorithms (such as Dijkstra algorithm, fast random exploration tree algorithm, dynamic window method, etc.), so as to achieve accurate acquisition of the second position coordinates.

[0102] Optionally, the target inspection route is determined in the following manner: the target inspection route is determined according to the target inspection area. The target inspection route refers to a pre-planned or dynamically generated inspection path in the target inspection area according to inspection requirements (such as inspection point distribution, obstacle location, equipment distribution, etc.). The target inspection route is intended to ensure that the inspection robot can fully and completely cover all inspection points and complete the inspection task.

[0103] In some embodiments, a target inspection route is pre-planned in the target inspection area. In an actual application, different inspection routes are pre-planned in different inspection areas. Then, the step of determining the target inspection route according to the target inspection area includes: using the inspection route corresponding to the target inspection area as the target inspection route. Figure 3 As shown, when the inspection robot 10 is deployed on the track 242, the target inspection route is the distribution route of the track 424 in the target inspection area. Then, according to the target inspection area, the steps of determining the target inspection route include: obtaining the distribution route of the track in the target inspection area, and using the distribution route of the track as the target inspection route.

[0104] In this embodiment, by pre-planning the inspection route corresponding to the inspection area, or taking the distribution route of the track in the target inspection area as the target inspection route, the target inspection route can be quickly acquired, the response speed of the inspection robot is improved, and thus the inspection efficiency of the inspection robot is improved.

[0105] In some embodiments, the step of determining a target inspection route according to a target inspection area includes: obtaining an equipment layout diagram of the target inspection area; and generating a target inspection route of the inspection robot according to the equipment layout diagram.

[0106] In this embodiment, the equipment layout diagram refers to a drawing that details all the equipment, facilities and their relative positions in the target inspection area. The equipment layout diagram can be obtained by the technician through input from an electronic device that is connected to the inspection robot for communication, or by using modern technology (such as drone aerial photography, laser scanning, etc.) to generate a three-dimensional model, and extract the equipment layout information from it to obtain the equipment layout diagram. By obtaining the equipment layout diagram of the target inspection area, this embodiment can accurately understand the distribution and relative position of the equipment in the area, thereby generating a more accurate inspection route, so that the inspection robot can follow each checkpoint of the target inspection route to avoid omissions or misjudgments. In addition, this embodiment can dynamically and autonomously generate the target inspection route of the inspection robot based on the equipment layout diagram, thereby improving the autonomy and intelligence of the inspection robot.

[0107] Optionally, the step of generating a target inspection route for the inspection robot based on the equipment layout diagram includes: obtaining operating parameters of the equipment and environmental parameters of the target inspection area; determining the target detection device based on the environmental parameters and operating parameters; and generating the target inspection route for the inspection robot based on the position coordinates of the target detection device in the equipment layout diagram.

[0108] In this embodiment, the target detection equipment refers to the equipment distributed in the target inspection area that the inspection robot needs to detect. The equipment operation parameters refer to the parameters that reflect the operation status, performance and health of the equipment, including but not limited to the current, voltage, temperature, vibration, working time, number of historical failures, etc. of the equipment. The environmental parameters of the target inspection area refer to the parameters that have an important impact on the working effect, stable operation and performance of the electrical components of the equipment, including but not limited to temperature, humidity, light intensity, vibration, electromagnetic interference, etc.

[0109] Different environmental parameters and operating parameters will have an impact on the failure probability of the equipment. For example, too high or too low temperature will cause equipment performance degradation or failure. For example, equipment that continues to work at high temperatures is prone to damage due to overheating, while low temperatures will cause certain parts of the equipment to become fragile; excessive humidity can cause internal corrosion or short circuits in the equipment; continuous vibration can cause loose connections or wear of parts inside the equipment, increasing the risk of failure; strong electromagnetic fields can interfere with the normal operation of the equipment, causing communication failures or data errors; equipment with long working hours is prone to failure due to wear or aging; equipment with a high number of historical failures and frequent failures has design defects or improper maintenance problems, and has a higher probability of failure.

[0110] In this embodiment, a relationship mapping table between environmental parameters and operating parameters and equipment failure probability is pre-saved, and the relationship mapping table is used to reflect the impact of environmental parameters and operating parameters on equipment failure probability. By comparing different equipment operating parameters and environmental parameters, equipment that is in a high-risk state and more prone to failure (such as equipment whose failure probability exceeds a preset failure probability threshold) is identified, so that the equipment that is in a high-risk state and more prone to failure is determined as a target detection device. After determining the target detection device, refer to the equipment layout diagram, obtain the position coordinates of the target detection device in the target inspection area as the detection point, and use a path planning algorithm (such as a breadth-first search algorithm, a Dijkstra algorithm, an ant colony algorithm, etc.) to generate a target inspection route to ensure that the inspection robot can efficiently cover all target detection devices, i.e., detection points, while avoiding unnecessary duplication and omissions.

[0111] Optionally, the step of determining the volume of the obstacle includes: obtaining the propagation speed and propagation direction of the radar signal; determining the relative distance between each point on the obstacle surface and the inspection robot based on the round-trip time and the propagation speed; determining the relative position coordinates of each point on the obstacle surface relative to the inspection robot based on the propagation direction and the relative distance; constructing a point cloud model of the obstacle based on the relative position coordinates; and determining the volume of the obstacle based on the point cloud model.

[0112] In this embodiment, after obtaining the relative position coordinates of each point on the obstacle surface relative to the inspection robot, the point cloud generation technology can be used to construct a point cloud model of the obstacle. The point cloud model intuitively displays the shape and outline of the obstacle, providing a visual basis for subsequent volume calculation. After obtaining the point cloud model of the obstacle, the volume of the obstacle can be calculated by performing geometric analysis or numerical integration on the point cloud model, or by using the point cloud processing software installed on the inspection robot, so as to achieve accurate acquisition of the volume of the obstacle.

[0113] S705: The processor uses the position and volume of the obstacle as feature information of the obstacle.

[0114] S706: The processor evaluates the volume of the obstacle and determines the hindrance index of the obstacle to the inspection robot.

[0115] S707, the processor determines a target obstacle coping strategy according to the location and the obstruction index of the obstacle;

[0116] S708: The processor controls the inspection robot to handle obstacles according to the target obstacle response strategy.

[0117] The control method of the inspection robot provided in the embodiment of the present disclosure can control the built-in radar component of the inspection robot to transmit radar signals in the moving direction of the inspection robot. When the radar signal encounters an obstacle, it will be reflected, and part of the reflected signal will return to the radar component. The inspection robot will receive these reflected signals and record the time from emission to return, that is, the round-trip time. The round-trip time is then used to determine the position and volume of the obstacle, and to obtain the characteristic information of the obstacle, so as to subsequently determine the target obstacle response strategy. The embodiment of the present disclosure analyzes the radar signal to achieve accurate measurement of the position and volume of the obstacle, so that the inspection robot can more accurately identify different types of obstacles and determine the corresponding response strategies.

[0118] The control method of the inspection robot provided by the embodiment of the present disclosure can evaluate the degree of obstruction of the obstacle to the movement of the robot, that is, the obstruction index, after obtaining the characteristic information of the obstacle, that is, the position and volume of the obstacle, based on the volume of the obstacle, combined with the size and mobility of the inspection robot. The obstruction index refers to the degree of obstruction of the obstacle to the movement of the inspection robot. Then, based on the position of the obstacle and the obstruction index, the degree of threat posed by the obstacle to the inspection robot is comprehensively judged so that the inspection robot can select an appropriate response strategy, that is, the target obstacle response strategy. By comprehensively considering the volume and position of the obstacle, the embodiment of the present disclosure enables the inspection robot to formulate a response strategy more intelligently, avoid blind actions or ineffective attempts, and improve its adaptability and safety in complex environments.

[0119] Combination Figure 8 As shown, the embodiment of the present disclosure provides another control method of the inspection robot, comprising:

[0120] S801, the processor controls the inspection robot to detect obstacles in the moving direction.

[0121] S802: When there is an obstacle in the moving direction, the processor obtains feature information of the obstacle.

[0122] In this step, the characteristic information of the obstacle includes position and volume.

[0123] S803: The processor obtains the type of obstacle.

[0124] In some embodiments, the types of obstacles include static obstacles and dynamic obstacles. Static obstacles refer to immovable obstacles, such as walls, trees, fixed equipment, etc.; dynamic obstacles refer to moving obstacles, such as pedestrians, animals, other inspection mobile equipment, etc.

[0125] Optionally, the obstacle type is obtained in the following manner: control the radar component to transmit a radar signal toward the location of the obstacle; receive a reflected signal after the radar signal encounters the obstacle, and obtain a round-trip time; determine the moving speed of the obstacle based on the round-trip time; when the moving speed of the obstacle is 0, determine that the type of the obstacle is a static obstacle; when the moving speed of the obstacle is greater than 0, determine that the type of the obstacle is a dynamic obstacle.

[0126] In this embodiment, the round-trip time of the radar signal can be introduced to calculate the obstacle movement speed, so that the inspection robot can more accurately identify the type of obstacle, distinguish between static obstacles and dynamic obstacles, and improve the recognition accuracy of obstacle properties.

[0127] Optionally, the step of determining the moving speed of the obstacle based on the round-trip time includes: obtaining the current speed of the inspection robot; and obtaining the propagation speed of the radar signal; determining the relative distance between the radar component and the obstacle based on the propagation speed of the radar signal and the round-trip time; obtaining the change in the relative distance; determining the relative speed between the radar component and the obstacle based on the change in the relative distance; when the relative speed is equal to the current speed, determining that the moving speed of the obstacle is 0; when the relative speed is not equal to the current speed, determining that the moving speed of the obstacle is greater than 0.

[0128] In this embodiment, after the radar component transmits the radar signal, the time difference (i.e., the round-trip time) between the received reflected signal and the transmitted signal (radar signal) can be obtained to calculate the relative distance between the radar component and the obstacle. The specific calculation method is: divide the round-trip time by 2, and then multiply it by the propagation speed of the radar signal. By measuring the relative distance between the radar component and the obstacle for multiple times in a row and observing the trend of the relative distance change, the change in the relative distance can be obtained. The change reflects the change in the distance between the radar component and the obstacle, and provides a basis for the subsequent calculation of the relative speed. The relative speed between the radar component and the obstacle can be calculated using the change in the relative distance and the time interval (i.e., the time difference between two radar component measurements). The specific calculation method is: divide the change in the relative distance by the time interval. When the relative speed is equal to the current speed, it can be considered that the change in the relative distance between the obstacle and the radar component is caused by the movement of the inspection robot, and the moving speed of the obstacle is 0. When the relative speed is not equal to the current speed, it can be considered that the change in the relative distance between the obstacle and the radar component is caused by the movement of the inspection robot and the obstacle, and the moving speed of the obstacle is not 0. At this time, the moving speed of the obstacle can be calculated by the difference between the relative speed and the current speed of the inspection robot.

[0129] In this embodiment, by combining the current speed of the inspection robot, the propagation speed of the radar signal, and the change in relative distance, the moving speed of the obstacle can be more accurately determined. In this embodiment, not only the relative motion between the radar signal and the obstacle is considered, but also the motion state of the inspection robot itself is considered, thereby improving the accuracy of the obstacle moving speed judgment.

[0130] In some embodiments, the types of obstacles include hard obstacles and soft obstacles. Hard obstacles refer to obstacles that will not deform under the action of external forces, or the deformation that occurs is negligible relative to their own size, such as walls, buildings or equipment made of hard materials such as metal or concrete; soft obstacles refer to obstacles that will deform under the action of external forces and the deformation amount is large, such as vegetation, cloth, paper balls, etc.

[0131] In some embodiments, in combination Figure 1 , Figure 4 and Figure 5 As shown, the inspection robot 10 includes an image acquisition device 513. The image acquisition device 513 is used to acquire image data of obstacles. Obtain the obstacle type in the following manner: acquire the image data of the obstacle; input the image data into a pre-trained target recognition model to obtain the obstacle type.

[0132] In this embodiment, a target recognition model is pre-trained to accurately identify different objects in the image data, including hard obstacles and soft obstacles. In this embodiment, by introducing image recognition technology, the inspection robot can more accurately identify the type of obstacles. Compared with traditional recognition methods based on sensor data, image recognition technology can capture more detailed information, thereby improving the accuracy of recognition.

[0133] Optionally, before inputting the image data into the pre-trained target recognition model, the method further includes: pre-processing the image data; the pre-processing includes one or more of image enhancement, denoising, graying, and binarization. In this embodiment, the image data is pre-processed before being input into the pre-trained target recognition model to optimize the image data, enhance the robustness of the image data, reduce noise and interference, and thus improve the recognition accuracy of the target recognition model.

[0134] Optionally, the target recognition model includes a YOLO model. The YOLO model is an algorithm that converts the target detection problem into a regression problem, which can simultaneously predict multiple bounding boxes (Bounding Box) and their categories in a single network. The YOLO series of algorithms include multiple versions such as YOLOv1, YOLOv2 (YOLO9000), YOLOv3, YOLOv4 to YOLOv10, each version is improved and optimized on the basis of the previous version, thereby improving the detection speed and accuracy.

[0135] Optionally, the target recognition model is trained in the following manner: obtaining training samples; the training samples are image data of various obstacles with annotations; generating more training samples through data enhancement to obtain a training data set; data enhancement includes rotation, scaling, translation, brightness adjustment, contrast adjustment, noise addition, etc.; inputting the training samples in the training data set into the image detection model for training to obtain a trained image detection model.

[0136] Optionally, the obstacle type is obtained in the following manner: image data of the obstacle and environmental parameters of the target inspection area are obtained; the image data and environmental parameters are input into a pre-trained target recognition model to obtain the obstacle type.

[0137] In this embodiment, environmental parameters refer to parameters that have an important impact on the interpretation of image data and the identification of obstacle types, such as lighting conditions, weather, temperature, etc. For example, when the temperature is less than -5°C on a snowy day and there are snow blocks in the moving direction of the inspection robot, the combination of weather and temperature information helps the target recognition model to identify snow blocks as white block obstacles and then classify them. In this embodiment, environmental parameters are used to provide additional contextual information for image data so that the target recognition model can make more accurate judgments in complex environments and improve recognition accuracy.

[0138] In this embodiment, the acquired environmental parameters and their corresponding image data can be input into the target recognition model, and the environmental parameters are fused as feature data with the features extracted from the image data to obtain fused features, and the fusion method includes feature splicing or weighted summation. The target recognition model then classifies the objects in the image data into predefined categories based on the extracted fused features to achieve obstacle recognition and classification. Exemplarily, taking YOLOv4 as the target recognition model as an example, the process of target recognition and output is as follows: the input image data is first subjected to feature extraction through the CSPDarknet53 backbone network; the extracted features are further fused and processed with the environmental parameters as feature data through the SPP layer and the PANet layer; finally, the Yolov3Head structure will output the initial prediction box position information and the score information of the detected target based on the extracted and fused features; after post-processing steps such as non-maximum suppression, the target recognition model will obtain the final recognition result.

[0139] Optionally, the obstacle type is obtained in the following manner: obtaining image data of the obstacle and environmental parameters of the target inspection area; preprocessing the image data of the obstacle according to the environmental parameters; inputting the preprocessed image data into a pre-trained target recognition model to obtain the obstacle type.

[0140] In this embodiment, environmental parameters refer to parameters that have an important impact on image data, such as light intensity, weather (such as rain, snow, fog, etc.). In this embodiment, the image data of obstacles can be preprocessed according to the environmental parameters to optimize the quality and recognizability of the image data. For example, when the light intensity is insufficient, the brightness or contrast of the image data is increased; in rainy and snowy weather, denoising is performed to reduce the impact of raindrops or snowflakes on the image data. The preprocessed image data is then input into a pre-trained target recognition model for recognition to obtain the obstacle type. In this embodiment, by preprocessing the image data according to the environmental parameters, the image data quality is optimized and the recognition accuracy of the target recognition model is improved.

[0141] In some embodiments, the types of obstacles include static obstacles, dynamic obstacles, hard obstacles and soft obstacles. The method of obtaining the obstacle type is referred to the above embodiment and will not be repeated here.

[0142] S804: The processor determines an evaluation coefficient of the obstacle volume according to the type of the obstacle.

[0143] In this embodiment, an evaluation coefficient table is stored in advance, and different evaluation coefficients are assigned to different types of obstacles to reflect the corresponding relationship between the type of obstacle and the evaluation coefficient of the obstacle volume. For example, for static and hard obstacles, the impact on the movement of the inspection robot is high, and its evaluation coefficient is high, and the inspection robot needs to completely bypass or adjust the route; for dynamic and soft obstacles, the impact on the movement of the inspection robot is low, and its evaluation coefficient is low, and the inspection robot can cross the obstacle without adjusting the route.

[0144] In a practical application, the evaluation coefficient of a static and hard obstacle>the evaluation coefficient of a static and soft obstacle>the evaluation coefficient of a dynamic and hard obstacle>the evaluation coefficient of a dynamic and soft obstacle.

[0145] S805: The processor determines an obstruction index of the obstacle to the inspection robot according to the evaluation coefficient and the volume of the obstacle.

[0146] Optionally, the step of determining the obstruction index of the obstacle to the inspection robot based on the evaluation coefficient and the volume of the obstacle includes: obtaining the obstacle avoidance space volume of the inspection robot; and determining the obstruction index of the obstacle to the inspection robot based on the obstacle avoidance space volume, the evaluation coefficient and the volume of the obstacle.

[0147] In this embodiment, combined Figure 1 , Figure 2 , Figure 4 and Figure 5 As shown, the inspection robot 10 includes a chassis support 601, which is arranged at the bottom of the box 101 along the height direction of the box 101. The walking wheels 410 and the proximity switch 510 are arranged at intervals on the side of the chassis support 601 away from the box 101. The obstacle avoidance space volume of the inspection robot refers to the volume of the cavity formed between the chassis support of the inspection robot and the ground. Figure 4 and Figure 5 As shown in Figure 2, when the inspection robot is deployed on the ground, the obstacle avoidance space of the inspection robot is Figure 4 The area shown in A in the figure; when the inspection robot is deployed on the track, the obstacle avoidance space of the inspection robot is Figure 5The area shown in B in the figure. The volume of the obstacle avoidance space can be determined by experimental measurement or simulation. In this embodiment, the obstruction index is a quantitative indicator that combines the obstacle avoidance space volume, the evaluation coefficient and the obstacle volume, and is used to indicate the degree of obstruction of the obstacle to the movement of the inspection robot. The specific calculation method of the obstruction index is: obstruction index = (obstacle volume / obstacle avoidance space volume) × evaluation coefficient. In this embodiment, the obstruction index comprehensively considers multiple factors, including the volume and type of the obstacle, the obstacle avoidance space volume of the inspection robot, etc., so that the inspection robot can maintain a high adaptability in different environments and scenarios, and more accurately evaluate the impact of obstacles on its movement, so that the inspection robot can make more reasonable obstacle avoidance decisions when encountering obstacles, thereby improving the success rate and safety of obstacle avoidance.

[0148] S806: The processor determines a target obstacle coping strategy based on the location and obstruction index of the obstacle.

[0149] Optionally, the inspection robot 10 includes walking wheels 410. The obstacle response strategy includes an obstacle crossing strategy, an obstacle avoidance strategy, and an obstacle clearing strategy. According to the position of the obstacle and the obstruction index, the step of determining the target obstacle response strategy includes: when the obstacle position is located on the walking route of the walking wheel and the obstruction index is less than the index threshold, the obstacle clearing strategy is used as the target obstacle response strategy; when the obstacle position is located between the walking routes of the two walking wheels and the obstruction index is less than the index threshold, the obstacle crossing strategy is used as the target obstacle response strategy; when the obstacle position is located on the target inspection route of the inspection robot and the obstruction index is greater than or equal to the index threshold, the obstacle avoidance strategy is used as the target obstacle response strategy.

[0150] In this embodiment, it is possible to select a suitable obstacle response strategy according to the location and obstruction index of the obstacle, so that the inspection robot can respond to the obstacle more quickly, reduce the time and energy wasted due to obstacle avoidance, and improve the inspection efficiency. In this embodiment, the inspection robot can respond flexibly according to different types of obstacles and different environmental conditions, which enhances the adaptability of the inspection robot and enables the inspection robot to maintain efficient and stable operation in various complex environments. By accurately assessing the degree of obstruction of the obstacle and selecting an appropriate response strategy, the inspection robot can avoid collisions with obstacles, thereby reducing the risk of damage or failure and improving the safety of the inspection robot.

[0151] S807: The processor controls the inspection robot to handle obstacles according to the target obstacle response strategy.

[0152] The control method of the inspection robot provided in the embodiment of the present disclosure, after determining the corresponding evaluation coefficient according to the type of obstacle, further obtains the obstruction index of the obstacle to the inspection robot according to the evaluation coefficient and the volume of the obstacle. The higher the obstruction index, the greater the obstruction of the obstacle to the inspection robot, and a more cautious or complex response strategy needs to be adopted. By introducing the evaluation coefficient of the obstacle type and volume, the embodiment of the present disclosure enables the inspection robot to more accurately evaluate the degree of obstruction of different obstacles to the movement of the inspection robot, thereby formulating a more accurate response strategy and improving the accuracy of the inspection robot's decision-making.

[0153] In some embodiments, in combination Figure 1 , Figure 2 , Figure 4 and Figure 5 As shown, the inspection robot 10 includes a cleaning mechanism 610 and a walking wheel 410. The cleaning mechanism 610 is disposed on the chassis bracket 601 and is located in front of the walking wheel 410 along the moving direction of the inspection robot 10. When the target obstacle response strategy is an obstacle removal strategy, the step of controlling the inspection robot to handle obstacles according to the target obstacle response strategy includes: controlling the cleaning mechanism to clean the obstacles on the walking route of the walking wheel; after the cleaning is completed, controlling the inspection robot to move according to the target inspection route.

[0154] In this embodiment, obstacles on the walking path of the walking wheels are cleared by a cleaning mechanism installed on the inspection robot. After the cleaning is completed, there are no obstacles on the walking path or the obstacles have been effectively handled. The inspection robot continues to move according to the pre-planned target inspection route, thereby quickly restoring the inspection robot's traffic capacity, reducing the inspection interruption time caused by obstacles, and improving the inspection efficiency.

[0155] Optionally, combined Figure 1 , Figure 2 , Figure 4 and Figure 5 As shown, the cleaning mechanism 610 includes a first motor, a telescopic assembly 612 and a cleaning member 617. The first motor is arranged on the chassis bracket 601. One end of the telescopic assembly 612 is connected to the output end of the first motor, and the first motor can drive the telescopic assembly 612 to move along the cleaning direction. The cleaning member 617 is connected to the end of the telescopic assembly 612 away from the first motor, and the telescopic assembly 612 can drive the cleaning member 617 to move along the height direction of the inspection robot 10. The cleaning direction is perpendicular to the extension direction of the walking route and perpendicular to the height direction of the inspection robot 10. The step of controlling the cleaning mechanism to clean the obstacles on the walking route includes: controlling the telescopic assembly to extend and retract so that the cleaning member abuts against the obstacles on the walking route; controlling the first motor to drive the telescopic assembly to move along the cleaning direction to clean the obstacles on the walking route.

[0156] Optionally, combined Figure 1 , Figure 2 , Figure 4 and Figure 5 As shown, the telescopic assembly 612 includes a mounting tube 613, a connecting tube 615 and a second motor. One end of the mounting tube 613 is connected to the output end of the first motor. The second motor is arranged at the other end of the mounting tube 613, and the output end of the second motor is connected to one end of the connecting tube 615, and the other end of the connecting tube 615 is connected to the cleaning member 617. The second motor can drive the connecting tube 615 to move along the height direction of the inspection robot 10. Controlling the telescopic assembly to extend and retract so that the cleaning member abuts against obstacles on the walking route includes: controlling the second motor to drive the connecting tube to move along the height direction of the inspection robot so that the cleaning member abuts against obstacles on the walking route.

[0157] In some embodiments, when the target obstacle response strategy is an obstacle crossing strategy, the steps of controlling the inspection robot to handle obstacles according to the target obstacle response strategy include: obtaining the height and width of the obstacle; and obtaining the obstacle avoidance height and obstacle avoidance width of the obstacle avoidance space of the inspection robot; when the height of the obstacle is less than the obstacle avoidance height and the width of the obstacle is less than the obstacle avoidance width, controlling the inspection robot to move according to the target inspection route.

[0158] In this embodiment, the height and width of the obstacle can be obtained by the radar assembly installed on the inspection robot. The obstacle avoidance space of the inspection robot refers to the cavity formed between the chassis bracket of the inspection robot and the ground. The obstacle avoidance height and obstacle avoidance width of the obstacle avoidance space of the inspection robot can be determined by experimental measurement or simulation. After obtaining the size information of the obstacle and the obstacle avoidance space, a comparative analysis is performed. If the height of the obstacle is less than the obstacle avoidance height and the width of the obstacle is less than the obstacle avoidance width, it is determined that the inspection robot itself has the ability to cross the obstacle, and the inspection robot is controlled to continue to move along the target inspection route to cross the obstacle. In this embodiment, by accurately obtaining the size information of the obstacle and the obstacle avoidance space, the inspection robot can more accurately judge its own obstacle crossing ability and improve the success rate of obstacle crossing.

[0159] In some embodiments, the inspection robot 10 includes a knocking component, which is located at the end of the chassis bracket 601 along the moving direction of the inspection robot 10. According to the target obstacle response strategy, the step of controlling the inspection robot to handle obstacles also includes: when the height of the obstacle is greater than or equal to the obstacle avoidance height, controlling the knocking component to knock the obstacle so that the height of the obstacle is less than the obstacle avoidance height; after the knocking is completed, controlling the inspection robot to move according to the target inspection route.

[0160] In this embodiment, when the height of the obstacle is greater than or equal to the obstacle avoidance height, a knocking strategy can be adopted to preferentially handle the obstacle. By controlling the knocking component to knock the obstacle, the height of the obstacle is reduced to less than the obstacle avoidance height, so that the inspection robot can cross the obstacle, overcome the obstacle crossing problem caused by the obstacle being too high, and enhance the obstacle crossing ability of the inspection robot. Exemplarily, the knocking component can be controlled to knock the obstacle in a direction perpendicular to the height direction of the obstacle, so that the height of the obstacle is reduced to less than the obstacle avoidance height.

[0161] Optionally, the knocking assembly includes a third motor, a connecting rod and a knocking piece. The third motor is located at the end of the chassis bracket 601 along the moving direction of the inspection robot 10. The connecting rod is connected to the output end of the third motor. The knocking piece is connected to the connecting rod. The third motor can drive the connecting rod to move in the direction of the obstacle, thereby driving the knocking piece to move in the direction of the obstacle. The step of controlling the knocking assembly to knock on the obstacle includes: controlling the third motor to drive the connecting rod to move in the direction of the obstacle, so that the knocking piece moves in the direction of the obstacle.

[0162] In some embodiments, the inspection robot includes a knocking component. According to the target obstacle coping strategy, the step of controlling the inspection robot to handle obstacles also includes: when the width of the obstacle is greater than or equal to the obstacle avoidance width, controlling the knocking component to knock the obstacle so that the width of the obstacle is less than the obstacle avoidance width; after the knocking is completed, controlling the inspection robot to move according to the target inspection route.

[0163] In this embodiment, when the width of the obstacle is greater than or equal to the obstacle avoidance width, a knocking strategy can be adopted to preferentially handle the obstacle. By controlling the knocking component to knock the obstacle, the width of the obstacle is reduced to less than the obstacle avoidance width, so that the inspection robot can cross the obstacle, overcome the obstacle crossing problem caused by the obstacle being too wide, and enhance the obstacle crossing ability of the inspection robot. Exemplarily, the knocking component can be controlled to knock the obstacle in a direction perpendicular to the width direction of the obstacle, so that the width of the obstacle is reduced to less than the obstacle avoidance width.

[0164] In some embodiments, when the target obstacle response strategy is an obstacle avoidance strategy, the steps of controlling the inspection robot to handle obstacles according to the target obstacle response strategy include: correcting the target inspection route according to the position and volume of the obstacle; and controlling the inspection robot to move according to the corrected target inspection route.

[0165] In this embodiment, the process of correcting the target inspection route according to the position and volume of the obstacle can be understood as the process of deleting the coordinate points corresponding to the position information of the obstacle and the coordinate points covered by the volume, adding the coordinate points of the movable area around the obstacle, and regenerating the target inspection route according to the updated coordinate points. Therefore, the process of correcting the target inspection route according to the position and volume of the obstacle can refer to the process of generating the target inspection route in the above embodiment, and will not be repeated here.

[0166] In this embodiment, by correcting the target inspection route according to the position and volume information of the obstacle, the inspection robot can accurately and safely bypass the obstacle, improve the robot's obstacle avoidance ability, and enable it to maintain efficient and stable operation in complex environments. The corrected inspection route not only avoids obstacles, but also minimizes path deviation and time waste, so as to optimize the inspection path and ensure inspection efficiency.

[0167] Combination Fig. 9 As shown, the embodiment of the present disclosure provides a control device 70 for an inspection robot, comprising a detection module 71, an acquisition module 72, a determination module 73 and a control module 74. The detection module 71 is configured to control the inspection robot to detect obstacles in the moving direction; the acquisition module 72 is configured to acquire feature information of the obstacle when there is an obstacle in the moving direction; the determination module 73 is configured to determine a target obstacle coping strategy based on the feature information of the obstacle; and the control module 74 is configured to control the inspection robot to handle the obstacle based on the target obstacle coping strategy.

[0168] The control device 70 of the inspection robot provided in the embodiment of the present disclosure can implement the control method of the inspection robot described in the above embodiment. Therefore, the technical effects possessed by the control method of the inspection robot described in the above embodiment are all possessed by the embodiment of the present disclosure and will not be repeated here.

[0169] Optionally, the acquisition module 72 is also configured to control the radar component to transmit a radar signal; receive a reflected signal reflected by the radar signal after encountering an obstacle, and obtain a round-trip time; determine the position and volume of the obstacle based on the round-trip time; and use the position and volume of the obstacle as characteristic information of the obstacle.

[0170] Optionally, the characteristic information of the obstacle includes position and volume. The determination module 73 is further configured to evaluate the volume of the obstacle, determine the obstruction index of the obstacle to the inspection robot, and determine the target obstacle coping strategy according to the position and obstruction index of the obstacle.

[0171] Optionally, the determination module 73 is further configured to obtain the type of obstacle; determine an evaluation coefficient of the obstacle volume according to the type of obstacle; and determine an obstruction index of the obstacle to the inspection robot according to the evaluation coefficient and the volume of the obstacle.

[0172] Optionally, the determination module 73 is further configured to obtain image data of the obstacle; input the image data into a pre-trained target recognition model to obtain the obstacle type.

[0173] Optionally, the determination module 73 is further configured to obtain image data of obstacles and environmental parameters of the target inspection area; input the image data and environmental parameters into a pre-trained target recognition model to obtain the obstacle type.

[0174] Optionally, the determination module 73 is further configured to obtain image data of obstacles and environmental parameters of the target inspection area; preprocess the image data of obstacles according to the environmental parameters; and input the preprocessed image data into a pre-trained target recognition model to obtain the obstacle type.

[0175] Optionally, the determination module 73 is further configured to obtain the obstacle avoidance space volume of the inspection robot; determine the obstacle hindrance index of the inspection robot according to the obstacle avoidance space volume, the evaluation coefficient and the volume of the obstacle.

[0176] Optionally, the inspection robot includes walking wheels, and the obstacle response strategy includes an obstacle crossing strategy, an obstacle avoidance strategy, and an obstacle clearing strategy. The determination module 73 is further configured to use the obstacle clearing strategy as the target obstacle response strategy when the obstacle is located on the walking route of the walking wheels and the obstruction index is less than the index threshold; use the obstacle crossing strategy as the target obstacle response strategy when the obstacle is located between the walking routes of the two walking wheels and the obstruction index is less than the index threshold; use the obstacle avoidance strategy as the target obstacle response strategy when the obstacle is located on the target inspection route of the inspection robot and the obstruction index is greater than or equal to the index threshold.

[0177] Optionally, the inspection robot includes a cleaning mechanism and walking wheels. When the target obstacle response strategy is an obstacle removal strategy, the control module 74 is further configured to control the cleaning mechanism to clean obstacles on the walking route; after cleaning, the inspection robot is controlled to move along the target inspection route.

[0178] Optionally, when the target obstacle response strategy is an obstacle crossing strategy, the control module 74 is also configured to obtain the height and width of the obstacle; and obtain the obstacle avoidance height and obstacle avoidance width of the obstacle avoidance space of the inspection robot; when the height of the obstacle is less than the obstacle avoidance height and the width of the obstacle is less than the obstacle avoidance width, the inspection robot is controlled to move according to the target inspection route.

[0179] Optionally, the inspection robot includes a knocking component. When the target obstacle response strategy is an obstacle crossing strategy, the control module 74 is further configured to control the knocking component to knock the obstacle when the height of the obstacle is greater than or equal to the obstacle avoidance height, so that the height of the obstacle is less than the obstacle avoidance height; after the knocking is completed, the inspection robot is controlled to move according to the target inspection route.

[0180] Optionally, the inspection robot includes a knocking component. When the target obstacle response strategy is an obstacle crossing strategy, the control module 74 is further configured to control the knocking component to knock the obstacle when the width of the obstacle is greater than or equal to the obstacle avoidance width, so that the width of the obstacle is less than the obstacle avoidance width; after the knocking is completed, the inspection robot is controlled to move according to the target inspection route.

[0181] Optionally, when the target obstacle response strategy is an obstacle avoidance strategy, the control module 74 is further configured to correct the target inspection route according to the position and volume of the obstacle; and control the inspection robot to move according to the corrected target inspection route.

[0182] Combination Fig.10 As shown, the embodiment of the present disclosure provides a control device 90 of an inspection robot, including a processor 900 and a memory 901. Optionally, the device 90 may also include a communication interface 902 and a bus 903. The processor 900, the communication interface 902, and the memory 901 may communicate with each other through the bus 903. The communication interface 902 may be used for information transmission. The processor 900 may call the logic instructions in the memory 901 to execute the control method of the inspection robot of the above embodiment.

[0183] In addition, the logic instructions in the memory 901 described above may be implemented in the form of software functional units and when sold or used as independent products, may be stored in a computer-readable storage medium.

[0184] The memory 901 is a computer-readable storage medium that can be used to store software programs and computer executable programs, such as program instructions / modules corresponding to the method in the embodiment of the present disclosure. The processor 900 executes the functional application and data processing by running the program instructions / modules stored in the memory 901, that is, the control method of the inspection robot in the above embodiment is implemented.

[0185] The memory 901 may include a program storage area and a data storage area, wherein the program storage area may store an operating system and an application required for at least one function; the data storage area may store data created according to the use of the terminal device, etc. In addition, the memory 901 may include a high-speed random access memory and may also include a non-volatile memory.

[0186] An embodiment of the present disclosure provides a computer-readable storage medium storing computer-executable instructions, wherein the computer-executable instructions are configured to execute the control method of the inspection robot.

[0187] The technical solution of the embodiment of the present disclosure can be embodied in the form of a software product, which is stored in a storage medium and includes one or more instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method described in the embodiment of the present disclosure. The aforementioned storage medium may be a non-transient storage medium, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a disk or an optical disk, and other media that can store program codes.

[0188] The above description and the accompanying drawings fully illustrate the embodiments of the present disclosure so that those skilled in the art can practice them. Other embodiments may include structural, logical, electrical, process and other changes. The embodiments represent only possible changes. Unless explicitly required, separate components and functions are optional, and the order of operation may vary. The parts and features of some embodiments may be included in or replace the parts and features of other embodiments. Moreover, the words used in this application are only used to describe the embodiments and are not used to limit the claims. As used in the description of the embodiments and the claims, unless the context clearly indicates, the singular forms of "a", "an" and "the" are intended to include plural forms as well. Similarly, the term "and / or" as used in this application refers to any and all possible combinations of listings containing one or more associated ones. In addition, when used in the present application, the term "comprise" and its variants "comprises" and / or comprising refer to the presence of stated features, wholes, steps, operations, elements, and / or components, but do not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or groups thereof. In the absence of further restrictions, the elements defined by the sentence "comprising a ..." do not exclude the presence of other identical elements in the process, method or device comprising the elements. In this article, each embodiment may focus on the differences from other embodiments, and the same and similar parts between the various embodiments may refer to each other. For the methods, products, etc. disclosed in the embodiments, if they correspond to the method part disclosed in the embodiments, then the relevant parts can refer to the description of the method part.

[0189] Those skilled 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, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software may depend on the specific application and design constraints of the technical solution. The technicians may use different methods for each specific application to implement the described functions, but such implementations should not be considered to exceed the scope of the embodiments of the present disclosure. The technicians may clearly understand that, for the convenience and simplicity of description, the specific working processes of the systems, devices and units described above may refer to the corresponding processes in the aforementioned method embodiments, and will not be repeated here.

[0190] In the embodiments disclosed herein, the disclosed methods and products (including but not limited to devices, equipment, etc.) can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units can be only a logical function division. 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 coupling or direct coupling or communication connection between each other shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms. The units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the units may be selected according to actual needs to implement this embodiment. In addition, each functional unit in the embodiment of the present disclosure may be integrated in a processing unit, or each unit may exist physically alone, or two or more units may be integrated in one unit.

[0191] The flowchart and block diagram in the accompanying drawings show the possible architecture, function and operation of the system, method and computer program product according to the embodiment of the present disclosure. In this regard, each box in the flowchart or block diagram can represent a module, a program segment or a part of the code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. In some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, which can depend on the functions involved. In the description corresponding to the flowchart and the block diagram in the accompanying drawings, the operations or steps corresponding to different boxes can also occur in a different order from the order disclosed in the description, and sometimes there is no specific order between different operations or steps. For example, two consecutive operations or steps can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, which can depend on the functions involved. Each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, may be implemented by a dedicated hardware-based system that performs the specified functions or actions, or may be implemented by a combination of dedicated hardware and computer instructions.

Claims

1. A control method for an inspection robot, characterized in that: include: Control the inspection robot to detect obstacles in the moving direction; When there is an obstacle in the moving direction, obtain characteristic information of the obstacle; Determine the target obstacle response strategy based on the characteristic information of the obstacle; According to the target obstacle response strategy, the inspection robot is controlled to handle obstacles.

2. The control method according to claim 1, characterized in that: The inspection robot includes a radar component; the steps of obtaining characteristic information of an obstacle include: Controlling the radar component to transmit radar signals; Receive the reflected signal of the radar signal after it encounters an obstacle and obtain the round-trip time; Determine the location and volume of the obstacle based on the round trip time; The position and volume of the obstacle are used as the feature information of the obstacle.

3. The control method according to claim 1 or 2, characterized in that: The characteristic information of the obstacle includes the position and volume. According to the characteristic information of the obstacle, the steps of determining the target obstacle response strategy include: Evaluate the volume of obstacles and determine the hindrance index of obstacles to the inspection robot; Determine the target obstacle response strategy based on the location and hindrance index of the obstacle.

4. The control method according to claim 3, characterized in that: The steps of evaluating the volume of the obstacle and determining the obstacle index of the obstacle to the inspection robot include: Get the type of obstacle; Determine the obstacle volume assessment coefficient based on the type of obstacle; According to the evaluation coefficient and the volume of the obstacle, the obstacle hindrance index to the inspection robot is determined.

5. The control method according to claim 4, characterized in that: Obtain the obstacle type in the following manner: obtain image data of the obstacle; input the image data into a pre-trained target recognition model to obtain the obstacle type; or, Obtain the obstacle type in the following manner: obtain image data of the obstacle and environmental parameters of the target inspection area; input the image data and environmental parameters into a pre-trained target recognition model to obtain the obstacle type; or, Obstacle types are obtained in the following manner: image data of the obstacle and environmental parameters of the target inspection area are obtained; the image data of the obstacle is preprocessed according to the environmental parameters; and the preprocessed image data is input into a pre-trained target recognition model to obtain the obstacle type.

6. The control method according to claim 4, characterized in that: The steps of determining the obstacle hindrance index of the obstacle to the inspection robot according to the evaluation coefficient and the volume of the obstacle include: Obtain the obstacle avoidance space volume of the inspection robot; According to the volume of the obstacle avoidance space, the evaluation coefficient and the volume of the obstacle, the obstacle hindrance index to the inspection robot is determined.

7. The control method according to claim 3, characterized in that: The inspection robot includes walking wheels. The obstacle response strategy includes obstacle crossing strategy, obstacle avoidance strategy and obstacle clearing strategy. According to the location and obstruction index of the obstacle, the steps of determining the target obstacle response strategy include: When the obstacle is located on the walking path of the walking wheels and the obstruction index is less than the index threshold, the obstacle removal strategy is used as the target obstacle response strategy; When the obstacle is located between the walking paths of the two walking wheels and the obstruction index is less than the index threshold, the obstacle crossing strategy is used as the target obstacle coping strategy; When the obstacle is located on the target inspection route of the inspection robot and the obstruction index is greater than or equal to the index threshold, the obstacle avoidance strategy is used as the target obstacle response strategy.

8. The control method according to any one of claims 1 to 7, characterized in that: The inspection robot includes a cleaning mechanism and walking wheels; when the target obstacle response strategy is an obstacle removal strategy, the steps of controlling the inspection robot to handle obstacles according to the target obstacle response strategy include: controlling the cleaning mechanism to clean the obstacles on the walking route; after the cleaning is completed, controlling the inspection robot to move along the target inspection route; or, When the target obstacle response strategy is the obstacle crossing strategy, the steps of controlling the inspection robot to handle obstacles according to the target obstacle response strategy include: obtaining the height and width of the obstacle; and obtaining the obstacle avoidance height and obstacle avoidance width of the obstacle avoidance space of the inspection robot; when the height of the obstacle is less than the obstacle avoidance height and the width of the obstacle is less than the obstacle avoidance width, controlling the inspection robot to move according to the target inspection route; or, The inspection robot includes a knocking component; when the target obstacle response strategy is an obstacle crossing strategy, the steps of controlling the inspection robot to handle obstacles according to the target obstacle response strategy include: obtaining the height and width of the obstacle; and obtaining the obstacle avoidance height and obstacle avoidance width of the obstacle avoidance space of the inspection robot; when the height of the obstacle is greater than or equal to the obstacle avoidance height, controlling the knocking component to knock on the obstacle so that the height of the obstacle is less than the obstacle avoidance height; after the knocking is completed, controlling the inspection robot to move according to the target inspection route; and / or, when the width of the obstacle is greater than or equal to the obstacle avoidance width, controlling the knocking component to knock on the obstacle so that the width of the obstacle is less than the obstacle avoidance width; after the knocking is completed, controlling the inspection robot to move according to the target inspection route; or, When the target obstacle response strategy is the obstacle avoidance strategy, the steps of controlling the inspection robot to handle obstacles according to the target obstacle response strategy include: correcting the target inspection route according to the position and volume of the obstacle; and controlling the inspection robot to move according to the corrected target inspection route.

9. A control device for an inspection robot, characterized in that: include: A detection module is configured to control the inspection robot to detect obstacles in the moving direction; An acquisition module, configured to acquire feature information of an obstacle when there is an obstacle in the moving direction; A determination module is configured to determine a target obstacle coping strategy based on characteristic information of the obstacle; The control module is configured to control the inspection robot to handle obstacles according to the target obstacle response strategy.

10. A control device for an inspection robot, comprising a processor and a memory storing program instructions, characterized in that: The processor is configured to execute the control method of the inspection robot according to any one of claims 1 to 8 when running the program instructions.

11. A patrol robot, characterized in that: include: Robot body; The control device of the inspection robot as described in claim 9 or 10 is installed on the robot body.

Images