Inspection method based on inspection robot and control system

Abstract

The invention relates to the technical field of robot inspection, in particular to an inspection method based on an inspection robot and a control system. The method has the beneficial effects that when the inspection robot recognizes that the to-be-detected equipment is abnormal under the offline sensing model, the help seeking instruction is generated according to the grade parameter of the abnormal condition, the optimal network signal coverage area is screened, the inspection robot is guided to move towards the optimal network signal coverage area, and the network signal coverage area is optimized. After a network signal coverage area is reached, a warning signal is sent to a cloud platform; after a response instruction of the cloud platform is received, the inspection robot continues to execute the inspection task on the to-be-detected equipment which is not detected according to the preset inspection path, the problem that the abnormal condition of the equipment cannot be fed back in time in an offline state is solved, and the inspection robot can make a judgment autonomously and move to a network signal coverage area in time; and the help-seeking instruction is sent out, so that a control room can make a correct decision instruction in time, and equipment loss is prevented from being increased.

Description

Technical Field

[0001] The present invention relates to the technical field of robot inspection, and specifically to an inspection method and control system based on an inspection robot. Background Art

[0002] An inspection robot is an intelligent device with capabilities of autonomous navigation, environment perception, and data analysis, mainly used to replace humans to complete high-risk, high-intensity, or repetitive inspection tasks. With the maturity of industrial automation and robot technology, its application scenarios have gradually expanded. In the early stage, the inspection system mainly consisted of rail-mounted or magnetic adsorption robots, mainly used for preliminary equipment monitoring in high-risk scenarios such as nuclear power plants and substations. With the rapid development of sensor technology, artificial intelligence, and the Internet of Things, inspection robots have entered the intelligent stage and began to possess capabilities of autonomous navigation, multi-modal perception, and real-time analysis.

[0003] Existing inspection robots can make intelligent decisions for autonomous navigation based on multi-modal perception and real-time analysis capabilities. For example, when detecting an abnormal situation of equipment, they can automatically make corresponding decisions. However, this function depends on real-time network transmission. If the inspection robot travels to an area with unstable signals, such as a tunnel, it will cause network instability, slow real-time data transmission, and inability to timely feedback abnormal situations, thus unable to make corresponding decisions in a timely manner, resulting in increased losses. Summary of the Invention

[0004] The purpose of the present invention is to provide an inspection method and control system based on an inspection robot to solve the problems raised in the prior art.

[0005] To achieve the above purpose, the present invention provides the following technical solution: An inspection method based on an inspection robot,

[0006] Step S1: Obtain a map of the target area and inspection path planning data. The map of the target area includes spatial position markings of static obstacles, and the inspection path planning data includes a preset inspection path and inspection tasks;

[0007] Step S2: When the network communication of the inspection robot is abnormal, switch to the offline perception mode, obtain the environmental information in the forward direction of the inspection robot through a visual sensor, and perform dynamic obstacle detection;

[0008] Step S3: Select an operation plan based on the detection result:

[0009] If no dynamic obstacles are detected, the inspection robot executes the inspection task along the preset inspection path;

[0010] If dynamic obstacles are detected, generate a corrected path and send it to the inspection robot, where the corrected path is to guide the inspection robot not to come into contact with the dynamic obstacles;

[0011] Step S4. When the inspection robot identifies an abnormal situation of the device to be detected, generate a task execution strategy according to the level parameter of the abnormal situation:

[0012] In case of a low-level fault, maintain the current inspection path and record the abnormal data;

[0013] In case of a high-level fault, plan a network communication recovery path and guide the inspection robot to move towards the network signal coverage area;

[0014] Step S5. Record the offline operation data, where the offline operation data are all the instructions executed by the inspection robot in the offline perception mode; after the network is restored, synchronize the offline operation data to the remote server and update the local environment data.

[0015] The said Step S1 includes:

[0016] S11. Mark the area responsible for inspection by the inspection robot as the target environment, periodically collect images of the target area through the image acquisition device and generate a map of the target area, establish a three-dimensional coordinate system, and mark the spatial positions of the static obstacles in the target area map, where the static obstacles are certain items fixedly distributed at a certain location on the inspection path;

[0017] S12. Input the inspection start point and the inspection end point, mark them on the target area map, generate a set of paths connecting the start point to the end point, select the shortest path in the set of paths as the preset inspection path, and formulate an inspection task according to the devices to be detected passed by the preset inspection path, where the inspection task is the detection instruction for the devices to be detected.

[0018] Step S2 includes:

[0019] Real-time detect the network communication of the inspection robot. When it is detected that the transmission speed of the network communication is lower than the transmission speed threshold and the delay time exceeds the time threshold, automatically switch to the offline perception mode. In the offline perception mode:

[0020] Start the vision sensor to collect images in the forward direction of the inspection robot, transmit the images to the local central processor for image preprocessing, and perform dynamic obstacle detection by analyzing the image data. The dynamic obstacle detection process is as follows: perform gray-scale processing on the image, analyze whether there is an image of an obstacle in the image. If there is an obstacle image, calculate the position of the obstacle.

[0021] Extract the spatial positions of the marked static obstacles. If they coincide with the position of the obstacle, output the detection result as no dynamic obstacle detected; if the position of the static obstacle does not coincide with the position of the obstacle, output the detection result as dynamic obstacle detected.

[0022] Wherein the visual sensor includes a first binocular camera and a second binocular camera. The first binocular camera is used to collect images directly in front of the inspection robot. The second binocular camera is located above the inspection robot and is used to collect images in front of the inspection robot. And the acquisition direction of the first binocular camera and the acquisition direction of the second binocular camera form an angle less than 90 degrees.

[0023] The process of calculating the position of the obstacle is as follows: Obtain the focal length of the camera and the shooting angle of the camera. In the image captured by the first binocular camera, calculate the horizontal distance from the object to the inspection robot as D1 = H1×(f1 / Y1) through the position Y1 of the bottom of the object in the image, where H1 is the vertical height of the first binocular camera, f1 is the focal length of the first binocular camera, and D1 is the horizontal distance from the object to the inspection robot.

[0024] In the image captured by the second binocular camera, calculate the vertical distance from the object to the inspection robot as D2 = H2×(f2 / Y2×sinθ) through the position Y2 of the bottom of the object in the image, where H2 is the vertical height of the second binocular camera, f2 is the focal length of the second binocular camera, D2 is the vertical height from the object to the inspection robot, and θ is the angle between the second binocular camera and the first binocular camera.

[0025] The position coordinates of the obstacle can be obtained according to D1 and D2.

[0026] The step S3 includes:

[0027] When no dynamic obstacle is detected, obtain the preset inspection path, and the inspection robot moves along the preset inspection path and executes corresponding inspection instructions on the equipment to be detected passed by, completing the inspection task.

[0028] When a dynamic obstacle is detected, obtain the current position coordinates of the inspection robot in real time and the distance between it and the dynamic obstacle. When the distance between the dynamic obstacle and the inspection robot is less than the threshold, trigger the instruction for the inspection robot to avoid. The inspection robot generates a corrected path through the built-in algorithm logic to guide the inspection robot not to contact the dynamic obstacle.

[0029] The step S4 includes:

[0030] S41. When an abnormal situation of the equipment is detected, calculate the level parameter of the abnormal situation. The calculation process is as follows:

[0031] Obtain the fault type corresponding to this abnormal situation and the urgency level corresponding to this fault type. Each type of fault type is preset with a corresponding urgency level. The urgency levels include low, medium, and high. Each level of urgency corresponds to its own urgency weight, and each level of urgency is scored, and the scoring result is used as the urgency value of this level;

[0032] The urgency value of the low level is 1-4, the urgency value of the medium level is 5-7, the urgency value of the high level is 8-10. The weight corresponding to the low level of urgency is 0.2, the weight corresponding to the medium level of urgency is 0.45, and the weight corresponding to the high level of urgency is 0.68. This data is obtained from multiple experiments;

[0033] S42. Retrieve the total number of all abnormal situations detected in the current offline sensing mode and the number of devices to be detected that have completed the inspection. Divide the total number of abnormal situations by the number of devices to be detected that have completed the inspection to calculate the offline failure rate;

[0034] S43. Calculate the level parameter of the abnormal situation that occurred this time. The calculation process is: level parameter = (urgency value × urgency weight) + (offline failure rate × failure rate weight);

[0035] If the level parameter is greater than the set parameter threshold, output it as a high-level fault. If the level parameter is less than the set parameter threshold, output it as a low-level fault; the parameter threshold can be preset in advance;

[0036] S44. If the output of S43 is a low-level fault, obtain the preset inspection path and inspection tasks that the inspection robot has not performed, and continue to perform the inspection tasks according to the unperformed preset inspection path;

[0037] If the output of S43 is a high-level fault, generate a distress instruction, screen the optimal network signal coverage area, guide the inspection robot to move towards the optimal network signal coverage area. After reaching the network signal coverage area, send a warning signal to the cloud platform; after receiving the response instruction from the cloud platform, the inspection robot continues to perform the inspection tasks on the devices to be detected that have not been inspected according to the preset inspection path.

[0038] The process of screening the optimal network signal coverage area is as follows:

[0039] Analysis of candidate area 1: Obtain the inspection status of the inspection robot during the inspection process. The inspection status includes a preset inspection mode and an offline perception mode, where the preset inspection mode is the status when the network communication of the inspection robot is normal; mark the inspection status of the inspection robot on the passed inspection path, divide the inspection path according to the inspection status, divide the inspection path passed in the preset inspection mode into a network communication section, and divide the inspection path passed in the offline perception model into a network anomaly section; obtain the network communication section closest to the current position of the inspection robot as the target area, obtain the position coordinates of the target area, calculate the path length between the inspection robot and the target area through the coordinates, and calculate the distress duration 1 required to reach the target area according to the driving speed of the inspection robot. At the same time, obtain the failure rate 1 of encountering dynamic obstacles during the process of the inspection robot reaching the target area from the current position. The failure rate 1 is the number of times of encountering dynamic obstacles during the process of reaching the target area from the current position in the historical inspection records divided by the total number of historical inspections;

[0040] Analysis of candidate area 2: Mark the unpassed preset inspection path as the target path, obtain the historical inspection records of the target path, mark the section that has not switched to the offline perception mode in the historical inspection records as the historical network communication section, select the historical network communication section closest to the current position of the inspection robot as the target section, obtain the position coordinates of the target section, calculate the path length between the inspection robot and the target section through the coordinates, and calculate the distress duration 2 required to reach the target section according to the driving speed of the inspection robot. At the same time, obtain the failure rate 2 of encountering dynamic obstacles during the process of the inspection robot reaching the target section from the current position. The failure rate 2 is the number of times of encountering dynamic obstacles during the process of reaching the target section from the current position in the historical inspection records divided by the total number of historical inspections;

[0041] Analysis of candidate area 3: Obtain the positions of each artificial base station marked on the target area map. The artificial base station is a service area fixedly set somewhere and providing services for the inspection robot. Select the artificial base station closest to the current inspection robot as the target base station, obtain the position coordinates of the target base station, calculate the path length between the inspection robot and the target base station through the coordinates, calculate the distress duration 2 required to reach the target base station according to the driving speed of the inspection robot. At the same time, obtain the failure rate 3 of encountering dynamic obstacles during the process of the inspection robot reaching the target base station from the current position. The failure rate 3 is the number of times of encountering dynamic obstacles during the process of reaching the target base station from the current position in the historical inspection records divided by the total number of historical inspections;

[0042] S45. Calculate the level value of each candidate area. The calculation process is as follows: level value A = distress duration A × weight one + failure rate A × weight two + area weight A; where the level value A ∈ {level value of candidate area one, level value of candidate area two, level value of candidate area three}; the distress duration A ∈ {distress duration one, distress duration two, distress duration three}; the failure rate A ∈ {failure rate one, failure rate two, failure rate three}; the area weight A ∈ {area weight one, area weight two, area weight three}, and each candidate area corresponds to an area weight respectively.

[0043] Output the candidate area with the highest level value. The candidate area ∈ {candidate area one, candidate area two, candidate area three}, generate a task execution strategy for the inspection robot to move to this candidate area, and when the communication is restored, upload the data of the detected abnormal situation to the cloud platform and send out a warning signal.

[0044] A control system based on an inspection robot. The control system includes:

[0045] An inspection planning module: Obtain the target area map and inspection path planning data. The target area map contains the spatial position markings of static obstacles, and the inspection path planning data includes a preset inspection path and inspection tasks.

[0046] A mode switching module: When the network communication of the inspection robot is abnormal, switch to the offline perception mode, obtain the environmental information in the forward direction of the inspection robot through a vision sensor, and perform dynamic obstacle detection.

[0047] An operation decision module: Select an operation plan based on the detection results: If no dynamic obstacles are detected, the inspection robot performs inspection tasks along the preset inspection path; if dynamic obstacles are detected, generate a corrected path and send it to the inspection robot. The corrected path is to guide the inspection robot not to contact the dynamic obstacles.

[0048] An abnormality judgment module: When the inspection robot identifies that an abnormal situation occurs in the device to be detected, generate a task execution strategy according to the level parameters of the abnormal situation:

[0049] Maintain the current inspection path and record abnormal data in case of a low-level fault;

[0050] Plan a network communication restoration path in case of a high-level fault, and guide the inspection robot to move towards the network signal coverage area;

[0051] A transmission module: Record offline operation data, where the offline operation data is all instructions executed by the inspection robot in the offline perception mode; synchronize the offline operation data to the remote server after the network is restored, and update the local environment data.

[0052] The mode switching module includes:

[0053] Image acquisition unit: It is used to acquire images in the forward direction of the inspection robot, transmit the images to the local central processor for image preprocessing, and perform dynamic obstacle detection by analyzing the image data;

[0054] Dynamic obstacle analysis unit: It performs grayscale processing on the image, analyzes whether there is an obstacle image in the image. If there is an obstacle image, it calculates the position of the obstacle, extracts the spatial position of the marked static obstacle. If it coincides with the position of the obstacle, it outputs the detection result as no dynamic obstacle detected; if the position of the static obstacle does not coincide with the position of the obstacle, it outputs the detection result as dynamic obstacle detected;

[0055] Network detection unit: It detects the network communication of the inspection robot in real time. When it detects that the transmission speed of the network communication is lower than the transmission speed threshold and the delay time exceeds the time threshold, it automatically switches to the offline perception mode.

[0056] The abnormal judgment module includes:

[0057] Level judgment unit: It obtains the fault type corresponding to the abnormal situation and the urgency corresponding to the fault type. Each type of fault type has a preset urgency, and calculates the level parameter of the abnormal situation that appears this time;

[0058] Output unit: If the level parameter of the abnormal situation corresponds to a low-level fault output, it obtains the preset inspection path and inspection tasks that the inspection robot has not performed, and continues to perform the inspection tasks according to the unperformed preset inspection path;

[0059] If the level parameter of the abnormal situation corresponds to a high-level fault output, it generates a distress instruction, screens the optimal network signal coverage area, guides the inspection robot to move towards the optimal network signal coverage area. After reaching the network signal coverage area, it sends a warning signal to the cloud platform.

[0060] Compared with the prior art, the beneficial effects of the present invention are:

[0061] 1. When the network communication of the patrol robot is detected to be abnormal, switch to the offline sensing mode. In the offline sensing mode, if a dynamic obstacle is detected, generate a corrected path and send it to the patrol robot. The corrected path is to guide the patrol robot not to contact the dynamic obstacle. And when the patrol robot identifies that the device to be detected has an abnormal situation under the offline sensing model, generate a distress signal according to the level parameter of the abnormal situation, screen the optimal network signal coverage area, guide the patrol robot to move towards the optimal network signal coverage area. After reaching the network signal coverage area, send a warning signal to the cloud platform. After receiving the response instruction from the cloud platform, the patrol robot continues to perform the patrol task on the devices to be detected that have not been detected according to the preset patrol path, overcoming the problem that the abnormal situation of the device cannot be timely feedback in the offline state. The patrol robot can make an autonomous judgment, move towards the network signal coverage area in time, and send out the distress signal so that the control room can make a correct decision instruction in time and avoid increasing equipment losses. Brief Description of the Drawings

[0062] Figure 1 It is a flowchart of the patrol method based on the patrol robot. Detailed Embodiments

[0063] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0064] Embodiment 1: As Figure 1 shown, the present invention provides a patrol method based on a patrol robot:

[0065] Step S1: Obtain the target area map and patrol path planning data. The target area map includes the spatial position markings of static obstacles. The patrol path planning data includes a preset patrol path and a patrol task.

[0066] Step S2: When the network communication of the patrol robot is abnormal, switch to the offline sensing mode, obtain the environmental information in the forward direction of the patrol robot through a visual sensor, and perform dynamic obstacle detection.

[0067] Step S3: Select an operation plan based on the detection result:

[0068] If no dynamic obstacle is detected, the patrol robot performs the patrol task along the preset patrol path.

[0069] If a dynamic obstacle is detected, a corrected path is generated and sent to the inspection robot, and the corrected path is to guide the inspection robot not to contact the dynamic obstacle;

[0070] Step S4: When the inspection robot identifies that an abnormal situation occurs in the device to be detected, a task execution strategy is generated according to the level parameter of the abnormal situation:

[0071] In case of a low-level fault, maintain the current inspection path and record the abnormal data;

[0072] In case of a high-level fault, plan a network communication recovery path and guide the inspection robot to move towards the network signal coverage area;

[0073] Step S5: Record the offline operation data, where the offline operation data is all the instructions executed by the inspection robot in the offline perception mode; after the network is restored, synchronize the offline operation data to the remote server and update the local environment data.

[0074] The step S1 includes:

[0075] S11: Mark the area responsible for inspection by the inspection robot as the target environment, periodically collect images of the target area through an image acquisition device and generate a target area map, establish a three-dimensional coordinate system, and mark the spatial positions of static obstacles in the target area map, where the static obstacles are certain items fixed at a certain place on the inspection path;

[0076] S12: Input the inspection start point and the inspection end point, mark them on the target area map, generate a path set connecting the start point to the end point, select the shortest path in the path set as the preset inspection path, and formulate an inspection task according to the devices to be detected passed by the preset inspection path, where the inspection task is a detection instruction for the devices to be detected.

[0077] The step S2 includes:

[0078] Real-time detect the network communication of the inspection robot. When it is detected that the transmission speed of the network communication is lower than the transmission speed threshold and the delay time exceeds the time threshold, automatically switch to the offline perception mode. In the offline perception mode:

[0079] Start the vision sensor to collect images in the forward direction of the inspection robot, transmit the images to the local central processor for image preprocessing, and perform dynamic obstacle detection by analyzing the image data. The dynamic obstacle detection process is as follows: Perform grayscale processing on the image, analyze whether there is an obstacle scene in the image. If there is an obstacle scene, calculate the position of the obstacle, extract the spatial position of the marked static obstacle. If it coincides with the position of the obstacle, output the detection result as no dynamic obstacle detected; if the position of the static obstacle does not coincide with the position of the obstacle, output the detection result as dynamic obstacle detected.

[0080] Wherein the vision sensor includes a first binocular camera and a second binocular camera. The first binocular camera is used to collect images directly in front of the inspection robot. The second binocular camera is located above the inspection robot and is used to collect images in front of the inspection robot. And the acquisition direction of the first binocular camera and the acquisition direction of the second binocular camera form an angle less than ninety degrees.

[0081] Step S3 includes:

[0082] When no dynamic obstacle is detected, obtain the preset inspection path, and the inspection robot moves along the preset inspection path and executes corresponding inspection instructions on the equipment to be inspected passed by to complete the inspection task.

[0083] When a dynamic obstacle is detected, obtain the current position coordinates of the inspection robot in real time and the distance between it and the dynamic obstacle. When the distance between the dynamic obstacle and the inspection robot is less than the threshold, trigger the instruction for the inspection robot to avoid. The inspection robot generates a correction path through the built-in algorithm logic to guide the inspection robot not to contact the dynamic obstacle.

[0084] Step S4 includes:

[0085] S41. When an abnormal situation of the equipment is detected, calculate the level parameter of the abnormal situation. The calculation process is as follows:

[0086] Obtain the fault type corresponding to the abnormal situation and the urgency corresponding to the fault type. Each type of fault type has a preset urgency. The urgency includes low level, medium level and high level. Each level of urgency corresponds to its own urgency weight respectively, and score each level of urgency, and use the scoring result as the urgency value of this level.

[0087] S42. Retrieve the total number of all abnormal situations detected in the current offline sensing mode and the number of equipment to be inspected that have been inspected. Divide the total number of abnormal situations by the number of equipment to be inspected that have been inspected to calculate the offline failure rate.

[0088] S43. Calculate the level parameter of the abnormal situation that occurs this time. The calculation process is: level parameter = (urgency value × urgency weight) + (offline failure rate × failure rate weight);

[0089] If the level parameter is greater than the set parameter threshold, the output is a high-level fault. If the level parameter is less than the set parameter threshold, the output is a low-level fault;

[0090] S44. If the output of S43 is a low-level fault, obtain the preset inspection path and inspection tasks that the inspection robot has not performed, and continue to perform the inspection tasks according to the unperformed preset inspection path;

[0091] If the output of S43 is a high-level fault, generate a distress instruction, screen the optimal network signal coverage area, guide the inspection robot to move towards the optimal network signal coverage area. After reaching the network signal coverage area, send a warning signal to the cloud platform; after receiving the response instruction from the cloud platform, the inspection robot continues to perform the inspection tasks on the equipment to be inspected that has not been detected according to the preset inspection path.

[0092] The process of screening the optimal network signal coverage area is as follows:

[0093] Analyze candidate area 1: Obtain the inspection status of the inspection robot during the inspection process. The inspection status includes the preset inspection mode and the offline sensing mode. Among them, the preset inspection mode is the state when the network communication of the inspection robot is normal; mark the inspection status of the inspection robot on the passed inspection path, divide the inspection path according to the inspection status, divide the inspection path passed in the preset inspection mode into network communication sections, and divide the inspection path passed in the offline sensing model into network abnormal sections; obtain the network communication section closest to the current position of the inspection robot as the target area, obtain the position coordinates of the target area, calculate the path length between the inspection robot and the target area through the coordinates, and calculate the distress duration 1 required to reach the target area according to the driving speed of the inspection robot. At the same time, obtain the failure rate 1 of encountering dynamic obstacles during the process of the inspection robot reaching the target area from the current position. The failure rate 1 is the number of times of encountering dynamic obstacles during the process of reaching the target area from the current position in the historical inspection records divided by the total number of historical inspections;

[0094] Analyze candidate area 2: Mark the unpassed preset inspection path as the target path, obtain the historical inspection records of the target path, mark the sections where the offline perception mode has not been switched in the historical inspection records as the historical network communication sections, select the section of the historical network communication section closest to the current position of the inspection robot as the target section, obtain the position coordinates of the target section, calculate the path length between the inspection robot and the target section through the coordinates, and calculate the distress duration 2 required to reach the target section according to the driving speed of the inspection robot. At the same time, obtain the failure rate 2 of encountering dynamic obstacles during the process of the inspection robot reaching the target section from the current position. The failure rate 2 is the number of times of encountering dynamic obstacles during the process of reaching the target section from the current position in the historical inspection records divided by the total number of historical inspections;

[0095] Analyze candidate area 3: Obtain the positions of each artificial base station marked on the target area map. The artificial base station is a service area fixedly set at a certain place and providing services for the inspection robot. Select the artificial base station closest to the current inspection robot as the target base station, obtain the position coordinates of the target base station, calculate the path length between the inspection robot and the target base station through the coordinates, calculate the distress duration 2 required to reach the target base station according to the driving speed of the inspection robot. At the same time, obtain the failure rate 3 of encountering dynamic obstacles during the process of the inspection robot reaching the target base station from the current position. The failure rate 3 is the number of times of encountering dynamic obstacles during the process of reaching the target base station from the current position in the historical inspection records divided by the total number of historical inspections;

[0096] S45. And calculate the grade value of each candidate area. The calculation process is as follows: Grade value A = distress duration A × weight 1 + failure rate A × weight 2 + area weight A; where grade value A ∈ {grade value of candidate area 1, grade value of candidate area 2, grade value of candidate area 3}; distress duration A ∈ {distress duration 1, distress duration 2, distress duration 3}; failure rate A ∈ {failure rate 1, failure rate 2, failure rate 3}; area weight A ∈ {area weight 1, area weight 2, area weight 3}. Each candidate area corresponds to an area weight, and the sum of area weight 1 + area weight 2 + area weight 3 is 1;

[0097] Output the candidate area with the highest grade value. The candidate area ∈ {candidate area 1, candidate area 2, candidate area 3}, generate a task execution strategy for the inspection robot to move to this candidate area, and when the communication is restored, upload the data detected with abnormal conditions to the cloud platform and send out a warning signal.

[0098] Embodiment 2: A control system based on an inspection robot. The control system includes:

[0099] Patrol Planning Module: Obtain the map of the target area and the patrol path planning data. The map of the target area contains the spatial position markings of static obstacles, and the patrol path planning data includes a preset patrol path and patrol tasks.

[0100] Mode Switching Module: When the network communication of the patrol robot is abnormal, switch to the offline perception mode, obtain the environmental information in the forward direction of the patrol robot through the vision sensor, and perform dynamic obstacle detection.

[0101] Operation Decision Module: Select an operation plan based on the detection results: If no dynamic obstacles are detected, the patrol robot performs patrol tasks along the preset patrol path; If dynamic obstacles are detected, generate a corrected path and send it to the patrol robot. The corrected path is to guide the patrol robot not to come into contact with dynamic obstacles.

[0102] Abnormality Judgment Module: When the patrol robot identifies that an abnormal situation has occurred in the device to be detected, generate a task execution strategy according to the level parameter of the abnormal situation:

[0103] Maintain the current patrol path and record abnormal data in case of a low-level fault;

[0104] Plan a network communication recovery path in case of a high-level fault, and guide the patrol robot to move towards the network signal coverage area;

[0105] Transmission Module: Record the offline operation data, which are all the instructions executed by the patrol robot in the offline perception mode; After the network is restored, synchronize the offline operation data to the remote server and update the local environment data.

[0106] The mode switching module includes:

[0107] Image Acquisition Unit: Used to acquire the images in the forward direction of the patrol robot, transmit the images to the local central processor for image preprocessing, and perform dynamic obstacle detection by analyzing the image data.

[0108] Dynamic Obstacle Analysis Unit: Perform grayscale processing on the images, analyze whether there are obstacle images in the images. If there are obstacle images, calculate the position of the obstacles, extract the spatial positions of the marked static obstacles. If they coincide with the positions of the obstacles, output the detection result as no dynamic obstacles detected; If the positions of the static obstacles do not coincide with the positions of the obstacles, output the detection result as dynamic obstacles detected.

[0109] Network Detection Unit: Real-time detect the network communication of the patrol robot. When it detects that the transmission speed of the network communication is lower than the transmission speed threshold and the delay time exceeds the time threshold, automatically switch to the offline perception mode.

[0110] The abnormality judgment module includes:

[0111] Level judgment unit: Obtain the fault type corresponding to the abnormal situation and the urgency corresponding to the fault type. Each type of fault type is preset with a corresponding urgency, and calculate the level parameter of the abnormal situation that occurs this time;

[0112] Output unit: If the level parameter of the abnormal situation corresponds to a low-level fault output, obtain the preset inspection path and inspection tasks that the inspection robot has not performed, and continue to perform the inspection tasks according to the unperformed preset inspection path;

[0113] If the level parameter of the abnormal situation corresponds to a high-level fault output, generate a distress instruction, screen the optimal network signal coverage area, guide the inspection robot to move towards the optimal network signal coverage area, and after reaching the network signal coverage area, send a warning signal to the cloud platform.

[0114] For those skilled in the art, it is obvious that the present invention is not limited to the details of the above exemplary embodiments, and without departing from the spirit or basic characteristics of the present invention, the present invention can be implemented in other specific forms. Therefore, from any point of view, the embodiments should be regarded as exemplary and non-limiting. The scope of the present invention is defined by the appended claims rather than the above description. Therefore, all changes falling within the meaning and scope of the equivalent elements of the claims are intended to be encompassed within the present invention. Any reference signs in the claims should not be regarded as limiting the claims involved.

Claims

1. An inspection method based on an inspection robot, characterized in that: Step S1: Obtain the target area map and inspection path planning data. The target area map contains the spatial position markings of static obstacles, and the inspection path planning data includes a preset inspection path and inspection tasks; Step S2: When the network communication of the inspection robot is abnormal, switch to the offline perception mode, and obtain the environmental information in the forward direction of the inspection robot through a visual sensor and perform dynamic obstacle detection; Step S3: Select an operation plan based on the detection result: If no dynamic obstacle is detected, the inspection robot performs inspection tasks along the preset inspection path; If a dynamic obstacle is detected, a corrected path is generated and sent to the inspection robot. The corrected path is to guide the inspection robot not to contact the dynamic obstacle; Step S4: When the inspection robot identifies that an abnormal situation occurs in the device to be inspected, generate a task execution strategy according to the level parameter of the abnormal situation: In case of a low-level fault, maintain the current inspection path and record the abnormal data; In case of a high-level fault, plan a network communication restoration path to guide the inspection robot to move towards the network signal coverage area; Step S5: Record the offline operation data. The offline operation data is all instructions executed by the inspection robot in the offline perception mode; after the network is restored, synchronize the offline operation data to the remote server and update the local environment data.

2. The inspection method based on the inspection robot according to claim 1, wherein: The step S1 includes: S11: Mark the area responsible for inspection by the inspection robot as the target environment, periodically collect images of the target area through an image acquisition device and generate a target area map, establish a three-dimensional coordinate system, and mark the spatial positions of static obstacles in the target area map. The static obstacles are certain items fixedly distributed at a certain place on the inspection path; S12: Input the inspection start point and inspection end point, mark them on the target area map, generate a path set connecting the start point to the end point, select the shortest path in the path set as the preset inspection path, and formulate inspection tasks according to the devices to be inspected passed by the preset inspection path. The inspection tasks are inspection instructions for the devices to be inspected.

3. The inspection method based on an inspection robot according to claim 1, wherein: Step S2 includes: Real-time detect the network communication of the inspection robot. When it is detected that the transmission speed of the network communication is lower than the transmission speed threshold and the delay time exceeds the time threshold, automatically switch to the offline perception mode. In the offline perception mode: Start the visual sensor to collect images in the forward direction of the inspection robot, transmit the images to the local central processor for image preprocessing, and perform dynamic obstacle detection by analyzing the image data. The dynamic obstacle detection process is as follows: perform grayscale processing on the image, analyze whether there is an obstacle image in the image. If there is an obstacle image, calculate the position of the obstacle, extract the spatial positions of the marked static obstacles. If it coincides with the position of the obstacle, output the detection result as no dynamic obstacle detected; if the position of the static obstacle does not coincide with the position of the obstacle, output the detection result as a dynamic obstacle detected; The visual sensor includes a first binocular camera and a second binocular camera. The first binocular camera is used to collect images directly in front of the inspection robot, and the second binocular camera is located above the inspection robot and is used to collect images in front of the inspection robot. The collection direction of the first binocular camera forms an angle less than 90 degrees with the collection direction of the second binocular camera.

4. The inspection method based on the inspection robot according to claim 1, characterized in that: Step S3 includes: When no dynamic obstacle is detected, obtain a preset inspection path, and the inspection robot moves along the preset inspection path and executes corresponding inspection instructions on the devices to be detected passed by, completing the inspection task; When a dynamic obstacle is detected, obtain the current position coordinates of the inspection robot in real time and the distance between it and the dynamic obstacle. When the distance between the dynamic obstacle and the inspection robot is less than the threshold, trigger an instruction for the inspection robot to avoid. The inspection robot generates a corrected path through the built-in algorithm logic to guide the inspection robot not to contact the dynamic obstacle.

5. The inspection method based on an inspection robot according to claim 1, characterized in that: Step S4 includes: S41. When an abnormal situation of the device is detected, calculate the level parameter of the abnormal situation. The calculation process is as follows: Obtain the fault type corresponding to the abnormal situation and the urgency corresponding to the fault type. Each type of fault type has a preset urgency, and the urgency includes low level, medium level, and high level. Each level of urgency corresponds to its own urgency weight respectively, and score each level of urgency, and use the scoring result as the urgency value of this level; S42. Retrieve the total number of all abnormal situations detected in the current offline sensing mode and the number of devices to be detected that have completed the inspection. Divide the total number of abnormal situations by the number of devices to be detected that have completed the inspection to calculate the offline failure rate; S43. Calculate the level parameter of the current abnormal situation. The calculation process is: level parameter = (urgency value × urgency weight) + (offline failure rate × failure rate weight); If the level parameter is greater than the set parameter threshold, output it as a high-level fault. If the level parameter is less than the set parameter threshold, output it as a low-level fault; S44. If the output of S43 is a low-level fault, obtain the preset inspection path and inspection task that the inspection robot has not performed, and continue to perform the inspection task according to the unperformed preset inspection path; If the output of S43 is a high-level fault, generate a distress instruction, screen the optimal network signal coverage area, guide the inspection robot to move towards the optimal network signal coverage area. After reaching the network signal coverage area, send a warning signal to the cloud platform; after receiving the response instruction from the cloud platform, the inspection robot continues to perform the inspection task on the devices to be detected that have not been detected according to the preset inspection path.

6. The inspection method based on an inspection robot according to claim 5, characterized in that: The process of screening the optimal network signal coverage area is as follows: Analyze candidate area 1: Obtain the inspection state of the inspection robot during the inspection process. The inspection state includes a preset inspection mode and an offline sensing mode, where the preset inspection mode is the state when the network communication of the inspection robot is normal; Mark the inspection status of the inspection robot on the passed inspection path, divide the inspection path according to the inspection status, divide the inspection path passed under the preset inspection mode into network communication sections, and divide the inspection path passed under the offline perception model into network anomaly sections; Obtain the network communication section closest to the current position of the inspection robot as the target area, obtain the position coordinates of the target area, calculate the path length between the inspection robot and the target area through the coordinates, and calculate the distress time one required to reach the target area according to the driving speed of the inspection robot. At the same time, obtain the failure rate one of encountering dynamic obstacles during the process of the inspection robot moving from the current position to the target area. The failure rate one is the number of times of encountering dynamic obstacles during the process of moving from the current position to the target area in the historical inspection records divided by the total number of historical inspections; Analyze the candidate area two: Mark the unpassed preset inspection path as the target path, obtain the historical inspection records of the target path, mark the section that has not switched to the offline perception mode in the historical inspection records as the historical network communication section, select the historical network communication section closest to the current position of the inspection robot as the target section, obtain the position coordinates of the target section, calculate the path length between the inspection robot and the target section through the coordinates, and calculate the distress time two required to reach the target section according to the driving speed of the inspection robot. At the same time, obtain the failure rate two of encountering dynamic obstacles during the process of the inspection robot moving from the current position to the target section. The failure rate two is the number of times of encountering dynamic obstacles during the process of moving from the current position to the target section in the historical inspection records divided by the total number of historical inspections; Analyze the candidate area three: Obtain the positions of each artificial base station marked on the target area map. The artificial base station is a service area fixedly set at a certain place and providing services for the inspection robot. Select the artificial base station closest to the current inspection robot as the target base station, obtain the position coordinates of the target base station, calculate the path length between the inspection robot and the target base station through the coordinates, calculate the distress time two required to reach the target base station according to the driving speed of the inspection robot. At the same time, obtain the failure rate three of encountering dynamic obstacles during the process of the inspection robot moving from the current position to the target base station. The failure rate three is the number of times of encountering dynamic obstacles during the process of moving from the current position to the target base station in the historical inspection records divided by the total number of historical inspections; S45. Calculate the grade value of each candidate area, and the calculation process is: Grade value A = distress time A × weight one + failure rate A × weight two + area weight A; Where the grade value A ∈ {grade value of candidate area one, grade value of candidate area two, grade value of candidate area three}; distress time A ∈ {distress time one, distress time two, distress time three}; failure rate A ∈ {failure rate one, failure rate two, failure rate three}; area weight A ∈ {area weight one, area weight two, area weight three}, and each candidate area corresponds to an area weight; Output the candidate area with the highest level value, where the candidate area ∈ {Candidate Area One, Candidate Area Two, Candidate Area Three}, generate a task execution strategy for the inspection robot to move to this candidate area, and when the communication is restored, upload the data of the detected abnormal situation to the cloud platform and send out a warning signal.

7. A control system based on an inspection robot, which is applied to the inspection method based on an inspection robot according to any one of claims 1-6, and is characterized in that: The control system includes: Inspection Planning Module: Obtain the target area map and inspection path planning data. The target area map contains the spatial position markings of static obstacles, and the inspection path planning data includes a preset inspection path and inspection tasks; Mode Switching Module: When the network communication of the inspection robot is abnormal, switch to the offline perception mode, obtain the environmental information in the forward direction of the inspection robot through the vision sensor, and perform dynamic obstacle detection; Operation Decision Module: Select an operation plan based on the detection results: If no dynamic obstacles are detected, the inspection robot performs inspection tasks along the preset inspection path; If dynamic obstacles are detected, generate a corrected path and send it to the inspection robot. The corrected path is to guide the inspection robot not to contact the dynamic obstacles; Abnormality Judgment Module: When the inspection robot identifies an abnormal situation in the device to be detected, generate a task execution strategy according to the level parameter of the abnormal situation: Maintain the current inspection path and record abnormal data in case of a low-level fault; Plan a network communication restoration path in case of a high-level fault to guide the inspection robot to move towards the network signal coverage area; Transmission Module: Record offline operation data, which are all instructions executed by the inspection robot in the offline perception mode; Synchronize the offline operation data to the remote server after the network is restored and update the local environment data.

8. The control system based on the inspection robot according to claim 7, wherein: The mode switching module includes: Image Acquisition Unit: Used to acquire images in the forward direction of the inspection robot, transmit the images to the local central processor for image preprocessing, and perform dynamic obstacle detection by analyzing the image data; Dynamic Obstacle Analysis Unit: Process the image in grayscale, analyze whether there is an obstacle image in the image. If there is an obstacle image, calculate the position of the obstacle, extract the spatial position of the marked static obstacle. If it coincides with the position of the obstacle, output the detection result as no dynamic obstacle detected; If the position of the static obstacle does not coincide with the position of the obstacle, output the detection result as dynamic obstacle detected; Network Detection Unit: Real-time detect the network communication of the inspection robot. When the detected network communication transmission speed is lower than the transmission speed threshold and the delay time exceeds the time threshold, automatically switch to the offline perception mode.

9. The control system based on the inspection robot according to claim 7, wherein: The abnormality judgment module includes: Level Judgment Unit: Obtain the fault type corresponding to this abnormal situation and the urgency corresponding to this fault type. Each type of fault type has a preset urgency, and calculate the level parameter of the abnormal situation that occurs this time; Output Unit: If the level parameter of the abnormal situation corresponds to a low-level fault output, obtain the preset inspection path and inspection tasks that the inspection robot has not performed, and continue to perform the inspection tasks according to the unperformed preset inspection path; If the level parameter of the abnormal situation corresponds to a high-level fault output, a distress instruction is generated, the optimal network signal coverage area is screened, and the inspection robot is guided to move towards the optimal network signal coverage area. After reaching the network signal coverage area, a warning signal is sent to the cloud platform.

Images