Multi-task collaboration method, device, equipment and storage medium for inspection robots

Abstract

The present application discloses a multi-task collaboration method, apparatus, equipment, and storage medium for an inspection robot, and relates to the technical field of intelligent inspection robots. The method of the present application includes: acquiring multi-sensor data, wherein the multi-sensor data includes visible light image data, infrared thermal imaging data, and gas concentration data; processing the multi-sensor data according to a Kalman filtering strategy to obtain target feature data; judging the target feature data according to a preset task scheduling strategy to obtain a danger level; and controlling the robot to perform corresponding inspection tasks according to the danger level, wherein the inspection tasks include fire suppression, temperature anomaly warning, and execution of a preset inspection path. The present application effectively solves the problem of multi-task collaborative processing by intelligently distinguishing task priorities and quickly responding to emergencies, thereby improving the safety and inspection efficiency of high-risk industrial scenarios.

Description

Technical Field

[0001] The present application relates to the technical field of intelligent inspection robots, and in particular to a multi-task collaboration method, apparatus, equipment and storage medium for inspection robots. Background Art

[0002] With the continuous advancement of industrial automation and intelligence, intelligent inspection robots are increasingly being used in high-risk industrial scenarios such as the petrochemical industry, electric power, and other fields. By replacing manual inspection tasks, these robots effectively reduce personnel safety risks and improve inspection efficiency and accuracy. However, existing inspection robots still have significant shortcomings when handling multiple tasks and emergency situations. On the one hand, traditional inspection robots often use a fixed polling mechanism to handle tasks, and are unable to dynamically adjust priorities based on the urgency of the task. This leads to delayed responses in emergencies such as fires, potentially missing the optimal time to respond, and increasing the risk of accidents. On the other hand, while existing multi-machine collaborative solutions are designed to improve inspection efficiency, in practice they often face communication delays and equipment conflicts, which affect the effectiveness of collaborative work. Furthermore, single-machine inspection robots lack intelligent multi-tasking collaborative processing capabilities when faced with complex and changing industrial environments, making it difficult to simultaneously respond to multiple potential threats.

[0003] Therefore, how to improve the safety and inspection efficiency of inspection robots when facing multi-task conflicts is a problem that needs to be solved urgently. Summary of the Invention

[0004] The main purpose of this application is to provide a multi-task collaboration method, device, equipment and storage medium for an inspection robot, aiming to solve the technical problem of how to improve the safety and inspection efficiency of the inspection robot when facing multi-task conflicts.

[0005] To achieve the above objectives, the present application proposes a multi-task collaboration method for an inspection robot, the method comprising:

[0006] Acquiring multi-sensor data, wherein the multi-sensor data includes visible light image data, infrared thermal imaging data, and gas concentration data;

[0007] Processing the multi-sensor data according to a Kalman filter strategy to obtain target feature data;

[0008] Determine the target feature data according to a preset task scheduling strategy to obtain a danger level;

[0009] The robot is controlled to perform corresponding inspection tasks according to the danger level, and the inspection tasks include fire suppression, temperature anomaly warning and execution of preset inspection paths.

[0010] In one embodiment, the step of determining the target characteristic data according to a preset task scheduling strategy to obtain a danger level includes:

[0011] Obtaining a preset lower explosion limit and a preset temperature threshold according to a preset task scheduling strategy;

[0012] Obtaining target gas concentration and target area temperature according to the target characteristic data;

[0013] When the target gas concentration is greater than or equal to the preset lower explosion limit and the target area temperature is greater than or equal to the preset temperature threshold, determining the hazard level to be the first hazard level;

[0014] When the temperature of the target area is greater than or equal to the preset temperature threshold, determining the danger level to be the second danger level;

[0015] When the target gas concentration is less than the preset lower explosion limit and the target area temperature is less than the preset temperature threshold, the hazard level is determined to be the third hazard level, the first hazard level is greater than the second hazard level, and the second hazard level is greater than the third hazard level.

[0016] In one embodiment, the step of controlling the robot to perform a corresponding inspection task according to the danger level includes:

[0017] When the danger level is the first danger level, an interrupt signal is generated to control the robot to stop the current task, and a first navigation path to reach the fire area is generated according to a preset first path planning algorithm;

[0018] The robot is controlled to move to the fire extinguishing point through the first navigation path, and the water spray device of the robot is activated to perform fire suppression operations.

[0019] In one embodiment, the step of controlling the robot to perform a corresponding inspection task according to the danger level includes:

[0020] When the danger level is the second danger level, generating pan / tilt control parameters and lens control parameters according to a preset dynamic adjustment strategy, and obtaining current coordinates;

[0021] Recollecting visible light image data and infrared thermal imaging data according to the pan / tilt control parameters and the lens control parameters, and transmitting the visible light image data, the infrared thermal imaging data and the current coordinates to the backend to obtain an audit result;

[0022] When the audit result is normal, the inspection task is performed according to the preset inspection path;

[0023] When the audit result is abnormal, the second danger level is raised to the first danger level so that the robot performs a fire suppression operation.

[0024] In one embodiment, the step of controlling the robot to perform a corresponding inspection task according to the danger level includes:

[0025] When the danger level is the third danger level, controlling the robot to perform the inspection task according to the preset inspection path;

[0026] During the inspection task, when new multi-sensor data is received, the process returns to the step of performing data targeting on the multi-sensor data according to the Kalman filtering strategy to obtain target feature data, and obtains an updated danger level.

[0027] In one embodiment, the step of processing the multi-sensor data according to the Kalman filtering strategy to obtain target feature data includes:

[0028] Preprocessing the visible light image data, infrared thermal imaging data, and gas concentration data to obtain target visible light image data, initial infrared thermal imaging data, and target gas concentration data;

[0029] performing anti-reflection processing on the initial infrared thermal imaging data according to the target visible light image data to obtain target infrared thermal imaging data;

[0030] The target infrared thermal imaging data and the target gas concentration data are filtered according to a Kalman filtering strategy to obtain target feature data.

[0031] In one embodiment, after the step of controlling the robot to perform the corresponding inspection task according to the hazard level, the method further includes:

[0032] When the robot completes the inspection task or the battery level is lower than a preset threshold, a second navigation path to the charging point is generated according to a preset second path planning algorithm;

[0033] The robot is controlled by the second navigation path to move to a charging point for charging.

[0034] In addition, to achieve the above objectives, the present application also proposes a multi-task collaboration device for an inspection robot, the device comprising:

[0035] A data acquisition module is used to acquire multi-sensor data, wherein the multi-sensor data includes visible light image data, infrared thermal imaging data, and gas concentration data;

[0036] A data processing module is used to process the multi-sensor data according to a Kalman filter strategy to obtain target feature data;

[0037] A danger determination module is used to determine the danger level of the target feature data according to a preset task scheduling strategy;

[0038] The task coordination module is used to control the robot to perform corresponding inspection tasks according to the danger level. The inspection tasks include fire suppression, temperature anomaly warning and execution of preset inspection paths.

[0039] In addition, to achieve the above-mentioned purpose, the present application also proposes a multi-task collaboration device for a patrol robot, which includes: a memory, a processor, and a computer program stored on the memory and runnable on the processor, and the computer program is configured to implement the steps of the multi-task collaboration method of the patrol robot as described above.

[0040] In addition, to achieve the above-mentioned purpose, the present application also proposes a storage medium, which is a computer-readable storage medium. A computer program is stored on the storage medium, and when the computer program is executed by the processor, the steps of the multi-task collaboration method of the inspection robot as described above are implemented.

[0041] In addition, to achieve the above-mentioned purpose, the present application also provides a computer program product, which includes a computer program, and when the computer program is executed by a processor, it implements the steps of the multi-task collaboration method of the inspection robot as described above.

[0042] The present application provides a multi-task collaboration method for an inspection robot, the method of the present application includes: acquiring multi-sensor data, the multi-sensor data including visible light image data, infrared thermal imaging data and gas concentration data; processing the multi-sensor data according to a Kalman filtering strategy to obtain target feature data; judging the target feature data according to a preset task scheduling strategy to obtain a danger level; controlling the robot to perform corresponding inspection tasks according to the danger level, the inspection tasks including fire suppression, temperature anomaly warning and execution of preset inspection paths. In summary, the present application effectively solves the problem of multi-task collaborative processing by intelligently distinguishing task priorities and quickly responding to emergencies, thereby improving the safety and inspection efficiency of high-risk industrial scenarios. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0044] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0045] Figure 1 A flowchart illustrating a first embodiment of a multi-task collaboration method for an inspection robot according to the present application;

[0046] Figure 2 A flowchart of the second embodiment of the multi-task collaboration method for the inspection robot of this application is provided;

[0047] Figure 3 This is a schematic diagram of the entire process of an embodiment of a multi-task collaboration method for an inspection robot of the present application;

[0048] Figure 4 This is a schematic diagram of the module structure of the multi-task collaborative device of the inspection robot according to an embodiment of the present application;

[0049] Figure 5 This is a schematic diagram of the equipment structure of the hardware operating environment involved in the multi-task collaboration method of the inspection robot in the embodiment of the present application.

[0050] The purpose, features and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0051] It should be understood that the specific embodiments described herein are merely used to explain the technical solutions of the present application and are not intended to limit the present application.

[0052] In order to better understand the technical solution of the present application, a detailed description will be given below in conjunction with the accompanying drawings and specific implementation methods.

[0053] The main solution of the embodiment of the present application is: obtaining multi-sensor data, which includes visible light image data, infrared thermal imaging data and gas concentration data; processing the multi-sensor data according to the Kalman filtering strategy to obtain target feature data; judging the target feature data according to the preset task scheduling strategy to obtain the danger level; controlling the robot to perform corresponding inspection tasks according to the danger level, and the inspection tasks include fire suppression, temperature anomaly warning and execution of preset inspection paths.

[0054] With the continuous advancement of industrial automation and intelligence, intelligent inspection robots are increasingly being used in high-risk industrial scenarios, such as the petrochemical and power energy sectors. By replacing human operators in performing inspection tasks, these robots effectively reduce safety risks for personnel and improve inspection efficiency and accuracy. However, existing inspection robots still have significant shortcomings when handling multiple tasks and emergencies. For one thing, traditional inspection robots often use a fixed polling mechanism to handle tasks, unable to dynamically adjust priorities based on task urgency. This leads to delayed responses in emergencies such as fires, potentially missing the optimal opportunity to respond, and increasing the risk of accidents. Furthermore, while existing multi-robot collaborative solutions aim to improve inspection efficiency, they often face communication delays and device conflicts in practice, hindering effective collaboration. Furthermore, single-robot inspection robots lack intelligent multi-tasking collaborative processing capabilities in complex and changing industrial environments, making it difficult to simultaneously respond to multiple potential threats. Therefore, improving the safety and efficiency of inspection robots in the face of multi-tasking conflicts is a pressing issue.

[0055] This application effectively solves the problem of multi-task collaborative processing by intelligently distinguishing task priorities and quickly responding to emergencies, thereby improving the safety and inspection efficiency of high-risk industrial scenarios.

[0056] It should be noted that the execution entity of this embodiment can be a multi-task collaborative system of an inspection robot, a computing service device with data processing, network communication, and program execution functions, or an electronic device capable of implementing the multi-task collaborative functions of the inspection robot, etc. This embodiment is not specifically limited to this. The following uses the multi-task collaborative system of an inspection robot as an example to illustrate this embodiment and the following embodiments.

[0057] Based on this, the embodiment of the present application provides a multi-task collaboration method for an inspection robot, referring to Figure 1 , Figure 1 This is a flow chart of the first embodiment of the multi-task collaboration method of the inspection robot of the present application.

[0058] In this embodiment, the multi-task collaboration method of the inspection robot includes steps S10 to S40:

[0059] Step S10: Acquire multi-sensor data, where the multi-sensor data includes visible light image data, infrared thermal imaging data, and gas concentration data.

[0060] It should be noted that inspection robots are equipped with multiple sensors, including visible light cameras, infrared thermal imaging sensors, and gas concentration detection sensors. Multi-sensor data refers to various types of data, including images, temperature, and gas concentration, collected by these devices.

[0061] Additionally, it should be noted that during the inspection process, the inspection robot's visible light camera collects real-time image data of the inspection area. This image data is used to identify general conditions in the inspection area, such as the appearance, color, and shape of objects. Infrared thermal imaging sensors continuously detect infrared radiation from the surrounding environment and convert it into infrared thermal imaging data. This data reflects the temperature distribution on the surface of objects, helping to identify areas of abnormal temperature, such as potential overheating equipment or fire sources. Gas concentration detection sensors monitor specific gas concentrations (such as combustible and toxic gases) within the inspection area in real time. Understandably, this data is primarily used to detect abnormally high temperature and explosive areas, such as overheating equipment, potential fire sources, and combustible gas leaks.

[0062] Step S20: Processing the multi-sensor data according to a Kalman filter strategy to obtain target feature data.

[0063] It should be noted that target feature data refers to a data set obtained by processing multi-sensor data using a Kalman filter strategy, which more accurately and comprehensively reflects the characteristics of objects and the environment within the inspection area. In this embodiment, this data includes temperature characteristics (such as average temperature), gas concentration characteristics (such as concentration values) of the inspection area, and characteristic information such as the position and size of objects in the visible light image. Specifically, in this step, the system denoises the visible light image for clarity, performs temperature correction on the infrared thermal imaging data to eliminate sensor errors, and performs a sliding average filter on the gas concentration data to reduce data fluctuations. These processed data are then fused using a Kalman filter strategy to generate the target feature data.

[0064] In a feasible implementation manner, the step S20 specifically includes:

[0065] Step S201: pre-processing the visible light image data, infrared thermal imaging data and gas concentration data to obtain target visible light image data, initial infrared thermal imaging data and target gas concentration data.

[0066] It should be noted that target visible light image data refers to visible light image data that, after pre-processing operations such as denoising and image enhancement, more clearly and accurately reflects visual information such as the appearance, color, and shape of objects within the inspection area. Initial infrared thermal imaging data refers to the infrared thermal imaging data obtained after temperature correction and smoothing, which has initially eliminated sensor errors and random noise, but has not yet undergone anti-reflection processing. Target gas concentration data refers to the more stable and accurate gas concentration data obtained after pre-processing operations such as sliding average filtering on the raw gas concentration data.

[0067] It's also important to note that visible light image data is first denoised. During the inspection process, visible light cameras may be affected by factors such as ambient lighting fluctuations and sensor noise, resulting in noise points in the image. Therefore, a median filter algorithm is used. For each pixel in the image, the median value of all pixels in its neighborhood is used as the new pixel value, effectively removing salt and pepper noise and other artifacts. Image enhancement is then performed using histogram equalization to adjust the image's grayscale distribution and enhance contrast, making objects within the inspection area more clearly visible and producing the target visible light image data. During data acquisition, infrared thermal imaging sensors are affected by factors such as their own thermal noise and ambient temperature interference. Temperature correction is performed on the infrared thermal imaging data. Using a pre-calibrated temperature-voltage curve, the sensor's output voltage is converted into an accurate temperature value, eliminating inherent sensor errors. A Gaussian filter algorithm is then used to smooth the image, reducing random noise and producing the initial infrared thermal imaging data. During measurement, gas concentration sensors may be affected by factors such as ambient airflow and sensor zero drift, resulting in fluctuations and deviations in the measured data. Gas concentration data requires a sliding average filter, which takes multiple consecutive measurements and calculates their average as the current gas concentration value. This reduces random fluctuations in the data and allows you to obtain the target gas concentration data.

[0068] Step S202: performing anti-reflection processing on the initial infrared thermal imaging data according to the target visible light image data to obtain target infrared thermal imaging data.

[0069] It should be noted that in this step, the system will determine the boundaries and surface features of the objects in the inspection area based on the target visible light image data. Through image segmentation algorithms, such as edge detection-based segmentation methods, the contour information of the object is extracted from the target visible light image data, and the boundary position of the object is clarified. Then, based on the boundary and surface features of the object, anti-reflection processing is performed on the corresponding area in the initial infrared thermal imaging data. For areas with strong reflection on the surface of the object, false high-temperature signals will be generated in the infrared thermal imaging data. By analyzing the surface material, smoothness and other information of the object in the target visible light image data, the corresponding algorithm is used to suppress the reflection interference in the initial infrared thermal imaging data. For example, for a smooth metal surface, strong reflection will be generated, forming a false high-temperature area in the infrared thermal imaging data. By analyzing the characteristics of the metal surface in the target visible light image data, the high-temperature signal of this area in the infrared thermal imaging data is corrected to reduce the impact of reflection interference and obtain the target infrared thermal imaging data.

[0070] It can be understood that anti-reflection processing refers to the process of suppressing or correcting interference signals generated by surface reflections in the initial infrared thermal imaging data by analyzing the boundaries and surface features of the target object in the visible light image data. The goal is to eliminate the impact of reflection interference on the accuracy of infrared thermal imaging data, ensuring that the infrared thermal imaging data more accurately reflects the temperature of the object. Target infrared thermal imaging data refers to infrared thermal imaging data that has undergone anti-reflection processing, eliminating reflection interference and more accurately and realistically reflecting the temperature distribution of objects within the inspection area.

[0071] Step S203: filtering the target infrared thermal imaging data and the target gas concentration data according to a Kalman filtering strategy to obtain target feature data.

[0072] It should be noted that in this step, the system establishes a system state model and observation model for the target infrared thermal imaging data and target gas concentration data. For the target infrared thermal imaging data, the surface temperature distribution is used as the system state, and the infrared thermal imaging sensor's measurements are used as the observations. For the target gas concentration data, the concentration of a specific gas in the environment is used as the system state, and the gas concentration sensor's measurements are used as the observations. A recursive Kalman filter algorithm is then used for calculations. In the prediction step, the current state is predicted based on the previous state estimate and the system dynamic model. In the update step, the predicted state is corrected using the current observations to obtain a more accurate state estimate. Through repeated iterations of the prediction and update steps, the target infrared thermal imaging data and target gas concentration data are fused and filtered to obtain target feature data. This target feature data includes information such as the average temperature within the inspection area and the concentration trends and average concentrations of specific gases (such as flammable and explosive gases).

[0073] Step S30: determining the target characteristic data according to a preset task scheduling strategy to obtain a danger level.

[0074] It should be noted that the danger level refers to the classification used to measure the degree of danger of the inspection area or the urgency of the task after judging the target feature data according to the preset task scheduling strategy. In this embodiment, the danger level is divided into multiple levels. For example, the first danger level indicates that there is a serious danger and immediate measures need to be taken; the second danger level indicates that there is a certain danger and needs to be closely monitored and handled in a timely manner; the third danger level indicates that the inspection area is in a safe state. The preset task scheduling strategy refers to a pre-set three-level task priority scheduling strategy, which is used to guide the robot to perform corresponding inspection tasks according to different danger levels. Specifically, in this step, the system will judge the danger level of the inspection area based on the target feature data and the three-level task priority scheduling strategy to determine the danger level of the inspection area.

[0075] It can be understood that the purpose of this step is to accurately judge the degree of danger of the inspection area based on the target feature data and the preset task scheduling strategy, providing a basis for how the subsequent robot performs inspection tasks when faced with multiple tasks being executed simultaneously.

[0076] In a feasible implementation manner, the step S30 specifically includes:

[0077] Step S301: obtaining a preset lower explosion limit and a preset temperature threshold according to a preset task scheduling strategy.

[0078] It should be noted that the preset lower explosion limit refers to the lowest concentration of combustible gas that can explode when mixed with air. The preset temperature threshold is a temperature limit set based on industrial safety requirements. When the ambient temperature exceeds this limit, dangerous situations such as fire may occur.

[0079] Additionally, it should be noted that in this step, the corresponding preset LEL (Lower Explosive Limit) and preset temperature threshold are extracted from the preset task scheduling strategy database based on the specific high-risk industrial scenarios in which the inspection robot is used, such as petrochemical, electric power, and other scenarios. These preset values ​​are determined based on a large amount of experimental data, industry standards, and safety regulations. For example, in the petrochemical scenario, for common combustible gases such as methane, the preset lower explosion limit is usually set to 5%LEL (for ease of explanation, to distinguish it from the ≥LEL50% scenario mentioned below; the actual preset value is determined based on the specific gas and safety requirements); the preset temperature threshold is set based on the normal operating temperature range of the equipment and the temperature threshold that may cause a fire.

[0080] Step S302: Obtain target gas concentration and target area temperature according to the target characteristic data.

[0081] It's important to note that the system extracts target gas concentration and target area temperature from target feature data processed using the Kalman filter strategy. Target gas concentration refers to the total concentration of specific combustible gases within the inspection area, such as methane and hydrogen; target area temperature refers to the average temperature within the inspection area. This data is collected by the multi-sensor fusion module and processed through preprocessing, anti-reflection processing, and Kalman filtering, resulting in high accuracy and reliability.

[0082] Step S303: When the target gas concentration is greater than or equal to the preset lower explosion limit and the target area temperature is greater than or equal to the preset temperature threshold, determining that the hazard level is the first hazard level.

[0083] It's important to note that in this step, the system compares the extracted target gas concentration with the preset lower explosion limit (LEL), and the target area temperature with a preset temperature threshold. When the target gas concentration (i.e., the total concentration of combustible gases) is greater than or equal to the preset lower explosion limit (e.g., LEL 50%), and the target area temperature is greater than or equal to the preset temperature threshold (e.g., 150°C), the inspection area is determined to be at the first hazard level. This step is designed to quickly identify the extremely dangerous situation of both high concentrations of combustible gases and high temperatures within the inspection area, promptly issuing the highest-level hazard alert so that emergency measures can be taken to prevent accidents.

[0084] Step S304: When the temperature of the target area is greater than or equal to the preset temperature threshold, determining the danger level to be the second danger level.

[0085] It should be noted that in this step, if the target area temperature is greater than or equal to a preset temperature threshold (such as 150°C), but the target gas concentration (i.e., the total concentration of combustible gases) is less than the preset lower explosion limit (LEL 50%), the inspection area is determined to be at the second hazard level. This step is used to identify situations where the temperature is abnormally high despite the absence of high concentrations of combustible gases, indicating a fire hazard or other abnormal condition in the area that requires prompt attention and action.

[0086] In addition, it should be noted that the second danger level indicates that there is an abnormal temperature rise in the inspection area. Although the direct conditions for causing fire or explosion have not yet been reached, corresponding measures need to be taken to prevent the situation from worsening.

[0087] Step S305: When the target gas concentration is less than the preset lower explosion limit and the target area temperature is less than the preset temperature threshold, the hazard level is determined to be the third hazard level, the first hazard level is greater than the second hazard level, and the second hazard level is greater than the third hazard level.

[0088] It should be noted that in this step, when the target gas concentration (i.e., the total concentration of combustible gases) is less than the preset lower explosion limit (e.g., LEL 50%) and the target area temperature is less than a preset temperature threshold (e.g., 150°C), the inspection area is determined to be at the third hazard level. The hazard level decreases as the number increases, with the third hazard level being the lowest, indicating that the inspection area is relatively safe. However, regular inspections are still required to ensure timely detection of potential safety hazards.

[0089] Step S40: Control the robot to perform corresponding inspection tasks according to the danger level, wherein the inspection tasks include fire suppression, temperature anomaly warning, and execution of a preset inspection path.

[0090] It should be noted that inspection tasks refer to specific operations performed by the robot based on different danger levels, including fire suppression, temperature anomaly warning, and executing pre-set inspection routes. These tasks are designed to ensure the safety of the inspection area and to take timely measures when dangerous situations are discovered. A fire suppression task, as it is understood, involves the robot using its equipped fire extinguishing equipment to extinguish or control the source of a fire in the inspection area (i.e., when the danger level is high). A temperature anomaly warning task involves the robot alerting relevant personnel by issuing alarm signals and recording abnormal information when temperature anomalies occur in the inspection area (i.e., when the danger level is relatively low). Executing pre-set inspection routes involves the robot performing routine inspections of equipment and the environment within the inspection area according to pre-set inspection routes and inspection points.

[0091] In a feasible implementation manner, after step S40, the method further includes:

[0092] Step S50: When the robot completes the inspection task or the battery level is lower than a preset threshold, a second navigation path to the charging point is generated according to a preset second path planning algorithm.

[0093] It should be noted that when the inspection robot completes all pre-set inspection tasks or detects that its battery level falls below a pre-set safety threshold, it activates a pre-set secondary path planning algorithm. This algorithm calculates and generates an optimal navigation path (the secondary navigation path) based on the robot's current location, the location of the charging point, and environmental map information, guiding the robot safely and efficiently to the charging point.

[0094] In addition, it should be noted that the preset second path planning algorithm in this embodiment specifically refers to the Dijkstra algorithm. The Dijkstra algorithm is a classic algorithm for calculating the shortest path from a single source in a weighted graph, which can efficiently find the shortest path from a starting point to an end point.

[0095] Step S60: Control the robot to move to a charging point for charging via the second navigation path.

[0096] It's important to note that once the secondary navigation path is generated, the inspection robot immediately activates its navigation system and moves along that path toward the charging point. During this movement, the robot continuously monitors for obstacles and hazardous areas along the path, adjusting its speed and direction accordingly to ensure safe arrival at the charging point. Upon arrival, the robot automatically docks with the charging equipment and begins charging.

[0097] This embodiment provides a multi-task collaboration method for an inspection robot, and the method of this embodiment includes: acquiring multi-sensor data, wherein the multi-sensor data includes visible light image data, infrared thermal imaging data, and gas concentration data; processing the multi-sensor data according to a Kalman filtering strategy to obtain target feature data; judging the target feature data according to a preset task scheduling strategy to obtain a danger level; and controlling the robot to perform corresponding inspection tasks according to the danger level, wherein the inspection tasks include fire suppression, temperature anomaly warning, and execution of a preset inspection path. In summary, this application effectively solves the problem of multi-task collaborative processing by intelligently distinguishing task priorities and quickly responding to emergencies, thereby improving the safety and inspection efficiency of high-risk industrial scenarios.

[0098] Based on the first embodiment of the present application, in the second embodiment of the present application, the same or similar contents as those in the above embodiment 1 can be referred to the above introduction and will not be described in detail later. Figure 2 and Figure 3 , Figure 2 This is a flow chart of the second embodiment of the multi-task collaboration method of the inspection robot of this application. Figure 3 This is a schematic diagram of the entire process of an embodiment of the multi-task collaboration method of the inspection robot of the present application. Step S40 specifically includes:

[0099] Step A10: When the danger level is the first danger level, an interrupt signal is generated to control the robot to stop the current task, and a first navigation path to reach the fire area is generated according to a preset first path planning algorithm.

[0100] It should be noted that an interrupt signal refers to a signal used to control the robot to immediately stop the current task and switch to emergency processing mode. The preset first path planning algorithm refers to an algorithm pre-programmed in the robot control system, which is used to generate an optimal navigation path based on the current position information and the target position information. In this embodiment, the algorithm is the A* algorithm, but other suitable path planning algorithms can also be selected according to actual needs. In this step, when the inspection robot determines that the inspection area is at the first danger level according to the preset task scheduling strategy, an interrupt signal is immediately generated. This interrupt signal is used to control the robot to immediately stop the currently executing task, regardless of whether the task is a preset inspection path or other low-priority task. Subsequently, the robot will call the preset first path planning algorithm (such as the A* algorithm), combine the current position information and the location information of the fire area, and generate an optimal first navigation path to ensure that the robot can reach the fire area quickly and accurately.

[0101] It is understandable that the purpose of this step is to ensure that when an extremely dangerous situation occurs, the inspection robot can respond quickly, interrupt the current task, and plan an efficient navigation path to reach the fire area as soon as possible for disposal.

[0102] Step A20: Control the robot to move to the fire extinguishing point through the first navigation path, and activate the robot's water spray device to perform fire suppression operations.

[0103] It should be noted that the water sprinkler refers to a fire extinguishing device installed on the inspection robot, including parts such as a water pump, a nozzle and a control system. When performing a fire suppression operation, the robot will adjust the water spray angle and flow rate according to the size and location of the fire to ensure the maximum fire extinguishing effect. Specifically, in this step, the inspection robot will control itself to move to the fire extinguishing point through the autonomous navigation system according to the generated first navigation path. During the movement, the robot will continuously monitor the situation in the fire area to ensure the accuracy and safety of the path. After arriving at the fire extinguishing point, the robot will immediately activate the water sprinkler, adjust the water spray angle and flow rate according to the size and location of the fire, and perform a fire suppression operation until the fire is under control or completely extinguished.

[0104] In a feasible implementation manner, the step S40 further includes:

[0105] Step B10: When the danger level is the second danger level, pan / tilt control parameters and lens control parameters are generated according to a preset dynamic adjustment strategy, and current coordinates are obtained.

[0106] It's important to note that during this step, if the inspection robot determines, based on the preset task scheduling strategy, that the inspection area is at the second danger level (e.g., abnormal temperature but not fire-related), it will automatically generate appropriate pan / tilt and lens control parameters based on the preset dynamic adjustment strategy. Pan / tilt control parameters include the adjustment range of pitch and yaw angles (e.g., -30° to +90° for pitch and -30° to +30° for yaw) to ensure the robot can accurately focus on the abnormal area. Lens control parameters involve adjusting the focal length of the zoom lens (e.g., 5-50mm zoom) to obtain clearer image data. The robot also uses its built-in positioning system to obtain its current coordinates for subsequent data transmission and path planning.

[0107] Step B20: re-collecting visible light image data and infrared thermal imaging data according to the pan / tilt control parameters and the lens control parameters, and transmitting the visible light image data, the infrared thermal imaging data and the current coordinates to the backend to obtain an audit result.

[0108] It should be noted that during this step, the inspection robot readjusts the pan / tilt and lens positions based on the generated pan / tilt control parameters to collect visible light image data and infrared thermal imaging data. Once collected, the robot transmits this data, along with its current coordinates, to the backend system via a wireless communication module. Upon receiving the data, the backend system conducts further analysis and processing to determine whether a genuine safety hazard exists. It should be understood that this step, by re-collecting image and thermal imaging data, provides the backend system with more accurate and comprehensive information, enabling accurate judgment and decision-making.

[0109] Step B30: When the audit result is normal, the inspection task is performed according to the preset inspection path.

[0110] It's important to note that in this step, after the backend system reviews the data transmitted by the inspection robot and determines it to be normal (i.e., posing no safety risks), it sends instructions to the robot, instructing it to continue its inspection mission along the pre-set inspection route. This step ensures that, if no safety risks are identified, the inspection robot can continue its pre-set inspection mission, covering a wider inspection area and ensuring overall safety.

[0111] Step B40: When the audit result is abnormal, the second danger level is increased to the first danger level so that the robot performs a fire suppression operation.

[0112] It's important to note that in this step, after the backend system reviews the data transmitted by the inspection robot and determines it to be abnormal (i.e., a potential safety hazard exists that could escalate to a fire risk), it will send a command to the robot to raise the current danger level from Level 2 to Level 1. Upon receiving this command, the robot will immediately cease its current mission and perform fire suppression operations according to the procedures for Level 1. It's understandable that this step ensures that when a potential safety hazard is discovered, the inspection robot can quickly escalate the level of response and implement more effective measures to prevent the hazard from escalating into a serious incident such as a fire.

[0113] In a feasible implementation manner, the step S40 further includes:

[0114] Step C10: When the danger level is the third danger level, the robot is controlled to perform the inspection task according to the preset inspection path.

[0115] It should be noted that the third danger level refers to situations where no direct safety threats are detected within the inspection area, such as flames, combustible gas concentrations not exceeding standards, or temperatures not reaching abnormal thresholds. At this level, the robot primarily performs routine inspection tasks to maintain continuous monitoring of the inspection area. In this step, when the inspection robot determines that the inspection area is at the third danger level based on the preset task scheduling strategy (i.e., no direct threats such as flames, combustible gas concentrations exceeding standards, or significant temperature anomalies are detected), it will automatically execute the inspection task according to the preset inspection route. This route is pre-planned based on the layout of the inspection area, the location of key equipment, and historical inspection data, aiming to comprehensively cover the inspection area and ensure timely detection of potential safety hazards.

[0116] Step C20: When receiving new multi-sensor data during the inspection task, return to the step of performing data targeting on the multi-sensor data according to the Kalman filtering strategy to obtain target feature data, and obtain an updated danger level.

[0117] It should be noted that while the inspection robot is performing its inspection mission along a pre-set inspection route, it continuously receives real-time data from multiple sensors, including visible light cameras, infrared thermal imagers, and gas sensors. Whenever new multi-sensor data is received, the robot immediately returns to the data fusion step based on a Kalman filter strategy. This generates more accurate and reliable target feature data, such as temperature distribution and gas concentration. The robot then reassesses the danger level of the inspection area based on this updated target feature data. If the new assessment indicates a change in danger level (e.g., from danger level 3 to danger level 2 or 1), the robot immediately adjusts its inspection mission and implements appropriate emergency response measures, such as temperature anomaly warnings or fire suppression operations.

[0118] In this embodiment, by setting response mechanisms under different danger levels (including interrupting the current task, planning the fire path, dynamically adjusting sensor parameters, transmitting data review, and updating the danger level through multi-sensor data fusion), rapid response and effective handling of emergency situations such as sudden fires are achieved, solving the problem of response delay caused by the inability of traditional inspection robots to distinguish task priorities, and improving the execution efficiency and safety of inspection tasks in high-risk industrial scenarios.

[0119] This application also provides a multi-task collaborative device for inspection robots, please refer to Figure 4 , the multi-task coordination device of the inspection robot includes:

[0120] A data acquisition module 10 is used to acquire multi-sensor data, wherein the multi-sensor data includes visible light image data, infrared thermal imaging data, and gas concentration data;

[0121] A data processing module 20 is configured to process the multi-sensor data according to a Kalman filter strategy to obtain target feature data;

[0122] The danger determination module 30 is used to determine the danger level of the target feature data according to a preset task scheduling strategy;

[0123] The task coordination module 40 is used to control the robot to perform corresponding inspection tasks according to the danger level. The inspection tasks include fire suppression, temperature anomaly warning, and execution of preset inspection paths.

[0124] The multi-task coordination device for inspection robots provided in this application, which employs the multi-task coordination method for inspection robots in the aforementioned embodiments, can address the technical problem of improving the safety and inspection efficiency of inspection robots when faced with multi-task conflicts. Compared to the prior art, the beneficial effects of the multi-task coordination device for inspection robots provided in this application are the same as those of the multi-task coordination method for inspection robots provided in the aforementioned embodiments. Other technical features of the multi-task coordination device for inspection robots are the same as those disclosed in the aforementioned embodiments and are not further elaborated here.

[0125] In one embodiment, the data processing module 20 is further used to preprocess the visible light image data, infrared thermal imaging data and gas concentration data to obtain target visible light image data, initial infrared thermal imaging data and target gas concentration data; perform anti-reflection processing on the initial infrared thermal imaging data according to the target visible light image data to obtain target infrared thermal imaging data; and filter the target infrared thermal imaging data and the target gas concentration data according to the Kalman filtering strategy to obtain target feature data.

[0126] In one embodiment, the danger judgment module 30 is further used to obtain a preset lower explosion limit and a preset temperature threshold according to a preset task scheduling strategy; obtain a target gas concentration and a target area temperature according to the target characteristic data; when the target gas concentration is greater than or equal to the preset lower explosion limit and the target area temperature is greater than or equal to the preset temperature threshold, determine the danger level to be a first danger level; when the target area temperature is greater than or equal to the preset temperature threshold, determine the danger level to be a second danger level; when the target gas concentration is less than the preset lower explosion limit and the target area temperature is less than the preset temperature threshold, determine the danger level to be a third danger level, the first danger level is greater than the second danger level, and the second danger level is greater than the third danger level.

[0127] In one embodiment, the danger judgment module 30 is also used to generate an interrupt signal to control the robot to stop the current task when the danger level is the first danger level, and generate a first navigation path to reach the fire area according to a preset first path planning algorithm; control the robot to move to the fire extinguishing point through the first navigation path, and activate the robot's water spray device to perform fire suppression operations.

[0128] In one embodiment, the danger judgment module 30 is further used to generate pan-tilt control parameters and lens control parameters according to a preset dynamic adjustment strategy and obtain current coordinates when the danger level is the second danger level; re-collect visible light image data and infrared thermal imaging data according to the pan-tilt control parameters and lens control parameters, and transmit the visible light image data, the infrared thermal imaging data and the current coordinates to the background to obtain an audit result; when the audit result is normal, perform the inspection task according to the preset inspection path; when the audit result is abnormal, increase the second danger level to the first danger level so that the robot performs a fire suppression operation.

[0129] In one embodiment, the danger judgment module 30 is also used to control the robot to perform the inspection task according to the preset inspection path when the danger level is the third danger level; in the process of performing the inspection task, when new multi-sensor data is received, it returns to execute the step of performing data target acquisition of target feature data on the multi-sensor data according to the Kalman filtering strategy to obtain an updated danger level.

[0130] In one embodiment, the task collaboration module 40 is also used to generate a second navigation path to the charging point according to a preset second path planning algorithm when the robot completes the inspection task or the battery level is lower than a preset threshold; and control the robot to move to the charging point for charging through the second navigation path.

[0131] The present application provides a multi-task collaborative device for an inspection robot, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the multi-task collaborative method for the inspection robot in the above-mentioned embodiment one.

[0132] Reference below Figure 5 , which shows a schematic diagram of the structure of a multi-task collaborative device suitable for implementing the inspection robot in the embodiments of the present application. The multi-task collaborative device of the inspection robot in the embodiments of the present application may include, but is not limited to, mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions), PMPs (Portable Media Players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), and fixed terminals such as digital TVs and desktop computers. Figure 5 The multi-task collaborative device of the inspection robot shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0133] like Figure 5As shown, the multi-task collaborative device of the inspection robot may include a processing device 1001 (e.g., a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes based on programs stored in ROM (Read Only Memory) 1002 or programs loaded from storage device 1003 into RAM (Random Access Memory) 1004. RAM 1004 also stores various programs and data required for the operation of the multi-task collaborative device of the inspection robot. Processing device 1001, ROM 1002, and RAM 1004 are interconnected via bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems can be connected to the I / O interface 1006: input devices 1007 including, for example, a touch screen, touchpad, keyboard, mouse, image sensor, microphone, accelerometer, gyroscope, etc.; output devices 1008 including, for example, an LCD (Liquid Crystal Display), speaker, vibrator, etc.; storage devices 1003 including, for example, a magnetic tape, hard disk, etc.; and communication devices 1009. Communication devices 1009 can allow the multi-task collaborative device of the inspection robot to communicate with other devices wirelessly or by wire to exchange data. Although the figure shows the multi-task collaborative device of the inspection robot with various systems, it should be understood that implementation or presence of all the illustrated systems is not required. More or fewer systems may alternatively be implemented or present.

[0134] In particular, according to the embodiments disclosed in the present application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, the embodiments disclosed in the present application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program comprising program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network via a communication device, or installed from a storage device 1003, or installed from a ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiment disclosed in the present application are executed.

[0135] The multi-task collaborative device for inspection robots provided in this application, which employs the multi-task collaborative method for inspection robots in the aforementioned embodiments, can solve the technical problem of how to improve the safety and inspection efficiency of inspection robots when faced with multi-task conflicts. Compared with the prior art, the beneficial effects of the multi-task collaborative device for inspection robots provided in this application are the same as those of the multi-task collaborative method for inspection robots provided in the aforementioned embodiments, and the other technical features of the multi-task collaborative device for inspection robots are the same as those disclosed in the aforementioned embodiments, and are not further described here.

[0136] It should be understood that the various parts disclosed in this application can be implemented using hardware, software, firmware, or a combination thereof. In the description of the above embodiments, specific features, structures, materials, or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0137] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

[0138] The present application provides a computer-readable storage medium having computer-readable program instructions (ie, a computer program) stored thereon, and the computer-readable program instructions are used to execute the multi-task collaboration method of the inspection robot in the above-mentioned embodiment.

[0139] The computer-readable storage medium provided herein may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, systems, or devices, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to, an electrical connection having one or more wires, a portable computer disk, a hard disk, RAM (Random Access Memory), ROM (Read Only Memory), EPROM (Erasable Programmable Read Only Memory or Flash memory), optical fiber, CD-ROM (CD-Read Only Memory), optical storage device, magnetic storage device, or any suitable combination thereof. In this embodiment, the computer-readable storage medium may be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, system, or device. The program code contained on the computer-readable storage medium may be transmitted using any suitable medium, including, but not limited to, wires, optical cables, RF (Radio Frequency), etc., or any suitable combination thereof.

[0140] The computer-readable storage medium may be included in the multi-task cooperative device of the inspection robot; or it may exist independently without being assembled into the multi-task cooperative device of the inspection robot.

[0141] The above-mentioned computer-readable storage medium carries one or more programs. When the above-mentioned one or more programs are executed by the multi-task collaborative device of the patrol robot, the multi-task collaborative device of the patrol robot enables the multi-task collaborative device to: obtain multi-sensor data; process the multi-sensor data according to the Kalman filtering strategy to obtain target feature data; judge the target feature data according to the preset task scheduling strategy to obtain the danger level; and control the robot to perform corresponding patrol tasks according to the danger level, and the patrol tasks include fire suppression, temperature abnormality warning and execution of preset patrol paths.

[0142] The computer program code for performing the operations of the present application may be written in one or more programming languages, or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a stand-alone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer via any type of network, including a LAN (Local Area Network) or a WAN (Wide Area Network), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0143] The flow charts and block diagrams in the accompanying drawings illustrate the possible architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present application. In this regard, each box in the flow chart or block diagram can represent a module, program segment or a part of code, and the module, program segment or a part of code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order than that marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flow chart, and the combination of the boxes in the block diagram and / or flow chart can be implemented by a dedicated hardware-based system that performs the specified function or operation, or can be implemented by a combination of dedicated hardware and computer instructions.

[0144] The modules described in the embodiments of the present application may be implemented in software or hardware, wherein the name of a module does not necessarily limit the unit itself.

[0145] The computer-readable storage medium provided in this application stores computer-readable program instructions (i.e., a computer program) for executing the multi-task coordination method for the inspection robot described above. This computer-readable storage medium addresses the technical problem of improving the safety and efficiency of inspection robots when faced with multi-task conflicts. Compared to the prior art, the beneficial effects of the computer-readable storage medium provided in this application are the same as those of the multi-task coordination method for the inspection robot provided in the aforementioned embodiments, and are not further elaborated here.

[0146] The present application also provides a computer program product, including a computer program, which implements the steps of the multi-task collaboration method of the inspection robot as described above when executed by a processor.

[0147] The computer program product provided in this application can solve the technical problem of improving the safety and inspection efficiency of inspection robots when faced with multi-task conflicts. Compared with the prior art, the beneficial effects of the computer program product provided in this application are the same as those of the multi-task coordination method for inspection robots provided in the above-mentioned embodiments, and will not be elaborated here.

[0148] The above description is only part of the embodiments of the present application and does not limit the patent scope of the present application. All equivalent structural transformations made by using the contents of the present application specification and drawings under the technical concept of the present application, or direct / indirect application in other related technical fields are included in the patent protection scope of the present application.

Claims

1. A multi-task collaboration method for an inspection robot, characterized in that: The method comprises: Acquiring multi-sensor data, wherein the multi-sensor data includes visible light image data, infrared thermal imaging data, and gas concentration data; Processing the multi-sensor data according to a Kalman filter strategy to obtain target feature data; Obtaining a preset lower explosion limit and a preset temperature threshold according to a preset task scheduling strategy; Obtaining target gas concentration and target area temperature according to the target characteristic data; When the target gas concentration is greater than or equal to the preset lower explosion limit and the target area temperature is greater than or equal to the preset temperature threshold, determining the hazard level to be the first hazard level; When the temperature of the target area is greater than or equal to the preset temperature threshold, determining the danger level to be the second danger level; When the target gas concentration is less than the preset lower explosion limit and the target area temperature is less than the preset temperature threshold, determining that the hazard level is the third hazard level, the first hazard level is greater than the second hazard level, and the second hazard level is greater than the third hazard level; Control the robot to perform corresponding inspection tasks according to the danger level, including fire suppression, temperature anomaly warning, and execution of preset inspection paths; The step of controlling the robot to perform the corresponding inspection task according to the danger level includes: When the danger level is the second danger level, generating pan / tilt control parameters and lens control parameters according to a preset dynamic adjustment strategy, and obtaining current coordinates; Recollecting visible light image data and infrared thermal imaging data according to the pan / tilt control parameters and the lens control parameters, and transmitting the visible light image data, the infrared thermal imaging data and the current coordinates to the backend to obtain an audit result; When the audit result is normal, the inspection task is performed according to the preset inspection path; When the audit result is abnormal, the second danger level is raised to the first danger level so that the robot performs a fire suppression operation.

2. The method according to claim 1, wherein The step of controlling the robot to perform corresponding inspection tasks according to the danger level includes: When the danger level is the first danger level, an interrupt signal is generated to control the robot to stop the current task, and a first navigation path to reach the fire area is generated according to a preset first path planning algorithm; The robot is controlled to move to the fire extinguishing point through the first navigation path, and the water spray device of the robot is activated to perform fire suppression operations.

3. The method according to claim 1, wherein The step of controlling the robot to perform corresponding inspection tasks according to the danger level includes: When the danger level is the third danger level, controlling the robot to perform the inspection task according to the preset inspection path; During the inspection task, when new multi-sensor data is received, the process returns to the step of performing data targeting on the multi-sensor data according to the Kalman filtering strategy to obtain target feature data, and obtains an updated danger level.

4. The method according to claim 1, wherein The step of processing the multi-sensor data according to the Kalman filtering strategy to obtain target feature data includes: Preprocessing the visible light image data, infrared thermal imaging data, and gas concentration data to obtain target visible light image data, initial infrared thermal imaging data, and target gas concentration data; performing anti-reflection processing on the initial infrared thermal imaging data according to the target visible light image data to obtain target infrared thermal imaging data; The target infrared thermal imaging data and the target gas concentration data are filtered according to a Kalman filtering strategy to obtain target feature data.

5. The method according to claim 1, wherein After the step of controlling the robot to perform the corresponding inspection task according to the hazard level, the method further includes: When the robot completes the inspection task or the battery level is lower than a preset threshold, a second navigation path to the charging point is generated according to a preset second path planning algorithm; The robot is controlled by the second navigation path to move to a charging point for charging.

6. A multi-task collaborative device for an inspection robot, characterized in that: The device comprises: A data acquisition module is used to acquire multi-sensor data, wherein the multi-sensor data includes visible light image data, infrared thermal imaging data, and gas concentration data; A data processing module is used to process the multi-sensor data according to a Kalman filter strategy to obtain target feature data; a hazard determination module, configured to obtain a preset lower explosion limit and a preset temperature threshold according to a preset task scheduling strategy; obtain a target gas concentration and a target area temperature according to the target characteristic data; determine the hazard level to be a first hazard level when the target gas concentration is greater than or equal to the preset lower explosion limit and the target area temperature is greater than or equal to the preset temperature threshold; determine the hazard level to be a second hazard level when the target area temperature is greater than or equal to the preset temperature threshold; and determine the hazard level to be a third hazard level when the target gas concentration is less than the preset lower explosion limit and the target area temperature is less than the preset temperature threshold, wherein the first hazard level is greater than the second hazard level and the second hazard level is greater than the third hazard level; A task coordination module is used to control the robot to perform corresponding inspection tasks according to the hazard level, and the inspection tasks include fire suppression, temperature anomaly warning, and execution of preset inspection paths; The task collaboration module is also used to generate pan-tilt control parameters and lens control parameters according to a preset dynamic adjustment strategy and obtain current coordinates when the danger level is the second danger level; re-collect visible light image data and infrared thermal imaging data according to the pan-tilt control parameters and lens control parameters, and transmit the visible light image data, the infrared thermal imaging data and the current coordinates to the background to obtain an audit result; when the audit result is normal, perform the inspection task according to the preset inspection path; when the audit result is abnormal, increase the second danger level to the first danger level so that the robot performs a fire suppression operation.

7. A multi-task collaborative device for an inspection robot, characterized in that: The device includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the multi-task collaboration method of the inspection robot according to any one of claims 1 to 5.

8. A storage medium, characterized in that: The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of the multi-task collaboration method of the inspection robot according to any one of claims 1 to 5 are implemented.

Images