A robot intelligent inspection method, system, device and storage medium

Abstract

The present application provides a robot intelligent inspection method, system, equipment and storage medium, which relates to the field of intelligent robot technology. The method includes: obtaining the detection time of each waterproof tester on the test piece in the laboratory, and based on the water pressure pressurization law of each waterproof tester, predicting the target time period for the test piece to appear with the preset result on each waterproof tester according to the detection time; combining the current position of the inspection robot and the target time period, generating the initial inspection route of the inspection robot; obtaining the first position information of the fixed obstacles in the laboratory and the historical movement trajectory information of the mobile obstacles; predicting the position distribution of the mobile obstacles in the target time period according to the historical movement trajectory information; adjusting the initial inspection route according to the first position information and the position distribution, and generating the target inspection route of the inspection robot. The technical effect of the present application is: improving the inspection efficiency of the robot.

Description

Technical Field

[0001] The present application relates to the field of intelligent robot technology, and specifically to a robot intelligent inspection method, system, equipment and storage medium. Background Art

[0002] When conducting waterproofing tests in the laboratory, it is necessary to promptly observe and record any water seepage in the specimens. Since the test process is long and the time it takes for water to seep varies from specimen to specimen, relying solely on manual inspections is not only labor-intensive but also prone to missing critical water seepage moments, affecting the accuracy of the test results.

[0003] Currently, some laboratories use robots for automated inspections, completing tasks by pre-setting fixed inspection routes and inspection cycles. While this approach reduces the workload of manual inspections to a certain extent, this fixed-route inspection method fails to fully consider the timing requirements of the test process and the dynamic changes in the environment. This can cause the inspection robot to arrive at the inspection point at the wrong time, thus affecting inspection efficiency. Summary of the Invention

[0004] The present application provides a robot intelligent inspection method, system, device and storage medium for improving the inspection efficiency of the robot.

[0005] In the first aspect, the present application provides a robot intelligent inspection method, the method comprising: obtaining the inspection time of each waterproof testing instrument on the test piece in the laboratory, and based on the water pressure pressurization law of each waterproof testing instrument, predicting the target time period for the test piece to appear with a preset result on each waterproof testing instrument according to the inspection time; obtaining the current position of the inspection robot, and generating an initial inspection route of the inspection robot by combining the current position and the target time period; obtaining the first position information of the fixed obstacles in the laboratory, and the historical movement trajectory information of the mobile obstacles; predicting the position distribution of the mobile obstacles within the target time period according to the historical movement trajectory information; adjusting the initial inspection route according to the first position information and the position distribution to generate the target inspection route of the inspection robot.

[0006] By employing this technical solution, the inspection robot can arrive at the inspection point for observation at the most appropriate time by measuring the inspection duration and predicting the target time period for the test piece to produce a preset result based on the hydraulic pressure application pattern. Simultaneously, the system generates an initial inspection route based on the inspection robot's current position and optimizes the route by obtaining information about the locations of fixed obstacles and predicting the distribution of mobile obstacles, thereby ensuring the timeliness and feasibility of the inspection route. This inspection method, based on time series prediction and environmental perception, not only improves the accuracy and efficiency of inspections but also enhances the safety and reliability of the inspection process.

[0007] Optionally, predicting a target time period for the test piece on each of the water-resistance testing instruments to produce a preset result based on the test duration includes: obtaining historical test data of the test piece on each of the water-resistance testing instruments, and determining a preset time period for the test piece on each of the water-resistance testing instruments to produce a preset result based on the historical test data, wherein the preset result is water seepage in the test piece; and predicting a target time period for the test piece on each of the water-resistance testing instruments to produce a preset result based on the test duration and the preset time period.

[0008] By adopting this technical solution, the target time period is determined by acquiring and analyzing the water seepage time records of the test pieces from historical test data. This is then combined with the current test duration to make the prediction more targeted and accurate. This historical data-based prediction method fully considers the individual differences in water seepage time between different test pieces, effectively improving the accuracy of water seepage prediction. This allows the inspection robot to more accurately grasp the observation time and reduce the number of invalid observations during the inspection process.

[0009] Optionally, the initial inspection route of the inspection robot is generated by combining the current position and the target time period, including: obtaining the second position information of each of the anti-seepage detectors, and calculating the movement time of the inspection robot to reach each of the anti-seepage detectors in combination with the current position and the second position information of each of the anti-seepage detectors; sorting the inspection order of each of the anti-seepage detectors according to the movement time and the target time period to generate an inspection sequence; and generating the initial inspection route of the inspection robot according to the inspection sequence.

[0010] By adopting the above technical solution, the inspection sequence is rationally sorted by obtaining the location information of the water-resistance detector and calculating the travel time, combined with the target time period. The generated initial inspection route satisfies both the optimal spatial distance and time constraints. This route planning method based on the dual constraints of space and time ensures that the inspection robot can reach the designated location for observation when the test piece is expected to see water, while also reducing the distance of ineffective movement, thereby improving the efficiency and accuracy of the inspection task.

[0011] Optionally, predicting the position distribution of the mobile obstacle within the target time period based on the historical movement trajectory information includes: determining the position distribution pattern of the mobile obstacle in each time period based on the historical movement trajectory information; and predicting the position distribution of the mobile obstacle within the target time period based on the position distribution pattern.

[0012] By employing this technical solution, the system analyzes the historical movement trajectory information of mobile obstacles to determine their location distribution patterns. Based on this pattern, it predicts their location distribution within a target time period, enabling the system to predict the movement of mobile obstacles such as personnel and equipment within the laboratory in advance. This historical data-based obstacle location prediction method improves foresight of dynamic changes in the laboratory environment, helps generate more proactive and feasible inspection routes, and thus reduces the risk of collisions during inspections.

[0013] Optionally, the initial inspection route is adjusted according to the first position information and the position distribution to generate a target inspection route for the inspection robot, including: determining the overlapping area between the initial inspection route and the position of the fixed obstacle, and the overlapping area with the position distribution of the mobile obstacle; generating an obstacle avoidance route segment by combining the position overlapping area and the distribution overlapping area; replacing the corresponding route segment in the initial inspection route with the obstacle avoidance route segment to obtain the target inspection route.

[0014] By employing this technical solution, the target inspection route is effectively avoided by identifying the overlapping areas between the initial inspection route and fixed and mobile obstacles, and generating corresponding obstacle avoidance route segments for replacement. This route optimization method, based on overlapping area analysis, not only ensures a safe distance between the inspection route and obstacles, but also minimizes route changes caused by obstacle avoidance, thereby ensuring inspection safety while maintaining the temporal and spatial efficiency of the route.

[0015] Optionally, after generating the target inspection route of the inspection robot, it also includes: obtaining the remaining power and energy consumption per unit distance of the inspection robot; calculating the expected total energy consumption of the target inspection route based on the energy consumption per unit distance; when the remaining power is less than the expected total energy consumption, obtaining the third position information of the charging pile; based on the third position information, inserting the route segment of the inspection robot to and from the charging pile into the target inspection route to generate a final inspection route, and determining the charging time point of the inspection robot.

[0016] By employing this technical solution, the estimated total energy consumption of the target inspection route is calculated and compared with the remaining power. When the battery is low, the charging route and time points are planned in advance, allowing the inspection robot to complete charging at the appropriate time. This charging planning method based on energy consumption prediction not only avoids mission interruptions caused by battery depletion, but also minimizes the impact of the charging process on the inspection mission by rationally arranging charging times and routes, thereby ensuring the continuity and reliability of the inspection mission.

[0017] Optionally, after generating the target inspection route of the patrol robot, it also includes: monitoring the actual operating status of the patrol robot on the target inspection route; when it is detected that the patrol robot deviates from the target inspection route, obtaining the actual position of the patrol robot; regenerating the first patrol route based on the current actual position; combining the first position information of the fixed obstacle and the position distribution of the mobile obstacle, adjusting the first patrol route to obtain a second patrol route, so that the patrol robot performs inspection according to the second patrol route.

[0018] By adopting this technical solution, the inspection robot's operating status is monitored in real time. When a deviation occurs, the robot's actual position is promptly acquired and its route is replanned. This route optimization also takes into account the impact of fixed and mobile obstacles, enabling the inspection robot to quickly adjust to a new, feasible route. This dynamic route adjustment method based on real-time monitoring improves the inspection system's ability to respond to emergencies, ensuring that inspection tasks can be promptly resumed and safely continued after deviations, thereby enhancing the inspection system's environmental adaptability and mission reliability.

[0019] In a second aspect, the present application provides a robot intelligent inspection system, the system comprising: a first acquisition module, a second acquisition module, a third acquisition module, a prediction module and an adjustment module; wherein,

[0020] The first acquisition module is used to obtain the testing time of the test piece by each water-resistance tester in the laboratory, and predict the target time period for the test piece to show the preset result on each water-resistance tester based on the water pressure application law of each water-resistance tester according to the testing time; the second acquisition module is used to obtain the current position of the inspection robot, and generate the initial inspection route of the inspection robot in combination with the current position and the target time period; the third acquisition module is used to obtain the first position information of the fixed obstacles in the laboratory, and the historical movement trajectory information of the mobile obstacles; the prediction module is used to predict the position distribution of the mobile obstacles within the target time period based on the historical movement trajectory information; the adjustment module is used to adjust the initial inspection route according to the first position information and the position distribution to generate the target inspection route of the inspection robot.

[0021] In a third aspect, the present application provides an electronic device that adopts the following technical solution: it includes a processor, a memory, a user interface and a network interface, the memory is used to store instructions, the user interface and the network interface are used to communicate with other devices, and the processor is used to execute the instructions stored in the memory so that the electronic device executes a computer program such as any of the above-mentioned robot intelligent inspection methods.

[0022] In a fourth aspect, the present application provides a computer-readable storage medium, which adopts the following technical solution: storing a computer program that can be loaded by a processor and execute any of the above-mentioned robot intelligent inspection methods.

[0023] In summary, this application includes at least one of the following beneficial technical effects:

[0024] By measuring the inspection duration and predicting the target time period for the test piece to produce a preset result based on the hydraulic pressure pattern, the inspection robot can arrive at the inspection point for observation at the most appropriate time. The system also generates an initial inspection route based on the inspection robot's current position. It optimizes and adjusts the route by obtaining information about the locations of fixed obstacles and predicting the distribution of mobile obstacles, ensuring the timeliness and feasibility of the inspection route. This inspection method, based on time series prediction and environmental perception, not only improves the accuracy and efficiency of inspections but also enhances the safety and reliability of the inspection process. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] Figure 1 This is a flow chart of a robot intelligent inspection method provided in an embodiment of the present application;

[0026] Figure 2 This is a schematic diagram of the structure of a robot intelligent inspection system provided in an embodiment of the present application;

[0027] Figure 3 This is a structural diagram of an electronic device provided in an embodiment of the present application.

[0028] Description of reference numerals: 1000, electronic device; 1001, processor; 1002, communication bus; 1003, user interface; 1004, network interface; 1005, memory. DETAILED DESCRIPTION

[0029] In order to enable people skilled in the art to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below in conjunction with the drawings in the embodiments of this specification. Obviously, the described embodiments are only part of the embodiments of this application, not all of the embodiments.

[0030] In the description of the embodiments of this application, words such as "exemplary," "for example," or "for example" are used to indicate examples, illustrations, or descriptions. Any embodiment or design described as "exemplary," "for example," or "for example" in the embodiments of this application should not be construed as being preferred or advantageous over other embodiments or designs. Rather, the use of words such as "exemplary," "for example," or "for example" is intended to present the relevant concepts in a concrete manner.

[0031] Figure 1This is a flow chart of a robot intelligent inspection method provided by an embodiment of the present application. Figure 1 As shown, the method includes S101-S105:

[0032] S101, obtaining the testing time of each waterproof tester on the test piece in the laboratory, and based on the water pressure application law of each waterproof tester and the testing time, predicting the target time period for the test piece to show the preset result on each waterproof tester.

[0033] In this embodiment, to improve the efficiency of intelligent inspections for concrete impermeability testing, it is first necessary to obtain the testing duration of each test specimen by each impermeability testing instrument in the laboratory. The testing duration here refers to the duration from the start of pressurization testing of the specimen to the current moment. Because the concrete impermeability testing uses a step-by-step pressurization method, with the water pressure starting at 0.1 MPa and increasing by 0.1 MPa every 8 hours, the current water pressure level of each specimen can be determined based on the testing duration.

[0034] On the basis of obtaining the test duration and combining the water pressure application rules of each water-resistance tester, the target time period for the test piece to show the preset result can be predicted. The preset result here specifically refers to the state of water seepage in the test piece, and the target time period indicates the time range in which water seepage is expected to occur in the test piece. Specifically, the historical test data of the test piece on each water-resistance tester is first obtained. These data contain the time distribution rules of water seepage in concrete test pieces of different strength grades under different water pressures. By analyzing the historical data, the preset time period for water seepage in concrete test pieces of various strength grades under a certain water pressure level can be obtained.

[0035] For example, suppose a specimen on a water-resistance tester is tested for 20 hours. Based on the water pressure regulation, the current water pressure is 0.3 MPa. By querying historical data, it is found that concrete specimens of this strength grade, under 0.3 MPa water pressure, typically experience water seepage within 4-6 hours of the test. Therefore, it can be predicted that this specimen is likely to experience water seepage within the next 4-6 hours, meaning the target time period is 24-26 hours after the test begins.

[0036] The primary purpose of predicting target time periods is to provide inspection robots with more targeted inspection schedules. This prediction allows them to increase inspection frequency during times when water leakage is most likely to occur, while appropriately reducing it during other times. This optimizes the allocation of inspection resources and improves inspection efficiency. This intelligent prediction method, based on historical data and pressurization patterns, not only reduces unnecessary inspections but also ensures that critical moments of water leakage are not missed. It also provides an important time dimension for subsequent inspection route planning.

[0037] Based on the above embodiment, as an optional implementation, in S101, based on the test duration, predicting the target time period for the test piece on each anti-permeability tester to show a preset result specifically includes S11-S12:

[0038] S11, obtaining historical test data of the test piece on each anti-seepage tester, and determining a preset time period in which a preset result occurs on the test piece on each anti-seepage tester based on the historical test data, the preset result being that water seepage occurs on the test piece.

[0039] S12, combining the test duration and the preset time period, predicting the target time period for the test piece on each anti-permeability tester to show the preset result.

[0040] To more accurately predict the time it takes for a test specimen to seep, the system first needs to establish a historical data analysis mechanism. In this embodiment, this historical test data includes test records of concrete specimens of varying strength grades under various water pressure levels. Each record contains information such as specimen specifications, water pressure level, test start time, and water seepage occurrence time. This historical test data reflects the time it takes for a specimen to seep from the start of pressurization to the onset of water seepage under different test conditions.

[0041] After acquiring historical test data, the system classifies, counts, and analyzes the data. Specifically, the data is first grouped according to the specimen strength grade and water pressure level, and the time distribution from the start of pressurization to the occurrence of water seepage is calculated for each data set. Through statistical analysis, the system can determine the time range within which water seepage occurs in specimens under specific strength grade and water pressure conditions, namely the preset time period. The preset time period represents the time interval from the start of pressurization to the occurrence of water seepage. For example, under a water pressure of 0.3 MPa, specimens of a certain strength grade typically experience water seepage within 4-6 hours after pressurization.

[0042] For example, if a test piece on a water-resistance tester has been tested for 20 hours, and the water pressure is currently 0.3 MPa based on the water pressure regulation, querying the historical test data for this strength grade test piece under 0.3 MPa water pressure reveals that water seepage occurs primarily between 4 and 6 hours after the test begins. Combined with the current test duration, the system can predict that water seepage is likely to occur within 24 to 26 hours of the start of the test, which is the target time period.

[0043] During the prediction process, the system also considers other factors that affect water seepage time, such as ambient temperature and specimen curing conditions. By correcting for the impact of these factors, the accuracy of the prediction results can be improved. For example, if the current ambient temperature is significantly higher than the temperature when the historical data was recorded, the system will appropriately shorten the target prediction time period, as higher temperatures may accelerate the water seepage process of the specimen.

[0044] S102, obtaining the current position of the inspection robot, and generating an initial inspection route of the inspection robot in combination with the current position and the target time period.

[0045] After predicting the target time period for water seepage in the specimen, a reasonable inspection route must be planned to ensure efficient operation of the inspection robot. First, the inspection robot's current position is acquired through multi-sensor fusion technology. This includes posture information provided by the inertial measurement unit (IMU), environmental information collected by the lidar sensor, and position feature information acquired by the visual sensor. After this sensor data is fused and processed, the inspection robot's current coordinates can be accurately located within the laboratory's three-dimensional map.

[0046] An IMU is an electronic sensor device that measures the three-dimensional motion parameters of an object. It consists of an accelerometer and a gyroscope. The accelerometer measures the object's linear acceleration along three orthogonal axes, while the gyroscope measures the object's angular velocity around those three orthogonal axes. By integrating this data, motion parameters such as the inspection robot's velocity, position, and attitude angle can be obtained.

[0047] In addition to obtaining the current position, the system also needs to obtain the secondary position information of each waterproofing tester—that is, the fixed coordinate position of each tester on the laboratory's 3D map. Combining the inspection robot's current position with the secondary position information of each waterproofing tester, the system can calculate the travel time required for the inspection robot to reach each waterproofing tester. This travel time is calculated based on the inspection robot's maximum speed, acceleration, and other motion parameters, as well as the length of the planned path.

[0048] To generate the optimal initial inspection route, the system prioritizes the inspections of each water-resistance tester based on travel time and the previously predicted target time period, creating an inspection sequence. Specifically, the system prioritizes testers located on test pieces predicted to be leaking. Furthermore, considering the impact of travel time, the system calculates whether the inspection robot, starting from its current position, can reach the corresponding tester before leaks occur. If it is predicted that the robot will not be able to reach the target tester in time, the inspection sequence will be adjusted appropriately to ensure optimal overall inspection efficiency.

[0049] For example, suppose there are three water-insulation testers in a laboratory: A, B, and C. The prediction indicates that water may seep into the specimen in tester A in 30 minutes, into tester B in 2 hours, and into tester C in 4 hours. If it takes 5 minutes, 3 minutes, and 10 minutes to reach these three testers from the inspection robot's current location, respectively, the system will generate an inspection sequence of BAC, because heading to tester B first ensures that it arrives in time before water seeps into tester A.

[0050] Based on the finalized inspection sequence, the system generates an initial inspection route for the inspection robot. This initial route is a pre-defined path connecting the various detector locations, but it does not account for obstacles within the laboratory. This route planning method, based on time and space dimensions, ensures accurate identification of key time points while also ensuring the rationality of the spatial path, providing a foundation for subsequent route optimization.

[0051] Based on the above embodiment, as an optional implementation, in S102, combining the current position and the target time period to generate the initial inspection route of the inspection robot specifically includes S21-S23:

[0052] S21, obtaining the second position information of each anti-seepage detector, combining the current position and the second position information of each anti-seepage detector, and calculating the movement time of the inspection robot to reach each anti-seepage detector.

[0053] To generate the optimal initial inspection route, the system needs to comprehensively consider spatial distance and time constraints. In this embodiment, the system first obtains the second position information of each waterproofing tester in the three-dimensional laboratory map. This second position information includes the spatial coordinates of each tester. Based on the inspection robot's current position, the system calculates the travel time required for the inspection robot to reach each waterproofing tester. This travel time calculation takes into account the inspection robot's maximum speed and the straight-line distance between the two points.

[0054] Specifically, the system calculates travel time based on the inspection robot's maximum speed and the spatial distance covered. For example, if the inspection robot's maximum speed is 1 meter per second and the distance from its current position to a detector is 10 meters, the estimated travel time to reach the detector is 10 seconds. To account for actual acceleration and deceleration, the system adds a time margin to the theoretical calculated time to ensure the reliability of the results.

[0055] S22, sorting the inspection order of each anti-seepage detector according to the moving time and the target time period to generate an inspection sequence.

[0056] After obtaining the travel time, the system prioritizes the inspection order for each waterproofing tester based on the target time period. The principle behind this prioritization is to prioritize test pieces predicted to seep first, while ensuring that the inspection robot can reach the corresponding location before any such leaks occur. Specifically, the system first performs a preliminary sorting of the testers based on the target time period, then makes adjustments taking into account the impact of travel time. If the preliminary sorting cannot guarantee timely arrival, the system adjusts the inspection order to optimize the route.

[0057] For example, a laboratory contains three water-resistance testers, A, B, and C. Test pieces in tester A are expected to seep in 30 minutes, test pieces in tester B are expected to seep in 2 hours, and test pieces in tester C are expected to seep in 4 hours. If it takes 5 minutes, 3 minutes, and 10 minutes to reach these three testers from the inspection robot's current location, respectively, the system will generate the optimal inspection sequence through comparative analysis. In this example, although test pieces in tester A are likely to seep first, given that the travel time from the current location to tester B is shorter and there's still ample time to reach tester A, the system will generate the inspection sequence BAC.

[0058] S23, generating an initial inspection route for the inspection robot according to the inspection sequence.

[0059] Based on the finalized inspection sequence, the system generates an initial inspection route for the inspection robot. This initial route is a path connecting the locations of each detector and contains a detailed sequence of path point coordinates. This route, which does not yet account for the impact of obstacles, serves as the basis for subsequent path optimization. When generating the initial inspection route, the system uses straight lines to connect adjacent detector locations, forming a preliminary trajectory.

[0060] S103: Acquire first position information of fixed obstacles in the laboratory and historical movement trajectory information of mobile obstacles.

[0061] To ensure the safe and efficient operation of inspection robots within the laboratory, it is necessary to accurately understand the location information of various obstacles within the laboratory. In this embodiment, obstacles within the laboratory are divided into two categories: fixed obstacles and mobile obstacles. Fixed obstacles include objects that do not change position, such as laboratory tables, storage cabinets, and wall pillars; mobile obstacles mainly include inspection personnel, other inspection robots, and potentially movable laboratory equipment.

[0062] For fixed obstacles, the inspection robot uses its onboard LiDAR sensor to scan and map the laboratory, obtaining first-level position information. This first-level position information includes the fixed obstacle's position coordinates, shape, dimensions, and other spatial characteristic parameters within the laboratory's three-dimensional coordinate system. Specifically, the LiDAR sensor emits a laser beam and receives the reflected signal. By measuring the laser signal's time of flight, it calculates the obstacle's distance. Combined with the laser beam's scanning angle, it can construct an accurate spatial distribution map of the fixed obstacles within the laboratory.

[0063] For moving obstacles, the system needs to obtain their historical movement trajectory information. This historical movement trajectory information refers to the position change data of the moving obstacle over a period of time, including a sequence of position coordinates and corresponding timestamps. The inspection robot uses visual sensors and lidar sensors to detect and track moving obstacles in real time. The visual sensors are responsible for identifying and classifying the type of moving obstacles, while the lidar sensors provide accurate distance measurements. The system stores this data in a database, forming a historical movement trajectory database of moving obstacles.

[0064] For example, as inspectors perform their daily work in the laboratory, the system records their movement patterns, such as the time periods during which they frequently travel between certain inspection instruments and their commonly used movement paths. For other inspection robots, the system records their pre-set inspection routes and actual operating trajectories. This historical data provides a crucial basis for predicting the location and distribution of moving obstacles.

[0065] The purpose of obtaining this obstacle information is to provide the necessary environmental information for subsequent path planning, ensuring that the inspection robot can accurately predict and avoid possible collisions.

[0066] S104: predicting the position distribution of the moving obstacles within the target time period based on the historical movement trajectory information.

[0067] In this embodiment, the system first segments historical movement trajectory information by time. For each moving obstacle, activity characteristics are extracted for each time period. These characteristics include the obstacle's location coordinates, movement speed, direction, duration of stay in a specific area, and frequency of movement between different areas. By performing statistical analysis on these characteristics, the activity patterns of the moving obstacles over different time periods can be determined.

[0068] Specifically, the system divides the laboratory space into several area units, each of which is sized based on the laboratory layout and obstacle dimensions. For each time period, the system counts the number of times each obstacle appears in each area unit, calculates its frequency of occurrence, and thus derives the probability distribution of the obstacle's location within that time period. The system also records the movement of obstacles between adjacent areas and calculates the frequency of use of their movement paths.

[0069] For example, if historical data shows that an inspector spends 80% of their time between 10:00 AM and 11:00 AM on weekdays traveling back and forth between Area A and Area B, spending an average of 10 minutes in Area A and 15 minutes in Area B, the system will predict that the inspector will also have a high probability of appearing in both areas and the path between them during the same time period in the future. For other inspection robots, since they have pre-set inspection routes and fixed work schedules, the system can directly predict their location distribution based on their task schedules.

[0070] The system displays the prediction results as a probability distribution graph, with different probability values assigned to different areas. Areas with higher probability values are more likely to have moving obstacles appear within that timeframe. This prediction method comprehensively considers the historical patterns of moving obstacles and the influence of time, making the predictions more realistic.

[0071] Based on the above embodiment, as an optional implementation, in S104, predicting the position distribution of the moving obstacle within the target time period based on the historical movement trajectory information specifically includes S41-S42:

[0072] S41, determining the position distribution pattern of the moving obstacle in each time period based on the historical movement trajectory information.

[0073] To accurately predict the location distribution of mobile obstacles, the system needs to conduct in-depth analysis of historical movement trajectory information. In this embodiment, a day is first divided into multiple time periods, such as one hour per time period. Then, the activity characteristics of each mobile obstacle in each time period are counted. These activity characteristics include the location coordinates of the mobile obstacle, movement speed, direction of movement, duration of stay in a specific area, and frequency of movement between different areas.

[0074] Specifically, the system divides the laboratory space into several area units and performs statistical analysis on the movement of mobile obstacles within each time period. By calculating the number of times a mobile obstacle appears and how long it stays in each area unit, the location distribution pattern of the mobile obstacles within that time period is determined. For example, statistics show that between 10:00 AM and 11:00 AM on weekdays, a tester spends 80% of his time moving back and forth between Area A and Area B, spending an average of 10 minutes in Area A and 15 minutes in Area B. This constitutes the location distribution pattern of the tester within that time period.

[0075] To improve the reliability of statistical results, the system aggregates and analyzes data from multiple working days. By observing the movement patterns of moving obstacles over the same time period, we can identify periodic characteristics in their behavior patterns. For example, other inspection robots, due to their fixed inspection tasks, exhibit distinct temporal periodicity in their movement patterns. While the activities of inspection personnel may exhibit a certain degree of randomness, they maintain a relatively fixed range and pattern of movement within working hours.

[0076] S42: predicting the position distribution of the moving obstacles within the target time period based on the position distribution rule.

[0077] After determining the location distribution pattern, the system predicts the location distribution of mobile obstacles within the target time period based on the pattern corresponding to the current time. The location distribution is expressed as a probability, reflecting the likelihood of mobile obstacles appearing in different areas. For example, if historical data shows that a certain inspector has an 80% probability of being in areas A and B between 10:00 and 11:00 AM, the system will predict that the inspector will also have a high probability of appearing in these two areas and the connecting path during the same time period in the future.

[0078] The system records the prediction results as regional probability values for subsequent route planning. Regions with higher probability values are more likely to have moving obstacles appear within that timeframe. This prediction method not only considers spatial location information but also incorporates temporal factors, making the predictions more realistic.

[0079] S105 , adjusting the initial inspection route according to the first position information and the position distribution to generate a target inspection route for the inspection robot.

[0080] In this example, the system first maps the locations of fixed obstacles and areas with a high probability of mobile obstacles on a 3D map of the laboratory. Based on this, a safety buffer zone is defined. This safety buffer zone extends outward from the obstacle to a predetermined distance, determined based on the robot's motion characteristics and the nature of the obstacle. For fixed obstacles, the safety buffer zone remains constant; for areas with a high probability of mobile obstacles, the range of the safety buffer zone varies over time.

[0081] The system divides the initial inspection route into segments, checking each segment for overlap with the safety buffer zone. If a path overlaps with the safety buffer zone, the system adjusts the route. This adjustment occurs in the following scenarios: If the path overlaps with the safety buffer zone for fixed obstacles, the system redirects the route by adding waypoints. If the path overlaps with an area with a high probability of mobile obstacles, the system prioritizes avoiding it by adjusting the transit time. This involves calculating a time period with a low probability of obstacles in that area and scheduling the inspection robot to pass through during that time period.

[0082] For example, if the initial inspection route requires passing through a passage frequently visited by inspectors, and the route is predicted to be heavily trafficked between 10:00 AM and 11:00 AM, the system will prioritize passing through that passage during other time periods. If the time adjustment fails to meet the timeliness requirements of the inspection task, the system will plan an alternative route, bypassing other passages to reach the target location. When making route adjustments, the system considers the total length and estimated time of the adjusted route to ensure that the adjusted route still meets the inspection time requirements of each detector.

[0083] After adjusting all road sections, the system connects the optimized paths to form a target inspection route. This target inspection route includes a detailed sequence of path coordinate points and corresponding time schedules, guiding the inspection robot to complete its inspection mission at the appropriate time and along the appropriate path. The system also annotates recommended speeds for each key path point to ensure the inspection robot can complete its movement safely and smoothly.

[0084] Based on the above embodiment, as an optional implementation, in S105, adjusting the initial inspection route according to the first position information and the position distribution to generate the target inspection route of the inspection robot specifically includes S51-S53:

[0085] S51, determining the overlapping area between the initial inspection route and the location of fixed obstacles, and the overlapping area between the initial inspection route and the location distribution of mobile obstacles.

[0086] Specifically, the system first compares the initial inspection route with the safety buffer zone of fixed obstacles to determine the location overlap area. This location overlap area refers to the section where the initial inspection route crosses the safety buffer zone of fixed obstacles. Simultaneously, the system compares the initial inspection route with the location distribution of mobile obstacles to determine the distribution overlap area. This distribution overlap area refers to the section where the initial inspection route crosses the area with a high probability of mobile obstacles.

[0087] For example, if the initial inspection route requires passing through a passage between test benches, and the width of that passage is smaller than the diameter of the safety buffer zone, then this section of the route will overlap with fixed obstacles. Similarly, if the route passes through an area where inspectors frequently move around, and the probability of personnel appearing in that area during the target time period is high, then this section of the route will overlap with mobile obstacles.

[0088] S52: Combining the position overlap area and the distribution overlap area, generating an obstacle avoidance route segment.

[0089] S53: Replace the corresponding route segment in the initial inspection route with the obstacle avoidance route segment to obtain the target inspection route.

[0090] For identified overlapping areas, the system needs to generate corresponding obstacle avoidance route segments. When generating these routes, the system employs different obstacle avoidance strategies: For areas where fixed obstacles overlap, the system plans detours by adding waypoints to ensure that the newly generated route segments do not overlap with the safety buffer zones of fixed obstacles. For areas where mobile obstacles overlap, the system prioritizes avoiding them by adjusting transit times. This involves calculating time periods with a low probability of obstacle occurrence and scheduling inspection robots to pass through them. If the time adjustment fails to meet the timeliness requirements of the inspection task, a detour is also employed to generate the obstacle avoidance route segments.

[0091] After generating obstacle avoidance route segments, the system replaces these with corresponding overlapping segments in the initial inspection route to form a complete target inspection route. This target inspection route contains a detailed sequence of path coordinate points and corresponding time schedules, guiding the inspection robot to complete the inspection task at the appropriate time and along the appropriate path. For example, if a segment of the initial route overlaps with a fixed obstacle, the system generates a detour route segment and replaces the overlapping segment to obtain a new feasible route.

[0092] On the basis of the above embodiment, after the target inspection route of the inspection robot is generated, the following steps S61-S64 are further included:

[0093] S61, obtaining the remaining power and energy consumption per unit distance of the inspection robot.

[0094] To ensure the inspection robot can continuously complete its inspection mission, the system needs to manage the robot's power status. In this embodiment, the current remaining power is first detected by the onboard power detection module of the inspection robot, along with the robot's energy consumption per unit distance. This energy consumption per unit distance refers to the amount of power consumed by the inspection robot per unit distance under standard operating conditions. This value is related to the robot's motion parameters, such as weight and speed.

[0095] S62: Calculate the estimated total energy consumption of the target inspection route based on the energy consumption per unit distance.

[0096] Specifically, the system calculates the estimated total energy consumption required to complete the target inspection route based on its total length and energy consumption per unit distance. This calculation takes into account the differences in energy consumption of the inspection robot under different operating conditions. For example, when accelerating or climbing a slope, the robot's energy consumption is higher than when in constant motion. When stopped during an inspection task, its energy consumption primarily comes from the operation of the sensors and control system. By integrating these factors, the system can obtain a relatively accurate estimate of total energy consumption.

[0097] S63: When the remaining power is less than the estimated total energy consumption, obtain third location information of the charging pile.

[0098] When the system detects that the patrol robot's remaining battery life is less than its estimated total energy consumption, it must schedule a charging task. The system first obtains the third location information of the charging station, which includes the spatial coordinates of the charging station within the laboratory's three-dimensional map. Multiple charging stations may be located within the laboratory, and the system selects the closest, available charging station as the target charging location.

[0099] S64: inserting the route segment of the inspection robot going to and from the charging pile into the target inspection route based on the third position information, generating a final inspection route, and determining the charging time point of the inspection robot.

[0100] For example, if a patrol robot has a remaining battery charge of 60%, its energy consumption per unit distance is 2% / 100 meters, and the total length of the target patrol route is 2000 meters, the estimated total energy consumption is 40%. To provide a safety margin, the system reserves a 20% remaining battery charge as a safety threshold. At this point, the system determines that the remaining battery charge is insufficient to support the complete patrol mission, and charging planning is required.

[0101] Based on the charging station's third-party location information, the system appropriately inserts route segments to and from the charging station into the target inspection route to generate the final inspection route. The following factors should be considered when inserting charging route segments: First, choose an appropriate charging time, typically charging when the remaining battery power can still support the round-trip journey to the charging station; second, insert the charging route segment in a location that minimizes the impact on the original inspection task, preferably inserting it between adjacent detectors; finally, consider the impact of charging time on the overall inspection plan and rationally schedule subsequent inspection tasks.

[0102] For example, after completing an inspection of a detector, the system might schedule the inspection robot to head to the nearest charging station for recharging. Once recharging is complete, the robot can then continue with the remaining inspection tasks. The final inspection route not only includes detailed route information but also includes specific charging times, guiding the inspection robot to recharge at the appropriate time.

[0103] Based on the above embodiment, after generating the target inspection route of the inspection robot, the following steps are specifically included: S71-S74:

[0104] S71, monitoring the actual operating status of the inspection robot on the target inspection route.

[0105] To ensure reliable execution of inspection tasks, the system needs to monitor the inspection robot's operating status in real time and make dynamic adjustments. In this embodiment, the system continuously obtains the robot's actual position information through the robot's onboard positioning module and compares this information with the target inspection route in real time. The actual operating status includes parameters such as the robot's current position coordinates, movement speed, and movement direction.

[0106] S72, when it is detected that the inspection robot deviates from the target inspection route, obtaining the actual position of the inspection robot.

[0107] Specifically, the system sets a path deviation threshold. When the deviation between the inspection robot's actual position and the target inspection route exceeds this threshold, a path deviation is considered to have occurred. Causes of path deviation may include: the appearance of an unexpected obstacle requiring the robot to temporarily avoid it, accumulated positioning system errors, or changes in ground conditions affecting the robot's movement. For example, if the inspection robot encounters temporarily placed experimental equipment during its movement and needs to perform obstacle avoidance, this may cause the actual trajectory to deviate significantly from the preset route.

[0108] S73: Regenerate the first inspection route based on the current actual position.

[0109] When the system detects a deviation from the path, it immediately uses the positioning module to determine the inspection robot's actual location. Based on this new starting position, the system replans the inspection route to the next target detector, known as the first inspection route. This first inspection route is generated using the same planning method as the initial inspection route, taking into account spatial distance and time constraints to ensure that the target location can be reached within the scheduled time.

[0110] After obtaining the first inspection route, the system needs to perform obstacle avoidance optimization. The system first obtains the first position information of fixed obstacles and the position distribution information of mobile obstacles corresponding to the current time. By analyzing the positional relationship between the first inspection route and the obstacles, the system determines the road sections requiring avoidance optimization. For example, if the first inspection route passes through an area with frequent human activity during the current time period, the system will focus on optimizing that section.

[0111] S74 , combining the first position information of the fixed obstacles and the position distribution of the mobile obstacles, adjusting the first inspection route to obtain a second inspection route, so that the inspection robot performs inspection according to the second inspection route.

[0112] The system uses the same obstacle avoidance strategy as the target inspection route to adjust the first inspection route and generate a second inspection route. The adjustment process includes determining the overlap between the route and obstacles, generating obstacle avoidance route segments, and replacing route segments. This second inspection route avoids various obstacles while ensuring the timeliness of the inspection task. After receiving the second inspection route, the inspection robot will continue its inspection task along the new route.

[0113] To avoid frequent route adjustments, the system reserves a safety margin when generating the second inspection route. For example, to avoid moving obstacles, the system will choose a wider detour to reduce the possibility of further deviations. At the same time, the system continuously monitors the inspection robot's operating status along the second inspection route and makes new route adjustments as necessary.

[0114] Based on the above method, this application also discloses a robot intelligent inspection system, such as Figure 2 As shown, Figure 2 This is a schematic diagram of the structure of a robot intelligent inspection system provided by an embodiment of the present application. The system includes: a first acquisition module, a second acquisition module, a third acquisition module, a prediction module and an adjustment module; wherein,

[0115] The first acquisition module is used to obtain the testing time of the test piece by each waterproof tester in the laboratory, and predict the target time period for the test piece to show the preset result on each waterproof tester based on the water pressure application law of each waterproof tester according to the testing time; the second acquisition module is used to obtain the current position of the inspection robot, and generate the initial inspection route of the inspection robot in combination with the current position and the target time period; the third acquisition module is used to obtain the first position information of the fixed obstacles in the laboratory, and the historical movement trajectory information of the mobile obstacles; the prediction module is used to predict the position distribution of the mobile obstacles in the target time period based on the historical movement trajectory information; the adjustment module is used to adjust the initial inspection route based on the first position information and the position distribution, and generate the target inspection route of the inspection robot.

[0116] It should be noted that the above embodiments provide systems that implement their functions using only the division of the above functional modules as an example. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above. In addition, the system and method embodiments provided in the above embodiments are based on the same concept. The specific implementation process is detailed in the method embodiment and will not be repeated here.

[0117] See Figure 3 , is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. Figure 3 As shown, the electronic device 1000 may include: at least one processor 1001 , at least one network interface 1004 , a user interface 1003 , a memory 1005 , and at least one communication bus 1002 .

[0118] The communication bus 1002 is used to implement the connection and communication between these components.

[0119] The user interface 1003 may include a display screen (Display) and a camera (Camera). Optionally, the user interface 1003 may also include a standard wired interface and a wireless interface.

[0120] The network interface 1004 may optionally include a standard wired interface or a wireless interface (such as a WI-FI interface).

[0121] Processor 1001 may include one or more processing cores. Using various interfaces and circuits, processor 1001 connects to various components within the server. It executes instructions, programs, code sets, or instruction sets stored in memory 1005, as well as accesses data stored in memory 1005, to perform various server functions and process data. Optionally, processor 1001 may be implemented using at least one of the following hardware forms: a digital signal processing (DSP), a field-programmable gate array (FPGA), or a programmable logic array (PLA). Processor 1001 may integrate one or a combination of a central processing unit (CPU), a graphics processing unit (GPU), and a modem. The CPU primarily processes the operating system, user interface, and application programs; the GPU is responsible for rendering and drawing content displayed on the display; and the modem handles wireless communications. It is understood that the modem may not be integrated into processor 1001 but implemented as a separate chip.

[0122] Among them, the memory 1005 may include a random access memory (RAM) or a read-only memory (Read-Only Memory). Optionally, the memory 1005 includes a non-transitory computer-readable storage medium. The memory 1005 can be used to store instructions, programs, codes, code sets or instruction sets. The memory 1005 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for at least one function (such as a touch function, a sound playback function, an image playback function, etc.), instructions for implementing the above-mentioned various method embodiments, etc.; the data storage area may store data involved in the above-mentioned various method embodiments, etc. The memory 1005 may optionally be at least one storage device located away from the aforementioned processor 1001. As Figure 3 As shown, the memory 1005 as a computer storage medium may include an operating system, a network communication module, a user interface module, and an application program of a robot intelligent inspection method.

[0123] exist Figure 3In the electronic device 1000 shown, the user interface 1003 is mainly used to provide an input interface for the user and obtain data input by the user; and the processor 1001 can be used to call an application program for a robot intelligent inspection method stored in the memory 1005. When executed by one or more processors, the electronic device executes one or more methods described in the above embodiments.

[0124] An electronic device readable storage medium stores instructions, which, when executed by one or more processors, enable the electronic device to execute one or more of the methods described in the above embodiments.

[0125] It should be noted that for the aforementioned method embodiments, for simplicity of description, they are all expressed as a series of action combinations, but those skilled in the art should be aware that this application is not limited by the order of the actions described, because according to this application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required for this application.

[0126] In the above embodiments, the description of each embodiment has its own focus. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0127] In the several embodiments provided in this application, it should be understood that the disclosed devices can be implemented in other ways. For example, the device embodiments described above are merely schematic. For example, the division of the units is only a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some service interfaces, and the indirect coupling or communication connection of the devices or units can be electrical or other forms.

[0128] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0129] In addition, the functional units in the various embodiments of the present application may be integrated into a single processing unit, or each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0130] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of this application, or the portion that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a memory and includes several instructions for causing a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the method described in each embodiment of this application. The aforementioned memory includes various media that can store program code, such as USB flash drives, mobile hard drives, magnetic disks, or optical disks.

[0131] The above is only an exemplary embodiment of the present disclosure and cannot be used to limit the scope of the present disclosure. That is, any equivalent changes and modifications made according to the teachings of the present disclosure are still within the scope of the present disclosure. After considering the specification and practicing the disclosure herein, those skilled in the art will easily think of other embodiments of the present disclosure. This application is intended to cover any variations, uses or adaptations of the present disclosure, which follow the general principles of the present disclosure and include common knowledge or customary technical means in the art that are not recorded in the present disclosure. The description and examples are to be regarded as exemplary only, and the scope and spirit of the present disclosure are defined by the claims.

Claims

1. A robot intelligent inspection method, characterized in that: The method comprises: Obtaining the testing time of each test piece by each waterproof tester in the laboratory, and predicting the target time period for the test piece to show a preset result on each waterproof tester based on the testing time and the hydraulic pressure application rules of each waterproof tester; Obtaining the current position of the inspection robot, and combining the current position and the target time period to generate an initial inspection route for the inspection robot, including: obtaining second position information of each of the anti-seepage detectors, and combining the current position and the second position information of each of the anti-seepage detectors to calculate the movement time of the inspection robot to reach each of the anti-seepage detectors; Sorting the inspection order of each of the anti-seepage detectors according to the movement time and the target time period to generate an inspection sequence; generating an initial inspection route for the inspection robot according to the inspection sequence; Obtaining first position information of fixed obstacles in the laboratory and historical movement trajectory information of mobile obstacles; Predicting the position distribution of the moving obstacle within the target time period based on the historical movement trajectory information; The initial inspection route is adjusted according to the first position information and the position distribution to generate a target inspection route for the inspection robot.

2. The robot intelligent inspection method according to claim 1, characterized in that: The predicting, based on the test duration, of a target time period in which a preset result appears on the test piece on each of the anti-permeability testers comprises: Obtaining historical test data of the test piece on each of the anti-seepage testers, and determining, based on the historical test data, a preset time period in which a preset result occurs on the test piece on each of the anti-seepage testers, wherein the preset result is that water seepage occurs on the test piece; Combined with the detection duration and the preset time period, the target time period for the preset results of the test pieces on each of the anti-seepage testers is predicted.

3. The robot intelligent inspection method according to claim 1, characterized in that: The predicting, based on the historical movement trajectory information, the position distribution of the moving obstacle within the target time period includes: Determining the position distribution pattern of the moving obstacle in each time period based on the historical movement trajectory information; The position distribution of the moving obstacles within the target time period is predicted based on the position distribution rule.

4. The robot intelligent inspection method according to claim 1, characterized in that: The step of adjusting the initial inspection route according to the first position information and the position distribution to generate a target inspection route for the inspection robot includes: Determine an overlapping area between the initial inspection route and the position of the fixed obstacle, and an overlapping area between the initial inspection route and the position distribution of the mobile obstacle; Combining the position overlap area and the distribution overlap area to generate an obstacle avoidance route segment; The obstacle avoidance route segment replaces the corresponding route segment in the initial inspection route to obtain the target inspection route.

5. The robot intelligent inspection method according to claim 1, characterized in that: After generating the target inspection route of the inspection robot, the method further includes: Obtaining the remaining power and energy consumption per unit distance of the inspection robot; Calculating the estimated total energy consumption of the target inspection route based on the energy consumption per unit distance; When the remaining power is less than the estimated total energy consumption, obtaining third location information of the charging pile; According to the third position information, the route segment of the inspection robot traveling to and from the charging pile is inserted into the target inspection route to generate a final inspection route, and the charging time point of the inspection robot is determined.

6. The robot intelligent inspection method according to claim 1, characterized in that: After generating the target inspection route of the inspection robot, the method further includes: Monitoring the actual operating status of the inspection robot on the target inspection route; When detecting that the inspection robot deviates from the target inspection route, obtaining the actual position of the inspection robot; regenerating a first inspection route according to the actual position; The first inspection route is adjusted based on the first position information of the fixed obstacle and the position distribution of the mobile obstacle to obtain a second inspection route, so that the inspection robot performs inspection according to the second inspection route.

7. A robot intelligent inspection system, characterized in that: The system includes: a first acquisition module, a second acquisition module, a third acquisition module, a prediction module and an adjustment module; wherein, The first acquisition module is used to obtain the testing time of the test piece by each waterproof tester in the laboratory, and based on the water pressure application law of each waterproof tester and the testing time, predict the target time period for the test piece to show a preset result on each waterproof tester; The second acquisition module is used to obtain the current position of the inspection robot, and generate an initial inspection route for the inspection robot in combination with the current position and the target time period, including: obtaining the second position information of each of the anti-seepage detectors, and calculating the movement time of the inspection robot to reach each of the anti-seepage detectors in combination with the current position and the second position information of each of the anti-seepage detectors; sorting the inspection order of each of the anti-seepage detectors according to the movement time and the target time period to generate an inspection sequence; and generating the initial inspection route of the inspection robot according to the inspection sequence; The third acquisition module is used to obtain first position information of fixed obstacles in the laboratory and historical movement trajectory information of mobile obstacles; The prediction module is configured to predict the position distribution of the moving obstacle within the target time period based on the historical movement trajectory information; The adjustment module is used to adjust the initial inspection route according to the first position information and the position distribution to generate a target inspection route for the inspection robot.

8. An electronic device, characterized in that: It includes a processor, a memory, a user interface and a network interface, the memory is used to store instructions, the user interface and the network interface are used to communicate with other devices, and the processor is used to execute the instructions stored in the memory so that the electronic device executes the method according to any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that A computer program is stored which can be loaded by a processor and execute the method according to any one of claims 1 to 6.

Images