Method and device for optimizing track of nuclear pollution reconnaissance robot
By combining Gaussian multi-puff model and real-time monitoring data, the trajectory planning of nuclear pollution reconnaissance robot was optimized, solving the prediction error problem of information collection path at nuclear accident sites and achieving efficient and safe nuclear pollution reconnaissance.
Patent Information
- Application Number
- CN202511417583.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-09-30
- Publication Date
- 2026-01-13
AI Technical Summary
In existing technologies, the movement trajectory of nuclear contamination reconnaissance robots cannot adapt to the sudden changes in the environment at nuclear accident sites, resulting in significant prediction errors and an inability to effectively optimize information collection paths.
By acquiring parameter data of the nuclear leak area, a Gaussian multi-puff model is used to generate a predicted concentration field and an uncertainty field. Sensitive locations are calibrated by combining sensitivity thresholds and sensitive area layers, a set of target points is determined, and a patrol trajectory sequence of the nuclear pollution reconnaissance robot is planned based on real-time monitoring data.
Significantly improve regional coverage within the same task timeframe, ensure safe and reliable routes, guarantee personnel safety and data timeliness, and adapt to complex environments.
Smart Images
Figure CN121323633A_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of nuclear emergency technology, and in particular to a method and apparatus for optimizing the trajectory of a nuclear contamination reconnaissance robot. Background Technology
[0002] The nuclear emergency heavy contamination close-range reconnaissance robot vehicle fulfills the critical practical need for nuclear emergency rescue teams to simultaneously transport personnel and robots to approach heavily contaminated areas of nuclear accident sites to perform reconnaissance missions. It solves technical bottlenecks encountered when conducting reconnaissance missions in harsh environments and heavily contaminated areas at nuclear accident sites, including personnel radiation protection, equipment resistance to strong radiation, network communication, and rapid monitoring and sampling of all aerosol elements. It can quickly obtain first-hand, accurate, and real-time data at the accident source, providing strong support for nuclear accident emergency rescue command and decision-making. This is of paramount importance for improving the effectiveness of nuclear emergency response teams and ensuring the safety of nuclear and public lives.
[0003] In order to grasp the overall situation and its evolution direction in a timely manner during a sudden nuclear and chemical event, maximize resource utilization, and obtain the most comprehensive situational information at the lowest cost, the motion trajectory of robot information collection is particularly important. However, in the current technology, the motion trajectory of robot information collection cannot adapt to the sudden change environment at the nuclear accident site, resulting in a large prediction error. Summary of the Invention
[0004] The purpose of this application is to address at least one of the aforementioned technical deficiencies.
[0005] On the one hand, embodiments of this application provide a method for optimizing the trajectory of a nuclear contamination reconnaissance robot, the method comprising: Obtain parameter data corresponding to the nuclear leak area, and obtain the predicted concentration field and uncertainty field based on the parameter data through a Gaussian multi-puff model. The parameter data includes source parameters, meteorological data and geographical data. Obtain the preset sensitivity threshold and sensitive area layer, and mark the sensitive location of the nuclear leakage area based on the predicted concentration field, uncertainty field, preset sensitivity threshold and sensitive area layer to obtain the set of sensitive area coordinate points; Obtain the preset priority rules, and determine the priority of each sensitive area coordinate point in the sensitive area coordinate point set according to the priority rules to obtain the target point set; Real-time monitoring data corresponding to the leak area is obtained, and the target point set is planned and constrained based on the real-time monitoring data to obtain the patrol trajectory sequence of the nuclear pollution reconnaissance robot.
[0006] Optionally, source parameters include source strength, source location and release height, meteorological data includes wind speed and wind direction data, and geographic data includes three-dimensional terrain data and building distribution.
[0007] Optionally, based on the parameter data, a Gaussian multi-puff model is used to obtain the predicted concentration field and uncertainty field, including: Based on wind speed and wind direction data, diffusion parameters are determined, and the source term parameters and diffusion parameters are input into the Gaussian multi-puff model to obtain the predicted nuclide concentrations. A two-dimensional grid is established based on three-dimensional terrain data and building distribution. The predicted concentration of nuclides stored at each grid point in the two-dimensional grid is determined based on the predicted concentration of nuclides, thus obtaining the predicted concentration field. The standard deviation of the predicted nuclide concentration stored at each grid point was determined using the Monte Carlo simulation method, thus obtaining the uncertainty field.
[0008] Optionally, the preset sensitivity thresholds include a concentration threshold and an uncertainty threshold. Based on the predicted concentration field, the uncertainty field, the preset sensitivity thresholds, and the sensitive area layer, the sensitive locations of the nuclear leakage area are calibrated to obtain a set of sensitive area coordinate points, including: The gradient field of the predicted concentration field is determined based on the central difference method, and the high gradient region corresponding to the gradient field is identified. The grid points in the predicted concentration field are filtered based on the concentration threshold and the sensitive area layer to obtain the filtered predicted concentration field. The grid points in the uncertainty field are filtered according to the uncertainty threshold to obtain the filtered uncertainty field; Based on the selected predicted concentration field and the selected uncertainty field, a set of sensitive area coordinate points is obtained. The set of sensitive area coordinate points includes the coordinates, type, gradient magnitude, concentration value and uncertainty value of each sensitive point.
[0009] Optionally, the high gradient region corresponding to the gradient field is determined, including: Determine the gradient magnitude corresponding to each grid point in the gradient field; Based on the gradient magnitude corresponding to each grid point, all grid points in the gradient field are sorted in ascending and descending order, and high gradient regions are determined from all sorted grid points according to preset rules.
[0010] Optionally, the grid points in the predicted concentration field are filtered based on a concentration threshold and a sensitive region layer to obtain a filtered predicted concentration field, including: The grid points included in the predicted concentration field are initially screened based on the concentration threshold to obtain the grid points after initial screening. The initially filtered grid points are overlaid with each sensitive point in the sensitive area layer to obtain the filtered predicted concentration field.
[0011] Optionally, the target point set includes each geographic coordinate point and its corresponding priority type and weight. The priority of each sensitive area coordinate point in the sensitive area coordinate point set is determined according to priority rules, resulting in the target point set, which includes: Convert each sensitive area coordinate point in the sensitive area coordinate point set into a geographic coordinate point set to obtain a geographic coordinate point set. The priority type of each geographic coordinate point in the set of geographic coordinate points is determined according to the priority rules. The weight corresponding to each geographic coordinate point is determined based on the weight corresponding to each priority type and the priority type corresponding to each geographic coordinate point.
[0012] Optionally, the target point set is subjected to planning constraints based on real-time monitoring data to obtain the patrol trajectory sequence of the nuclear contamination reconnaissance robot, including: The highest priority geographic coordinate point in the target point set is selected as the candidate driving point for the nuclear contamination reconnaissance robot at the next moment, and the shortest path from the nuclear contamination reconnaissance robot to the candidate driving point is determined based on real-time monitoring data. If the shortest path meets the shortest path radiation dose rate requirement, then the candidate travel point will be used as the travel point of the nuclear contamination reconnaissance robot at the next moment, and the geographical coordinates corresponding to the travel point of the nuclear contamination reconnaissance robot at the next moment will be deducted from the target point set to obtain the remaining target point set. The remaining target point set is used as the target point set for iteration until the resulting remaining target point set no longer includes geographic coordinate points; The sequence obtained by combining the next travel points of the nuclear pollution reconnaissance robot during the iteration process is used as the patrol trajectory sequence of the nuclear pollution reconnaissance robot.
[0013] Optionally, real-time monitoring data includes the current location, terrain accessibility, and radiation dose rate of the nuclear contamination reconnaissance robot. Based on this data, the shortest path from the nuclear contamination reconnaissance robot to the candidate travel point is determined, including: Based on radiation dose rate and terrain accessibility, the cumulative radiation dose of the nuclear contamination reconnaissance robot from its current location to the candidate travel point is determined; Determine the Euclidean distance from the nuclear contamination reconnaissance robot's current location to the candidate travel point; The shortest path from the nuclear contamination reconnaissance robot to the candidate driving point is determined based on the cumulative radiation dose and Euclidean distance.
[0014] On the other hand, embodiments of this application provide an optimization device for the trajectory of a nuclear contamination reconnaissance robot, characterized in that it includes: The data acquisition module is used to acquire parameter data corresponding to the nuclear leak area, and obtain the predicted concentration field and uncertainty field based on the parameter data through the Gaussian multi-puff model. The parameter data includes source parameters, meteorological data and geographical data. The sensitive area coordinate point processing module is used to obtain the preset sensitivity threshold and sensitive area layer, and to perform sensitive area location calibration on the nuclear leakage area based on the predicted concentration field, uncertainty field, preset sensitivity threshold and sensitive area layer, to obtain a set of sensitive area coordinate points; The target point set processing module is used to obtain preset priority rules and determine the priority of each sensitive area coordinate point in the sensitive area coordinate point set according to the priority rules, so as to obtain the target point set. The trajectory sequence determination module is used to acquire real-time monitoring data corresponding to the leak area, and to perform planning constraint processing on the target point set based on the real-time monitoring data to obtain the patrol trajectory sequence of the nuclear pollution reconnaissance robot.
[0015] In another aspect, embodiments of this application provide an electronic device, including a processor and a memory: The memory is configured to store machine-readable instructions that, when executed by the processor, cause the processor to perform any of the methods in an optimized approach for tracing the trajectory of a nuclear contamination reconnaissance robot.
[0016] The beneficial effects of the technical solutions provided in this application include at least the following: In this application, source parameters, meteorological data, and geographical data corresponding to the nuclear leak area can be obtained. Then, a Gaussian multi-puff model is used to obtain the predicted concentration field and uncertainty field. During this process, measured data and model data can be fused to reduce prediction errors. Furthermore, based on the determined predicted concentration field, uncertainty field, preset sensitivity threshold, and sensitive area layer, the sensitive location of the nuclear leak area can be calibrated to obtain a set of sensitive area coordinate points. Finally, based on the obtained set of sensitive area coordinate points and real-time monitoring data, the patrol trajectory sequence of the nuclear contamination reconnaissance robot is obtained. In other words, the hierarchical sensitive location calibration dynamic path planning in this application can significantly improve the coverage of the area within the same task time. At the same time, multiple constraints are used in the path planning process to ensure the safety and reliability of the path, guaranteeing personnel safety, data timeliness, and adaptability to complex environments. Attached Figure Description
[0017] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.
[0018] Figure 1 A schematic flowchart illustrating the optimization of the trajectory of a nuclear contamination reconnaissance robot provided in this application embodiment; Figure 2 A schematic diagram of the structure of a device for optimizing the trajectory of a nuclear contamination reconnaissance robot provided in an embodiment of this application; Figure 3 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation
[0019] The embodiments of this application are described in detail below. Examples of these embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain this application, and should not be construed as limiting the invention.
[0020] Those skilled in the art will understand that, unless specifically stated otherwise, the singular forms “a,” “an,” “the,” and “the” used herein may also include the plural forms. It should be further understood that the term “comprising” as used in this application means the presence of the stated features, integers, steps, operations, elements, and / or components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups thereof. It should be understood that when we say an element is “connected” or “coupled” to another element, it can be directly connected or coupled to the other element, or there may be intermediate elements. Furthermore, “connected” or “coupled” as used herein can include wireless connections or wireless coupling. The term “and / or” as used herein includes all or any units and all combinations of one or more associated listed items.
[0021] To make the objectives, technical solutions, and advantages of this application clearer, the embodiments of this application will be described in further detail below with reference to the accompanying drawings.
[0022] The technical solution of this application and how the technical solution of this application solves the above-mentioned technical problems are described in detail below with specific embodiments. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments. The embodiments of this application will now be described with reference to the accompanying drawings.
[0023] Specifically, such as Figure 1 As shown, the method may include: Step S101: Obtain parameter data corresponding to the nuclear leakage area, and obtain the predicted concentration field and uncertainty field based on the parameter data through the Gaussian multi-puff model. The parameter data includes source parameters, meteorological data and geographical data.
[0024] In optional embodiments of this application, the source parameters include source strength, source location and release height, the meteorological data includes wind speed data and wind direction data, and the geographic data includes three-dimensional terrain data and building distribution.
[0025] Optionally, meteorological data refers to parameters such as wind speed and direction at the nuclear leak area. In practical applications, meteorological data can be collected using miniature meteorological sensors (anemometers, thermometers, hygrometers, and barometers, etc.) integrated on the top of the robotic vehicle. Source term parameters refer to the source strength, release location, and effective height of the radioactive material. The source strength specifically refers to the release rate of the radioactive material, and the release location can be expressed using latitude and longitude. In practical applications, the hazard range corresponding to the nuclear leak area can be predicted based on the source term parameters, and subsequent work can be carried out based on the obtained hazard range. Geographic data refers to three-dimensional geographic information, which can include three-dimensional terrain data and building distribution information, and can be collected through the GIS (Geographic Information System) system integrated into the system. Furthermore, based on the acquired parameter data, a Gaussian multi-puff model can be used to obtain the predicted concentration field and uncertainty field.
[0026] Optionally, the source term parameters can be determined in the following ways: The diffusion coefficient value was calculated based on geographical and meteorological data, and a Gaussian multiplying smoke model was constructed based on the diffusion coefficient value. The initial leakage source term information is obtained, and the predicted nuclide activity concentration is obtained based on the initial leakage source term information and the Gaussian multipuff model. The initial leakage source term information includes the assumed leakage source strength and the assumed leakage location. Based on the predicted nuclide activity concentration and the nuclide activity concentration processed by Kalman filtering, leakage source term information is obtained.
[0027] Optionally, the diffusion coefficient value can be determined based on geographic and meteorological data and existing atmospheric stability classification tables. s x , s y and s z (σ) x σ y σ represents the atmospheric lateral diffusion coefficient. z (This represents the atmospheric vertical diffusion coefficient). Then, based on the determined diffusion coefficient value, a Gaussian multiplying smoke model is constructed, as shown below:
[0028] in, These represent the coordinates of the calculation point relative to the leak point. Indicates in t At any point in time and space（ ） The predicted nuclide concentration at the release location (in the source term parameters) is given, with the leak point at (0, 0, 0). Q This represents the source strength in the initial source term parameters. u This represents the average wind speed at the source elevation. This represents the atmospheric lateral diffusion coefficient. s z Indicates the atmospheric vertical diffusion coefficient. H This indicates the effective height of the source strength in the initial term parameters. f d This is a radioactive decay term. f q For deposition attenuation term, L The wet deposition coefficient is... The settling velocity is the dry deposition velocity of aerosol particles.
[0029] Optional, f d It satisfies the radionuclide decay formula. f q The deposition attenuation term satisfies the following formula:
[0030] L The wet deposition coefficient satisfies the following formula:
[0031] in, I The value represents the rainfall intensity (mm / h). a and b are empirical coefficients, assigned values based on whether the released substance contains iodine or not. For example, for iodine-containing substances, a can be taken as a = 8 × 10⁻⁶. -5 b = 0.6, while for substances without iodine, a = 1.2 × 10⁻⁶. -4 b=0.5.
[0032] Furthermore, the assumed leakage source strength and assumed leakage location are input into the Gaussian multi-puff model, at which point the predicted nuclide activity concentration can be obtained. Then, based on the predicted nuclide activity concentration and the nuclide activity concentration, the leakage source term information is obtained through Kalman filtering.
[0033] The Kalman filtering process includes a prediction step and an update step. The prediction step is expressed as follows:
[0034]
[0035] in, Information on the source of the leak at the current moment. This refers to the leak source information from the previous moment. Let be the error covariance matrix. Let be the error covariance matrix of the previous time step. Let Q be the state transition matrix and Q be the process noise covariance matrix.
[0036] The update steps are as follows:
[0037]
[0038]
[0039] in, Here is the Kalman gain matrix. Let be the error covariance matrix. For the observation matrix, To observe the noise covariance matrix, Information on the source of the leak at the current moment. This refers to the activity concentration of the radionuclide. It is an identity matrix.
[0040] In optional embodiments of this application, the predicted concentration field and uncertainty field are obtained based on parameter data using a Gaussian multi-puff model, including: Based on wind speed and wind direction data, diffusion parameters are determined, and the source term parameters and diffusion parameters are input into the Gaussian multi-puff model to obtain the predicted nuclide concentrations. A two-dimensional grid is established based on three-dimensional terrain data and building distribution. The predicted concentration of nuclides stored at each grid point in the two-dimensional grid is determined based on the predicted concentration of nuclides, thus obtaining the predicted concentration field. The standard deviation of the predicted nuclide concentration stored at each grid point was determined using the Monte Carlo simulation method, thus obtaining the uncertainty field.
[0041] Optionally, due to the diffusion parameter (i.e. s x , s y and s z The atmospheric stability is determined by atmospheric stability, which is classified into six categories (A, B, C) from highly unstable to stable. The specific atmospheric stability can be determined by referring to the table below based on the wind speed and direction data obtained from the meteorological data. Then, based on the corresponding atmospheric stability... s x , s y and s z The calculation formula in Table 2 is used to obtain the result.
[0042] Table 1. Correspondence of Atmospheric Stability
[0043] Table 2 Calculation Formulas
[0044] Furthermore, by inputting the determined diffusion parameters into the Gaussian multi-puff model, the predicted nuclide concentration can be obtained. For the corresponding nuclear leak area, a grid can be created based on the collected 3D terrain data and building distribution (e.g., a 10m × 10m grid) to obtain the corresponding 2D grid for the nuclear leak area. The concentration of each grid point in the 2D grid is then calculated based on the predicted nuclide concentration obtained through the Gaussian multi-puff model. The z-coordinate of the grid point is usually taken as the ground height (e.g., 1m). For grid points corresponding to areas blocked by buildings, the predicted nuclide concentration stored in those grid points is set to 0 (or ignored). After determining the concentration of each grid point in the 2D grid, the predicted concentration field is obtained.
[0045] Accordingly, after determining the predicted nuclide concentration stored at each grid point, the standard deviation of the predicted nuclide concentration stored at each grid point can be determined using the Monte Carlo simulation method. Specifically, this can be achieved by considering the input parameters (source strength, wind speed, and diffusion parameters). y Add random perturbations (following a normal distribution) to the grid, run multiple diffusion simulations, and then calculate the standard deviation of the concentration at each grid point to obtain the corresponding uncertainty field.
[0046] Step S102: Obtain the preset sensitivity threshold and sensitive area layer, and mark the sensitive location of the nuclear leakage area according to the predicted concentration field, uncertainty field, preset sensitivity threshold and sensitive area layer to obtain the set of sensitive area coordinate points.
[0047] Optionally, the sensitivity threshold may include a concentration threshold and an uncertainty threshold. The specific values of the thresholds can be set according to actual conditions, and this application embodiment does not impose any limitations. For example, the concentration threshold for a residential area is 1 μSv / h, and the corresponding uncertainty threshold is 0.5 μSv / h. The sensitive area layer comes from a GIS system, which marks the locations (polygons or point sets) of sensitive areas such as residential areas and water sources. Furthermore, the sensitive location of the nuclear leak area can be calibrated based on the predicted concentration field, the uncertainty field, the preset sensitivity threshold, and the sensitive area layer to obtain a set of sensitive area coordinate points.
[0048] In an optional embodiment of this application, the preset sensitivity threshold includes a concentration threshold and an uncertainty threshold. Based on the predicted concentration field, the uncertainty field, the preset sensitivity threshold, and the sensitive area layer, the sensitive location of the nuclear leakage area is calibrated to obtain a set of sensitive area coordinate points, including: The gradient field of the predicted concentration field is determined based on the central difference method, and the high gradient region corresponding to the gradient field is identified. The grid points in the predicted concentration field are filtered based on the concentration threshold and the sensitive area layer to obtain the filtered predicted concentration field. The grid points in the uncertainty field are filtered according to the uncertainty threshold to obtain the filtered uncertainty field; Based on the selected predicted concentration field and the selected uncertainty field, a set of sensitive area coordinate points is obtained. The set of sensitive area coordinate points includes the coordinates, type, gradient magnitude, concentration value and uncertainty value of each sensitive point.
[0049] Optionally, the concentration value can be stored for each grid point in the predicted concentration field. The horizontal and vertical gradients corresponding to each grid point are determined using the central difference method. Then, based on the obtained horizontal and vertical gradients, the high gradient corresponding to that grid point is obtained. Accordingly, after determining the high gradient for each grid point, the gradient field of the predicted concentration field is composed of the high gradients corresponding to all grid points.
[0050] The horizontal gradient is calculated using the central difference method (second-order accuracy):
[0051] in, Between two grid points Spacing between directions (e.g., 10m), left boundary ( i =0) Use forward difference right boundary ( i = N Based on backward difference .
[0052] Vertical gradient:
[0053] in, The distance between two grid points in the y-direction, left boundary ( j =0) Use forward difference right boundary ( i = N Based on backward difference .
[0054] Correspondingly, at this time each grid point Output a two-dimensional vector That is, gradient field Then, the high gradient region corresponding to the gradient field is determined, that is, the region with the maximum concentration gradient (diffusion front) is identified.
[0055] Furthermore, based on a preset concentration threshold and the acquired sensitive region layer, the grid points in the predicted concentration field are filtered to obtain a filtered predicted concentration field. Simultaneously, based on the standard deviation (i.e., uncertainty) of each grid point, grid points with uncertainties greater than the uncertainty threshold are identified from all grid points, resulting in a filtered uncertainty field. Correspondingly, the grid points in the filtered predicted concentration field and the grid points in the filtered uncertainty field are combined to obtain a set of sensitive region coordinate points. This set of sensitive region coordinate points is a list, where each element contains information about a sensitive point, including coordinates, type (specifically, whether it's a diffusion front, a point exceeding the sensitivity threshold, or a high gradient region), and additional information (such as the corresponding gradient magnitude, concentration value, uncertainty value, etc.).
[0056] In an optional embodiment of this application, determining the high gradient region corresponding to the gradient field includes: Determine the gradient magnitude corresponding to each grid point in the gradient field; Based on the gradient magnitude corresponding to each grid point, all grid points in the gradient field are sorted in ascending and descending order, and high gradient regions are determined from all sorted grid points according to preset rules.
[0057] Optionally, when determining the high gradient region corresponding to the gradient field, the gradient magnitude corresponding to each grid point is calculated based on the gradient magnitude formula:
[0058] in, The gradient magnitude corresponding to the grid point. For horizontal gradient, For vertical gradient, x and y These are the coordinates of the grid points.
[0059] Furthermore, all grid points in the entire region are sorted from largest to smallest according to their gradient magnitude. Based on preset rules, high gradient regions are determined from all sorted grid points, such as selecting the top 10% of grid points as high gradient regions.
[0060] In an optional embodiment of this application, the grid points in the predicted concentration field are filtered according to a concentration threshold and a sensitive region layer to obtain a filtered predicted concentration field, including: The grid points included in the predicted concentration field are initially screened based on the concentration threshold to obtain the grid points after initial screening. The initially filtered grid points are overlaid with each sensitive point in the sensitive area layer to obtain the filtered predicted concentration field.
[0061] Optionally, in the predicted concentration field, all grid points included in the predicted concentration field are filtered according to the concentration threshold to find all grid points with concentration values greater than the concentration threshold. Then, the grid points with concentration values greater than the concentration threshold are overlaid with the sensitive area layer, and the grid points located in the sensitive area (such as residential area or water source) are retained to obtain the filtered predicted concentration field. At this time, the grid points in the filtered predicted concentration field are of the type of points with super-sensitivity threshold.
[0062] Step S103: Obtain the preset priority rules, and determine the priority of each sensitive area coordinate point in the sensitive area coordinate point set according to the priority rules, so as to obtain the target point set.
[0063] Optionally, priority rules can be set according to the actual situation. For example, the first level is the high concentration gradient area (i.e., the diffusion front), which has the highest priority (largest weight); the second level is population / ecological sensitive points (points with supersensitivity threshold), which have medium priority; and the third level is the high gradient area, which has the lowest priority. Accordingly, after obtaining the set of sensitive area coordinate points, the priority of each sensitive area coordinate point in the set of sensitive area coordinate points can be determined according to this priority rule to obtain the target point set.
[0064] In an optional embodiment of this application, the target point set includes each geographic coordinate point and the priority type and weight corresponding to each geographic coordinate point. The priority of each sensitive area coordinate point in the sensitive area coordinate point set is determined according to priority rules to obtain the target point set, including: Convert each sensitive area coordinate point in the sensitive area coordinate point set into a geographic coordinate point set to obtain a geographic coordinate point set. The priority type of each geographic coordinate point in the set of geographic coordinate points is determined according to the priority rules. The weight corresponding to each geographic coordinate point is determined based on the weight corresponding to each priority type and the priority type corresponding to each geographic coordinate point.
[0065] Optionally, each sensitive area coordinate point in the sensitive area coordinate point set is converted into a geographic coordinate point. This will result in a geographic coordinate point set. Then, based on priority rules, the priority type and corresponding weight of each coordinate point in the geographic coordinate point set (i.e., the type of the corresponding network point) are determined. The resulting geographic coordinate point set is the target point set. Each point in the target point set includes coordinates, type, and priority weight.
[0066] Step S104: Obtain real-time monitoring data corresponding to the leak area, and perform planning constraint processing on the target point set based on the real-time monitoring data to obtain the patrol trajectory sequence of the nuclear pollution reconnaissance robot.
[0067] In an optional embodiment of this application, the target point set is subjected to planning constraint processing based on real-time monitoring data to obtain the patrol trajectory sequence of the nuclear contamination reconnaissance robot, including: The highest priority geographic coordinate point in the target point set is selected as the candidate driving point for the nuclear contamination reconnaissance robot at the next moment, and the shortest path from the nuclear contamination reconnaissance robot to the candidate driving point is determined based on real-time monitoring data. If the shortest path meets the shortest path radiation dose rate requirement, then the candidate travel point will be used as the travel point of the nuclear contamination reconnaissance robot at the next moment, and the geographical coordinates corresponding to the travel point of the nuclear contamination reconnaissance robot at the next moment will be deducted from the target point set to obtain the remaining target point set. The remaining target point set is used as the target point set for iteration until the resulting remaining target point set no longer includes geographic coordinate points; The sequence obtained by combining the next travel points of the nuclear pollution reconnaissance robot during the iteration process is used as the patrol trajectory sequence of the nuclear pollution reconnaissance robot.
[0068] Optionally, the highest priority geographic coordinate point can be selected from the set of target points as the candidate driving point for the robot at the next moment, and then the shortest path from the nuclear pollution reconnaissance robot to the candidate driving point can be determined based on real-time monitoring data.
[0069] In optional embodiments of this application, the real-time monitoring data includes the current location, terrain accessibility, and radiation dose rate of the nuclear contamination reconnaissance robot. Determining the shortest path from the nuclear contamination reconnaissance robot to the candidate travel point based on the real-time monitoring data includes: Based on radiation dose rate and terrain accessibility, the cumulative radiation dose of the nuclear contamination reconnaissance robot from its current location to the candidate travel point is determined; Determine the Euclidean distance from the nuclear contamination reconnaissance robot's current location to the candidate travel point; The shortest path from the nuclear contamination reconnaissance robot to the candidate driving point is determined based on the cumulative radiation dose and Euclidean distance.
[0070] Optionally, the acquired real-time monitoring data includes the current location, terrain accessibility, and radiation dose rate of the nuclear contamination reconnaissance robot. The robot's current location is represented by latitude and longitude or planar coordinates. The terrain accessibility data is a GIS layer of road networks (accessible paths) and obstacles (collapsed buildings, impassable areas). The radiation dose rate is the radiation dose rate distribution of the current area, which can be acquired by a vehicle-mounted gamma dose rate monitor.
[0071] Accordingly, after determining the next candidate travel point, the cumulative radiation dose of the nuclear contamination reconnaissance robot from its current location to the candidate travel point, as well as the Euclidean distance between the robot and the candidate travel point, can be determined based on the obtained radiation dose rate and terrain accessibility. The sum of the cumulative radiation dose and the Euclidean distance is then used as the shortest path from the nuclear contamination reconnaissance robot to the candidate travel point, which can be characterized by a cost function. f(n) = g(n) + h(n) Where g(n) is the actual cost from the current position to the next candidate travel point n (including distance and cumulative dose along the path), and h(n) is the heuristic cost (such as Euclidean distance). When estimating the cumulative radiation dose for the nuclear contamination reconnaissance robot from its current position to the candidate travel point, the path can be divided into small segments, the dose of each segment determined, and the dose and value of each segment used as the cumulative radiation dose. The dose of each segment = average dose rate of that segment × travel time (i.e., time = distance / robot speed).
[0072] Furthermore, if the obtained shortest path meets the shortest path radiation dose rate requirement (e.g., less than a set safety threshold), the candidate travel point is used as the travel point for the nuclear contamination reconnaissance robot at the next moment (i.e., added to the robot's travel path). The geographical coordinates corresponding to the candidate travel point are then deducted from the target point set to obtain the remaining target point set. This remaining target point set is used as the target point set, and the next target point is selected from it as the candidate travel point for the next moment. This process is iterated using the method described above until the remaining target point set no longer includes geographical coordinates. Accordingly, after the iteration ends, the sequence of robot travel points obtained during the iteration process is used as the nuclear contamination reconnaissance robot's patrol trajectory sequence and sent to the contamination reconnaissance robot for execution.
[0073] In this application, source parameters, meteorological data, and geographical data corresponding to the nuclear leak area can be obtained. Then, a Gaussian multi-puff model is used to obtain the predicted concentration field and uncertainty field. During this process, measured data and model data can be fused to reduce prediction errors. Furthermore, based on the determined predicted concentration field, uncertainty field, preset sensitivity threshold, and sensitive area layer, the sensitive location of the nuclear leak area can be calibrated to obtain a set of sensitive area coordinate points. Finally, based on the obtained set of sensitive area coordinate points and real-time monitoring data, the patrol trajectory sequence of the nuclear contamination reconnaissance robot is obtained. In other words, the hierarchical sensitive location calibration dynamic path planning in this application can significantly improve the coverage of the area within the same task time. At the same time, multiple constraints are used in the path planning process to ensure the safety and reliability of the path, guaranteeing personnel safety, data timeliness, and adaptability to complex environments.
[0074] This application provides an optimization device for the trajectory of a nuclear contamination reconnaissance robot, such as... Figure 2 As shown, the device may include: a data acquisition module 201, a sensitive area coordinate point processing module 202, a target point set processing module 203, and a trajectory sequence determination module 204, wherein, The data acquisition module is used to acquire parameter data corresponding to the nuclear leak area, and obtain the predicted concentration field and uncertainty field based on the parameter data through the Gaussian multi-puff model. The parameter data includes source parameters, meteorological data and geographical data. The sensitive area coordinate point processing module is used to obtain the preset sensitivity threshold and sensitive area layer, and to perform sensitive area location calibration on the nuclear leakage area based on the predicted concentration field, uncertainty field, preset sensitivity threshold and sensitive area layer, to obtain a set of sensitive area coordinate points; The target point set processing module is used to obtain preset priority rules and determine the priority of each sensitive area coordinate point in the sensitive area coordinate point set according to the priority rules, so as to obtain the target point set. The trajectory sequence determination module is used to acquire real-time monitoring data corresponding to the leak area, and to perform planning constraint processing on the target point set based on the real-time monitoring data to obtain the patrol trajectory sequence of the nuclear pollution reconnaissance robot.
[0075] Optionally, source parameters include source strength, source location and release height, meteorological data includes wind speed and wind direction data, and geographic data includes three-dimensional terrain data and building distribution.
[0076] Optionally, when the data acquisition module obtains the predicted concentration field and uncertainty field based on the parameter data using a Gaussian multi-puff model, it is specifically used for: Based on wind speed and wind direction data, diffusion parameters are determined, and the source term parameters and diffusion parameters are input into the Gaussian multi-puff model to obtain the predicted nuclide concentrations. A two-dimensional grid is established based on three-dimensional terrain data and building distribution. The predicted concentration of nuclides stored at each grid point in the two-dimensional grid is determined based on the predicted concentration of nuclides, thus obtaining the predicted concentration field. The standard deviation of the predicted nuclide concentration stored at each grid point was determined using the Monte Carlo simulation method, thus obtaining the uncertainty field.
[0077] Optionally, the preset sensitivity thresholds include a concentration threshold and an uncertainty threshold. When the sensitive area coordinate point processing module calibrates the sensitive location of the nuclear leakage area based on the predicted concentration field, uncertainty field, preset sensitivity thresholds, and sensitive area layer to obtain the sensitive area coordinate point set, it is specifically used for: The gradient field of the predicted concentration field is determined based on the central difference method, and the high gradient region corresponding to the gradient field is identified. The grid points in the predicted concentration field are filtered based on the concentration threshold and the sensitive area layer to obtain the filtered predicted concentration field. The grid points in the uncertainty field are filtered according to the uncertainty threshold to obtain the filtered uncertainty field; Based on the selected predicted concentration field and the selected uncertainty field, a set of sensitive area coordinate points is obtained. The set of sensitive area coordinate points includes the coordinates, type, gradient magnitude, concentration value and uncertainty value of each sensitive point.
[0078] Optionally, the sensitive area coordinate point processing module is specifically used to determine the high gradient region corresponding to the gradient field when: Determine the gradient magnitude corresponding to each grid point in the gradient field; Based on the gradient magnitude corresponding to each grid point, all grid points in the gradient field are sorted in ascending and descending order, and high gradient regions are determined from all sorted grid points according to preset rules.
[0079] Optionally, the sensitive area coordinate point processing module, when filtering the grid points in the predicted concentration field based on the concentration threshold and the sensitive area layer to obtain the filtered predicted concentration field, is specifically used for: The grid points included in the predicted concentration field are initially screened based on the concentration threshold to obtain the grid points after initial screening. The initially filtered grid points are overlaid with each sensitive point in the sensitive area layer to obtain the filtered predicted concentration field.
[0080] Optionally, the target point set includes each geographic coordinate point and its corresponding priority type and weight. When the target point set processing module determines the priority of each sensitive area coordinate point in the sensitive area coordinate point set according to the priority rules to obtain the target point set, it is specifically used for: Convert each sensitive area coordinate point in the sensitive area coordinate point set into a geographic coordinate point set to obtain a geographic coordinate point set. The priority type of each geographic coordinate point in the set of geographic coordinate points is determined according to the priority rules. The weight corresponding to each geographic coordinate point is determined based on the weight corresponding to each priority type and the priority type corresponding to each geographic coordinate point.
[0081] Optionally, when the trajectory sequence determination module performs planning and constraint processing on the target point set based on real-time monitoring data to obtain the patrol trajectory sequence of the nuclear contamination reconnaissance robot, it is specifically used for: The highest priority geographic coordinate point in the target point set is selected as the candidate driving point for the nuclear contamination reconnaissance robot at the next moment, and the shortest path from the nuclear contamination reconnaissance robot to the candidate driving point is determined based on real-time monitoring data. If the shortest path meets the shortest path radiation dose rate requirement, then the candidate travel point will be used as the travel point of the nuclear contamination reconnaissance robot at the next moment, and the geographical coordinates corresponding to the travel point of the nuclear contamination reconnaissance robot at the next moment will be deducted from the target point set to obtain the remaining target point set. The remaining target point set is used as the target point set for iteration until the resulting remaining target point set no longer includes geographic coordinate points; The sequence obtained by combining the next travel points of the nuclear pollution reconnaissance robot during the iteration process is used as the patrol trajectory sequence of the nuclear pollution reconnaissance robot.
[0082] Optionally, the real-time monitoring data includes the current location, terrain accessibility, and radiation dose rate of the nuclear contamination reconnaissance robot. When determining the shortest path from the nuclear contamination reconnaissance robot to the candidate travel point based on the real-time monitoring data, it is specifically used for: Based on radiation dose rate and terrain accessibility, the cumulative radiation dose of the nuclear contamination reconnaissance robot from its current location to the candidate travel point is determined; Determine the Euclidean distance from the nuclear contamination reconnaissance robot's current location to the candidate travel point; The shortest path from the nuclear contamination reconnaissance robot to the candidate driving point is determined based on the cumulative radiation dose and Euclidean distance.
[0083] The device for optimizing the trajectory of a nuclear contamination reconnaissance robot in this embodiment can execute the method for optimizing the trajectory of a nuclear contamination reconnaissance robot shown in the embodiment of this application. The implementation principle is similar and will not be described again here.
[0084] This application provides an electronic device, which includes: a processor; and a memory configured to store machine-readable instructions that, when executed by the processor, cause the processor to perform an optimization method for the trajectory of a nuclear contamination reconnaissance robot.
[0085] This application provides an electronic device, such as... Figure 3 As shown, Figure 3 The illustrated electronic device includes a processor 2001 and a memory 2003. The processor 2001 and the memory 2003 are connected, for example, via a bus 2002. Optionally, the electronic device 2000 may further include a transceiver 2004. It should be noted that in practical applications, the transceiver 2004 is not limited to one type, and the structure of this electronic device 2000 does not constitute a limitation on the embodiments of this application.
[0086] Processor 2001 may be a CPU, a general-purpose processor, a DSP, an ASIC, an FPGA, or other programmable logic device, transistor logic device, hardware component, or any combination thereof. It may implement or execute the various exemplary logic blocks, modules, and circuits described in conjunction with the disclosure of this application. Processor 2001 may also be a combination that implements computational functions, such as including one or more microprocessor combinations, a combination of a DSP and a microprocessor, etc.
[0087] Bus 2002 may include a pathway for transmitting information between the aforementioned components. Bus 2002 may be a PCI bus or an EISA bus, etc. Bus 2002 can be divided into address bus, data bus, control bus, etc. For ease of representation, Figure 3 The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.
[0088] The memory 2003 may be ROM or other type of static storage device capable of storing static information and instructions, RAM or other type of dynamic storage device capable of storing information and instructions, or EEPROM, CD-ROM or other optical disc storage, optical disc storage (including compressed optical discs, laser discs, optical discs, digital universal optical discs, Blu-ray discs, etc.), magnetic disk storage media or other magnetic storage devices, or any other medium capable of carrying or storing desired program code in the form of instructions or data structures and accessible by a computer, but not limited thereto.
[0089] The memory 2003 stores the application code that executes the scheme of this application, and its execution is controlled by the processor 2001. The processor 2001 executes the application code stored in the memory 2003 to implement... Figure 2 The illustrated embodiment provides the operation of an optimization device for the trajectory of a nuclear contamination reconnaissance robot.
[0090] It should be understood that although the steps in the flowcharts of the accompanying figures are shown sequentially as indicated by the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the accompanying figures may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily completed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the sub-steps or stages of other steps.
[0091] The above description is only a partial embodiment of the present invention. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principle of the present invention, and these improvements and modifications should also be considered within the scope of protection of the present invention.
Claims
1. A method for optimizing the trajectory of a nuclear contamination reconnaissance robot, characterized in that, include: Obtain parameter data corresponding to the nuclear leak area, and obtain the predicted concentration field and uncertainty field based on the parameter data using a Gaussian multi-puff model. The parameter data includes source term parameters, meteorological data, and geographical data. Obtain a preset sensitivity threshold and a sensitive area layer, and calibrate the sensitive location of the nuclear leakage area based on the predicted concentration field, the uncertainty field, the preset sensitivity threshold, and the sensitive area layer to obtain a set of sensitive area coordinate points; Obtain a preset priority rule, and determine the priority of each sensitive area coordinate point in the sensitive area coordinate point set according to the priority rule to obtain the target point set; Real-time monitoring data corresponding to the leak area is obtained, and the target point set is subjected to planning constraint processing based on the real-time monitoring data to obtain the patrol trajectory sequence of the nuclear pollution reconnaissance robot.
2. The method according to claim 1, characterized in that, The source parameters include source strength, source location, and release height; the meteorological data includes wind speed and wind direction data; and the geographic data includes three-dimensional terrain data and building distribution.
3. The method according to claim 2, characterized in that, The process of obtaining the predicted concentration field and uncertainty field based on the parameter data using a Gaussian multi-puff model includes: Based on the wind speed and wind direction data, the diffusion parameters are determined, and the source term parameters and diffusion parameters are input into the Gaussian multi-puff model to obtain the predicted nuclide concentration. A two-dimensional grid is established based on the three-dimensional terrain data and the building distribution, and the predicted nuclide concentration stored at each grid point in the two-dimensional grid is determined based on the predicted nuclide concentration to obtain the predicted concentration field. The standard deviation of the predicted nuclide concentration stored at each grid point is determined using the Monte Carlo simulation method to obtain the uncertainty field.
4. The method according to claim 3, characterized in that, The preset sensitivity threshold includes a concentration threshold and an uncertainty threshold. The sensitive area coordinate point set is obtained by calibrating the nuclear leakage area based on the predicted concentration field, the uncertainty field, the preset sensitivity threshold, and the sensitive area layer, including: The gradient field of the predicted concentration field is determined based on the central difference method, and the high gradient region corresponding to the gradient field is determined. The grid points in the predicted concentration field are filtered according to the concentration threshold and the sensitive region layer to obtain the filtered predicted concentration field. The grid points in the uncertainty field are filtered according to the uncertainty threshold to obtain the filtered uncertainty field; Based on the filtered predicted concentration field and the filtered uncertainty field, a set of sensitive area coordinate points is obtained. The set of sensitive area coordinate points includes the coordinates, type, gradient magnitude, concentration value, and uncertainty value corresponding to each sensitive point.
5. The method according to claim 4, characterized in that, Determining the high gradient region corresponding to the gradient field includes: Determine the gradient magnitude corresponding to each grid point in the gradient field; All grid points in the gradient field are sorted in ascending and descending order according to the gradient magnitude corresponding to each grid point, and the high gradient region is determined from all sorted grid points according to a preset rule.
6. The method according to claim 4, characterized in that, The step of filtering the grid points in the predicted concentration field according to the concentration threshold and the sensitive region layer to obtain the filtered predicted concentration field includes: Based on the concentration threshold, all grid points included in the predicted concentration field are initially screened to obtain the initially screened grid points; The initially filtered grid points are superimposed with each sensitive point in the sensitive region layer to obtain the filtered predicted concentration field.
7. The method according to claim 6, characterized in that, The target point set includes each geographic coordinate point and the priority type and weight corresponding to each geographic coordinate point. The step of determining the priority of each sensitive area coordinate point in the sensitive area coordinate point set according to the priority rules to obtain the target point set includes: Convert each sensitive area coordinate point in the set of sensitive area coordinate points into a geographic coordinate point to obtain a set of geographic coordinate points; The priority type corresponding to each geographic coordinate point in the set of geographic coordinate points is determined according to the priority rule; The weight corresponding to each geographic coordinate point is determined based on the weight corresponding to each priority type and the priority type corresponding to each geographic coordinate point.
8. The method according to claim 1, characterized in that, The step of performing planning and constraint processing on the target point set based on the real-time monitoring data to obtain the patrol trajectory sequence of the nuclear contamination reconnaissance robot includes: The highest priority geographic coordinate point in the target point set is selected as the candidate driving point for the nuclear contamination reconnaissance robot at the next moment, and the shortest path from the nuclear contamination reconnaissance robot to the candidate driving point is determined based on the real-time monitoring data. If the shortest path meets the shortest path radiation dose rate requirement, then the candidate travel point is used as the travel point of the nuclear contamination reconnaissance robot at the next moment, and the geographical coordinate point corresponding to the travel point of the nuclear contamination reconnaissance robot at the next moment is deducted from the target point set to obtain the remaining target point set. The remaining set of target points is used as the target point set for iteration until the resulting set of remaining target points no longer includes geographic coordinate points. The sequence obtained by combining the next travel points of the nuclear pollution reconnaissance robot obtained during the iteration process is used as the patrol trajectory sequence of the nuclear pollution reconnaissance robot.
9. The method according to claim 8, characterized in that, The real-time monitoring data includes the current location, terrain accessibility, and radiation dose rate of the nuclear contamination reconnaissance robot. Determining the shortest path from the nuclear contamination reconnaissance robot to the candidate travel point based on the real-time monitoring data includes: Based on the radiation dose rate and terrain accessibility, the cumulative radiation dose of the nuclear contamination reconnaissance robot from its current location to the candidate travel point is determined; Determine the Euclidean distance from the current position to the candidate travel point for the nuclear contamination reconnaissance robot; The shortest path from the nuclear contamination reconnaissance robot to the candidate travel point is determined based on the cumulative radiation dose and the Euclidean distance.
10. A device for optimizing the trajectory of a nuclear contamination reconnaissance robot, characterized in that, include: The data acquisition module is used to acquire parameter data corresponding to the nuclear leak area, and obtain the predicted concentration field and uncertainty field based on the parameter data through a Gaussian multi-puff model. The parameter data includes source parameters, meteorological data and geographical data. The sensitive area coordinate point processing module is used to obtain a preset sensitivity threshold and a sensitive area layer, and to perform sensitive area location calibration on the nuclear leakage area according to the predicted concentration field, the uncertainty field, the preset sensitivity threshold and the sensitive area layer, so as to obtain a set of sensitive area coordinate points; The target point set processing module is used to obtain a preset priority rule and determine the priority of each sensitive area coordinate point in the sensitive area coordinate point set according to the priority rule, so as to obtain the target point set. The trajectory sequence determination module is used to acquire real-time monitoring data corresponding to the leakage area, and to perform planning constraint processing on the target point set based on the real-time monitoring data to obtain the patrol trajectory sequence of the nuclear pollution reconnaissance robot.