A mobile environment treatment equipment path planning method and system based on air pollution hot zone fusion and a storage medium
By constructing a spatiotemporal distribution model of air pollution and adaptive path planning, the problem of air purification equipment's inability to identify pollution hotspots has been solved, achieving efficient air purification and resource optimization.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- QIERLING BEIJING HEALTH TECH CO LTD
- Filing Date
- 2026-05-22
- Publication Date
- 2026-07-14
Smart Images
Figure CN122390615A_ABST
Abstract
Description
Technical Field
[0001] This invention belongs to the field of intelligent mobile environmental governance equipment and mobile robot path planning technology, and particularly relates to a path planning method, system and storage medium for mobile environmental treatment equipment based on air pollution heat zone fusion. Background Technology
[0002] As people pay increasing attention to indoor air quality, air purifiers, air disinfection devices, and air conditioning equipment have gradually become common in homes and offices. However, most existing air environment treatment equipment adopts a fixed structure, and its treatment method mainly relies on air circulation to achieve overall purification, which often has certain limitations in complex indoor environments. Currently, air purification equipment on the market is usually placed in a fixed location indoors. A fan draws air into the device, purifies it through a filtration system, and then exhausts the purified air to achieve air circulation. This method can achieve certain results in open spaces, but in actual home environments, due to the influence of furniture, walls, and spatial layout, air circulation is often obstructed, resulting in problems such as higher local air pollutant concentrations, limited air circulation paths, uneven purification efficiency, and slower air renewal in certain areas. Especially in large spaces or environments with many pieces of furniture, fixed air purification equipment struggles to achieve uniform air treatment effects.
[0003] In real-world environments, air pollutants often exhibit significant spatial distribution differences. For example, cooking fumes are easily generated near cooking areas; pet activity areas may contain hair and odor pollution; external pollutants may seep in near doors and windows; and pollutants tend to accumulate in corners where airflow is weak. These pollution sources often form areas with high localized pollution concentrations, which can be considered "air pollution hotspots." However, traditional air purification equipment typically operates in a uniform circulation mode, lacking the ability to identify pollution hotspots and thus unable to target severely polluted areas for focused treatment.
[0004] To improve air pollution control efficiency, some new devices are adopting mobile structures, enabling air purifiers to actively move within indoor spaces and expand their coverage through patrol. However, current mobile devices typically employ simple patrol strategies such as random movement, fixed-path patrol, or simple room-by-room patrol. These methods do not fully utilize air quality data for path optimization, making it difficult to dynamically adjust based on actual pollution distribution. In the field of mobile robotics, path planning techniques typically focus on optimizing navigation efficiency and obstacle avoidance capabilities, such as shortest path planning, coverage path planning, and obstacle avoidance planning. When mobile devices undertake air pollution control tasks, relying solely on traditional path planning methods is insufficient to meet practical needs, as air pollution control requires consideration of not only spatial coverage but also pollution distribution characteristics. Current technologies generally lack methods for integrating air quality sensor data with path planning algorithms, making it impossible to dynamically adjust the device's operating path based on changes in air pollution concentration.
[0005] In practical applications, identifying indoor air pollution hotspots and prioritizing air treatment in these areas can significantly improve overall air pollution control efficiency. However, existing air purification devices or mobile environmental devices typically lack spatial distribution models of pollution concentrations, fail to identify air pollution hotspots, incorporate pollution hotspot information into path planning algorithms, and do not generate dynamically updated air treatment paths. Indoor air pollution exhibits significant dynamic changes. If mobile devices could sense changes in air quality in real time and dynamically adjust their paths based on pollution distribution, it would help improve air pollution control efficiency. Most existing devices lack a path adjustment mechanism driven by real-time environmental data. Therefore, it is necessary to propose a path planning method, system, and storage medium for mobile environmental treatment devices based on air pollution hotspot fusion. By establishing a spatial distribution model of air pollution and integrating pollution hotspot information into the path planning algorithm, mobile environmental treatment devices can prioritize air treatment in severely polluted areas. Summary of the Invention
[0006] The purpose of this invention is to provide a method, system, and storage medium for mobile environmental treatment equipment path planning based on air pollution hot zone fusion, so that the mobile environmental treatment equipment can preferentially cover high-pollution areas and improve purification efficiency.
[0007] This invention provides an adaptive path planning method for mobile environmental processing devices based on spatiotemporal heat zone prediction and fusion of air pollution, comprising the following steps: Step 1: Construct a 3D map model of the space to be processed and collect air pollution data. Establish a pollution spatiotemporal distribution model. Combine the pollution diffusion prediction model and pollution growth trend calculation to predict the pollution concentration distribution and pollution growth trend in the future time period. Step 2: Construct a fusion path cost function and generate adaptive path planning results based on the fusion path cost function; the cost function includes a path distance term, a pollution prediction concentration term, a pollution growth trend term, and an energy constraint term; Step 3: Monitor pollution changes in real time, and replan the route when preset conditions are met; the preset conditions include pollution prediction changes exceeding a threshold and the emergence of new pollution sources.
[0008] Furthermore, the three-dimensional map model described in step 1 includes spatial geometric structure information, obstacle information, airflow field boundary information, and spatial height layering information. The space is processed by rasterization or voxelization and divided into several units.
[0009] Furthermore, the pollution diffusion prediction model is as follows: ; in: P(t) represents the current pollution concentration time series; The pollution diffusion coefficient; This is the Laplace diffusion term, representing the natural diffusion of pollutants; This is the purification efficiency coefficient; This is the purification efficiency coefficient; This represents the current purification intensity of the equipment. It is a source of pollution.
[0010] Furthermore, the fusion path cost function described in step 2: gyPenalty; in: This is the path length; To predict pollution concentrations; This indicates a growing trend in pollution. gyPenalty is the ratio of path energy consumption to remaining power. , , This is the weighting adjustment coefficient.
[0011] Further, in step 2, when the adaptive path planning includes: Single-device contamination hot zone fusion path planning: The space is divided into several grid cells, the contamination weight of each grid cell is calculated, and when the contamination weight is greater than a set threshold, the grid cell is marked as a contamination hot zone. A fusion path cost function is constructed based on the contamination weight so that the device can preferentially cover the contamination hot zone. Pollution diffusion prediction-driven path adjustment: When the pollution growth trend calculation results of a certain area indicate that the pollution is in a state of growth, the area is taken as the priority factor for path planning, and the path is planned to the area in advance. At the same time, the diffusion path is predicted according to the air flow direction, and the predicted diffusion area is added to the priority intervention queue. Energy-coupled adaptive path planning: When the device's power level is below a preset threshold, an energy constraint term, EnergyPen, is added to the cost function. , For path energy consumption, To conserve remaining battery power and reduce the cost of long-distance routes, the adjusted route planning is more biased towards medium- to short-distance high-pollution areas to ensure the safe return of the equipment. Three-dimensional stratified pollution fusion path planning: The space is divided into upper, middle and lower layers according to height. If the pollution concentration in the upper layer is higher than that in the lower layer, the path is planned to the optimal coverage point below the high concentration area.
[0012] Furthermore, step 3 also includes: when the equipment performs a purification task, recording the purification start time, calculating the theoretical purification capacity based on the equipment's clean air output ratio, updating the pollution spatiotemporal distribution model, and if the updated predicted concentration is lower than a set threshold, reducing the access priority of the area in the path planning to avoid the equipment repeatedly staying in the purified area and saving operating resources.
[0013] Furthermore, when multiple devices are operating in tandem, the area is divided and tasks are assigned based on the density of the pollution hot zone, the direction of diffusion, and the remaining power of each device; areas with high heat zone density are preferentially assigned to devices with higher purification capacity or higher remaining power.
[0014] This invention also provides a path planning system for mobile environmental treatment devices based on spatiotemporal thermal zone prediction and fusion of air pollution, comprising: The pollution prediction module is used to construct a three-dimensional map model of the space to be processed and collect air pollution data, establish a pollution spatiotemporal distribution model, and combine the pollution diffusion prediction model and pollution growth trend calculation to predict the pollution concentration distribution and pollution growth trend in the future time period. The path planning module is used to construct a fused path cost function and generate adaptive path planning results based on the fused path cost function; the cost function includes a path distance term, a pollution prediction concentration term, a pollution growth trend term, and an energy constraint term. The path update module is used to monitor pollution changes in real time and replan the path when preset conditions are met; the preset conditions include pollution prediction changes exceeding a threshold and the emergence of new pollution sources.
[0015] The present invention also provides a mobile environment processing device, comprising: a processor, a memory, and an air quality sensor; the memory stores a computer program, which, when executed by the processor, implements the mobile environment processing device path planning method based on spatiotemporal heat zone prediction fusion of air pollution.
[0016] The present invention also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the mobile environmental processing device path planning method based on the prediction and fusion of air pollution spatiotemporal heat zones.
[0017] By employing the above-described scheme, and through the path planning method, system, and storage medium for mobile environmental treatment devices based on air pollution hotspot fusion, the following technical effects are achieved: 1) Breaking through traditional coverage-based path planning: For the first time, air pollution concentration, pollution change trends, pollution diffusion prediction and purification feedback attenuation model are systematically introduced into the path cost function to realize a "pollution-first" path planning mechanism.
[0018] 2) Introduce a pollution spatiotemporal prediction mechanism: Construct a pollution trend function and combine it with a diffusion model to identify the upward trend of pollution, predict the direction of diffusion, and realize the upgrade from passive response to active prevention.
[0019] 3) Achieve closed-loop feedback between pollution and purification: Dynamically reduce the weight of treated areas by calculating the purification effect in real time, avoid the equipment repeatedly passing through the purified area, and reduce the ineffective dwell time.
[0020] 4) Integrating energy constraints: When power is insufficient, the strategy is automatically adjusted to prioritize the treatment of high-pollution areas in the medium and near distance, so as to achieve "optimal pollution reduction under limited resources".
[0021] 5) Supports multi-device collaboration: Dynamically divides hot zone boundaries and assigns tasks to avoid path overlap and resource waste.
[0022] 6) Supports three-dimensional spatial stratification: Constructs a three-dimensional pollution model combined with height stratification weights to achieve priority for high-altitude pollution and vertical stratification optimization.
[0023] 7) Support historical data learning: Record the historical distribution characteristics of pollution and increase its priority in future tasks in advance to achieve long-term self-learning optimization.
[0024] 8) Improve the purification efficiency per unit of energy consumption: Increase the pollution reduction rate under the same operating time, and the pollution reduction efficiency can be increased by 15%-40%.
[0025] 9) Enhance response capabilities in extreme pollution scenarios: Quickly adjust path priorities to suppress pollution peaks during sudden high-concentration pollution events.
[0026] The above description is only an overview of the technical solution of the present invention. In order to better understand the technical means of the present invention and be able to implement it according to the content of the specification, the following will describe in detail with reference to the preferred embodiments of the present invention and the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS
[0027] Figure 1 It is a flowchart of an adaptive path planning method for a mobile environmental treatment device based on the prediction and fusion of air pollution spatio-temporal hotspots of the present invention; Figure 2 It is a schematic diagram of the overall structure of the system in an embodiment of the present invention; Figure 3 It is a flowchart of air pollution data collection and hotspot construction in an embodiment of the present invention; Figure 4 It is a schematic diagram of spatial grid and pollution weight in an embodiment of the present invention; Figure 5 It is a logic block diagram of fusion path planning in an embodiment of the present invention; Figure 6 It is a schematic diagram of dual-device collaborative pollution hotspot allocation in an embodiment of the present invention; Figure 7 It is an extended structure diagram of base centralized pollution hotspot scheduling in an embodiment of the present invention; Figure 8 It is a schematic diagram of three-dimensional pollution stratification in an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS
[0028] The following will further describe in detail the specific embodiments of the present invention with reference to the accompanying drawings and embodiments. The following embodiments are used to illustrate the present invention, but are not used to limit the scope of the present invention.
[0029] Refer Figure 1 As shown, this embodiment provides an adaptive path planning method for a mobile environmental treatment device based on the prediction and fusion of air pollution spatio-temporal hotspots. The mobile environmental treatment device can move autonomously in an indoor space and can integrate one or more environmental governance functions such as air purification, air circulation, humidification, dehumidification, and air disinfection, and actively manage the indoor air environment by means of mobile cruising. The path planning method includes the following steps: Step S1, construct a three-dimensional map model of the space to be processed, collect air pollution data, establish a pollution spatio-temporal distribution model, and combine pollution diffusion prediction models and pollution growth trend calculations to predict the pollution concentration distribution and pollution growth trend in the future time period; Step S2, construct a fusion path cost function, and generate an adaptive path planning result based on the fusion path cost function; the cost function includes a path distance term, a pollution prediction concentration term, a pollution growth trend term, and an energy constraint term; Step S3: Monitor pollution changes in real time, and replan the route when preset conditions are met; the preset conditions include pollution prediction changes exceeding a threshold and the emergence of new pollution sources.
[0030] In this embodiment, the three-dimensional map model in step S1 includes spatial geometric structure information, obstacle information, airflow field boundary information, and spatial height layering information. The space is processed by rasterization or voxelization and divided into several units.
[0031] In this embodiment, the pollution diffusion prediction model is: ; in: P(t) represents the current pollution concentration time series; The pollution diffusion coefficient; This is the Laplace diffusion term, representing the natural diffusion of pollutants; This is the purification efficiency coefficient; This is the purification efficiency coefficient; This represents the current purification intensity of the equipment. It is a source of pollution.
[0032] In this embodiment, the fusion path cost function in step 2 is: gyPenalty; in: This is the path length; To predict pollution concentrations; This indicates a growing trend in pollution. gyPenalty is the ratio of path energy consumption to remaining power. , , This is the weighting adjustment coefficient.
[0033] In this embodiment, step S2 includes the adaptive path planning as follows: Single-device contamination hot zone fusion path planning: The space is divided into several grid cells, the contamination weight of each grid cell is calculated, and when the contamination weight is greater than a set threshold, the grid cell is marked as a contamination hot zone. A fusion path cost function is constructed based on the contamination weight so that the device can preferentially cover the contamination hot zone. Pollution diffusion prediction-driven path adjustment: When the pollution growth trend calculation results of a certain area indicate that the pollution is in a state of growth, the area is taken as the priority factor for path planning, and the path is planned to the area in advance. At the same time, the diffusion path is predicted according to the air flow direction, and the predicted diffusion area is added to the priority intervention queue. Energy-coupled adaptive path planning: When the device's power level is below a preset threshold, an energy constraint term, EnergyPen, is added to the cost function. , For path energy consumption, To conserve remaining power and reduce the cost of long-distance routes, the adjusted route planning is more biased towards medium- to short-distance high-pollution areas to ensure the equipment's safe return.
[0034] In this embodiment, all spatial map data and pollution collection data are processed in a closed loop on the local main control MCU, or uploaded after being de-identified and encrypted.
[0035] This embodiment also provides a mobile environmental processing device path planning system based on spatiotemporal thermal zone prediction and fusion of air pollution, including: The pollution prediction module is used to construct a three-dimensional map model of the space to be processed and collect air pollution data, establish a pollution spatiotemporal distribution model, and combine the pollution diffusion prediction model and pollution growth trend calculation to predict the pollution concentration distribution and pollution growth trend in the future time period. The path planning module is used to construct a fused path cost function and generate adaptive path planning results based on the fused path cost function; the cost function includes a path distance term, a pollution prediction concentration term, a pollution growth trend term, and an energy constraint term. The path update module is used to monitor pollution changes in real time and replan the path when preset conditions are met; the preset conditions include pollution prediction changes exceeding a threshold and the emergence of new pollution sources.
[0036] The present invention also provides a mobile environment processing device, comprising: a processor, a memory, and an air quality sensor; the memory stores a computer program, which, when executed by the processor, implements the mobile environment processing device path planning method based on spatiotemporal heat zone prediction fusion of air pollution.
[0037] The present invention also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the mobile environmental processing device path planning method based on the prediction and fusion of air pollution spatiotemporal heat zones.
[0038] This invention breaks away from traditional coverage-based path planning and achieves "pollution-driven" dynamic path optimization, enabling mobile devices to prioritize intervention in highly polluted and potentially spreading areas, effectively improving indoor air purification efficiency and overall environmental governance.
[0039] Example 1: Single-device contamination hot zone fusion path planning like Figures 2 to 5 As shown, a mobile environmental treatment device 100 is deployed in an indoor room. The specific steps are as follows: S11: The mobile environment processing device 100 starts up, initiates SLAM mapping through the spatial mapping module 102, constructs a two-dimensional or three-dimensional spatial map, and divides the space into several grid units. ; S12: Real-time PM2.5 and TVOC data within the space are collected via the air quality acquisition module 101; S13: The current contamination weight of each grid cell is calculated using a weighted fusion method through the hot zone modeling module 103. And set pollution thresholds. .when At that time, the grid cell is marked as a contaminated hot zone; , These are the weighting coefficients. For example... Figure 4 As shown, G6 = 85 (high pollution hotspot); G7 = 90 (high pollution hotspot); G10 = 30 (low pollution hotspot).
[0040] S14: Construct the path cost function using path fusion module 104: Cost = d + and adopt Alternatively, Dijkstra's algorithm can be used to calculate the minimum cost path (minimizing cost to prioritize access to highly polluted areas); where d is the path length. This is the weighting adjustment coefficient.
[0041] S15: The control execution module 106 executes the mobile purification according to the planned path.
[0042] Effect: Enables the equipment to prioritize coverage of highly polluted areas, thereby increasing purification efficiency per unit time.
[0043] Example 2: Adjustment of Pollution Diffusion Prediction Driving Path When persistent oil fume pollution occurs in the kitchen area, the system performs the following steps: The air quality acquisition module 101 records the pollution concentration time series P(t); the system then calculates the pollution growth trend function using a prediction model. ; when When the value is >0 and exceeds the set threshold, it indicates that the pollution is in a state of growth. This is used as a priority factor for path planning. The path fusion module 104 plans a path to the high-growth area in advance. At the same time, the diffusion path is predicted according to the air flow direction, and the predicted diffusion area is added to the priority intervention queue. Finally, the control execution module 106 drives the mobile environmental treatment device 100 to go there.
[0044] Effect: Achieve "early intervention" rather than "post-event handling".
[0045] Example 3: Purification Feedback Inhibition Mechanism When the mobile environmental treatment device 100 is driven by the control execution module 106 to enter a certain polluted area for operation: The system records the start time of purification and calculates the theoretical purification capacity according to the clean air delivery rate (CADR) of the device; The dynamic update module 105 updates the pollution spatio-temporal distribution model based on the feedback mechanism: ; Where, is the updated predicted concentration, is the predicted concentration before update, is the purification efficiency parameter, Purification time.
[0046] If the updated predicted concentration is lower than the set threshold, the access priority of this area in the path fusion module 104 is reduced.
[0047] Effect: Avoid the device from staying in the purified area repeatedly, saving operation resources.
[0048] Example 4: Energy Coupling Adaptive Path When the power of the mobile environmental treatment device 100 is lower than 30%: The system calculates the remaining available operation time; If the distance to the remote high-pollution area is too far, the path fusion module 104 adds an energy constraint term in the cost function: EnergyPen ; making the adjusted path planning more biased towards the high-pollution areas in the medium and short distances to ensure the device can return safely.
[0049] Effect: While ensuring the priority of pollution control, effectively avoid the risk of power failure. <00 like Figure 7 As shown, when the system architecture includes an intelligent base: the air quality acquisition module 101 of each mobile environmental processing device 100 collects and uploads pollution data to the intelligent base in real time; the intelligent base uses centralized computing power to construct a unified three-dimensional pollution field and performs diffusion prediction calculations; the global path fusion module of the intelligent base generates the optimal path and issues instructions; the control execution module 106 of each device receives instructions to execute mobile purification and sends operational feedback back to the base.
[0053] Effect: Centralized computing power significantly improves prediction accuracy and the optimality of global scheduling.
[0054] Example 7: Three-dimensional layered contamination fusion pathway In high-ceilinged environments (e.g., high-ceilinged living rooms): a three-dimensional contamination field is constructed using the thermal modeling module 103, and the space is divided into upper, middle, and lower layers according to height (e.g., ...). Figure 8 (As shown); if the air quality acquisition module 101 detects that the upper layer pollution concentration is higher than the lower layer, the path fusion module 104 will prioritize planning a path to the optimal coverage point below the high concentration area; the control execution module 106 will adjust the air outlet angle of the equipment in conjunction with the path to perform directional purification.
[0055] Effect: Breaking through the limitations of two-dimensional space, it achieves efficient purification in three-dimensional space.
[0056] Example 8: Rapid Response to Extreme Pollution Scenarios In a scenario of sudden high-concentration pollution: the air quality acquisition module 101 detects a sudden increase in local concentration; the system calculates that the pollution growth trend function T rises sharply; the dynamic update module 105 triggers automatic adjustment of weight parameters, increasing the weight of pollution prediction concentration and pollution growth trend in the cost function; it triggers a reordering of the priorities of all paths, and then the control execution module 106 drives the equipment to move quickly toward the pollution source.
[0057] Effect: Quickly responds to and suppresses pollution peaks.
[0058] Example 9: Multiple Pollution Source Overlap Scenario When multiple pollution sources exist simultaneously in an indoor space: the thermal zone modeling module 103 forms an independent sub-thermal zone for each pollution source and calculates the comprehensive pollution superposition function; the path fusion module 104 evaluates each sub-thermal zone and prioritizes the pollution source area with the fastest growth or the widest diffusion direction; the dynamic update module 105 dynamically adjusts the intervention priority according to the real-time evolution status of each pollution source. This significantly improves the equipment's processing capability in complex pollution scenarios.
[0059] Example 10: Self-learning optimization scenario After long-term operation, the system utilizes storage media to store historical data on indoor pollution distribution; it identifies high-frequency pollution areas (such as kitchen entrances, near pet kennels, etc.) through data mining; in future routine patrol missions, the path fusion module 104 prioritizes the scanning and intervention of these high-frequency areas in advance, achieving adaptive optimization scheduling. This enhances the system's adaptability and improves long-term efficiency.
[0060] The present invention has the following technical effects: 1) Breaking through traditional coverage-based path planning: For the first time, air pollution concentration, pollution change trends, pollution diffusion prediction and purification feedback attenuation model are systematically introduced into the path cost function to realize a "pollution-first" path planning mechanism.
[0061] 2) Introduce a pollution spatiotemporal prediction mechanism: Construct a pollution trend function and combine it with a diffusion model to identify the upward trend of pollution, predict the direction of diffusion, and realize the upgrade from passive response to active prevention.
[0062] 3) Achieve closed-loop feedback between pollution and purification: Dynamically reduce the weight of treated areas by calculating the purification effect in real time, avoid the equipment repeatedly passing through the purified area, and reduce the ineffective dwell time.
[0063] 4) Integrating energy constraints: When power is insufficient, the strategy is automatically adjusted to prioritize the treatment of high-pollution areas in the medium and near distance, so as to achieve "optimal pollution reduction under limited resources".
[0064] 5) Supports multi-device collaboration: Dynamically divides hot zone boundaries and assigns tasks to avoid path overlap and resource waste.
[0065] 6) Supports three-dimensional spatial stratification: Constructs a three-dimensional pollution model combined with height stratification weights to achieve priority for high-altitude pollution and vertical stratification optimization.
[0066] 7) Support historical data learning: Record the historical distribution characteristics of pollution and increase its priority in future tasks in advance to achieve long-term self-learning optimization.
[0067] 8) Improve the purification efficiency per unit of energy consumption: Increase the pollution reduction rate under the same operating time, and the pollution reduction efficiency can be increased by 15%-40%.
[0068] 9) Enhance response capabilities in extreme pollution scenarios: Quickly adjust path priorities to suppress pollution peaks during sudden high-concentration pollution events.
[0069] The above description is merely a preferred embodiment of the present invention and is not intended to limit 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 technical principles of the present invention, and these improvements and modifications should also be considered within the scope of protection of the present invention.
Claims
1. An adaptive path planning method for mobile environmental processing equipment based on spatiotemporal heat zone prediction and fusion of air pollution, characterized in that, Includes the following steps: Step 1: Construct a 3D map model of the space to be processed and collect air pollution data. Establish a pollution spatiotemporal distribution model. Combine the pollution diffusion prediction model and pollution growth trend calculation to predict the pollution concentration distribution and pollution growth trend in the future time period. Step 2: Construct a fusion path cost function and generate adaptive path planning results based on the fusion path cost function; the cost function includes a path distance term, a pollution prediction concentration term, a pollution growth trend term, and an energy constraint term; Step 3: Monitor pollution changes in real time, and replan the route when preset conditions are met; the preset conditions include pollution prediction changes exceeding a threshold and the emergence of new pollution sources.
2. The adaptive path planning method for mobile environmental processing equipment based on spatiotemporal heat zone prediction fusion of air pollution according to claim 1, characterized in that, The three-dimensional map model described in step 1 includes spatial geometric structure information, obstacle information, airflow field boundary information, and spatial height layering information. The space is processed by rasterization or voxelization and divided into several units.
3. The adaptive path planning method for mobile environmental processing equipment based on spatiotemporal heat zone prediction fusion of air pollution according to claim 1, characterized in that, The pollution diffusion prediction model is as follows: ； in: P(t) represents the current pollution concentration time series; The pollution diffusion coefficient; This is the Laplace diffusion term, representing the natural diffusion of pollutants; This is the purification efficiency coefficient; This is the purification efficiency coefficient; This represents the current purification intensity of the equipment. It is a source of pollution.
4. The adaptive path planning method for mobile environmental processing equipment based on spatiotemporal heat zone prediction fusion of air pollution according to claim 1, characterized in that, The fusion path cost function described in step 2: gyPenalty; in: This is the path length; To predict pollution concentrations; This indicates a growing trend in pollution. gyPenalty is the ratio of path energy consumption to remaining power. , , This is the weighting adjustment coefficient.
5. The adaptive path planning method for mobile environmental processing equipment based on spatiotemporal heat zone prediction fusion of air pollution according to claim 1, characterized in that, In step 2, when the adaptive path planning includes: Single-device contamination hot zone fusion path planning: The space is divided into several grid cells, the contamination weight of each grid cell is calculated, and when the contamination weight is greater than a set threshold, the grid cell is marked as a contamination hot zone. A fusion path cost function is constructed based on the contamination weight so that the device can preferentially cover the contamination hot zone. Pollution diffusion prediction-driven path adjustment: When the pollution growth trend calculation results of a certain area indicate that the pollution is in a state of growth, the area is taken as the priority factor for path planning, and the path is planned to the area in advance. At the same time, the diffusion path is predicted according to the air flow direction, and the predicted diffusion area is added to the priority intervention queue. Energy-coupled adaptive path planning: When the device's power level is below a preset threshold, an energy constraint term, EnergyPen, is added to the cost function. , For path energy consumption, To conserve remaining battery power and reduce the cost of long-distance routes, the adjusted route planning is more biased towards medium- to short-distance high-pollution areas to ensure the safe return of the equipment. Three-dimensional stratified pollution fusion path planning: The space is divided into upper, middle and lower layers according to height. If the pollution concentration in the upper layer is higher than that in the lower layer, the path is planned to the optimal coverage point below the high concentration area.
6. The adaptive path planning method for mobile environmental processing equipment based on spatiotemporal heat zone prediction fusion of air pollution according to claim 1, characterized in that, Step 3 further includes: when the equipment performs a purification task, recording the purification start time, calculating the theoretical purification capacity based on the equipment's clean air output ratio, updating the pollution spatiotemporal distribution model, and if the updated predicted concentration is lower than a set threshold, reducing the access priority of the area in the path planning to avoid the equipment repeatedly staying in the purified area and saving operating resources.
7. The adaptive path planning method for mobile environmental processing equipment based on spatiotemporal heat zone prediction fusion of air pollution according to claim 1, characterized in that, When multiple devices are operating in tandem, the area is divided and tasks are assigned based on the density of the pollution hot zone, the direction of diffusion, and the remaining power of each device; areas with high heat zone density are given priority to devices with higher purification capacity or higher remaining power.
8. A path planning system for mobile environmental treatment equipment based on spatiotemporal thermal zone prediction and fusion of air pollution, characterized in that, include: The pollution prediction module is used to construct a three-dimensional map model of the space to be processed and collect air pollution data, establish a pollution spatiotemporal distribution model, and combine the pollution diffusion prediction model and pollution growth trend calculation to predict the pollution concentration distribution and pollution growth trend in the future time period. The path planning module is used to construct a fused path cost function and generate adaptive path planning results based on the fused path cost function; the cost function includes a path distance term, a pollution prediction concentration term, a pollution growth trend term, and an energy constraint term. The path update module is used to monitor pollution changes in real time and replan the path when preset conditions are met; the preset conditions include pollution prediction changes exceeding a threshold and the emergence of new pollution sources.
9. A mobile environmental processing device, characterized in that, include: The device includes a processor, a memory, and an air quality sensor. The memory stores a computer program that, when executed by the processor, implements the mobile environmental processing device path planning method based on the spatiotemporal heat zone prediction fusion of air pollution as described in any one of claims 1 to 7.
10. A computer-readable storage medium, characterized in that, It stores a computer program, which, when executed by a processor, implements the mobile environmental processing device path planning method based on the prediction and fusion of spatiotemporal heat zones of air pollution as described in any one of claims 1 to 7.