Mountain fire extinguishing task path planning method and system based on multiple unmanned aerial vehicles
By employing a path planning method involving multiple drones in collaborative operations, the problems of insufficient fire source identification and environmental adaptability in photovoltaic power plants with complex terrain were solved, achieving efficient fire response and path optimization, and improving the effectiveness of drone-based fire prevention and extinguishing systems.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2026-02-10
- Publication Date
- 2026-04-14
AI Technical Summary
Existing drone-based fire prevention and suppression technologies are insufficient in terms of accurate fire source identification in photovoltaic power plants with complex terrain, adaptability to complex environments, and multi-drone collaborative operation, resulting in low response speed and efficiency, and failing to fully realize their effectiveness.
A path planning method based on multi-UAV collaborative operation is adopted. By integrating multi-source data, quantifying uncertainty, and dynamically optimizing the path, a full-process path planning system is constructed to improve the scientific nature and robustness of path planning.
It enables precise response and efficient fire suppression in complex terrain fires, avoiding the problems of unfounded and inefficient route adjustments in traditional planning, and improving the scientific nature and coherence of route planning.
Smart Images
Figure CN121857787A_ABST
Abstract
Description
Technical Field
[0001] More specifically, this invention relates to a method and system for mountain firefighting mission path planning based on multiple unmanned aerial vehicles (UAVs). Background Technology
[0002] Currently, intelligent fire prevention and extinguishing using drones is a comprehensive fire prevention technology that integrates high-precision fire source location, multiple fire extinguishing methods, and automated operation and maintenance. It can accurately and efficiently respond to fires in complex terrains and has gained widespread attention from domestic and foreign research institutions in recent years.
[0003] However, with the rapid development of photovoltaic power plants in complex terrain, the current technology is inadequate in terms of accurate fire source identification, adaptability to complex environments, and multi-machine collaborative operation. This results in the response speed and efficiency of fire prevention and extinguishing systems lagging far behind, making it impossible for drone fire prevention and extinguishing technology to fully play its role in actual production. Consequently, fire hazards cannot be eliminated in a timely manner, and economic losses are amplified.
[0004] Therefore, how to provide a mountain firefighting mission path planning method that can solve the above problems is a problem that urgently needs to be solved by those skilled in the art. Summary of the Invention
[0005] In view of this, the present invention provides a method and system for mountain fire fighting mission path planning based on multiple UAVs. It constructs a full-process path planning system around multi-source data fusion, uncertainty quantification, dynamic path optimization, and multi-UAV collaborative adaptation, thereby improving the scientific nature and robustness of path planning.
[0006] To achieve the above objectives, the present invention adopts the following technical solution: A method for path planning in mountain firefighting missions based on multiple unmanned aerial vehicles (UAVs) includes the following steps: Meteorological data, location data, and spectral data of the mountainous area to be tested are acquired, and the meteorological data and spectral data are identified to determine the corresponding initial fire source location and initial fire range. Acquire the current location information of multiple drones, fire extinguishing equipment parameters, and drone flight parameters, and preprocess the current location information, fire extinguishing equipment parameters, and drone flight parameters; A path planning model is constructed, and the initial fire source location, initial fire range, pre-processed current location information, fire extinguishing equipment parameters, and UAV flight parameters are input into the path planning model for processing to obtain the corresponding initial UAV planned path. Determine whether the initial drone planning path needs adjustment, and based on the final determination result, determine whether the initial drone planning path needs to be adjusted and optimized, and generate the final drone planning path; Multiple drones completed firefighting operations according to their planned paths.
[0007] Preferably, the specific processing steps for generating the final drone planning path include: Uncertainty prediction is performed on the initial fire source location and the initial fire range, and uncertainty prediction is also performed on the fire extinguishing equipment parameters and drone flight parameters of multiple drones to obtain the corresponding fire uncertainty prediction results and drone uncertainty prediction results. The fire uncertainty prediction result and the drone uncertainty prediction result are comprehensively judged to determine whether they have an impact on the initial drone planning path. If they do, the initial drone planning path is adjusted to generate the final drone planning path.
[0008] Preferably, the specific processing procedure for comprehensively judging whether the fire uncertainty prediction result and the drone uncertainty prediction result have an impact on the initial drone planning path includes: The fire uncertainty prediction results and the drone uncertainty prediction results are quantitatively analyzed to obtain the corresponding fire uncertainty quantitative index and drone uncertainty quantitative index. The uncertainty quantification indicators for fire and drone are normalized. A comprehensive uncertainty impact analysis function is constructed, and the normalized fire uncertainty quantification index and the UAV uncertainty quantification index are substituted into the comprehensive uncertainty impact analysis function to obtain the corresponding calculation results. Determine the actual threshold corresponding to the calculation result, and determine whether the fire uncertainty prediction result and the drone uncertainty prediction result have an impact on the initial drone planning path based on the relationship between the actual threshold and the calculation result.
[0009] Preferably, the specific processing procedure for comprehensively judging whether the fire uncertainty prediction result and the drone uncertainty prediction result have an impact on the initial drone planning path further includes: When the calculation result is less than or equal to the actual threshold, the initial UAV planning path is taken as the final UAV planning path. When the calculation result is greater than the actual threshold, the fire uncertainty prediction result is extracted to obtain new fire source information and new UAV parameter information. By combining new fire source information, new UAV parameter information, and path planning model, the final UAV planned path is obtained.
[0010] Preferably, the specific processing procedure for making uncertainty predictions on the initial fire source location and the initial fire range includes: Preprocessing is performed on the meteorological data, location data, and spectral data of the mountainous area to be measured; A mutation risk prediction and decision model is constructed, and the preprocessed meteorological data, location data and spectral data are input into the mutation risk prediction and decision model for processing to obtain the corresponding fire uncertainty prediction results, the corresponding fire uncertainty occurrence probability and the fire uncertainty probability threshold. When the probability of fire uncertainty occurs meets the threshold requirement for fire uncertainty probability, the corresponding fire uncertainty prediction result is output.
[0011] Preferably, the specific processing procedure for uncertainty prediction of the fire extinguishing equipment parameters and drone flight parameters of multiple drones includes: The current location information, fire extinguishing equipment parameters, and drone flight parameters are preprocessed to obtain corresponding drone screening data. A mutation risk prediction and decision-making model is constructed, and the pre-processed UAV screening data is input into the mutation risk prediction and decision-making model for processing to obtain the corresponding UAV uncertainty prediction results, the corresponding UAV uncertainty occurrence probability, and the UAV uncertainty probability threshold. When the probability of the drone uncertainty occurs meets the drone uncertainty probability threshold requirement, the corresponding drone uncertainty prediction result is output.
[0012] This invention also provides a mountain firefighting mission path planning system based on multiple unmanned aerial vehicles (UAVs), comprising: The first acquisition module is used to acquire meteorological data, location data and spectral data of the mountainous area to be tested, and to identify the meteorological data and spectral data to determine the corresponding initial fire source location and initial fire range. The second acquisition module is used to acquire the current location information of multiple drones, fire extinguishing equipment parameters, and drone flight parameters, and to preprocess the current location information, fire extinguishing equipment parameters, and drone flight parameters. The path planning module is used to construct a path planning model and input the initial fire source location, initial fire range, pre-processed current location information, fire extinguishing equipment parameters and UAV flight parameters into the path planning model for processing to obtain the corresponding initial UAV planned path. The judgment module is used to determine whether the initial UAV planning path needs to be adjusted, and to determine whether the initial UAV planning path needs to be adjusted and optimized based on the final judgment result, so as to generate the final UAV planning path. The execution module is used by multiple drones to complete firefighting operations according to the drone's planned path. As can be seen from the above technical solution, compared with the prior art, the present invention discloses a method and system for mountain fire fighting mission path planning based on multiple UAVs, which has the following beneficial effects: 1. This invention performs uncertainty prediction on the initial fire source / fire range and UAV equipment / flight parameters respectively, and then obtains standardized indicators through quantitative analysis and normalization. At the same time, it realizes the coupled calculation of two-dimensional uncertainty through a comprehensive uncertainty impact analysis function, which breaks through the one-sidedness of single-dimensional analysis and can accurately reflect the actual impact of the dual uncertainties of fire spread (affected by meteorology / terrain) and UAV flight (affected by mountain airflow / equipment error) on the path in mountainous scenarios. 2. This invention sets an actual threshold as the core basis for path adjustment, making the triggering conditions for path adjustment standardized and implementable. At the same time, when replanning, it directly integrates new fire source information, new UAV parameter information and the original path planning model to achieve a logical closed loop of uncertain data, impact judgment and path optimization. This avoids the problems of path adjustment without basis and repeated planning with low efficiency in traditional planning, and improves the scientificity and coherence of path planning. Attached Figure Description
[0013] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on the provided drawings without creative effort.
[0014] Figure 1 The overall flowchart of a mountain firefighting mission path planning method based on multiple UAVs provided by the present invention; Figure 2 The present invention provides a structural principle block diagram of a mountain firefighting mission path planning system based on multiple unmanned aerial vehicles. Detailed Implementation
[0015] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.
[0016] See Figure 1 As shown in the figure, this invention discloses a method for path planning in mountain firefighting missions based on multiple unmanned aerial vehicles (UAVs), comprising the following steps: Meteorological data, location data, and spectral data of the mountainous area to be tested are acquired, and the meteorological data and spectral data are identified to determine the corresponding initial fire source location and initial fire range. The identification process can be achieved by constructing relevant neural network models and machine learning algorithms. The system acquires the current location information, fire extinguishing equipment parameters, and drone flight parameters of multiple drones, and preprocesses these parameters. The fire extinguishing equipment parameters may include parameters related to fire extinguishing loads (such as maximum fire extinguishing load) and fire extinguishing devices (such as spray parameters). The drone flight parameters may include power supply parameters, flight parameters, and data transmission parameters. The preprocessing process may include correlation analysis, outlier removal, and normalization. A path planning model is constructed, and the initial fire source location, initial fire range, pre-processed current location information, fire extinguishing equipment parameters, and UAV flight parameters are input into the path planning model for processing to obtain the corresponding initial UAV planned path. The path planning model includes, but is not limited to, various machine learning models. Determine whether the initial drone planning path needs adjustment, and based on the final determination result, determine whether the initial drone planning path needs to be adjusted and optimized, and generate the final drone planning path; Multiple drones completed firefighting operations according to their planned paths.
[0017] In one specific embodiment, the specific process for generating the final UAV planned path includes: Uncertainty prediction is performed on the initial fire source location and the initial fire range, and uncertainty prediction is also performed on the fire extinguishing equipment parameters and drone flight parameters of multiple drones to obtain the corresponding fire uncertainty prediction results and drone uncertainty prediction results. The fire uncertainty prediction result and the drone uncertainty prediction result are comprehensively judged to determine whether they have an impact on the initial drone planning path. If they do, the initial drone planning path is adjusted to generate the final drone planning path.
[0018] In a specific embodiment, the specific processing procedure for comprehensively judging whether the fire uncertainty prediction result and the drone uncertainty prediction result have an impact on the initial drone planning path includes: The fire uncertainty prediction results and the drone uncertainty prediction results are quantitatively analyzed to obtain the corresponding fire uncertainty quantitative index and drone uncertainty quantitative index. The uncertainty quantification indicators for fire and drone are normalized. A comprehensive uncertainty impact analysis function is constructed, and the normalized fire uncertainty quantification index and the UAV uncertainty quantification index are substituted into the comprehensive uncertainty impact analysis function to obtain the corresponding calculation results. Determine the actual threshold corresponding to the calculation result, and determine whether the fire uncertainty prediction result and the drone uncertainty prediction result have an impact on the initial drone planning path based on the relationship between the actual threshold and the calculation result.
[0019] In a specific embodiment, the process of comprehensively judging whether the fire uncertainty prediction result and the drone uncertainty prediction result have an impact on the initial drone planning path further includes: When the calculation result is less than or equal to the actual threshold, the initial UAV planning path is taken as the final UAV planning path. When the calculation result is greater than the actual threshold, the fire uncertainty prediction result is extracted to obtain new fire source information and new UAV parameter information. By combining new fire source information, new UAV parameter information, and path planning model, the final UAV planned path is obtained.
[0020] In a specific embodiment, the specific process for performing uncertainty prediction on the initial fire source location and the initial fire range includes: Preprocessing is performed on the meteorological data, location data, and spectral data of the mountainous area to be measured; A mutation risk prediction and decision model is constructed, and the preprocessed meteorological data, location data and spectral data are input into the mutation risk prediction and decision model for processing to obtain the corresponding fire uncertainty prediction results, the corresponding fire uncertainty occurrence probability and the fire uncertainty probability threshold. When the probability of fire uncertainty occurs meets the threshold requirement for fire uncertainty probability, the corresponding fire uncertainty prediction result is output.
[0021] In a specific embodiment, the specific processing procedure for uncertainty prediction of the fire extinguishing equipment parameters and drone flight parameters of multiple drones includes: The current location information, fire extinguishing equipment parameters, and drone flight parameters are preprocessed to obtain corresponding drone screening data. A mutation risk prediction and decision-making model is constructed, and the pre-processed UAV screening data is input into the mutation risk prediction and decision-making model for processing to obtain the corresponding UAV uncertainty prediction results, the corresponding UAV uncertainty occurrence probability, and the UAV uncertainty probability threshold. When the probability of the drone uncertainty occurs meets the drone uncertainty probability threshold requirement, the corresponding drone uncertainty prediction result is output.
[0022] Specifically, the process of comprehensively judging whether the fire uncertainty prediction results and the drone uncertainty prediction results have an impact on the initial drone planning path may also include: When the probability of drone uncertainty and the probability of fire uncertainty do not meet the threshold requirements, the initial drone planning path is directly output as the final drone planning path. When either the probability of drone uncertainty or the probability of fire uncertainty meets the threshold requirement, the corresponding drone uncertainty impact analysis function and fire uncertainty impact analysis function are constructed respectively. The normalized drone uncertainty quantification index is substituted into the corresponding drone uncertainty impact analysis function and the fire uncertainty quantification index is substituted into the corresponding fire uncertainty impact analysis function to obtain the corresponding drone uncertainty function calculation result or fire uncertainty function calculation result. A decision model is constructed, and the calculation results of the uncertainty function of the UAV or the uncertainty function of the fire are respectively input into the decision model for processing. Based on the processing results, it is determined whether the initial UAV planning path needs to be adjusted.
[0023] See Figure 2 As shown, this embodiment of the invention also provides a system for mountain firefighting mission path planning based on multiple unmanned aerial vehicles (UAVs) as described in any of the above embodiments, comprising: The first acquisition module is used to acquire meteorological data, location data and spectral data of the mountainous area to be tested, and to identify the meteorological data and spectral data to determine the corresponding initial fire source location and initial fire range. The second acquisition module is used to acquire the current location information of multiple drones, fire extinguishing equipment parameters, and drone flight parameters, and to preprocess the current location information, fire extinguishing equipment parameters, and drone flight parameters. The path planning module is used to construct a path planning model and input the initial fire source location, initial fire range, pre-processed current location information, fire extinguishing equipment parameters and UAV flight parameters into the path planning model for processing to obtain the corresponding initial UAV planned path. The judgment module is used to determine whether the initial UAV planning path needs to be adjusted, and to determine whether the initial UAV planning path needs to be adjusted and optimized based on the final judgment result, so as to generate the final UAV planning path. The execution module is used by multiple drones to complete firefighting operations according to the drone's planned path.
[0024] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on its differences from other embodiments. Similar or identical parts between embodiments can be referred to interchangeably. For the apparatus disclosed in the embodiments, since they correspond to the methods disclosed in the embodiments, the description is relatively simple; relevant parts can be referred to the method section.
[0025] The above description of the disclosed embodiments enables those skilled in the art to make or use the invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the invention. Therefore, the invention is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims
1. A method for path planning in mountain firefighting missions based on multiple unmanned aerial vehicles (UAVs), characterized in that, Includes the following steps: Meteorological data, location data, and spectral data of the mountainous area to be tested are acquired, and the meteorological data and spectral data are identified to determine the corresponding initial fire source location and initial fire range. Acquire the current location information of multiple drones, fire extinguishing equipment parameters, and drone flight parameters, and preprocess the current location information, fire extinguishing equipment parameters, and drone flight parameters; A path planning model is constructed, and the initial fire source location, initial fire range, pre-processed current location information, fire extinguishing equipment parameters, and UAV flight parameters are input into the path planning model for processing to obtain the corresponding initial UAV planned path. Determine whether the initial drone planning path needs adjustment, and based on the final determination result, determine whether the initial drone planning path needs to be adjusted and optimized, and generate the final drone planning path; Multiple drones completed firefighting operations according to their planned paths.
2. The method for mountain firefighting mission path planning based on multiple unmanned aerial vehicles (UAVs) according to claim 1, characterized in that, The specific processing steps for generating the final drone planning path include: Uncertainty prediction is performed on the initial fire source location and the initial fire range, and uncertainty prediction is also performed on the fire extinguishing equipment parameters and drone flight parameters of multiple drones to obtain the corresponding fire uncertainty prediction results and drone uncertainty prediction results. The fire uncertainty prediction result and the drone uncertainty prediction result are comprehensively judged to determine whether they have an impact on the initial drone planning path. If they do, the initial drone planning path is adjusted to generate the final drone planning path.
3. The method for mountain firefighting mission path planning based on multiple unmanned aerial vehicles (UAVs) according to claim 2, characterized in that, The specific process for comprehensively judging whether the fire uncertainty prediction results and the drone uncertainty prediction results have an impact on the initial drone planning path includes: The fire uncertainty prediction results and the drone uncertainty prediction results are quantitatively analyzed to obtain the corresponding fire uncertainty quantitative index and drone uncertainty quantitative index. The uncertainty quantification indicators for fire and drone are normalized. A comprehensive uncertainty impact analysis function is constructed, and the normalized fire uncertainty quantification index and the UAV uncertainty quantification index are substituted into the comprehensive uncertainty impact analysis function to obtain the corresponding calculation results. Determine the actual threshold corresponding to the calculation result, and determine whether the fire uncertainty prediction result and the drone uncertainty prediction result have an impact on the initial drone planning path based on the relationship between the actual threshold and the calculation result.
4. The method for mountain firefighting mission path planning based on multiple unmanned aerial vehicles (UAVs) according to claim 3, characterized in that, The specific processing procedure for comprehensively judging whether the fire uncertainty prediction results and the drone uncertainty prediction results have an impact on the initial drone planning path also includes: When the calculation result is less than or equal to the actual threshold, the initial UAV planning path is taken as the final UAV planning path. When the calculation result is greater than the actual threshold, the fire uncertainty prediction result is extracted to obtain new fire source information and new UAV parameter information. By combining new fire source information, new UAV parameter information, and path planning model, the final UAV planned path is obtained.
5. A method for mountain firefighting mission path planning based on multiple unmanned aerial vehicles (UAVs) according to claim 2, characterized in that, The specific process for uncertainty prediction of the initial fire source location and the initial fire range includes: Preprocessing is performed on the meteorological data, location data, and spectral data of the mountainous area to be measured; A mutation risk prediction and decision model is constructed, and the preprocessed meteorological data, location data and spectral data are input into the mutation risk prediction and decision model for processing to obtain the corresponding fire uncertainty prediction results, the corresponding fire uncertainty occurrence probability and the fire uncertainty probability threshold. When the probability of fire uncertainty occurs meets the threshold requirement for fire uncertainty probability, the corresponding fire uncertainty prediction result is output.
6. The method for mountain firefighting mission path planning based on multiple unmanned aerial vehicles (UAVs) according to claim 2, characterized in that, The specific process for uncertainty prediction of the firefighting equipment parameters and flight parameters of multiple drones includes: The current location information, fire extinguishing equipment parameters, and drone flight parameters are preprocessed to obtain corresponding drone screening data. A mutation risk prediction and decision-making model is constructed, and the pre-processed UAV screening data is input into the mutation risk prediction and decision-making model for processing to obtain the corresponding UAV uncertainty prediction results, the corresponding UAV uncertainty occurrence probability, and the UAV uncertainty probability threshold. When the probability of the drone uncertainty occurs meets the drone uncertainty probability threshold requirement, the corresponding drone uncertainty prediction result is output.
7. A system utilizing the multi-UAV-based mountain firefighting mission path planning method according to any one of claims 1-6, characterized in that, include: The first acquisition module is used to acquire meteorological data, location data and spectral data of the mountainous area to be tested, and to identify the meteorological data and spectral data to determine the corresponding initial fire source location and initial fire range. The second acquisition module is used to acquire the current location information of multiple drones, fire extinguishing equipment parameters, and drone flight parameters, and to preprocess the current location information, fire extinguishing equipment parameters, and drone flight parameters. The path planning module is used to construct a path planning model and input the initial fire source location, initial fire range, pre-processed current location information, fire extinguishing equipment parameters and UAV flight parameters into the path planning model for processing to obtain the corresponding initial UAV planned path. The judgment module is used to determine whether the initial UAV planning path needs to be adjusted, and to determine whether the initial UAV planning path needs to be adjusted and optimized based on the final judgment result, so as to generate the final UAV planning path. The execution module is used by multiple drones to complete firefighting operations according to the drone's planned path.