Fire-fighting unmanned aerial vehicle dispatching method and system based on multi-vehicle multi-nest intelligent matching

Abstract

The invention provides a fire-fighting unmanned aerial vehicle dispatching method and system based on multi-vehicle multi-nest intelligent matching, and belongs to the technical field of unmanned aerial vehicle dispatching. According to the method, a multi-dimensional state sensing system is constructed to obtain and preprocess fire-fighting unmanned aerial vehicle cluster and multi-nest operation information, and a global state data set is obtained; based on the data set, a nest matching priority evaluation model is established through an analytic hierarchy process, and accurate matching of the unmanned aerial vehicle and the nest is realized through a dynamic matching mechanism; multi-task pre-allocation and dynamic reallocation are completed by adopting a cluster collaborative scheduling optimization algorithm fusing multiple constraints, and a cross-nest switching track is generated in combination with an improved RRT track planning algorithm; a temporary landing preparation strategy is generated through the remaining voyage, the required electric quantity and risk judgment, and unmanned aerial vehicle parking supply, data uploading and position adjustment are achieved by means of a high-precision landing guide technology and a data synchronization protocol. And the requirements of high real-time performance and accuracy of multi-machine and multi-nest collaborative scheduling in a fire-fighting scene are met.

Description

Technical Field

[0001] This application relates to the field of drone dispatching technology, and more specifically, to a method and system for dispatching firefighting drones based on multi-drone and multi-nest intelligent matching. Background Technology

[0002] With the increasing demands for efficiency and safety in fire emergency rescue, drones, with their flexibility and maneuverability, are widely used in scenarios such as fire reconnaissance and material delivery. Multi-drone collaboration and cross-regional operations have become the mainstream application mode, and multi-nest layout is the core support for ensuring operational continuity. However, existing technologies for fire-fighting drone dispatching have several limitations: status perception relies heavily on single data sources, lacking comprehensive collaborative perception capabilities for the operational status of drone swarms and nests, resulting in insufficient spatiotemporal correlation of data; nest-drone matching often employs static strategies, failing to fully integrate dynamic adjustments based on task requirements and resource status, leading to low matching accuracy; task allocation does not systematically integrate multiple constraints such as range, battery power, and task priority, and lacks dynamic adjustment mechanisms to address battery depletion, resource changes, and scenario shifts; trajectory planning during cross-nest switching does not effectively balance energy consumption and obstacle avoidance, and the temporary diversion guarantee mechanism is inadequate, easily leading to flight safety risks; simultaneously, insufficient coordination in drone docking and resupply, and data transmission, affecting overall dispatch efficiency. These problems make existing dispatching schemes unable to meet the needs of large-scale, highly reliable collaborative operations with multiple drones and nests in fire-fighting scenarios, thus restricting the application effectiveness of fire-fighting drone systems.

[0003] There is an urgent need for a multi-drone, multi-nest intelligent matching fire-fighting drone dispatching solution that can achieve full-domain collaborative perception, dynamic and precise matching of drones and nests, flexible scheduling of multi-constraint tasks, safe switching across nests, and efficient docking interaction, in order to break through existing technical bottlenecks and improve the efficiency and safety of drone collaborative operations in fire rescue. Summary of the Invention

[0004] This invention provides a scheduling method and system for firefighting drones based on multi-drone, multi-nest intelligent matching. It constructs a multi-dimensional state perception system through multi-source sensor fusion, collecting flight parameters, task execution progress, resource occupancy status, docking readiness status, and location information of the firefighting drone swarm. After data cleaning and spatiotemporal alignment preprocessing, a spatiotemporally correlated global state dataset is obtained. Based on this dataset, a multi-dimensional indicator system is constructed, considering task response time, energy consumption cost, and nest resource utilization. The weights of these indicators are determined using the analytic hierarchy process (AHP), and a preliminary nest matching candidate set is generated. Frequency adaptation and spatial calibration are achieved through a dual-module dynamic matching mechanism, enabling precise matching between drones and nests. A cluster collaborative scheduling optimization algorithm with multiple constraints is employed. Based on the drone's received command information, multi-dimensional constraints such as range threshold and remaining battery power are extracted to construct a multi-objective optimization function, completing multi-task pre-allocation. Simultaneously, considering drone battery decay rate, nest resource changes, and task scenario changes, an improved Resource Response Time (RRT) is implemented through a resource conflict coordination algorithm, a fusion energy consumption prediction model, and a dynamic obstacle avoidance mechanism. The trajectory planning algorithm obtains the dynamic task redistribution results and collision-free cross-nest switching trajectories. Based on the remaining range and required power of the UAV during cross-nest switching, risk assessment is performed by combining a preset power redundancy threshold and remaining range adaptability calculation. Nest idle status information is retrieved for verification and sorted by distance priority to generate temporary alternate landing strategies and scheduling results for the nearest idle nest. Finally, relying on high-precision landing guidance technology fused with differential positioning and visual markers, incremental synchronization data protocol assisted by edge nodes, and scheduling instructions, the UAV docking and resupply, data upload, and position adjustment are completed. The corresponding system includes state perception, nest matching, task scheduling, trajectory planning, docking interaction modules, as well as memory and processor. Each module is sequentially signal-connected. The processor executes the program stored in the memory to realize the above scheduling methods, forming a multi-UAV, multi-nest intelligent scheduling scheme covering the entire process of perception, matching, scheduling, trajectory, and docking, comprehensively improving the accuracy, dynamic adaptability, and safety of fire-fighting UAV scheduling.

[0005] This application provides a method for dispatching firefighting drones based on multi-drone multi-nest intelligent matching, including the following steps: A multi-dimensional state perception system was constructed, and information on fire-fighting drone clusters and multi-nest operation was collected and preprocessed to obtain a spatiotemporally correlated global state dataset. Based on the global state dataset, a nest matching priority evaluation model is established, and the weights of each indicator are determined by the analytic hierarchy process to generate a preliminary nest matching candidate set. Based on the preliminary candidate set of nest matching, the UAV and nest are accurately matched through the nest dynamic matching mechanism; A cluster collaborative scheduling optimization algorithm integrating multiple constraints is adopted to pre-allocate multiple tasks based on the command information received by the UAV; Based on the drone's battery decay rate, changes in nest resources, and changes in mission scenarios, we obtain the results of dynamic mission reallocation and improved RRT trajectory planning. Based on the remaining range, required power, and risk assessment during the drone cross-nest switching, a temporary diversion strategy and the result of scheduling the nearest available drone nest are obtained. Based on high-precision landing guidance technology, data synchronization protocol and scheduling instructions, the results of UAV docking and resupply, data upload and position adjustment are obtained.

[0006] In the fire-fighting drone dispatching method based on multi-drone multi-nest intelligent matching described in this application, the construction of a multi-dimensional state perception system, collecting fire-fighting drone cluster information and multi-nest operation information and preprocessing them to obtain a spatiotemporally correlated global state dataset, specifically includes: Based on multi-source sensor fusion acquisition technology, information on firefighting drone clusters and multi-hub operation is obtained; The information of the firefighting drone cluster includes flight parameters and mission execution progress; The multi-nest operation information includes resource occupancy status, docking readiness status, and location information; The firefighting drone cluster information and multi-nest operation information are preprocessed by data cleaning and spatiotemporal alignment to obtain a spatiotemporally correlated global state dataset.

[0007] In the firefighting drone dispatching method based on multi-drone multi-nest intelligent matching described in this application, the step of establishing a nest matching priority evaluation model based on the global state dataset, determining the weights of each indicator through the analytic hierarchy process, and generating a preliminary nest matching candidate set specifically involves: Based on the task response time, energy consumption cost, and nest resource utilization rate in the global state dataset, a multi-dimensional indicator system is constructed as the core evaluation indicators of the model. A judgment matrix is ​​constructed by comparing multiple core indicators pairwise using the analytic hierarchy process. After consistency verification, the weights are quantified and normalized. By combining the real-time state parameters in the global state dataset, the matching fitness of multiple nests is comprehensively calculated and sorted to obtain a preliminary nest matching candidate set.

[0008] In the firefighting drone dispatching method based on multi-drone multi-nest intelligent matching described in this application, the precise matching of drones and nests based on the preliminary nest matching candidate set and through a nest dynamic matching mechanism includes: Based on the nest attributes of the preliminary nest matching candidate set and the real-time status parameters in the global status dataset, frequency adaptation is performed through a dual-module dynamic matching mechanism. Spatial calibration was completed through visual identifier extraction, laser ranging, and multimodal fusion positioning to verify the feasibility of candidate nest matching and obtain accurate matching results.

[0009] In the firefighting drone scheduling method based on multi-machine multi-nest intelligent matching described in this application, the adoption of a cluster collaborative scheduling optimization algorithm that integrates multiple constraints, and the pre-allocation of multiple tasks based on the drone's received instruction information, includes: Based on the information received by the UAV, extract the UAV's range threshold, remaining battery power, mission urgency priority, and mission location distribution, and construct a multi-dimensional constraint system. Based on the cluster collaborative scheduling optimization algorithm that integrates multiple constraints, a multi-objective optimization function is constructed, and each constraint condition is transformed into a function constraint term. The optimal solution for multi-task pre-allocation is obtained through iterative calculation by the optimization solution algorithm.

[0010] In the firefighting drone scheduling method based on multi-drone multi-nest intelligent matching described in this application, the step of obtaining the dynamic task reallocation result and the improved RRT trajectory planning result based on the drone's power decay rate, nest resource changes, and task scenario changes is as follows: Based on the drone's power decay rate, changes in nest resources, and mission scenario, and combined with the global state dataset, an improved RRT trajectory planning algorithm that integrates an energy consumption prediction model and a dynamic obstacle avoidance mechanism is used to update trajectory nodes and verify path feasibility. The resource conflict coordination algorithm yields the results of dynamic task reallocation and collision-free cross-nest switching trajectory planning.

[0011] In the firefighting drone scheduling method based on multi-drone multi-nest intelligent matching described in this application, the step of obtaining the temporary alternate landing strategy and the scheduling result of the nearest available nest based on the drone's remaining range, required power, and risk assessment when switching nests is specifically as follows: Risk assessment is based on the remaining range data and required power calculation results when the drone switches between different nests, combined with the preset power redundancy threshold and the remaining range adaptability calculation. The idle status information of the nests in the global status dataset is retrieved synchronously to complete real-time verification. Nests that meet the conditions are sorted according to the distance priority sorting algorithm to obtain the temporary alternate landing strategy and the scheduling result of the nearest idle nest.

[0012] In the firefighting drone dispatching method based on multi-drone multi-nest intelligent matching described in this application, the step of obtaining drone docking and resupply, data upload, and position adjustment results based on high-precision landing guidance technology, data synchronization protocol, and dispatching instructions specifically includes: Based on the high-precision landing guidance technology that combines differential positioning and visual marker fusion, the incremental synchronization data protocol assisted by edge nodes, and the scheduling instructions, the landing path is calibrated by multi-source positioning data fusion, the mission data is transmitted according to the incremental synchronization rules, and the position is dynamically adjusted in response to the instructions to obtain the corresponding execution results.

[0013] Secondly, this application provides a fire-fighting drone dispatch system based on multi-machine, multi-nest intelligent matching, characterized in that it includes: The state perception module is used to build a multi-dimensional state perception system, collect information on fire-fighting drone clusters and multi-nest operation information, preprocess them, and output a spatiotemporally correlated global state dataset. The nest matching module is used to establish a nest matching priority evaluation model based on the global state dataset, determine the weight of each indicator through the analytic hierarchy process, generate a preliminary nest matching candidate set, and complete the accurate matching of UAVs and nests through the nest dynamic matching mechanism. The task scheduling module is used to pre-allocate multiple tasks based on the drone's received instruction information using a cluster collaborative scheduling optimization algorithm that integrates multiple constraints. It also outputs the dynamic task reallocation results based on the drone's power decay rate, changes in nest resources, and changes in the task scenario. The trajectory planning module is used to generate cross-nest switching trajectories based on the task scheduling results and by improving the RRT trajectory planning algorithm. At the same time, based on the remaining range, required power and risk assessment of the UAV when switching across nests, it outputs temporary diversion strategies and the scheduling results of the nearest available nest. The docking interaction module is used to realize UAV docking and resupply, data uploading and position adjustment based on high-precision landing guidance technology, data synchronization protocol and scheduling instructions; The status perception module, nest matching module, task scheduling module, trajectory planning module, and docking interaction module are sequentially connected by signals to collaboratively complete the intelligent scheduling of multiple firefighting drones and nests.

[0014] The system also includes a memory and a processor. The memory contains a program for a multi-drone, multi-nest intelligent matching method for dispatching firefighting drones. When the processor executes the program for the multi-drone, multi-nest intelligent matching method for dispatching firefighting drones, it performs the following steps: A multi-dimensional state perception system was constructed, and information on fire-fighting drone clusters and multi-nest operation was collected and preprocessed to obtain a spatiotemporally correlated global state dataset. Based on the global state dataset, a nest matching priority evaluation model is established, and the weights of each indicator are determined by the analytic hierarchy process to generate a preliminary nest matching candidate set. Based on the preliminary candidate set of nest matching, the UAV and nest are accurately matched through the nest dynamic matching mechanism; A cluster collaborative scheduling optimization algorithm integrating multiple constraints is adopted to pre-allocate multiple tasks based on the command information received by the UAV; Based on the drone's battery decay rate, changes in nest resources, and changes in mission scenarios, we obtain the results of dynamic mission reallocation and improved RRT trajectory planning. Based on the remaining range, required power, and risk assessment during the drone cross-nest switching, a temporary diversion strategy and the result of scheduling the nearest available drone nest are obtained. Based on high-precision landing guidance technology, data synchronization protocol and scheduling instructions, the results of UAV docking and resupply, data upload and position adjustment are obtained.

[0015] As can be seen from the above, this invention provides a fire-fighting drone scheduling method and corresponding system based on multi-drone and multi-nest intelligent matching. It constructs a closed-loop scheduling system covering the entire process of perception, matching, scheduling, trajectory, and docking. It achieves full-domain state collaborative perception through multi-source sensor fusion, achieves precise adaptation between nests and drones by relying on the hierarchical analysis method and dynamic matching mechanism, completes task pre-allocation and dynamic reallocation by using multi-constraint fusion optimization algorithm, ensures safe and efficient cross-nest switching by combining improved RRT trajectory planning algorithm, generates scientific temporary alternate landing strategies through risk assessment and priority ranking, and achieves smooth coordination of docking resupply, data transmission, and position adjustment by using high-precision landing guidance and incremental synchronization protocol. The system, through the orderly linkage of five major modules—state perception, nest matching, task scheduling, trajectory planning, and docking interaction—and with the hardware support of memory and processor, ensures the stable implementation of the scheduling method. It comprehensively solves the problems of incomplete perception, inaccurate matching, inflexible scheduling, unsafe switching, and lack of coordination in existing technologies. It significantly improves the real-time performance, accuracy, safety, and overall efficiency of multi-drone and multi-nest collaborative operations in firefighting scenarios, providing reliable UAV scheduling technology support for fire emergency rescue.

[0016] Other features and advantages of this application will be set forth in the following description and will be apparent in part from the description or may be learned by practicing embodiments of this application. The objectives and other advantages of this application may be realized and obtained by means of the structures particularly pointed out in the written description and the accompanying drawings. Attached Figure Description

[0017] To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings used in the embodiments of this application will be briefly introduced below. It should be understood that the following drawings only show some embodiments of this application and should not be regarded as a limitation of the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0018] Figure 1This is a high-level flowchart of a fire-fighting drone scheduling method based on multi-machine multi-nest intelligent matching provided in the embodiments of this application, used for scheduling fire-fighting drones based on multi-machine multi-nest intelligent matching.

[0019] Figure 2 A flowchart of a fire-fighting drone dispatching method based on multi-machine multi-nest intelligent matching provided in this application embodiment; Figure 3 The structural block diagram of the fire-fighting drone dispatch system based on multi-machine multi-nest intelligent matching provided in the embodiments of this application. Detailed Implementation

[0020] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of the embodiments. The components of the embodiments of this application described and shown in the accompanying drawings can generally be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of this application provided in the accompanying drawings is not intended to limit the scope of the claimed application, but merely represents selected embodiments of this application. All other embodiments obtained by those skilled in the art based on the embodiments of this application without inventive effort are within the scope of protection of this application.

[0021] It should be noted that similar reference numerals and letters in the following figures indicate similar items; therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures. Furthermore, in the description of this application, terms such as "first" and "second" are used only to distinguish descriptions and should not be construed as indicating or implying relative importance. It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use, and processing of related data must comply with the relevant laws, regulations, and standards of the relevant countries and regions.

[0022] Please refer to Figure 1 , Figure 1 This is a high-level flowchart of a firefighting drone dispatching method based on multi-drone, multi-nest intelligent matching in some embodiments of this application. The high-level flowchart can be summarized as follows: First, multi-source sensor fusion is used to collect and preprocess drone and nest information to generate a global state dataset; then, based on this dataset, an evaluation model and dynamic mechanism are used to achieve precise matching between nests and drones; subsequently, multi-constraint optimization algorithms are used to achieve task pre-allocation and dynamic reallocation, combined with an improved RRT algorithm to plan cross-nest trajectories; simultaneously, risk assessment is used to generate an alternate landing strategy; finally, high-precision guidance and synchronization protocols are used to complete drone docking and resupply, data transmission, and position adjustment.

[0023] Please refer to Figure 2 , Figure 2 This is a flowchart of a fire-fighting drone scheduling method based on multi-machine multi-nest intelligent matching in some embodiments of this application.

[0024] The first aspect of this invention discloses a method for dispatching firefighting drones based on multi-drone multi-nest intelligent matching, which is used in terminal devices such as computers and mobile phones. This method for dispatching firefighting drones based on multi-drone multi-nest intelligent matching includes the following steps: S201. Construct a multi-dimensional state perception system, collect information on fire-fighting drone clusters and multi-nest operation information, and preprocess them to obtain a spatiotemporally correlated global state dataset. S202. Based on the global state dataset, establish a nest matching priority evaluation model, determine the weight of each indicator through the analytic hierarchy process, and generate a preliminary nest matching candidate set. S203. Based on the preliminary candidate set of nest matching, the UAV and nest are accurately matched through the nest dynamic matching mechanism; S204. A cluster collaborative scheduling optimization algorithm integrating multiple constraints is adopted to pre-allocate multiple tasks based on the UAV's received instruction information; S205. Based on the UAV battery decay rate, changes in nest resources, and changes in mission scenarios, the results of dynamic mission reallocation and improved RRT trajectory planning are obtained. S206. Based on the remaining range, required power, and risk assessment when the UAV switches between different nests, the temporary diversion strategy and the result of scheduling the nearest available nest are obtained. S207. Based on high-precision landing guidance technology, data synchronization protocol and scheduling instructions, the results of UAV docking and resupply, data upload and position adjustment are obtained.

[0025] First, a multi-dimensional state perception system is constructed through multi-source sensor fusion. This system collects information on firefighting drone clusters, including flight parameters and mission execution progress, as well as multi-nest operation information, including resource occupancy status, docking readiness status, and location information. After data cleaning and spatiotemporal alignment preprocessing, a spatiotemporally correlated global state dataset is obtained. Then, based on this dataset, a multi-dimensional indicator system is constructed, considering factors such as mission response timeliness, energy consumption cost, and nest resource utilization. A judgment matrix is ​​built using the analytic hierarchy process (AHP), and weight quantification and normalization are performed through consistency checks. This establishes a nest matching priority evaluation model and generates a preliminary nest matching candidate set. Subsequently, relying on a dual-module dynamic... A state matching mechanism is used to combine candidate nest attributes with real-time global parameters to complete frequency adaptation. Spatial calibration is achieved through visual identifier extraction, laser ranging, and multimodal fusion positioning to complete the accurate matching of UAVs and nests. A cluster collaborative scheduling optimization algorithm with multiple constraints is adopted. Based on the UAV's received command information, multi-dimensional constraints such as range threshold and remaining power are extracted to construct a multi-objective optimization function, and the optimal solution for multi-task pre-allocation is obtained through iterative calculation. Then, based on the UAV's power decay rate, nest resource changes, and task scenario changes, combined with the global state dataset, an improved RRT is achieved through a resource conflict coordination algorithm, a fusion energy consumption prediction model, and a dynamic obstacle avoidance mechanism. The trajectory planning algorithm obtains the dynamic task redistribution results and collision-free cross-nest switching trajectories. Simultaneously, based on the remaining range and required power of the UAV during cross-nest switching, risk assessment is performed by combining a preset power redundancy threshold and remaining range adaptability calculation. Nest idle status information is retrieved for verification and sorted by distance priority to generate temporary alternate landing strategies and scheduling results for the nearest idle nest. Finally, based on high-precision landing guidance technology that combines differential positioning and visual marker fusion, incremental synchronization data protocol assisted by edge nodes, and scheduling instructions, the landing path is calibrated, task data is transmitted, and dynamic position adjustment is completed, realizing UAV docking and resupply, data upload, and position adjustment.

[0026] According to an embodiment of the present invention, the construction of a multi-dimensional state perception system, the collection and preprocessing of fire-fighting drone swarm information and multi-nest operation information to obtain a spatiotemporally correlated global state dataset, specifically involves: Based on multi-source sensor fusion acquisition technology, information on firefighting drone clusters and multi-hub operation is obtained; The information of the firefighting drone cluster includes flight parameters and mission execution progress; The multi-nest operation information includes resource occupancy status, docking readiness status, and location information; The firefighting drone cluster information and multi-nest operation information are preprocessed by data cleaning and spatiotemporal alignment to obtain a spatiotemporally correlated global state dataset.

[0027] To construct a multi-dimensional state perception system and acquire fundamental data to support subsequent scheduling, this technology employs multi-source sensor fusion acquisition technology to comprehensively capture information on firefighting drone swarms and multi-nest operation. The firefighting drone swarm information specifically includes various flight parameters during drone flight (such as flight speed, altitude, and remaining battery power) and task execution progress data (such as task completion rate and current operation stage). Multi-nest operation information covers the nest's resource occupancy status (such as charging station occupancy and supply reserve), docking readiness status (such as whether drone docking conditions are met), and specific location information (such as latitude and longitude coordinates). For the two types of information collected, further data cleaning and preprocessing operations are performed to remove abnormal, redundant, and invalid data to ensure data quality. Simultaneously, spatiotemporal alignment processing is carried out to unify information from different sources and time points to the same time base and spatial coordinate system, ultimately forming a spatiotemporally correlated and reliable full-domain state dataset. This provides comprehensive and accurate data support for subsequent nest matching, task scheduling, and other stages, ensuring the coherence and synergy of the overall technical solution.

[0028] According to an embodiment of the present invention, the step of establishing a nest matching priority evaluation model based on the global state dataset, determining the weights of each indicator through the analytic hierarchy process, and generating a preliminary nest matching candidate set specifically involves: Based on the task response time, energy consumption cost, and nest resource utilization rate in the global state dataset, a multi-dimensional indicator system is constructed as the core evaluation indicators of the model. A judgment matrix is ​​constructed by comparing multiple core indicators pairwise using the analytic hierarchy process. After consistency verification, the weights are quantified and normalized. By combining the real-time state parameters in the global state dataset, the matching fitness of multiple nests is comprehensively calculated and sorted to obtain a preliminary nest matching candidate set.

[0029] In this process, after acquiring the spatiotemporally correlated global state dataset, to achieve scientific matching and screening of UAVs and their nests, this technology establishes a nest matching priority evaluation model based on this dataset. The weights of each core indicator are determined using the analytic hierarchy process (AHP) to generate a preliminary nest matching candidate set. Specifically, the model extracts task response timeliness (reflecting the speed of nest response to tasks), energy consumption cost (reflecting the energy consumption level after UAV and nest adaptation), and nest resource utilization rate (characterizing the utilization degree of existing nest resources) from the global state dataset as core evaluation indicators, constructing a multi-dimensional indicator system covering efficiency, cost, and resource dimensions. The AHP is then used to compare these core indicators pairwise, and a judgment matrix is ​​constructed based on the comparison results. The matrix is ​​used to perform a consistency check to ensure the logical rationality of the indicator comparison. After the check passes, the weights of each core indicator are quantified, and then the quantified weight values ​​are normalized so that the sum of the weights of each indicator is 1 to ensure the scientific nature of the evaluation. Finally, the matching adaptability of multiple nests to be matched is comprehensively calculated by combining the real-time status parameters of the nests (such as resource occupancy status, docking readiness status, etc.) contained in the global status dataset with the relevant parameters of the UAV. Based on the calculation results, the nests are prioritized and selected to form a preliminary matching candidate set. This lays the foundation for the subsequent accurate matching of UAVs and nests and ensures that the matching process is consistent with the technical logic of global status perception and subsequent dynamic matching mechanism.

[0030] According to an embodiment of the present invention, the precise matching of UAVs and nests based on the preliminary nest matching candidate set and through a nest dynamic matching mechanism includes: Based on the nest attributes of the preliminary nest matching candidate set and the real-time status parameters in the global status dataset, frequency adaptation is performed through a dual-module dynamic matching mechanism. Spatial calibration was completed through visual identifier extraction, laser ranging, and multimodal fusion positioning to verify the feasibility of candidate nest matching and obtain accurate matching results.

[0031] In this process, based on the inherent attributes of each nest in the initial candidate nest matching set (such as interface type, communication frequency band, resupply capability, etc.), and combined with the real-time status parameters such as nest resource occupancy status, docking readiness status, and UAV flight parameters updated centrally in the global status dataset, the communication frequency and operating frequency band of the UAV and the candidate nest are adapted and adjusted by a dual-module dynamic matching mechanism to ensure signal transmission compatibility between the two. At the same time, by extracting the visual identification features of the candidate nests and using laser ranging technology to obtain the distance data between the UAV and the nests, and combining the multimodal fusion positioning algorithm to complete the spatial positioning calibration of the UAV and the candidate nests, the relative position relationship between the two is accurately obtained. On this basis, it is verified whether the candidate nests meet the adaptation requirements for UAV docking, resupply, and mission coordination, and finally the accurate matching result between the UAV and the nest is obtained. This process is consistent with the technical logic of the global status dataset support and the generation of the initial candidate nest matching set mentioned above, and forms a coherent and collaborative technical link with the subsequent mission scheduling and trajectory planning stages.

[0032] According to an embodiment of the present invention, the cluster cooperative scheduling optimization algorithm employing multiple constraints, which performs multi-task pre-allocation based on UAV received instruction information, includes: Based on the information received by the UAV, extract the UAV's range threshold, remaining battery power, mission urgency priority, and mission location distribution, and construct a multi-dimensional constraint system. Based on the cluster collaborative scheduling optimization algorithm that integrates multiple constraints, a multi-objective optimization function is constructed, and each constraint condition is transformed into a function constraint term. The optimal solution for multi-task pre-allocation is obtained through iterative calculation by the optimization solution algorithm.

[0033] The process involves extracting key constraint parameters from the instructions received by the UAV, including the UAV's own range threshold, current remaining battery power, and mission-level urgency priority and mission location distribution. Based on this, a multi-dimensional constraint system covering UAV performance and mission requirements is constructed. Relying on a cluster collaborative scheduling optimization algorithm that integrates multiple constraints, a multi-objective optimization function is constructed in conjunction with the above multi-dimensional constraint system. Each constraint condition, such as range limit, battery threshold, priority ranking, and location distribution adaptation, is transformed into specific constraint terms in the function. Through iterative calculation using an optimization algorithm, the influence weight of each constraint condition is fully weighed, and the optimal solution for multi-mission pre-allocation that balances mission execution efficiency, resource utilization rationality, and UAV operational safety is finally obtained. This allocation result forms a technical linkage with the previous precise nest matching result, providing a reliable initial scheduling basis for subsequent dynamic adjustment of missions and trajectory planning, ensuring the consistency and scientific nature of the overall scheduling scheme.

[0034] According to an embodiment of the present invention, the step of obtaining the task dynamic reallocation result and the improved RRT trajectory planning result based on the UAV battery decay rate, changes in nest resources, and changes in mission scenario specifically includes: Based on the drone's power decay rate, changes in nest resources, and mission scenario, and combined with the global state dataset, an improved RRT trajectory planning algorithm that integrates an energy consumption prediction model and a dynamic obstacle avoidance mechanism is used to update trajectory nodes and verify path feasibility. The resource conflict coordination algorithm yields the results of dynamic task reallocation and collision-free cross-nest switching trajectory planning.

[0035] To address the dynamically changing needs of firefighting operations, this technology utilizes an improved RRT (Resource-Based Tracking) trajectory planning algorithm that integrates an energy consumption prediction model and a dynamic obstacle avoidance mechanism. This algorithm is based on the drone's battery depletion rate (reflecting changes in the drone's remaining endurance), changes in nest resources (such as replenishment resource consumption and changes in available landing spots), and changes in mission scenarios (such as adjustments to the fire area and new rescue missions). It combines real-time updates of drone, nest, and mission-related data from a global state dataset. The algorithm dynamically updates existing trajectory nodes while verifying the feasibility of the updated path, ensuring the trajectory adapts to changes in energy consumption and the real-time obstacle environment. Simultaneously, a resource conflict coordination algorithm addresses task execution conflicts and resource allocation conflicts arising from state changes, ultimately resulting in a dynamic task reallocation and a collision-free trajectory planning result that meets the requirements of cross-nest operations. This process follows the multi-task pre-allocation logic described earlier, achieving dynamic adaptation and adjustment based on the global state dataset. It forms a closed-loop scheduling link with subsequent temporary landing strategies and docking interactions, ensuring the dynamic adaptability and consistency of the overall technical solution.

[0036] According to an embodiment of the present invention, the step of obtaining a temporary alternate landing strategy and the scheduling result of the nearest available drone nest based on the remaining range, required power, and risk assessment during the drone's cross-nest switching is specifically as follows: Risk assessment is based on the remaining range data and required power calculation results when the drone switches between different nests, combined with the preset power redundancy threshold and the remaining range adaptability calculation. The idle status information of the nests in the global status dataset is retrieved synchronously to complete real-time verification. Nests that meet the conditions are sorted according to the distance priority sorting algorithm to obtain the temporary alternate landing strategy and the scheduling result of the nearest idle nest.

[0037] During the cross-nest handover process, to ensure UAV flight safety and operational continuity, this technology uses the UAV's current remaining range data, the calculated power required for cross-nest handover, a preset power redundancy threshold (for reserving emergency endurance), and the remaining range adaptability calculation (to verify whether the remaining range can support the handover requirements) to conduct risk assessment and clarify the safety risk level of UAV cross-nest handover. Simultaneously, it retrieves real-time updated nest idle status information (including idle positions, supply resource reserves, etc.) from the global status dataset to complete adaptability verification, selects nests that meet the conditions for temporary diversion and resupply, and then sorts the nests that meet the conditions using a distance priority sorting algorithm. Finally, it obtains a temporary diversion strategy that balances safety and convenience, as well as the scheduling result of the nearest idle nest. This process relies on the global status dataset for real-time data support and is deeply coordinated with the previously mentioned dynamic task reallocation and improved RRT trajectory planning results to form a safety assurance closed loop in the cross-nest handover scenario, ensuring the dynamic fault tolerance and reliability of the overall scheduling scheme.

[0038] According to an embodiment of the present invention, the process of obtaining the UAV docking and resupply, data upload, and position adjustment results based on high-precision landing guidance technology, data synchronization protocol, and scheduling instructions specifically includes: Based on the high-precision landing guidance technology that combines differential positioning and visual marker fusion, the incremental synchronization data protocol assisted by edge nodes, and the scheduling instructions, the landing path is calibrated by multi-source positioning data fusion, the mission data is transmitted according to the incremental synchronization rules, and the position is dynamically adjusted in response to the instructions to obtain the corresponding execution results.

[0039] After completing cross-nest switching scheduling or mission execution, this technology, based on high-precision landing guidance technology fusion of differential positioning and visual marking, and incremental synchronization data protocol assisted by edge nodes, combined with scheduling instructions issued by the system, accurately calibrates the UAV landing path by fusing multi-source positioning data to ensure the accuracy of the docking position. At the same time, it transmits various data collected by the UAV during the mission execution according to incremental synchronization rules, achieving efficient and complete data upload. It also responds to scheduling instructions in real time to dynamically adjust the UAV position, ultimately obtaining the corresponding execution results of UAV docking and resupply at the target nest, mission data upload, and precise position adjustment. This process follows the precise matching, trajectory planning, and alternate landing scheduling logic mentioned above, and relies on the collaborative support of the full-domain status dataset to form a closed loop of the entire scheduling process, ensuring the continuity and reliability of fire-fighting UAV operations.

[0040] Please refer to Figure 3 , Figure 3 This is a structural block diagram of a fire-fighting drone dispatch system based on multi-machine, multi-nest intelligent matching provided in an embodiment of this application.

[0041] The second aspect of this invention also discloses a fire-fighting drone dispatch system based on multi-machine, multi-nest intelligent matching, comprising: The state perception module 301 is used to construct a multi-dimensional state perception system, collect information on fire-fighting drone clusters and multi-nest operation information, preprocess them, and output a spatiotemporally correlated global state dataset. The nest matching module 302 is used to establish a nest matching priority evaluation model based on the global state dataset, determine the weight of each indicator through the analytic hierarchy process, generate a preliminary nest matching candidate set, and complete the accurate matching of UAVs and nests through the nest dynamic matching mechanism. The task scheduling module 303 is used to pre-allocate multiple tasks based on the received instruction information of the UAV using a cluster collaborative scheduling optimization algorithm that integrates multiple constraints, and outputs the dynamic task reallocation results according to the UAV power decay rate, changes in nest resources and changes in task scenarios. The trajectory planning module 304 is used to generate cross-nest switching trajectories based on the task scheduling results by improving the RRT trajectory planning algorithm. At the same time, based on the remaining range, required power and risk assessment of the UAV when switching across nests, it outputs temporary diversion strategies and the scheduling results of the nearest available nest. The docking interaction module 305 is used to realize UAV docking and resupply, data uploading and position adjustment based on high-precision landing guidance technology, data synchronization protocol and scheduling instructions; The status perception module, nest matching module, task scheduling module, trajectory planning module, and docking interaction module are sequentially connected by signals to collaboratively complete the intelligent scheduling of multiple firefighting drones and nests.

[0042] The system also includes a memory and a processor. The memory includes a program for a fire-fighting drone scheduling method based on multi-drone multi-nest intelligent matching. When the program for the fire-fighting drone scheduling method based on multi-drone multi-nest intelligent matching is executed by the processor, it implements the steps of the fire-fighting drone scheduling method based on multi-drone multi-nest intelligent matching as described in any one of the first aspects.

[0043] This invention provides a method and system for scheduling firefighting drones based on multi-drone, multi-nest intelligent matching. It constructs a multi-source sensor fusion, multi-dimensional state perception system to collect information such as drone swarm flight parameters, mission progress, multi-nest resource occupancy, docking status, and location. After data cleaning and spatiotemporal alignment preprocessing, a spatiotemporally correlated global state dataset is obtained. Based on this dataset, a multi-dimensional index system including mission response time, energy consumption cost, and resource utilization is constructed using the analytic hierarchy process (AHP). A nest matching priority evaluation model is established to generate a preliminary matching candidate set. Precise matching is then achieved through dual-module dynamic frequency adaptation, visual identifier extraction, and multi-modal fusion positioning. A cluster collaborative scheduling optimization algorithm integrating multiple constraints is employed. Multi-task pre-allocation is achieved based on constraints such as range, battery power, and mission priority. Combined with drone battery decay, nest resource changes, and scene modifications, resource conflict coordination and improved response time (RRT) are implemented. The system completes task dynamic reallocation and collision-free cross-nest trajectory generation through trajectory planning. During cross-nest switching, based on remaining range, required power, and risk assessment, it retrieves global status data to verify available nests and sorts them by distance to generate temporary alternate landing strategies. Finally, relying on high-precision landing guidance technology that combines differential positioning and visual marker fusion, and edge node-assisted incremental synchronization protocol, combined with scheduling commands, the system completes UAV docking and resupply, data uploading, and position adjustment. Through the collaborative operation of modules such as status perception, nest matching, and task scheduling, as well as memory and processor, the system forms a closed loop of perception, matching, scheduling, trajectory, and docking, comprehensively improving the accuracy, dynamic adaptability, and safety of multi-UAV, multi-nest collaborative operations of firefighting UAVs.

[0044] In the several embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are merely illustrative. For example, the division of units is only a logical functional division, and in actual implementation, there may be other division methods, such as: multiple units or components can be combined, or integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the various components shown or discussed can be through some interfaces, and the indirect coupling or communication connection between devices or units can be electrical, mechanical, or other forms.

[0045] The units described above as separate components may or may not be physically separate. The components shown as units may or may not be physical units. They may be located in one place or distributed across multiple network units. Some or all of the units may be selected to achieve the purpose of this embodiment according to actual needs.

[0046] In addition, in the various embodiments of the present invention, each functional unit can be integrated into one processing unit, or each unit can be a separate unit, or two or more units can be integrated into one unit; the integrated unit can be implemented in hardware or in the form of hardware plus software functional units.

[0047] Those skilled in the art will understand that all or part of the steps of the above method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a readable storage medium. When the program is executed, it performs the steps of the above method embodiments. The aforementioned storage medium includes various media that can store program code, such as mobile storage devices, read-only memory, random access memory, magnetic disks, or optical disks.

[0048] Alternatively, if the integrated units of this invention are implemented as software functional modules and sold or used as independent products, they can also be stored in a readable storage medium. Based on this understanding, the technical solutions of the embodiments of this invention, or the parts that contribute to the prior art, can be embodied in the form of a software product. This software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the methods described in the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as mobile storage devices, ROM, RAM, magnetic disks, or optical disks.

Claims

1. A method for dispatching firefighting drones based on multi-drone, multi-nest intelligent matching, characterized in that: Includes the following steps: A multi-dimensional state perception system was constructed, and information on fire-fighting drone clusters and multi-nest operation was collected and preprocessed to obtain a spatiotemporally correlated global state dataset. Based on the global state dataset, a nest matching priority evaluation model is established, and the weights of each indicator are determined by the analytic hierarchy process to generate a preliminary nest matching candidate set. Based on the preliminary candidate set of nest matching, the UAV and nest are accurately matched through the nest dynamic matching mechanism; A cluster collaborative scheduling optimization algorithm integrating multiple constraints is adopted to pre-allocate multiple tasks based on the command information received by the UAV; Based on the drone's battery decay rate, changes in nest resources, and changes in mission scenarios, we obtain the results of dynamic mission reallocation and improved RRT trajectory planning. Based on the remaining range, required power, and risk assessment during the drone cross-nest switching, a temporary diversion strategy and the result of scheduling the nearest available drone nest are obtained. Based on high-precision landing guidance technology, data synchronization protocol and scheduling instructions, the results of UAV docking and resupply, data upload and position adjustment are obtained.

2. The firefighting drone dispatching method based on multi-machine multi-nest intelligent matching according to claim 1, characterized in that, The construction of a multi-dimensional state perception system involves collecting and preprocessing information on firefighting drone swarms and multi-nest operation, resulting in a spatiotemporally correlated global state dataset. Specifically: Based on multi-source sensor fusion acquisition technology, information on firefighting drone clusters and multi-hub operation is obtained; The information of the firefighting drone cluster includes flight parameters and mission execution progress; The multi-nest operation information includes resource occupancy status, docking readiness status, and location information; The firefighting drone cluster information and multi-nest operation information are preprocessed by data cleaning and spatiotemporal alignment to obtain a spatiotemporally correlated global state dataset.

3. The firefighting drone dispatching method based on multi-machine multi-nest intelligent matching according to claim 1, characterized in that, Based on the global state dataset, a nest matching priority evaluation model is established. The weights of each indicator are determined using the analytic hierarchy process (AHP), and a preliminary nest matching candidate set is generated. Specifically: Based on the task response time, energy consumption cost, and nest resource utilization rate in the global state dataset, a multi-dimensional indicator system is constructed as the core evaluation indicators of the model. A judgment matrix is ​​constructed by comparing multiple core indicators pairwise using the analytic hierarchy process. After consistency verification, the weights are quantified and normalized. By combining the real-time state parameters in the global state dataset, the matching fitness of multiple nests is comprehensively calculated and sorted to obtain a preliminary nest matching candidate set.

4. The firefighting drone dispatching method based on multi-machine multi-nest intelligent matching according to claim 1, characterized in that, The precise matching of UAVs and nests based on the preliminary nest matching candidate set and through the nest dynamic matching mechanism includes: Based on the nest attributes of the preliminary nest matching candidate set and the real-time status parameters in the global status dataset, frequency adaptation is performed through a dual-module dynamic matching mechanism. Spatial calibration was completed through visual identifier extraction, laser ranging, and multimodal fusion positioning to verify the feasibility of candidate nest matching and obtain accurate matching results.

5. The firefighting drone dispatching method based on multi-machine multi-nest intelligent matching according to claim 1, characterized in that, The cluster collaborative scheduling optimization algorithm, which incorporates multiple constraints, pre-allocates multiple tasks based on the UAV's received instruction information, including: Based on the information received by the UAV, extract the UAV's range threshold, remaining battery power, mission urgency priority, and mission location distribution, and construct a multi-dimensional constraint system. Based on the cluster collaborative scheduling optimization algorithm that integrates multiple constraints, a multi-objective optimization function is constructed, and each constraint condition is transformed into a function constraint term. The optimal solution for multi-task pre-allocation is obtained through iterative calculation by the optimization solution algorithm.

6. The firefighting drone dispatching method based on multi-machine multi-nest intelligent matching according to claim 5, characterized in that, The process of obtaining dynamic task reallocation results and improved RRT trajectory planning results based on UAV battery decay rate, changes in nest resources, and changes in mission scenario is as follows: Based on the drone's power decay rate, changes in nest resources, and mission scenario, and combined with the global state dataset, an improved RRT trajectory planning algorithm that integrates an energy consumption prediction model and a dynamic obstacle avoidance mechanism is used to update trajectory nodes and verify path feasibility. The resource conflict coordination algorithm yields the results of dynamic task reallocation and collision-free cross-nest switching trajectory planning.

7. The firefighting drone dispatching method based on multi-machine multi-nest intelligent matching according to claim 1, characterized in that, The temporary diversion strategy and the result of scheduling the nearest available drone nest are obtained based on the remaining range, required power, and risk assessment during the drone's cross-nest switching. Risk assessment is based on the remaining range data and required power calculation results when the drone switches between different nests, combined with the preset power redundancy threshold and the remaining range adaptability calculation. The idle status information of the nests in the global status dataset is retrieved synchronously to complete real-time verification. Nests that meet the conditions are sorted according to the distance priority sorting algorithm to obtain the temporary alternate landing strategy and the scheduling result of the nearest idle nest.

8. The firefighting drone dispatching method based on multi-machine multi-nest intelligent matching according to claim 1, characterized in that, The process of obtaining UAV docking and resupply, data upload, and position adjustment results based on high-precision landing guidance technology, data synchronization protocol, and scheduling instructions is as follows: Based on the high-precision landing guidance technology that combines differential positioning and visual marker fusion, the incremental synchronization data protocol assisted by edge nodes, and the scheduling instructions, the landing path is calibrated by multi-source positioning data fusion, the mission data is transmitted according to the incremental synchronization rules, and the position is dynamically adjusted in response to the instructions to obtain the corresponding execution results.

9. A fire-fighting drone dispatch system based on multi-machine, multi-nest intelligent matching, characterized in that, include: The state perception module is used to build a multi-dimensional state perception system, collect information on fire-fighting drone clusters and multi-nest operation information, preprocess them, and output a spatiotemporally correlated global state dataset. The nest matching module is used to establish a nest matching priority evaluation model based on the global state dataset, determine the weight of each indicator through the analytic hierarchy process, generate a preliminary nest matching candidate set, and complete the accurate matching of UAVs and nests through the nest dynamic matching mechanism. The task scheduling module is used to pre-allocate multiple tasks based on the drone's received instruction information using a cluster collaborative scheduling optimization algorithm that integrates multiple constraints. It also outputs the dynamic task reallocation results based on the drone's power decay rate, changes in nest resources, and changes in the task scenario. The trajectory planning module is used to generate cross-nest switching trajectories based on the task scheduling results and by improving the RRT trajectory planning algorithm. At the same time, based on the remaining range, required power and risk assessment of the UAV when switching across nests, it outputs temporary diversion strategies and the scheduling results of the nearest available nest. The docking interaction module is used to realize UAV docking and resupply, data uploading and position adjustment based on high-precision landing guidance technology, data synchronization protocol and scheduling instructions; The status perception module, nest matching module, task scheduling module, trajectory planning module, and docking interaction module are sequentially connected by signals to collaboratively complete the intelligent scheduling of multiple firefighting drones and nests.

10. A fire-fighting drone dispatch system based on multi-machine, multi-nest intelligent matching, characterized in that: The system also includes a memory and a processor. The memory contains a program for a multi-drone, multi-nest intelligent matching method for dispatching firefighting drones. When the processor executes the program for the multi-drone, multi-nest intelligent matching method for dispatching firefighting drones, it performs the following steps: A multi-dimensional state perception system was constructed, and information on fire-fighting drone clusters and multi-nest operation was collected and preprocessed to obtain a spatiotemporally correlated global state dataset. Based on the global state dataset, a nest matching priority evaluation model is established, and the weights of each indicator are determined by the analytic hierarchy process to generate a preliminary nest matching candidate set. Based on the preliminary candidate set of nest matching, the UAV and nest are accurately matched through the nest dynamic matching mechanism; A cluster collaborative scheduling optimization algorithm integrating multiple constraints is adopted to pre-allocate multiple tasks based on the command information received by the UAV; Based on the drone's battery decay rate, changes in nest resources, and changes in mission scenarios, we obtain the results of dynamic mission reallocation and improved RRT trajectory planning. Based on the remaining range, required power, and risk assessment during the drone cross-nest switching, a temporary diversion strategy and the result of scheduling the nearest available drone nest are obtained. Based on high-precision landing guidance technology, data synchronization protocol and scheduling instructions, the results of UAV docking and resupply, data upload and position adjustment are obtained.

Images