Intelligent collaborative operation methods, systems, electronic devices and storage media for multi-heterogeneous unmanned aerial vehicle (UAV) swarms

Abstract

This invention discloses an intelligent collaborative operation method, system, electronic device, and storage medium for multi-heterogeneous unmanned aerial vehicle (UAV) swarms, relating to the field of UAV application technology. The method includes the following steps: S10, receiving and maintaining a resource pool containing UAV status information in real time, and receiving emergency event information in real time; S20, using a multi-dimensional weighted scoring scheduling algorithm to select the optimal scheduling object to perform the initial response; S30, quantitatively evaluating the event level of the current scenario and estimating the task duration and required swarm size to generate a recommended grouping scheme; S40, dynamically calculating and managing the number of standby UAVs required for relay rotation based on the estimated task duration and single-UAV endurance; S50, coordinating the multi-heterogeneous UAV sub-swarms to perform collaborative operations; S60, after the emergency event is handled, controlling the UAVs to return to base and generating a task debriefing report. The beneficial effects of this invention are: improved collaborative response efficiency and operational continuity in the face of emergencies.

Description

Technical Field

[0001] This invention relates to the field of unmanned aerial vehicle (UAV) application technology, and more specifically, to a method, system, electronic device, and storage medium for intelligent collaborative operation of a multi-heterogeneous UAV swarm. Background Technology

[0002] In recent years, with the rapid development and maturation of drone technology, its application in fields such as security patrol, emergency rescue, and disaster response has become increasingly widespread. However, when faced with complex real-world mission scenarios, especially emergencies requiring the simultaneous execution of multiple tasks such as reconnaissance, early warning, firefighting, and material delivery, existing technological solutions have revealed significant shortcomings.

[0003] Currently, the mainstream drone operation mode still mainly involves a single drone performing a single task, or a swarm of drones of the same type performing simple collaborative operations. This mode has inherent defects such as limited task capabilities, low overall response efficiency, and weak cross-functional collaboration capabilities. More importantly, there is usually a lack of a unified intelligent management and control platform for overall coordination and scheduling among drone swarms of different models and functions, resulting in rigid resource allocation and an inability to meet the stringent requirements of real-time performance, flexibility, and global collaboration in emergencies.

[0004] Specifically, at the emergency dispatch level, existing technologies fail to fully and scientifically integrate and comprehensively optimize multi-dimensional dynamic parameters such as the real-time location of drones, remaining battery power, specific mission payload status, and recharging waiting time. This makes it difficult to quickly and accurately select the optimal dispatch target in emergency situations, affecting the initial response speed. At the mission planning and execution level, existing solutions lack the ability to quantitatively assess and intelligently analyze the mission situation. They cannot dynamically generate scientific drone swarm formation schemes based on event level and type, nor can they support automated, battery-predictive-based relay rotation support for drones requiring long-term operation, making it difficult to maintain the continuity and stability of critical operations. Furthermore, at the command and control level, existing systems often suffer from an imbalance between automatic execution and human intervention. Either insufficient automation leads to inefficiency, or excessive automation weakens the final decision-making power of human commanders in critical decisions, lacking an efficient and scientific human-machine collaborative decision-making mechanism.

[0005] To this end, the present invention provides an intelligent collaborative operation method, system, electronic device and storage medium for multiple heterogeneous UAV swarms, which can realize intelligent unified scheduling of multiple heterogeneous UAV swarms, dynamic grouping based on event level and automatic relay based on power prediction, thereby greatly improving the collaborative response efficiency and operational continuity in the event of emergencies. Summary of the Invention

[0006] To overcome the shortcomings of existing technologies, this invention provides an intelligent collaborative operation method, system, electronic device, and storage medium for multiple heterogeneous UAV swarms. It can realize intelligent unified scheduling of multiple heterogeneous UAV swarms, dynamic grouping based on event levels, and automatic relay based on power prediction, thereby significantly improving the collaborative response efficiency and operational continuity in the event of emergencies.

[0007] The technical solution adopted by this invention to solve its technical problem is: an intelligent collaborative operation method for multiple heterogeneous drone swarms, applied to a drone scheduling system that includes at least a cloud control platform and multiple heterogeneous drone swarms, the improvement of which includes the following steps: S10, the cloud control platform receives and maintains a resource pool containing status information of all drones in the entire domain in real time, and receives information on emergencies through multiple channels; S20: Based on information about emergencies, the cloud control platform uses a multi-dimensional weighted scoring scheduling algorithm to select the optimal scheduling objects from the reconnaissance drone swarm and the early warning drone swarm to execute the initial response. S30: Based on the on-site data transmitted back by the reconnaissance drones in the early response, the cloud control platform quantifies the event level of the current scenario and estimates the mission duration and required fleet size to generate a recommended formation plan. S40, the cloud control platform dynamically calculates and manages the number of standby machines required for relay rotation based on the estimated mission duration and single-machine battery life. S50, based on the confirmed formation scheme, the cloud control platform coordinates multiple heterogeneous UAV subswarms to perform collaborative operations in layered mission airspace; After the emergency response is completed, the cloud control platform controls the drone to return to base and generates a mission debriefing report.

[0008] Furthermore, in step S10, the state vector corresponding to the state information of each UAV in the resource pool is defined as S={aircraft type, location, battery level, payload type, takeoff preparation time, current speed, maximum flight speed}; the emergency event information includes 110 / 119 emergency linkage, fixed sensor detection, early warning UAV airborne AI visual recognition events, event location, event type, and preliminary event situation.

[0009] Furthermore, in step S20, the specific method by which the cloud control platform uses a multi-dimensional weighted scoring scheduling algorithm to select the optimal scheduling object from the reconnaissance drone swarm and the early warning drone swarm to execute the preliminary response based on the information of the sudden event includes: S201 sets a task threshold power level for current emergencies. Its calculation expression is: In the formula, R represents a reconnaissance aircraft, W represents an early warning aircraft, and X represents the current UAV model. This represents the flight distance calculated based on the mission location and the current location of the UAV, using GIS path planning, and the converted flight energy consumption. This represents the minimum initial operation time required based on the task type, converted into energy consumption. This indicates the energy consumption reserved for safe return to base for this aircraft model; S202, Calculate the integrated response time of individual aircraft within the candidate reconnaissance aircraft set and the candidate early warning aircraft set. Its calculation expression is: In the formula, This indicates the flight time to the task point based on GIS route planning; Indicates the refueling wait time; i represents the i-th UAV in the candidate reconnaissance aircraft set or candidate early warning aircraft set; S203 selects the UAV with the shortest overall response time from the candidate reconnaissance aircraft set and the candidate early warning aircraft set, respectively, and issues mission scheduling instructions.

[0010] Furthermore, in step S202, the energy replenishment waiting time... The value is determined by the drone's current battery level. Determine if Then no energy replenishment is needed. ;like Then the charging time needs to be calculated. In the formula, This indicates the current real-time charging power of the drone.

[0011] Furthermore, in step S30, the specific method for quantitatively assessing the event level of the current scenario is as follows: the event level is divided into three levels: general, relatively large, or serious. When the event simultaneously meets the following conditions: no casualties or trapped personnel, fire area less than 50 square meters, affected area less than 500 square meters, and no hazardous materials, the current event level is general. When the event meets at least one of the following conditions: 1-4 casualties or trapped personnel, fire area between 50-150 square meters, affected area between 500-1000 square meters, and hazardous materials present, the current event level is relatively large. When the event meets at least one of the following conditions: 5 or more casualties or trapped personnel, fire area greater than 150 square meters, affected area greater than 1000 square meters, and hazardous materials leaked or exploded, the current event level is serious.

[0012] Furthermore, in step S40, the specific calculation expression for the number of standby aircraft required for the relay rotation is as follows: The calculation result is taken upwards, where, This indicates the pre-set scale of standby aircraft models on the scene. Indicates the estimated total task duration; The calculation expression for the pure on-site operation time of a single machine is as follows: In the formula, Indicates the total battery life of a single device; This indicates the one-way flight time from the hangar to the mission point; This represents the remaining safe return time, and its calculation expression is: In the formula, This indicates the energy consumption value reserved for a safe return trip. This indicates the power of the return flight.

[0013] Furthermore, during the standby drone rotation process, the cloud control platform monitors the battery level of each drone in real time. To achieve seamless rotation, if the battery level of any drone falls below the threshold triggering the rotation, a switch will be activated. At that moment, the cloud control platform immediately dispatched a standby aircraft to take off. By the time the standby aircraft arrived at the mission point, the original aircraft's remaining battery power had just dropped to the return-to-base threshold. At this point, the original aircraft begins its return journey, and the standby aircraft takes over the mission; among these, the relay triggers the power threshold. The calculation expression is: .

[0014] An intelligent collaborative operation system for a multi-heterogeneous UAV swarm, used to implement the intelligent collaborative operation method for a multi-heterogeneous UAV swarm as described above, is improved by including: The global status monitoring and event access module is used to receive and maintain a resource pool containing status information of all drones in the global domain in real time, and to receive information on emergencies through multiple channels. The emergency dispatch and early response module is used to select the optimal dispatch object from the reconnaissance drone swarm and the early warning drone swarm respectively to perform early response using a multi-dimensional weighted scoring dispatch algorithm; The situation assessment and dynamic grouping module is used to quantitatively assess the event level of the current scenario based on the field data transmitted back by reconnaissance drones in the early response, and to estimate the mission duration and required fleet size in order to generate a recommended grouping scheme. The relay support and mission takeover module is used to dynamically calculate and manage the number of standby aircraft required for relay rotation based on the estimated mission duration and single-aircraft endurance. The multi-drone on-site dynamic command module is used to coordinate multiple heterogeneous UAV subswarms to perform collaborative operations in layered mission airspaces according to the confirmed formation scheme; The task completion and system reset module is used to control the drone to return to base and generate a task review report after the emergency response is completed.

[0015] An electronic device, improved in that it includes at least one processor and at least one memory, wherein, The memory stores computer-readable instructions; The computer-readable instructions are executed by one or more processors, enabling the electronic device to implement the intelligent collaborative operation method for a multi-heterogeneous drone swarm as described above.

[0016] An improvement of a storage medium storing computer-readable instructions is that the computer-readable instructions are executed by one or more processors to achieve the intelligent collaborative operation method for a multi-heterogeneous unmanned aerial vehicle (UAV) swarm as described above.

[0017] The beneficial effects of this invention are as follows: First, by maintaining a resource pool containing the status information of all UAVs within the entire domain, this invention solves the problems of platform fragmentation and inflexible scheduling, achieving centralized management and control of resources across the entire domain. Second, by utilizing a multi-dimensional weighted scoring scheduling algorithm to optimally select scheduling objects and execute early responses, it solves the problem of unscientific scheduling, ensuring rapid and accurate early responses. Third, by performing quantitative evaluation based on field data and generating recommended grouping schemes, it solves the problem of being unable to dynamically and scientifically form multi-task UAV groups based on events, achieving flexible capability adaptation. Fourth, by dynamically calculating and managing the number of standby UAVs, it establishes an automatic relay mechanism based on endurance time, solving the problem of operational interruption caused by endurance limitations and ensuring mission continuity. Finally, by coordinating multiple heterogeneous UAV sub-groups to perform collaborative operations in layered mission airspaces, it solves the problems of aerial conflicts and weak coordination among multiple UAV groups. Therefore, this invention can achieve intelligent unified scheduling of multiple heterogeneous UAV groups, dynamic grouping based on event levels, and automatic relay based on battery prediction, thereby significantly improving the efficiency of collaborative response and operational continuity in the face of emergencies. Attached Figure Description

[0018] Figure 1 This is a flowchart of an intelligent collaborative operation method for a multi-heterogeneous unmanned aerial vehicle (UAV) swarm according to the present invention; Figure 2 This is a block diagram of an intelligent collaborative operation system for a multi-heterogeneous unmanned aerial vehicle (UAV) swarm according to the present invention. Figure 3 This is a hardware structure diagram of an electronic device as an example embodiment; Figure 4 This is a block diagram illustrating an electronic device as an example embodiment. Detailed Implementation

[0019] The present invention will be further described below with reference to the accompanying drawings and embodiments.

[0020] The following will clearly and completely describe the concept, specific structure, and technical effects of the present invention in conjunction with embodiments and accompanying drawings, so as to fully understand the purpose, features, and effects of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, not all of them. Other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative effort are all within the scope of protection of the present invention. Furthermore, all connections / linkages involved in the patent do not simply refer to direct contact between components, but rather to the ability to form a better connection structure by adding or reducing connecting accessories according to specific implementation conditions. The various technical features in this invention can be combined interactively without contradicting each other.

[0021] like Figure 1 As shown, this invention discloses an intelligent collaborative operation method for multiple heterogeneous drone swarms, which is applied to a drone scheduling system that includes at least a cloud control platform and multiple heterogeneous drone swarms.

[0022] It should be noted that the cloud control platform, as a unified command and control center, is capable of registering and monitoring the status of various types of UAVs (early warning, reconnaissance, firefighting, material delivery, etc.) and their swarms, and possesses the capabilities for task scheduling, path planning, and multi-swarm collaborative decision-making. Its main functions are as follows: It has a built-in Geographic Information System (GIS) map and resource pool management module, which is used to monitor the model, location, battery level, payload status and other information of all drones in real time; It is responsible for receiving alarm information from across the entire region and supports linkage access to the 110 / 119 emergency command system; it also supports automatic reporting of events by airborne intelligent sensors and AI visual recognition from early warning aircraft. It has a built-in auxiliary decision engine for automatically performing situational analysis, dynamic scheduling, swarm formation, path planning, relay and collaborative operations based on event information and UAV status. Provides a human-computer interaction interface for commanders to make final decisions regarding "people in the loop," including confirming and issuing key instructions and modifying plans. The heterogeneous drone swarm mainly includes early warning drone swarms, reconnaissance drone swarms, material delivery drone swarms, and firefighting drone swarms, which can be flexibly grouped according to the type of emergency. Each swarm is a functional operational unit, which can independently perform special tasks or cooperate with other swarms to complete complex tasks. The descriptions of each swarm are as follows: Early warning drone swarm: Equipped with image analysis and recognition modules and area warning modules, it can realize routine patrol and early warning, early warning around the scene of emergencies, airspace security, and traffic control assistance. Reconnaissance UAV swarm: Equipped with high-definition visual reconnaissance modules and emergency command modules, it can conduct aerial reconnaissance of personnel casualties, facility damage, and environmental situation at the incident site, and transmit data to the cloud control platform in real time; it also supports 3D modeling to provide data support and command basis for emergency response. Logistics delivery drone fleet: Equipped with a precision delivery module, it can accurately deliver medical / rescue emergency supplies such as stretchers, medical kits, and oxygen cylinders. It also has lightweight lifting capabilities and can assist in transferring injured or deceased personnel to ambulances. Firefighting drone swarm: It includes two types: bombardment drones and guided firefighting drones. Equipped with intelligent bombing modules, it can accurately deliver firefighting munitions. Among them, bombardment drones are responsible for firefighting tasks in forest areas and open areas, while guided firefighting drones are responsible for breaking windows in buildings to guide firefighting. The swarm has the ability to accurately locate fire points, extinguish small fires and suppress large fires. In addition, the drone dispatch system is also equipped with ground support infrastructure, which includes distributed automated hangars / charging / battery swapping stations. By connecting to the cloud control platform, the cloud control platform enables drones to automatically dock, charge / swap batteries, load fire extinguishing bombs / supplies, and perform status self-checks. It also supports autonomous relay of drone fleets, continuous operation, and rapid re-flight, ensuring that emergency missions are not interrupted.

[0023] The intelligent collaborative operation method for multi-heterogeneous drone swarms includes the following steps: S10, the cloud control platform receives and maintains a resource pool containing status information of all drones in the entire domain in real time, and receives emergency information through multiple channels; wherein, the status vector corresponding to the status information of each drone in the resource pool is defined as S={drone type, location, battery level, payload type, takeoff preparation time, current speed, maximum flight speed}; the emergency information includes 110 / 119 emergency linkage, fixed sensor detection, early warning drone onboard AI visual recognition events, event location, event type and preliminary event situation.

[0024] It should be noted that, in this embodiment, the cloud control platform receives the status data periodically reported or triggered by events from each UAV within the entire domain in real time through the IoT communication link, and dynamically updates it to the central database to maintain the resource pool. The static information of each UAV's status vector S, namely "model" and "mount type", is obtained from the onboard registration information. The "location", "battery level", and "current speed" are reported in real time by the UAV's GPS, BMS, and flight control system. The "takeoff preparation time" is calculated by combining the mount replacement and battery charging / recharging status of the hangar where it is located. At the same time, the platform connects with the 110 / 119 emergency command system through a standardized interface to receive structured alarm information, accesses the monitoring data streams of various fixed sensors (such as smoke and traffic monitoring sensors) through network protocols, and analyzes the AI ​​visual event alarm information identified by the early warning UAV through the onboard edge computing device and transmitted back through the wireless network. Then, it processes this multi-channel information in a unified manner to extract the event location (such as latitude and longitude), event type (such as fire and traffic accident), and preliminary situation description to form a standardized event task.

[0025] S20: Based on information about emergencies, the cloud control platform uses a multi-dimensional weighted scoring scheduling algorithm to select the optimal scheduling objects from the reconnaissance drone swarm and the early warning drone swarm to execute the initial response. Specifically, the cloud control platform uses a multi-dimensional weighted scoring scheduling algorithm to select the optimal scheduling target from the reconnaissance drone swarm and the early warning drone swarm to execute the initial response based on emergency event information. The specific methods include: S201 sets a task threshold power level for current emergencies. Its calculation expression is: In the formula, R represents a reconnaissance aircraft, W represents an early warning aircraft, and X represents the current UAV model. This represents the flight distance calculated based on the mission location and the current location of the UAV, using GIS path planning, and the converted flight energy consumption. This represents the minimum initial operation time required based on the task type, converted into energy consumption. This indicates the energy consumption reserved for safe return to base for this aircraft model; S202, Calculate the integrated response time of individual aircraft within the candidate reconnaissance aircraft set and the candidate early warning aircraft set. Its calculation expression is: In the formula, This indicates the flight time to the task point based on GIS route planning; Indicates the refueling wait time; i represents the i-th UAV in the candidate reconnaissance aircraft set or candidate early warning aircraft set; S203 selects the UAV with the shortest overall response time from the candidate reconnaissance aircraft set and the candidate early warning aircraft set, respectively, and issues mission scheduling instructions.

[0026] Furthermore, in step S202, the energy replenishment waiting time... The value is determined by the drone's current battery level. Determine if Then no energy replenishment is needed. ;like Then the charging time needs to be calculated. In the formula, This indicates the current real-time charging power of the drone.

[0027] It should be noted that in this embodiment, after receiving information about an emergency, the cloud control platform will immediately activate the multi-dimensional weighted scoring and scheduling algorithm. The specific implementation process is as follows: First, the platform calculates the task threshold power consumption for executing this initial response mission for both reconnaissance drones and early warning drones. This power consumption (… The energy consumption of the flight to reach the incident site ( ), and the energy consumption required to complete the initial minimum operation time ( ) and redundant energy consumption to ensure safe return ( The system consists of three parts: a selection mechanism, a system for selecting drones, and a system for calculating the overall response time. The system ensures that the selected drones have sufficient energy to complete the mission. Next, the platform selects drones from the available reconnaissance and early warning aircraft whose battery levels are not lower than the mission threshold for their respective models, forming a candidate set. For each drone in the candidate set, the platform calculates its overall response time. This time is not simply the flight time, but the flight time from the point of arrival at the scene. ) and the possible waiting time for recharging ( The sum of the current battery level and the recharge waiting time depends on the drone's current battery level. Judgment: If the battery is sufficient ( ≥ If the battery is low, the waiting time is zero; if the battery is low, the charging time will be adjusted according to the real-time charging power. The system calculates the charging time required to replenish the battery to the threshold level. Finally, the cloud control platform selects the drone with the shortest overall response time from the candidate sets of reconnaissance and early warning drones, deeming it the optimal scheduling target, and issues mission instructions to it. If the drone needs charging (…), the system will then determine the optimal scheduling target. Then, a "replenishment of energy" order will be issued. "Take off in seconds" command; if the battery level is sufficient (i.e. If the selected early warning drone is currently performing a routine patrol mission, the system will issue an "immediate takeoff" command. Alternatively, if the selected drone is already performing a routine patrol mission, the system must first issue an "interrupt original mission" command before issuing the above command. Reconnaissance drone groups generally do not perform routine patrols, therefore there is no interruption step. Through this process, the system can scientifically and quickly select the optimal drone from global resources that can arrive at the scene and begin operations with the shortest "total preparation time," achieving efficient early response.

[0028] S30, the cloud control platform quantifies the event level of the current scenario based on the on-site data transmitted back by the reconnaissance drones in the initial response, and estimates the mission duration and required fleet size to generate a recommended formation plan. Specifically, the method for quantifying the event level of the current scenario is as follows: the event level is divided into three levels: general, relatively large, or serious. When the event simultaneously meets the following conditions: no casualties or trapped personnel, fire area less than 50 square meters, affected area less than 500 square meters, and no hazardous materials, the current event level is general. When the event meets at least one of the following conditions: 1-4 casualties or trapped personnel, fire area between 50-150 square meters, affected area between 500-1000 square meters, and hazardous materials present, the current event level is relatively large. When the event meets at least one of the following conditions: 5 or more casualties or trapped personnel, fire area greater than 150 square meters, affected area greater than 1000 square meters, and hazardous materials leaked or exploded, the current event level is serious.

[0029] It should be noted that, in this embodiment, after the reconnaissance drone transmits real-time video and data from the scene back to the cloud control platform, the commander enters or confirms key quantitative information on the human-computer interaction interface of the cloud control platform according to the preset standardized forms (as shown in Table 1). This includes determining the event type, casualty / trapped level, and burned area by clicking, determining the affected area by circling on the map, and selecting whether material delivery, firefighting operations, and airspace surveillance are needed. Subsequently, the platform's decision engine automatically compares this entered information with the preset event level judgment matrix (as shown in Table 2), and quantifies the event as general based on the rule of "meeting any one of the criteria triggers the event and the higher level is chosen." (L1), Major (L2), or Serious (L3) level; Next, based on the determined event type and level, the cloud control platform queries the preset formation strategy matrix (as shown in Table 3), automatically matching and generating a recommended formation scheme containing the specific number of each aircraft type (reconnaissance, early warning, firefighting, and material delivery). During this process, the cloud control platform searches the historical case library for similar successful cases as auxiliary recommendation criteria and checks the number of available aircraft in the resource pool in real time. If the number is insufficient, a downgrade scheme is automatically generated and a prompt is displayed. Finally, the generated complete recommended scheme (including event level, estimated duration, aircraft size, and specific formation) will be presented to the commander for review, modification, and final confirmation. Among them: Table 1:

[0030] Table 2:

[0031] Table 3:

[0032] In addition, if the number of a certain type of fire extinguisher in the recommended plan is insufficient, the system will automatically prompt (e.g., "Only 2 fire extinguishers are currently available, 3 are recommended"); and generate a downgrade plan that only reduces the number of that type of fire extinguisher on site (other types remain unchanged), for the commander to select and confirm.

[0033] S40, the cloud control platform dynamically calculates and manages the number of standby aircraft required for relay rotation based on the estimated task duration and single-aircraft battery life; wherein, the specific calculation expression for the number of standby aircraft required for relay rotation is: The calculation result is taken upwards, where, This indicates the pre-set scale of standby aircraft models on the scene. Indicates the estimated total task duration; The calculation expression for the pure on-site operation time of a single machine is as follows: In the formula, Indicates the total battery life of a single device; This indicates the one-way flight time from the hangar to the mission point; This represents the remaining safe return time, and its calculation expression is: In the formula, This indicates the energy consumption value reserved for a safe return trip. This indicates the power of the return flight.

[0034] Furthermore, during the standby drone rotation process, the cloud control platform monitors the battery level of each drone in real time. To achieve seamless rotation, if the battery level of any drone falls below the threshold triggering the rotation, a switch will be activated. At that moment, the cloud control platform immediately dispatched a standby aircraft to take off. By the time the standby aircraft arrived at the mission point, the original aircraft's remaining battery power had just dropped to the return-to-base threshold. At this point, the original aircraft begins its return journey, and the standby aircraft takes over the mission; among these, the relay triggers the power threshold. The calculation expression is: .

[0035] It should be noted that, in this embodiment, the cloud control platform first determines the preset simultaneous presence scale that a certain model needs to maintain based on task requirements. and the estimated total task duration Next, the platform calculates the pure on-site operation time for a single machine. Its value is the total battery life of a single machine. Subtract the one-way flight time from the hangar to the mission point Subtract the remaining flight time for safe return. ( Based on the reserved safe return energy consumption value Divide by the drone's flight power (derived); subsequently, the platform uses the formula The minimum number of standby drones required is calculated by rounding up, and the corresponding number of drones is reserved from the resource pool accordingly, forming a "standby pool". During the execution phase, the platform monitors the battery level of each drone on site in real time. If the battery level of any drone falls below the relay trigger threshold, a relay will be initiated. ( When the mission is about to begin, a standby aircraft will be immediately dispatched from the standby pool. Upon arrival at the mission point, the standby aircraft will follow the original aircraft at a safe distance. Once the overlap of the two aircraft's video fields of view reaches 70%, the cloud control platform will control the standby aircraft to take over the mission. The original aircraft will then return to its home base, enter the hangar for refueling, and re-enter the standby pool to await dispatch. Additionally, during the relay process, because the standby aircraft has arrived while the original mission aircraft has not yet departed, the number of aircraft of that type on the field will temporarily change to [missing information]. +1, after switching, revert to the previous state. This brief overlap is a necessary guarantee for ensuring mission continuity, thereby ensuring seamless handover between the standby aircraft and the original aircraft.

[0036] S50, based on the confirmed formation scheme, the cloud control platform coordinates multiple heterogeneous UAV subswarms to perform collaborative operations in layered mission airspace; It should be noted that, in this embodiment, after receiving the final formation plan confirmed by the commander, the cloud control platform immediately decomposes the plan into specific task instructions for each UAV sub-swarm (such as reconnaissance, early warning, firefighting, and material delivery). Based on preset hierarchical airspace management rules, it assigns different flight altitude layers to UAV sub-swarms performing different functions (for example, reconnaissance aircraft conduct detailed reconnaissance at low altitudes, early warning aircraft conduct wide-area surveillance at medium altitudes, and firefighting and material delivery aircraft operate at specific operational altitudes), thereby spatially isolating flight trajectories and avoiding collisions. Subsequently, the platform issues task instructions containing airspace hierarchical information to each UAV in the corresponding sub-swarm. It coordinates them to fly to the site according to the established procedures and start collaborative operations at the designated altitude. During this process, the relay support mechanism (step S40) will continue to operate, automatically dispatching standby aircraft to take over from low-power aircraft to maintain the preset on-site scale of each subgroup and ensure the continuity of operations. At the same time, all key operational instructions (such as fire extinguishing, material delivery, and emergency evacuation) must be finally confirmed by the commander on the human-machine interface before they are issued for execution. The commander can also dynamically adjust the operational position and target of each aircraft group or issue temporary control instructions based on the real-time images and data transmitted back, thereby achieving safe, compliant, and efficient multi-aircraft group collaborative operations.

[0037] After the emergency response is completed, the cloud control platform controls the drone to return to base and generates a mission debriefing report.

[0038] It should be noted that, in this embodiment, after the commander confirms the completion of the event handling on the human-machine interface of the cloud control platform and issues the "mission ended" command, the cloud control platform immediately issues a return command to all UAVs of various types still operating in the mission airspace. This command includes the coordinates and flight path of their respective parking points (such as their respective distributed automated hangars). After receiving the command, the UAVs automatically detach from the mission formation and fly to the designated parking point along the planned safe flight path, then land and return to the hangar. After returning to the hangar, the UAVs automatically enter the maintenance and recharge process (charging / battery swapping, payload replacement) according to their own status (such as battery power and payload consumption), or according to the preset normal... The system automatically resumes routine patrol operations once the patrol task list is ready. Simultaneously, the cloud control platform automatically retrieves log data from the entire mission process, generating a structured mission debriefing report based on this data. Key data in the report includes the response time of the first batch of drones arriving, drone swarm utilization efficiency, sortie counts and operation times for each type of drone (based on swarm utilization efficiency), total mission energy consumption statistics, and an evaluation of the handling effectiveness based on the commander's input and target comparison. This report is automatically archived and imported into the system's historical case library, providing data mining and model training support for subsequent optimization of scheduling algorithm parameters and adjustment of grouping strategies.

[0039] Reference Figure 2As shown, the present invention also discloses an intelligent collaborative operation system 600 for a multi-heterogeneous UAV swarm, used to implement the intelligent collaborative operation method for a multi-heterogeneous UAV swarm as described above, including: The global status monitoring and event access module 601 is used to receive and maintain a resource pool containing status information of all UAVs in the global domain in real time, and to receive information on emergencies through multiple channels. The emergency dispatch and early response module 602 is used to select the optimal dispatch object from the reconnaissance drone swarm and the early warning drone swarm respectively to perform early response using a multi-dimensional weighted scoring dispatch algorithm; The situation assessment and dynamic grouping module 603 is used to quantitatively assess the event level of the current scenario based on the field data transmitted back by the reconnaissance UAVs in the early response, and to estimate the mission duration and the required fleet size in order to generate a recommended grouping scheme. The relay support and mission takeover module 604 is used to dynamically calculate and manage the number of standby aircraft required for relay rotation based on the estimated mission duration and single-aircraft endurance. The multi-drone on-site dynamic command module 605 is used to coordinate multiple heterogeneous UAV subswarms to perform collaborative operations in layered mission airspace according to the confirmed formation scheme. The task completion and system reset module 606 is used to control the drone to return to base and generate a task review report after the emergency response is completed.

[0040] It should be noted that the intelligent collaborative operation strategy based on multiple heterogeneous UAV swarms provided in the above embodiments is only an example of the division of the above functional modules. In actual applications, the above functions can be assigned to different functional modules as needed. That is, the internal structure of the intelligent collaborative operation system 600 based on multiple heterogeneous UAV swarms will be divided into different functional modules to complete all or part of the functions described above. Furthermore, the intelligent collaborative operation system 600 based on multiple heterogeneous UAV swarms provided in the above embodiments and the intelligent collaborative operation method based on multiple heterogeneous UAV swarms belong to the same concept. The specific way each module performs operations has been described in detail in the method embodiments, and will not be repeated here.

[0041] Figure 3 A schematic diagram of the structure of an electronic device according to an exemplary embodiment is shown.

[0042] It should be noted that this electronic device is merely an example adapted to the present invention and should not be construed as providing any limitation on the scope of use of the present invention. Furthermore, this electronic device should not be interpreted as requiring or depending on having... Figure 3 One or more components of the exemplary electronic device 2000 shown.

[0043] The hardware structure of electronic devices 2000 can vary significantly due to differences in configuration or performance, such as... Figure 3 As shown, the electronic device 2000 includes: a power supply 210, an interface 230, at least one memory 250, and at least one central processing unit (CPU) 270.

[0044] Specifically, power supply 210 is used to provide operating voltage for various hardware devices on electronic device 2000.

[0045] Interface 230 includes at least one wired or wireless network interface 231 for interacting with external devices. Of course, in other examples adapted to this invention, interface 230 may further include at least one serial-to-parallel conversion interface 233, at least one input / output interface 235, and at least one USB interface 237, etc. Figure 3 As shown, this does not constitute a specific limitation.

[0046] The memory 250 serves as a carrier for resource storage and can be a read-only memory, random access memory, disk, or optical disk, etc. The resources stored on it include the operating system 251, application programs 253, and data 255, etc., and the storage method can be temporary storage or permanent storage.

[0047] The operating system 251 is used to manage and control the various hardware devices and application programs 253 on the electronic device 2000, so as to enable the central processing unit 270 to perform calculations and processing on the massive data 255 in the memory 250. It can be Windows Server™, Mac OS X™, Unix™, Linux™, FreeBSD™, etc.

[0048] Application 253 is a computer-readable instruction based on operating system 251 that performs at least one specific task, and may include at least one module ( Figure 3 (Not shown), each module may contain computer-readable instructions for electronic device 2000. For example, an intelligent collaborative operation device based on a multi-heterogeneous UAV swarm can be considered as application 253 deployed on electronic device 2000.

[0049] Data 255 may be signal information, etc., and is stored in memory 250.

[0050] The central processing unit 270 may include one or more processors and is configured to communicate with the memory 250 via at least one communication bus to read computer-readable instructions stored in the memory 250, thereby enabling the computation and processing of massive amounts of data 255 in the memory 250. For example, an intelligent collaborative operation method based on a multi-heterogeneous UAV swarm can be implemented by the central processing unit 270 reading a series of computer-readable instructions stored in the memory 250.

[0051] Furthermore, the present invention can also be implemented through hardware circuits or a combination of hardware circuits and software. Therefore, the implementation of the present invention is not limited to any specific hardware circuit, software, or combination thereof.

[0052] Please see Figure 4 This invention provides an electronic device 4000, which may include: a desktop computer, a laptop computer, a server, etc., with sensor recognition capabilities.

[0053] exist Figure 4 In this context, the electronic device 4000 includes at least one processor 4001 and at least one memory 4003.

[0054] The data interaction between the processor 4001 and the memory 4003 can be achieved through at least one communication bus 4002. This communication bus 4002 may include a path for transmitting data between the processor 4001 and the memory 4003. The communication bus 4002 may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus, etc. The communication bus 4002 can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 4 The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0055] Optionally, the electronic device 4000 may further include a transceiver 4004, which can be used for data interaction between the electronic device and other electronic devices, such as sending and / or receiving data. It should be noted that in practical applications, the transceiver 4004 is not limited to one type, and the structure of the electronic device 4000 does not constitute a limitation on the embodiments of the present invention.

[0056] Processor 4001 may be a CPU (Central Processing Unit), a general-purpose processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array), or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. It can implement or execute the various exemplary logic blocks, modules, and circuits described in conjunction with the disclosure of this invention. Processor 4001 may also be a combination that implements computational functions, such as including one or more microprocessor combinations, a combination of a DSP and a microprocessor, etc.

[0057] The memory 4003 may be a ROM (Read Only Memory) or other type of static storage device capable of storing static information and instructions, RAM (Random Access Memory) or other type of dynamic storage device capable of storing information and instructions, or an EEPROM (Electrically Erasable Programmable Read Only Memory), CD-ROM (Compact Disc Read Only Memory) or other optical disc storage, optical disc storage (including compressed optical discs, laser discs, optical discs, digital universal optical discs, Blu-ray discs, etc.), magnetic disk storage media or other magnetic storage devices, or any other medium capable of carrying or storing desired program instructions or code in the form of instructions or data structures and accessible by the electronic device 4000, but not limited thereto.

[0058] The memory 4003 stores computer-readable instructions, and the processor 4001 can read the computer-readable instructions stored in the memory 4003 through the communication bus 4002.

[0059] The computer-readable instructions are executed by one or more processors 4001 to implement the intelligent collaborative operation method based on a multi-heterogeneous UAV swarm in the above embodiments.

[0060] Furthermore, this embodiment of the invention provides a storage medium storing computer-readable instructions, which are executed by one or more processors to implement the intelligent collaborative operation method based on a multi-heterogeneous UAV swarm as described above.

[0061] Compared with existing technologies, the beneficial effects of this invention are as follows: First, by maintaining a resource pool containing the status information of all UAVs in the entire domain, the problems of platform fragmentation and inflexible scheduling are solved, and centralized management and control of resources across the entire domain are achieved. Second, by using a multi-dimensional weighted scoring scheduling algorithm to optimally select scheduling objects and execute early responses, the problem of unscientific scheduling is solved, ensuring rapid and accurate early responses. Third, by performing quantitative evaluation based on field data and generating recommended grouping schemes, the problem of being unable to dynamically and scientifically form multi-task UAV groups based on events is solved, achieving flexible capability adaptation. Fourth, by dynamically calculating and managing the number of standby UAVs, an automatic relay mechanism based on endurance time is established, solving the problem of operation interruption caused by endurance limitations and ensuring mission continuity. Finally, by coordinating multiple heterogeneous UAV sub-groups to perform collaborative operations in layered mission airspaces, the problems of multi-group aerial conflicts and weak coordination are solved. Therefore, this invention can achieve intelligent unified scheduling of multiple heterogeneous UAV groups, dynamic grouping based on event levels, and automatic relay based on battery prediction, thereby significantly improving the efficiency of collaborative response and operational continuity in the face of emergencies.

[0062] The above is a detailed description of the preferred embodiments of the present invention. However, the present invention is not limited to the embodiments described. Those skilled in the art can make various equivalent modifications or substitutions without departing from the spirit of the present invention. All such equivalent modifications or substitutions are included within the scope defined by the claims of this application.

Claims

1. A method for intelligent collaborative operation of multiple heterogeneous unmanned aerial vehicle (UAV) swarms, applied to a UAV scheduling system comprising at least a cloud control platform and multiple heterogeneous UAV swarms, characterized in that, Includes the following steps: S10, the cloud control platform receives and maintains a resource pool containing status information of all drones in the entire domain in real time, and receives information on emergencies through multiple channels; S20: Based on information about emergencies, the cloud control platform uses a multi-dimensional weighted scoring scheduling algorithm to select the optimal scheduling objects from the reconnaissance drone swarm and the early warning drone swarm to execute the initial response. S30: Based on the on-site data transmitted back by the reconnaissance drones in the early response, the cloud control platform quantifies the event level of the current scenario and estimates the mission duration and required fleet size to generate a recommended formation plan. S40, the cloud control platform dynamically calculates and manages the number of standby aircraft required for relay rotation based on the estimated task duration and single-aircraft endurance; specifically, the calculation expression for the number of standby aircraft required for relay rotation is as follows: The calculation result is taken upwards, where, This indicates the pre-set scale of standby aircraft models on the scene. Indicates the estimated total task duration; The calculation expression for the pure on-site operation time of a single machine is as follows: In the formula, Indicates the total battery life of a single device; This indicates the one-way flight time from the hangar to the mission point; This represents the remaining safe return time, and its calculation expression is: In the formula, This indicates the energy consumption value reserved for a safe return trip. Indicates the return flight power; Furthermore, during the standby drone rotation process, the cloud control platform monitors the battery level of each drone in real time. To achieve seamless rotation, if the battery level of any drone falls below the threshold triggering the rotation, a switch will be activated. At that moment, the cloud control platform immediately dispatched a standby aircraft to take off. By the time the standby aircraft arrived at the mission point, the original aircraft's remaining battery power had just dropped to the return-to-base threshold. At this point, the original aircraft begins its return journey, and the standby aircraft takes over the mission; among these, the relay triggers the power threshold. The calculation expression is: ； S50, based on the confirmed formation scheme, the cloud control platform coordinates multiple heterogeneous UAV subswarms to perform collaborative operations in layered mission airspace; After the emergency response is completed, the cloud control platform controls the drone to return to base and generates a mission debriefing report.

2. The intelligent collaborative operation method for a multi-heterogeneous unmanned aerial vehicle (UAV) swarm according to claim 1, characterized in that, In step S10, the state vector corresponding to the state information of each UAV in the resource pool is defined as S={aircraft type, location, battery level, payload type, takeoff preparation time, current speed, maximum flight speed}; the emergency event information includes 110 / 119 emergency linkage, fixed sensor detection, early warning UAV onboard AI visual recognition events, event location, event type and preliminary event situation.

3. The intelligent collaborative operation method for a multi-heterogeneous unmanned aerial vehicle (UAV) swarm according to claim 2, characterized in that, In step S20, the specific method by which the cloud control platform uses a multi-dimensional weighted scoring scheduling algorithm to select the optimal scheduling object from the reconnaissance drone swarm and the early warning drone swarm to execute the preliminary response based on the information of the sudden event includes: S201 sets a task threshold power level for current emergencies. Its calculation expression is: In the formula, R represents a reconnaissance aircraft, W represents an early warning aircraft, and X represents the current UAV model. This represents the flight distance calculated based on the mission location and the current location of the UAV, using GIS path planning, and the converted flight energy consumption. This represents the minimum initial operation time required based on the task type, converted into energy consumption. This indicates the energy consumption reserved for safe return to base for this aircraft model; S202, Calculate the integrated response time of individual aircraft within the candidate reconnaissance aircraft set and the candidate early warning aircraft set. Its calculation expression is: In the formula, This indicates the flight time to the task point based on GIS route planning; Indicates the refueling wait time; i represents the i-th UAV in the candidate reconnaissance aircraft set or candidate early warning aircraft set; S203 selects the UAV with the shortest overall response time from the candidate reconnaissance aircraft set and the candidate early warning aircraft set, respectively, and issues mission scheduling instructions.

4. The intelligent collaborative operation method for a multi-heterogeneous unmanned aerial vehicle (UAV) swarm according to claim 3, characterized in that, In step S202, the energy replenishment waiting time The value is determined by the drone's current battery level. Determine if Then no energy replenishment is needed. ;like Then the charging time needs to be calculated. In the formula, This indicates the current real-time charging power of the drone.

5. The intelligent collaborative operation method for a multi-heterogeneous unmanned aerial vehicle (UAV) swarm according to claim 4, characterized in that, In step S30, the specific method for quantitatively assessing the event level of the current scenario is as follows: the event level is divided into three levels: general, relatively large, or serious. When the event simultaneously meets the following conditions, the current event level is general: there are no casualties or trapped personnel, the burned area is less than 50 square meters, the affected area is less than 500 square meters, and there are no hazardous materials. When the event meets at least one of the following conditions, the current event level is relatively large: the number of casualties or trapped personnel is between 1 and 4, the burned area is between 50 and 150 square meters, the affected area is between 500 and 1000 square meters, and there are hazardous materials. When the event meets at least one of the following conditions, the number of casualties or trapped personnel is greater than or equal to 5, the burned area is greater than 150 square meters, the affected area is greater than 1000 square meters, and there is a hazardous material leak or explosion, the current event level is serious.

6. An intelligent collaborative operation system for a multi-heterogeneous unmanned aerial vehicle (UAV) swarm, used to implement the intelligent collaborative operation method for a multi-heterogeneous UAV swarm as described in any one of claims 1-5, characterized in that, include: The global status monitoring and event access module is used to receive and maintain a resource pool containing status information of all drones in the global domain in real time, and to receive information on emergencies through multiple channels. The emergency dispatch and early response module is used to select the optimal dispatch object from the reconnaissance drone swarm and the early warning drone swarm respectively to perform early response using a multi-dimensional weighted scoring dispatch algorithm; The situation assessment and dynamic grouping module is used to quantitatively assess the event level of the current scenario based on the field data transmitted back by reconnaissance drones in the early response, and to estimate the mission duration and required fleet size in order to generate a recommended grouping scheme. The relay support and mission takeover module is used to dynamically calculate and manage the number of standby aircraft required for relay rotation based on the estimated mission duration and single-aircraft endurance. The multi-drone on-site dynamic command module is used to coordinate multiple heterogeneous UAV subswarms to perform collaborative operations in layered mission airspaces according to the confirmed formation scheme; The task completion and system reset module is used to control the drone to return to base and generate a task review report after the emergency response is completed.

7. An electronic device, characterized in that, Includes at least one processor and at least one memory, wherein, The memory stores computer-readable instructions; The computer-readable instructions are executed by one or more processors, causing the electronic device to implement the intelligent collaborative operation method for a multi-heterogeneous unmanned aerial vehicle (UAV) swarm as described in any one of claims 1-5.

8. A storage medium having computer-readable instructions stored thereon, characterized in that, The computer-readable instructions are executed by one or more processors to implement the intelligent collaborative operation method for a multi-heterogeneous unmanned aerial vehicle (UAV) swarm as described in any one of claims 1-5.

Images