Unmanned aerial vehicle-helicopter cooperative fire data real-time interaction and task scheduling system

Abstract

The application discloses a UAV-helicopter cooperative fire data real-time interaction and task scheduling system, belongs to the technical field of aviation fire fighting, and is characterized in that: fire-related data is collected, after processing, a fire point dynamic attribute set, a fire field environment state set and an aircraft situation set are generated, a three-dimensional fire field environment model is constructed, multi-source information fusion and visual presentation are realized, based on fire risk assessment and available aircraft state, a hierarchical matching and a greedy scheduling strategy based on priority rules are used to dynamically match fire extinguishing resources, high-risk fire points are preferentially disposed, fire execution data and fire data are continuously collected during the execution of the dual-machine cooperative task, the model is dynamically updated, situation awareness, real-time information sharing, intelligent task allocation and precise cooperative fire extinguishing are realized in the joint aerial operation of the UAV and the helicopter, the discovery and response capability and the efficient disposal capability of the fire are improved, and the precision and the success rate of the fire extinguishing operation are improved.

Description

Technical Field

[0001] This invention relates to the field of aviation firefighting technology, and more specifically, to a real-time fire data interaction and mission scheduling system that integrates unmanned aerial vehicles (UAVs) and helicopters. Background Technology

[0002] In emergency rescue scenarios such as forest fires, the use of drones and helicopters in collaborative operations has become an important means to improve firefighting efficiency. Drones can perform tasks such as fire reconnaissance and situational awareness, while helicopters undertake heavy-load firefighting operations. However, common collaborative operation systems still have shortcomings in multi-aircraft collaboration, dynamic task allocation, and low-latency communication.

[0003] For example, patent application CN119233320A discloses a drone-assisted integrated information and computing resource allocation method for forest fire fighting. This method optimizes task scheduling and resource allocation by constructing a drone-assisted ISCC system model to enhance real-time fire monitoring capabilities. However, this method has limitations in dynamic priority allocation of multiple fire points and is difficult to meet the needs of efficient multi-drone collaboration in complex fire environments.

[0004] For example, patent application CN121262245A proposes a multi-dimensional monitoring system for intelligent buildings that supports edge computing and cross-terminal collaborative management. It achieves distributed perception and collaborative control through a lightweight dynamic collaborative engine. However, the system still has shortcomings in low-latency communication protocol design and multi-machine collaborative dynamic resource allocation, and is especially unsuitable for scenarios where drones and helicopters work together in forest fire fighting.

[0005] In conclusion, there is an urgent need for a system that enables efficient data exchange and intelligent task scheduling between drones and helicopters to improve emergency response and handling capabilities for forest fires. Summary of the Invention

[0006] This invention aims to solve the technical problems of high communication latency, unreasonable task allocation, and lack of coordinated situational awareness in the existing technology of UAV and helicopter collaborative fire fighting. It provides a real-time interaction and task scheduling system for fire data in UAV-helicopter collaboration.

[0007] The objective of this invention can be achieved through the following technical solution: a real-time fire data interaction and task scheduling system for UAV-helicopter collaboration, comprising: The fire detection and continuous patrol module is configured to continuously collect fire-related data after receiving a fire signal using a drone performing a patrol mission. The situation model construction and visualization module is configured to receive fire-related data, and after spatiotemporal normalization processing, generate a dynamic attribute set of fire points, a fire environment state set, and an aircraft situation set. It also dynamically constructs and continuously updates a three-dimensional fire environment model, and visualizes the three-dimensional fire environment model to show the dynamics of fire points, the airspace environment state of the fire, and the trajectory status of UAVs. The rescue mission allocation and execution feedback module is configured to receive the dynamic attribute set of the fire point and the environmental status set of the fire scene to conduct fire risk assessment, obtain the aircraft situation set, the status data of the currently available helicopters / drones and the assessment results to formulate a fire-fighting mission allocation plan, and send it to the available helicopters and drones for dual-aircraft mission execution. At the same time, it acquires the dual-aircraft mission execution data in real time, and after spatiotemporal normalization processing, sends it to the situation model construction and visualization module. The situation model construction and visualization module is also configured to receive dual-machine task execution data and acquire new fire-related data in real time, continuously update the three-dimensional fire environment model, and render it in real time in the form of a three-dimensional map, dynamically displaying changes in fire point boundaries, fire spread trends, helicopter and drone trajectory status, fire temperature distribution map and meteorological environment layer.

[0008] Furthermore, the fire detection and continuous patrol module includes: The patrol route planning unit is configured to generate the patrol route of the drone based on the preset patrol area or the initial fire location. The fire triggering and acquisition unit is configured to monitor fire signals in real time through airborne sensors during drone patrols. When a fire is detected, it generates a trigger command to control the drone to hover or fly around it and continuously collect fire-related data. The data preprocessing unit is configured to timestamp and spatially calibrate the collected fire-related data to form a structured data packet with spatiotemporal labels.

[0009] Furthermore, the process of constructing a three-dimensional fire scene environment model includes: Receive structured data packets, parse out the geographical coordinates of the fire point, the set of fire point boundary points, the temperature field distribution, the smoke diffusion range, meteorological data and the drone mission status, perform time synchronization and spatial registration of data from different sources and timestamps, and unify multi-source data to the same spatiotemporal reference; The system employs Bayesian fusion or Kalman filtering methods to fuse spatiotemporally aligned multi-source data, generating a dynamic attribute set of fire points, a fire scene environmental state set, and an aircraft situation set. Combined with pre-stored geographic information system data, a three-dimensional fire scene environment model is constructed.

[0010] Furthermore, the fire risk assessment process in the rescue mission allocation module includes: The system receives the set of dynamic attributes of fire points and the set of environmental states of the fire scene, extracts the dynamic attributes and load attributes of each fire point, calculates the dynamic priority of each fire point according to the preset weight of each dynamic attribute, calculates the load priority of each fire point according to the preset weight of each load attribute, performs a weighted calculation on the dynamic priority and the load priority, assesses the fire risk of each fire point, and generates a fire risk level, including high risk, medium risk and low risk.

[0011] Furthermore, the fire risk assessment process in the rescue mission allocation module includes: The system receives the set of dynamic attributes of fire points and the set of environmental states of the fire scene, extracts the dynamic attributes and load attributes of each fire point, calculates the dynamic priority of each fire point according to the preset weight of each dynamic attribute, calculates the load priority of each fire point according to the preset weight of each load attribute, performs a weighted calculation on the dynamic priority and the load priority, assesses the fire risk of each fire point, and generates a fire risk level, including high risk, medium risk and low risk.

[0012] Furthermore, the process of developing a coordinated firefighting task allocation plan includes: All fire points are arranged in descending order of high risk, medium risk, and low risk according to their fire risk level. Within the same level, they are sorted by fire point area from largest to smallest. Acquire real-time status data of currently available helicopters and drones, and classify drones as reconnaissance and suppression available, and helicopters as firefighting available; Helicopters and drones are allocated according to the fire risk level, from highest to lowest.

[0013] Furthermore, the dual-machine coordinated firefighting task allocation scheme also includes: scientifically selecting the type and quantity of fire extinguishing bombs according to the load priority, wherein the types of fire extinguishing bombs include water-based, dry powder, foam, and flame retardant types; Plan a straight path for each assigned drone or helicopter, make simple detours in no-fly zones, and calculate the estimated arrival time; The final output includes a dual-aircraft collaborative firefighting mission allocation scheme that includes aircraft identification, fire point identification, mission type, fire extinguishing grenade configuration, planned route, and estimated arrival time.

[0014] The UAV-helicopter collaborative fire data real-time interaction and task scheduling system also includes the information communication module, which is configured to establish a two-way low-latency data link between the UAV and the helicopter, and between the UAV and the ground control station, for transmitting the fire-related data, the three-dimensional fire scene environment model data, and the dual-aircraft collaborative firefighting task allocation scheme.

[0015] Compared with the prior art, the advantages of this invention are: This invention utilizes a fire detection and continuous patrol module to continuously collect fire-related data after receiving a fire signal. A situational model construction and visualization module then generates a three-dimensional fire scene environment model, achieving the fusion and visualization of multi-source information. Based on the model presentation, a fire risk assessment is conducted, and a dual-aircraft collaborative firefighting task allocation plan is formulated in conjunction with the status of available aircraft. During the execution of the dual-aircraft mission, data on mission execution and fire-related data are continuously collected, and the model is constantly updated. This invention integrates situational awareness, real-time information sharing, intelligent task allocation, and precise collaborative firefighting in joint aerial operations between UAVs and helicopters, significantly improving forest fire detection and response capabilities and enabling efficient handling of forest fire accidents. In formulating a dual-aircraft collaborative firefighting task allocation scheme, this invention acquires real-time status data of currently available helicopters / drones, combines the fire risk level of each fire point, and uses a priority-based hierarchical matching and greedy scheduling strategy to scientifically match the complementary advantages of drones' fast reconnaissance response and helicopters' large payload capacity. This dynamically matches firefighting resources, prioritizes the handling of high-risk fire points, scientifically selects the type and quantity of fire extinguishing bombs, and implements precise firefighting operations to achieve the goal of maximizing fire suppression. Attached Figure Description

[0016] Figure 1 This is a system module block diagram of the present invention. Detailed Implementation

[0017] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative effort are within the scope of protection of the present invention.

[0018] Example 1: This invention discloses a real-time fire data interaction and task scheduling system that integrates UAVs and helicopters. Please refer to [link / reference]. Figure 1 It includes modules for fire detection and continuous patrol, situation model construction and visualization, rescue task allocation and execution feedback, and information communication.

[0019] The fire detection and continuous patrol module is configured to continuously collect fire-related data after receiving a fire signal using a drone performing a patrol mission. Specifically, the fire detection and continuous patrol module includes: The patrol route planning unit is configured to generate the patrol route of the drone based on the preset patrol area or the initial fire location. The fire triggering and acquisition unit is configured to monitor fire signals in real time through airborne sensors during drone patrols. When a fire is detected, a trigger command is generated to control the drone to hover or fly around it, continuously collecting fire-related data. The fire-related data includes the GPS coordinate sequence of the fire point, visible light and infrared video streams, estimated fire point area, spread speed, spread direction, fire temperature distribution data, smoke concentration data, as well as real-time meteorological data integrating wind speed, wind direction, temperature, humidity, drone position coordinates, flight trajectory, and payload status. The data preprocessing unit is configured to timestamp and spatially calibrate the collected fire-related data to form a structured data packet with spatiotemporal labels.

[0020] The situation model construction and visualization module is configured to receive fire-related data, and after spatiotemporal normalization processing, generate a dynamic attribute set of fire points, a fire environment state set, and an aircraft situation set. It also dynamically constructs and continuously updates a three-dimensional fire environment model, and visualizes the three-dimensional fire environment model to show the dynamics of fire points, the airspace environment state of the fire, and the trajectory status of UAVs. The process of constructing a three-dimensional fire scene environment model includes: Receive structured data packets, parse out the geographical coordinates of the fire point, the set of fire point boundary points, the temperature field distribution, the smoke diffusion range, meteorological data and the drone mission status, perform time synchronization and spatial registration of data from different sources and timestamps, and unify multi-source data to the same spatiotemporal reference; The Bayesian fusion or Kalman filtering method is used to fuse the spatiotemporally aligned multi-source data to generate a set of dynamic attributes of fire points, a set of environmental states of the fire scene, and a set of aircraft status. Based on the dynamic attribute set of fire points, the environmental state set of the fire scene, and the situation set of aircraft, combined with the pre-stored geographic information system data, a three-dimensional fire scene environment model is constructed. The model is continuously updated in a way that combines event triggering and periodic updates. The three-dimensional fire scene environment model integrates the unique physical attributes and dynamic evolution laws of the fire scene. The dynamic attribute set of fire points includes: unique fire point identifier, fire point center coordinates, fire point boundary point set, estimated fire point area, fire line length, spread speed, spread direction, highest fire temperature, average fire temperature, smoke concentration, hazard level, and fire point type, which includes surface fire, crown fire, and building fire. The fire scene environmental status set includes: wind speed, wind direction, ambient temperature, humidity, terrain elevation, terrain slope, vegetation type, combustible load, distance to residential areas, distance to important facilities, coordinates of water sources, and drone flight trajectory; The aircraft situation set includes: aircraft identification, aircraft type, position coordinates, flight trajectory, flight speed, flight altitude, remaining battery or fuel, payload type, remaining payload, current mission phase, and communication status; The event-triggered update method is as follows: when new fire-related data is received, the dynamic attributes of the fire point change, or the aircraft status changes, a local model update is triggered; the periodic update method is as follows: for meteorological data and aircraft position data, a global refresh is performed at preset time intervals.

[0021] The rescue mission allocation and execution feedback module is configured to receive the dynamic attribute set of the fire point and the environmental status set of the fire scene to conduct fire risk assessment, obtain the aircraft status set, the real-time status data of the currently available helicopters / drones and the assessment results to formulate a fire-fighting mission allocation plan, and distribute the fire-fighting mission allocation plan to the available helicopters and drones for dual-aircraft mission execution. The process of conducting a fire risk assessment includes: Receive the dynamic attribute set of fire points and the fire scene environment state set, and extract the dynamic attributes and load attributes of each fire point; Dynamic attributes include estimated area, spread rate, spread direction, hazard level, distance to residential areas, and distance to important facilities. The dynamic priority of each fire point is calculated according to the preset weights of each dynamic attribute. The load attributes include fire point type, fire point area, hazard level and vegetation type, and combustible load. The load priority of each fire point is calculated according to the preset weight of each load attribute. The fire risk of each fire point is assessed by weighting the dynamic priority and load priority, and a fire risk level is generated, including three levels: low, medium and high. The weight values ​​can be dynamically adjusted according to the actual fire fighting strategy. For example, when the fire point is close to the residential area, the weight of the residential area distance factor is increased. The process of developing a dual-machine coordinated firefighting task allocation plan includes: First, based on the fire risk assessment results, all fire points are arranged in descending order of fire risk level (high, medium, low), and within the same level, they are sorted in descending order of fire point area. All fire points are arranged in descending order of high risk, medium risk, and low risk according to their fire risk level. Within the same level, they are sorted by fire point area from largest to smallest. Acquire real-time status data of currently available helicopters and drones, and classify drones as reconnaissance and suppression available, and helicopters as firefighting available; Helicopters and drones are allocated according to the fire risk level, from highest to lowest: For high-risk fire points, allocate 2 nearest suppression drones and 2 nearest firefighting helicopters; if the number is insufficient, allocate all available helicopters. For medium-risk fire points, allocate one nearest reconnaissance drone and one nearest firefighting helicopter; For low-risk fire points, allocate one nearest reconnaissance drone; if no drone is available, allocate one firefighting helicopter. The dual-machine coordinated firefighting task allocation scheme also includes: scientifically selecting the type and quantity of fire extinguishing bombs according to the load priority, including water-based, dry powder, foam, and flame-retardant types of fire extinguishing bombs; Plan a straight path for each assigned drone or helicopter, make simple detours in no-fly zones, and calculate the estimated arrival time; The final output includes a dual-aircraft collaborative firefighting mission allocation scheme that includes aircraft identification, fire point identification, mission type, fire extinguishing grenade configuration, planned route and estimated arrival time. This module, in the process of formulating a dual-aircraft collaborative firefighting task allocation plan, obtains real-time status data of currently available helicopters / drones. Combined with the fire risk level of each fire point, the rule-based hierarchical matching and greedy scheduling strategy can scientifically match the complementary advantages of drones' fast reconnaissance response and helicopters' large payload capacity, so as to prioritize the handling of high-risk fire points and maximize the accuracy and success rate of firefighting operations. The rescue mission allocation and execution feedback module also acquires the dual-machine mission execution data in real time, and after spatiotemporal normalization processing, sends it to the situation model construction and visualization module. The situation model construction and visualization module is also configured to receive dual-aircraft mission execution data and acquire new fire-related data in real time. It updates the three-dimensional fire environment model in real time with the updated dynamic attribute set of fire points, fire environment status set, and aircraft situation set, and renders it in real time in the form of a three-dimensional map, dynamically displaying the changes in fire point boundaries, fire spread trend, helicopter and drone trajectory status, fire temperature distribution map, and meteorological environment layer.

[0022] The information and communication module is configured to establish a two-way low-latency data link between the UAV and the helicopter, and between the UAV and the ground control station, for transmitting fire-related data, three-dimensional fire scene environment model data, and dual-aircraft collaborative firefighting task allocation schemes.

[0023] In summary: the fire detection and continuous patrol module collects fire-related data in real time. After spatiotemporal normalization processing by the situation model construction and visualization module, a dynamic attribute set of fire points, a fire scene environment status set, and an aircraft status set are generated. A three-dimensional fire scene environment model is constructed to achieve multi-source information fusion and visualization. Based on the fire risk assessment and the status of available aircraft, a multi-objective optimization algorithm is used to calculate the mission suitability scores of UAVs (focusing on reconnaissance response) and helicopters (focusing on firefighting payload) respectively. The optimization objective is to maximize the total dynamic priority coverage and minimize the total response time, thereby generating a dual-aircraft collaborative firefighting task allocation scheme. Simultaneously, during mission execution, execution data and fire data are continuously collected, and the model is dynamically updated. This achieves a four-in-one integration of situational awareness, real-time information sharing, intelligent task allocation, and precise coordinated firefighting in joint aerial operations between drones and helicopters. It fully leverages the complementary advantages of drones' rapid reconnaissance response and helicopters' large payload capacity, enhancing the detection, response, and efficient handling capabilities of forest fires, and maximizing the accuracy and success rate of firefighting operations.

[0024] The above description is merely a preferred embodiment of the present invention; however, the scope of protection of the present invention is not limited thereto; any equivalent substitutions or modifications made by those skilled in the art within the technical scope disclosed in the present invention, based on the technical solution and its improved concept, should be covered within the scope of protection of the present invention.

Claims

1. A real-time fire data interaction and task scheduling system integrating UAVs and helicopters, characterized in that... include: The fire detection and continuous patrol module is configured to continuously collect fire-related data after receiving a fire signal using a drone performing a patrol mission. The situation model construction and visualization module is configured to receive fire-related data, and after spatiotemporal normalization processing, generate a dynamic attribute set of fire points, a fire environment state set, and an aircraft situation set. It also dynamically constructs and continuously updates a three-dimensional fire environment model, and visualizes the three-dimensional fire environment model to show the dynamics of fire points, the airspace environment state of the fire, and the trajectory status of UAVs. The rescue mission allocation and execution feedback module is configured to receive the dynamic attribute set of the fire point and the environmental status set of the fire scene to conduct fire risk assessment, obtain the aircraft situation set, the status data of the currently available helicopters / drones and the assessment results to formulate a fire-fighting mission allocation plan, and send it to the available helicopters and drones for dual-aircraft mission execution. At the same time, it acquires the dual-aircraft mission execution data in real time, and after spatiotemporal normalization processing, sends it to the situation model construction and visualization module. The situation model building and visualization module is also configured to receive dual-machine task execution data and acquire new fire-related data in real time, continuously update the three-dimensional fire environment model and visualize the changes in fire point boundaries, fire spread trends, helicopter and drone trajectory status, fire temperature distribution map and meteorological environment layer.

2. The UAV-helicopter collaborative real-time fire data interaction and task scheduling system according to claim 1, characterized in that: The fire detection and continuous patrol module includes: The patrol route planning unit is configured to generate the patrol route of the drone based on the preset patrol area or the initial fire location. The fire triggering and acquisition unit is configured to monitor fire signals in real time through airborne sensors during drone patrols. When a fire is detected, it generates a trigger command to control the drone to hover or fly around it and continuously collect fire-related data. The data preprocessing unit is configured to timestamp and spatially calibrate the collected fire-related data to form a structured data packet with spatiotemporal labels.

3. The UAV-helicopter collaborative real-time fire data interaction and task scheduling system according to claim 2, characterized in that: The process of constructing a three-dimensional fire scene environment model includes: Receive structured data packets, parse out the geographical coordinates of the fire point, the set of fire point boundary points, the temperature field distribution, the smoke diffusion range, meteorological data and the drone mission status, perform time synchronization and spatial registration of data from different sources and timestamps, and unify multi-source data to the same spatiotemporal reference; The system employs Bayesian fusion or Kalman filtering methods to fuse spatiotemporally aligned multi-source data, generating a dynamic attribute set of fire points, a fire scene environmental state set, and an aircraft situation set. Combined with pre-stored geographic information system data, a three-dimensional fire scene environment model is constructed.

4. The UAV-helicopter collaborative real-time fire data interaction and task scheduling system according to claim 3, characterized in that: The fire risk assessment process in the rescue mission allocation module includes: The system receives the set of dynamic attributes of fire points and the set of environmental states of the fire scene, extracts the dynamic attributes and load attributes of each fire point, calculates the dynamic priority of each fire point according to the preset weight of each dynamic attribute, calculates the load priority of each fire point according to the preset weight of each load attribute, performs a weighted calculation on the dynamic priority and the load priority, assesses the fire risk of each fire point, and generates a fire risk level, including high risk, medium risk and low risk.

5. The UAV-helicopter collaborative real-time fire data interaction and task scheduling system according to claim 4, characterized in that: The process of developing a dual-machine coordinated firefighting task allocation plan includes: All fire points are arranged in descending order of high risk, medium risk, and low risk according to their fire risk level. Within the same level, they are sorted by fire point area from largest to smallest. Acquire real-time status data of currently available helicopters and drones, and classify drones as reconnaissance and suppression available, and helicopters as firefighting available; Helicopters and drones are allocated according to the fire risk level, from highest to lowest.

6. The UAV-helicopter collaborative real-time fire data interaction and task scheduling system according to claim 5, characterized in that: The dual-machine coordinated firefighting task allocation scheme also includes: scientifically selecting the type and quantity of fire extinguishing bombs according to the load priority, including water-based, dry powder, foam, and flame-retardant types of fire extinguishing bombs; Plan a straight path for each assigned drone or helicopter, make simple detours in no-fly zones, and calculate the estimated arrival time; The final output includes a dual-aircraft collaborative firefighting mission allocation scheme that includes aircraft identification, fire point identification, mission type, fire extinguishing grenade configuration, planned route, and estimated arrival time.

7. The UAV-helicopter collaborative real-time fire data interaction and task scheduling system according to claim 1, characterized in that: It also includes the information communication module, configured to establish a two-way low-latency data link between the UAV and the helicopter, and between the UAV and the ground control station, for transmitting the fire-related data, the three-dimensional fire scene environment model data, and the dual-aircraft collaborative firefighting task allocation scheme.

Images