Unmanned aerial vehicle life detection and rescue system and detection and rescue method thereof

Abstract

The invention discloses an unmanned aerial vehicle life detection and rescue system and a detection and rescue method thereof, and relates to the technical field of unmanned aerial vehicles. The unmanned aerial vehicle group comprises a detection unmanned aerial vehicle and a material unmanned aerial vehicle; the detection unmanned aerial vehicle is configured to perform life signal detection on an affected area to determine a target position and transmit field data to the ground station in real time; the ground station is configured to receive the field data transmitted by the detection unmanned aerial vehicle, analyze the life signal condition of the affected area, and plan a material delivery route according to the analysis result; and the material unmanned aerial vehicle is configured to carry the materials to fly to a target position for delivery according to the planned material delivery route. The problems that when a single unmanned aerial vehicle executes multiple tasks, the load, the endurance and the detection capacity of the single unmanned aerial vehicle are limited, and due to the limitation of resource allocation, the single unmanned aerial vehicle is often difficult to ensure the detection accuracy and the timely delivery of rescue materials, so that the overall rescue efficiency is influenced are solved.

Description

Technical Field

[0001] This application relates to the technical field of unmanned aerial vehicles, and particularly to an unmanned aerial vehicle life detection and rescue system and its detection and rescue method. Background Art

[0002] In emergencies such as natural disasters like earthquakes, floods, and fires, quickly and accurately searching for and locating trapped people, as well as timely delivering rescue supplies, are the keys to rescue work. Traditional rescue methods are often limited by factors such as terrain and weather, making it difficult to efficiently complete these tasks. In recent years, the development of unmanned aerial vehicle technology has provided new solutions for disaster rescue.

[0003] However, existing unmanned aerial vehicle rescue systems adopt a single unmanned aerial vehicle operation mode, that is, a single unmanned aerial vehicle is responsible for both detecting life signals and delivering supplies. When a single unmanned aerial vehicle performs multiple tasks, its payload, endurance, and detection capabilities will be limited. And due to resource allocation limitations, a single unmanned aerial vehicle often has difficulty ensuring both the detection accuracy and the timely delivery of rescue supplies, thus affecting the overall rescue efficiency.

[0004] Therefore, how to design and implement an unmanned aerial vehicle rescue system that can operate efficiently in cooperation has become an urgent problem to be solved currently. Summary of the Invention

[0005] In the embodiments of this application, by providing an unmanned aerial vehicle life detection and rescue system, the problem that when a single unmanned aerial vehicle performs multiple tasks, its payload, endurance, and detection capabilities will be limited, and due to resource allocation limitations, a single unmanned aerial vehicle often has difficulty ensuring both the detection accuracy and the timely delivery of rescue supplies, thus affecting the overall rescue efficiency, is solved.

[0006] In a first aspect, the embodiments of this application provide an unmanned aerial vehicle life detection and rescue system, including a group of unmanned aerial vehicles and a ground station; the group of unmanned aerial vehicles includes detection unmanned aerial vehicles and supply unmanned aerial vehicles; the detection unmanned aerial vehicles are configured to detect life signals in the disaster area to determine the target location and transmit on-site data to the ground station in real time; the ground station is configured to analyze the life signal situation in the disaster area after receiving the on-site data transmitted by the detection unmanned aerial vehicles, and plan the supply delivery route according to the analysis result; the supply unmanned aerial vehicles are configured to fly to the target location with supplies for delivery according to the planned supply delivery route.

[0007] In a possible implementation, the detection UAV includes a fuselage module, a life detection module, a transmission and positioning module, and a data processing module; the fuselage module is designed as a quadrotor UAV and is equipped with an antenna to ensure stable signal transmission and reception; the life detection module includes a pyroelectric infrared sensor for human body, a pyroelectric infrared motion sensor for human body, a millimeter-wave radar, and an ultrasonic sub-module, which are used to determine whether there is a life signal in the disaster area; the transmission and positioning module includes a first optical flow sensor, a first GPS module, and an image transmission sub-module; the first GPS module is used to detect the positioning of the UAV, the first optical flow sensor is used to assist the flight control system in attitude adjustment and position holding, and the image transmission sub-module includes a first image transmission device, a first camera, a first microphone, and a first speaker, which are used to transmit on-site data to the ground station in real time; the data processing module includes a microcomputer controller, a first flight control system, and a buzzer; the microcomputer controller receives the detection data from the life detection module, activates the buzzer to work, processes and analyzes the detection data, and transmits the processed detection data to the first flight control system, and the first flight control system is used to control the flight operations of the detection UAV.

[0008] In a possible implementation, the supply UAV is designed as a fixed-wing UAV and is equipped with a second GPS module, a second flight control system, a second camera, a second image transmission device, a receiver, a second optical flow sensor, and a storage rack; the second GPS module is used to position the supply UAV, the second flight control system is used to control the flight operations of the supply UAV, the second camera and the second image transmission device are used to capture and transmit image data to the ground station, the receiver is used to receive remote control signals to ensure that the supply UAV can fly and drop supplies according to the supply delivery route, the second optical flow sensor is used to assist the flight control system in attitude adjustment and position holding, and the storage rack is used to place supplies.

[0009] In a second aspect, an embodiment of the present application provides a detection and rescue method for a UAV life detection and rescue system, including: the detection UAV detects life signals in the disaster area to determine the target position and transmits on-site data to the ground station in real time; after receiving the on-site data transmitted by the detection UAV, the ground station analyzes the life signal situation in the disaster area and plans the supply delivery route according to the analysis result; the supply UAV flies to the target position with supplies for delivery according to the planned supply delivery route; the ground station continuously monitors the flight status and task execution status of the detection UAV and the supply UAV; after the detection UAV and the supply UAV complete the tasks, they both return to the designated location according to the planned return route.

[0010] In a possible implementation, the detection UAV detects life signals in the disaster area to determine the target location, including determining the total safe flight path; the determination of the total safe flight path includes fusing the first safe flight path obtained by local path adjustment and the second safe flight path obtained by global path planning to select the optimal path as the total safe flight path.

[0011] In a possible implementation, the local path adjustment includes: using a first optical flow sensor to detect obstacles in the environment in real time and obtaining the position and radius information of the obstacles; for each potential path point of the detection UAV, calculating the distance from its current position to the center of each obstacle; performing an update step; the update step includes: if the current position of a potential path point of the detection UAV or the updated position of the potential path point is within the radius range of an obstacle, performing a path adjustment operation; the path adjustment operation is: starting from the current position of the potential path point and deflecting at the minimum angle to avoid the obstacle to obtain the updated position of the potential path point; the calculation formula for the updated position of the potential path point is: , ; where is the abscissa of the current position of the potential path point, is the ordinate of the current position of the potential path point, is the abscissa of the updated position of the potential path point, is the ordinate of the updated position of the potential path point, is the minimum deflection angle, is the radius of the obstacle, is the safety margin; using the updated position of the potential path point after the adjustment operation to continue iteratively performing the update step until all potential path points are outside the radius range of the obstacle to plan the first safe flight path that avoids obstacles.

[0012] In a possible implementation, the global path planning includes: globally optimizing the potential path points of the detection UAV on the basis of the first safe flight path; the global optimization of the potential path points of the detection UAV includes the calculation steps of the speed update formula and the calculation steps of the position update formula; the calculation steps of the speed update formula are: using the speed update formula to calculate the speed vector of each potential path point in the next iteration; the speed update formula is: ; where is the th potential path point at the th iteration, and it determines the moving direction and step size of the potential path of the detection UAV in the next iteration, is the inertia weight, is the th potential path point at the The velocity vector at the next iteration is the cognitive learning factor is the first random number between [0, 1] is the historical optimal position of the is the historical optimal position of the th potential path point at the is the social learning factor is the second random number between [0, 1] is the globally optimal position found by the potential path set in the update step; the calculation steps of the position update formula are: calculate the position of each potential path point at the next iteration using the position update formula; the position update formula is: ; where is the th potential path point at the th iteration; iteratively execute the calculation steps of the speed update formula and the calculation steps of the position update formula until the preset number of iterations is reached to obtain the second safe flight path after global optimization.

[0013] In a possible implementation, the planning steps of the material delivery route include: evaluating the quality of each potential path from the material drone to the target position according to the fitness formula, and taking the potential path with the largest fitness function value as the material delivery route; the fitness formula is: ; where is the fitness function value, and the larger the fitness function value, the better the potential path is the weight coefficient of the potential path length is the length of the potential path is the weight coefficient of the obstacle avoidance safety factor is the obstacle avoidance safety factor is the time weight coefficient is the time required to complete the task.

[0014] In a possible implementation, the calculation formula of the obstacle avoidance safety factor is: ; where is the obstacle avoidance safety factor is the number of obstacles detected by the second optical flow sensor is the distance between the material drone and the th obstacle is the th weight coefficient of the obstacle.

[0015] One or more technical solutions provided in the embodiments of the present application have at least the following technical effects: The embodiments of the present application provide an unmanned aerial vehicle (UAV) life detection and rescue system and its detection and rescue method. The detection UAV is equipped with a life detection module, which can quickly capture life signals in the disaster area, effectively improving the accuracy and efficiency of detection. At the same time, by transmitting on-site data to the ground station in real time, timely and reliable information support is provided for rescue decision-making. Based on the data of the detection UAV, the ground station plans the material delivery route. The material UAV then accurately delivers rescue materials to the target location according to the established route, ensuring that the trapped people can obtain necessary assistance in time. During the flight of the detection UAV, it can use devices such as the first optical flow sensor and the first GPS module to detect obstacles in real time and autonomously adjust the flight path, ensuring flight safety and stability. At the same time, by integrating local path adjustment and global path planning, the optimal flight path can be selected, further improving the efficiency of detection and delivery. This solves the problem that when a single UAV performs multiple tasks, its payload, endurance, and detection capabilities are all limited, and due to resource allocation limitations, it is often difficult for a single UAV to ensure both the accuracy of detection and the timely delivery of rescue materials, thus affecting the overall rescue efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments of the present application or the prior art. Obviously, the drawings in the following description are some embodiments of the present application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0017] Figure 1 It is a schematic diagram of a UAV life detection and rescue system provided in the embodiments of the present application; Figure 2 It is a flowchart of the detection and rescue method of a UAV life detection and rescue system provided in the embodiments of the present application; Figure 3 It is a schematic diagram of a UAV life detection and rescue server provided in the embodiments of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0018] The following will clearly and completely describe the technical solutions in the embodiments of the present application with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are some, but not all, of the embodiments of the present application. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present application without creative efforts fall within the scope of protection of the present application.

[0019] The following describes some of the technologies involved in the embodiments of the present application to facilitate understanding. It should be considered that they are merely exemplary. Therefore, those of ordinary skill in the art should recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of the present application. Similarly, for the sake of clarity and conciseness, some descriptions of well-known functions and structures are omitted in the following description.

[0020] The embodiments of the present application provide a drone life detection and rescue system, as Figure 1 shown, including a drone swarm and a ground station. The drone swarm includes detection drones and supply drones. The detection drones are configured to detect life signals in the disaster area to determine the target location and transmit the on-site data to the ground station in real time. The ground station is configured to analyze the life signal situation in the disaster area after receiving the on-site data transmitted by the detection drones, and plan the supply delivery route according to the analysis result. The supply drones are configured to fly to the target location with supplies for delivery according to the planned supply delivery route.

[0021] The detection drones include a body module, a life detection module, a transmission and positioning module, and a data processing module. The body module adopts a quadcopter drone design and is equipped with an antenna to ensure stable signal transmission and reception. The life detection module includes a pyroelectric infrared sensor for human body, a pyroelectric infrared motion sensor for human body, a millimeter-wave radar, and an ultrasonic sub-module, which are used to determine whether there are life signals in the disaster area. The transmission and positioning module includes a first optical flow sensor, a first GPS module, and an image transmission sub-module. The first GPS module is used for the positioning of the detection drones, the first optical flow sensor is used to assist the flight control system in attitude adjustment and position holding, and the image transmission sub-module includes a first image transmission device, a first camera, a first microphone, and a first speaker, which are used to transmit the on-site data to the ground station in real time. The data processing module includes a microcomputer controller, a first flight control system, and a buzzer. The microcomputer controller receives the detection data from the life detection module, activates the buzzer to work, processes and analyzes the detection data, and transmits the processed detection data to the first flight control system. The first flight control system is used to control the flight operations of the detection drones.

[0022] Specifically, the quadcopter drone design of the detection drone is composed of two upper and lower carbon fiber plates, four pairs of arms, and support arms. The arms and support arms are firmly connected to the lower carbon fiber plate, which also acts as a support plate. The upper carbon fiber plate is precisely fixed in place by screws on the four arms. This design not only ensures the stability and durability of the frame but also cleverly divides it into three functional areas: the top area (above the upper carbon fiber plate), the internal area (between the upper and lower carbon fiber plates), and the bottom area (extending from the lower carbon fiber plate to the support arms).

[0023] Furthermore, the detection range of the pyroelectric infrared sensor for the human body in the life detection module is 7 meters. It is installed at the connection between the arm of the detection UAV and the upper carbon fiber board and can sense the thermal signals released by the human body. The human infrared pyroelectric motion sensor also has a detection range of 7 meters and is installed at the rear end of the lower carbon fiber board, capable of detecting the thermal motion signals of the human body. The detection range of the millimeter-wave radar is 9 meters, which is fixed in the center of the lower carbon fiber board and detects the electrical signals of living beings by transmitting and receiving millimeter waves. The detection range of the ultrasonic sub-module is 450 cm, which is installed at the connection between the arm of the detection UAV and the upper carbon fiber board. As an auxiliary detection means, it improves the accuracy and reliability of life detection.

[0024] Furthermore, the microcomputer controller in the data processing module is installed in the internal area of the detection UAV, between the first camera and the first image transmission device. It is responsible for receiving the detection data from the life detection module, processing and analyzing the detection data. At the same time, it activates the buzzer according to the detection result and transmits the processed detection data to the first flight control system. The first flight control system, as the core control unit of the detection UAV, is also installed in the internal area of the detection UAV. It receives the data from the microcomputer controller, marks the geographical coordinates of the living being, i.e., the target location, according to the detection data, and displays it on the ground station map. The first flight control system in this application is the APM2.8 flight control system.

[0025] It should be noted that this application adopts a multi-processor parallel processing method to avoid overloading a single processor. Under this architecture, the detection data and the image / video data are strictly separated for processing. The image / video data is only processed through the first image transmission device to ensure smooth transmission and high-quality display of the image / video. The detection data is centrally processed by the microcomputer controller alone, and the processed detection data is transmitted to the first flight control system. This strategy effectively reduces the workload of the first flight control system and prevents the system protection phenomenon caused by excessive data processing volume.

[0026] Furthermore, the first GPS module in the transmission and positioning module selects the NEO-M8N module (a high-performance and high-sensitivity GPS module) with a positioning accuracy of no more than 2 meters. It is installed on the top of the detection UAV and fixed at the connection of the UAV arm and the upper carbon fiber board for the geographical coordinate positioning of the detection UAV to ensure the precise positioning of the detection UAV. The detection distance of the first optical flow sensor is 8 meters. It is installed at the very front of the detection UAV, and its detection end direction is the same as the camera direction to determine the spatial coordinates of the UAV and the distance from obstacles according to the optical signal. The working frequency of the first image transmission device is 5.8 GHz. It is fixed at the edge position of the lower carbon fiber board and can transmit the video and audio data collected by the camera and microphone to the ground station in real time. The first camera is fixed at the very front of the lower carbon fiber board for taking on-site images. The first microphone and the first speaker are used to assist the image transmission device to provide on-site real-time audio and video information.

[0027] The supply UAV adopts a fixed-wing UAV design and is equipped with a second GPS module, a second flight control system, a second camera, a second image transmission device, a receiver, a second optical flow sensor, and a storage rack.

[0028] The second GPS module is used for the positioning of the supply UAV. The second flight control system is used to control the flight operations of the supply UAV. The second camera and the second image transmission device are used to take and transmit image data to the ground station. The receiver is used to receive remote control signals to ensure that the supply UAV can fly and drop supplies according to the supply dropping route. The second optical flow sensor is used to assist the flight control system in attitude adjustment and position holding. The storage rack is used to place supplies.

[0029] It should be noted that in order to carry and transport rescue supplies, a storage rack is provided on the supply UAV. The storage rack has a strong structure and is easy to load and unload, and can safely place various rescue supplies such as food, medicine, rescue equipment, etc. to meet the needs of different rescue tasks.

[0030] Furthermore, the hardware of the life detection module and the transmission and positioning module of the present application can be disassembled and replaced, providing great flexibility and convenience for users.

[0031] To meet the special needs in different application scenarios, the application scenarios can be subdivided into multiple categories, such as high-temperature regions, high-altitude regions, and complex terrains. For each category, the hardware of the detection UAV can be replaced and adjusted accordingly according to the actual needs. In high-temperature regions, due to the extremely high environmental temperature, some sensors may not work properly or their performance may be limited. Therefore, it is possible to choose to use only millimeter-wave radar for detection operations. Millimeter-wave radar has the characteristics of high temperature resistance and strong penetration, and can work stably in extreme environments. In high-altitude regions, due to the thin air and low air pressure, the flight performance of the detection UAV and the working state of the sensors will be affected. At this time, all the sensors in the life detection module are required to ensure the accuracy and reliability of the detection results. At the same time, in order to extend the endurance time of the detection UAV, it is also necessary to replace the UAV propellers and adopt a propeller design more suitable for high-altitude environments to improve flight efficiency. In complex terrains such as forests and urban building clusters, due to numerous obstacles and serious signal interference, image transmission may be affected. To solve this problem, the power of the first image transmission device can be increased to improve the transmission distance and stability of the signal. In addition, in order to cope with the energy consumption problems during long-term flight and in complex environments, it is also necessary to replace the battery with a larger capacity to ensure that the detection UAV can work continuously and stably.

[0032] The embodiment of the present application provides a detection and rescue method for a UAV life detection and rescue system, as Figure 2 shown, this method includes steps S101 to S105. Among them, Figure 2 This is only an execution order shown in the embodiment of the present application, and does not represent the only execution order of a detection and rescue method for a UAV life detection and rescue system. In the case where the final result can be achieved, Figure 2 the steps shown can be executed in parallel or reversed.

[0033] S101: The detection UAV detects life signals in the disaster area to determine the target position and transmits the on-site data to the ground station in real time.

[0034] Specifically, the detection UAV is specially designed to detect life signals in the disaster area. Its primary task is to accurately locate the target position and transmit the detected on-site data to the ground station in real time. To ensure the smooth progress of this process, the detection UAV must plan and execute an efficient and safe flight path, namely the total safe flight path. The on-site data can be the images captured by the first camera, meteorological information, target position information, etc.

[0035] The detection UAV detects life signals in the disaster area to determine the target position, including determining the total safe flight path.

[0036] Determining the total safe flight path includes obtaining a first safe flight path through integrating local path adjustments and a second safe flight path through global path planning, so as to select the optimal path as the total safe flight path.

[0037] The local path adjustment includes: using a first optical flow sensor to detect obstacles in the environment in real time, and obtaining the position and radius information of the obstacles. For each potential path point of the detection UAV, calculate the distance from its current position to the center of each obstacle.

[0038] Execute the update step. The update step includes: if the current position of a certain potential path point of the detection UAV or the updated position of the potential path point is within the radius range of a certain obstacle, execute the path adjustment operation. The path adjustment operation is: starting from the current position of the potential path point and deflecting with the minimum angle to avoid the obstacle, so as to obtain the updated position of the potential path point.

[0039] The calculation formula for the updated position of the potential path point is: , . Among them, is the abscissa of the current position of the potential path point, is the ordinate of the current position of the potential path point, is the abscissa of the updated position of the potential path point, is the ordinate of the updated position of the potential path point, is the minimum deflection angle, is the radius of the obstacle, is the safety margin.

[0040] Continue to iteratively execute the update step using the updated position of the potential path point after the adjustment operation until all potential path points are outside the range, so as to plan the first safe flight path that avoids obstacles.

[0041] It should be noted that the angle between the line connecting the current position to the center of the obstacle and the tangent of the obstacle edge can be calculated, and then fine-tuned based on this angle to find a path that not only avoids the obstacle but also has the minimum deflection angle.

[0042] It should be noted that for an obstacle with an irregular shape, a minimum circular area that can completely contain the obstacle can be selected, and the radius of this area can be used as the radius of the obstacle.

[0043] Specifically, the first optical flow sensor can capture and analyze the obstacle information in the environment around the detection UAV in real time. The first optical flow sensor can not only detect the presence of obstacles, but also measure the position and radius information of the obstacles. During flight, the detection UAV divides its flight path into a series of potential path points. These potential path points represent the positions that the detection UAV may pass through during flight. For each potential path point, the first flight control system calculates the straight-line distance from its current position to the center of each detected obstacle. This step is to evaluate the relative position relationship between the potential path point and the obstacle.

[0044] The safety margin is to provide an additional safety buffer to cope with uncertain factors during flight, such as wind direction changes, flight control errors, etc. The determination of the safety margin can consider the maximum speed, acceleration, maneuverability of the UAV and the accuracy of the first flight control system. If the UAV has a high speed and maneuverability, a larger safety margin is required to cope with potential rapid changes.

[0045] The global path planning includes: globally optimizing the potential path points of the detection UAV based on the first safe flight path. The global optimization of the potential path points of the detection UAV includes the calculation steps of the speed update formula and the position update formula.

[0046] The calculation step of the speed update formula is: use the speed update formula to calculate the speed vector of each potential path point at the next iteration.

[0047] The speed update formula is: . Among them, is the speed vector of the th potential path point at the th iteration, which determines the moving direction and step size of the potential path of the detection UAV in the next iteration, is the inertia weight, is the speed vector of the th potential path point at the th iteration, is the cognitive learning factor, is the first random number between [0, 1], is the historical optimal position of the th potential path point, is the th potential path point at the th iteration, is the social learning factor, is the second random number between [0, 1], is the global optimal position found by the potential path set in the update step.

[0048] Specifically, a larger inertia weight enables the UAV to explore a wider flight space and find a better path. While a smaller makes the UAV more focused on the fine search of the current area and optimizes the local path. The cognitive learning factor is used to adjust the step size of the potential path point moving towards its historical optimal position A larger makes the potential path point more inclined to move towards the optimal path it has ever found, thus enhancing the self - awareness and learning ability of the potential path point. The randomness of helps the potential path point explore different flight directions and avoid being trapped in a local optimal path. The social learning factor is used to adjust the step size of the potential path point moving towards the global optimal position A larger makes the potential path point more inclined to move towards the position of the optimal path point in the group, thus reflecting the information sharing and cooperation among potential path points.

[0049] The calculation steps of the position update formula are as follows: Use the position update formula to calculate the position of each potential path point in the next iteration.

[0050] The position update formula is: . Where is the position of the th potential path point in the th iteration.

[0051] Iteratively execute the calculation steps of the speed update formula and the calculation steps of the position update formula until the preset number of iterations is reached to obtain the second safe flight path optimized globally.

[0052] Specifically, for the speed update formula, the inertia weight can be set to a fixed empirical value. For example, according to past experience, can be set to 0.7. The speed update formula can be simplified to: . In addition, in the preliminary experimental or simulation stage, if it is observed that the cognitive learning factor and the social learning factor have relatively stable effects on the results, they can also be set to fixed values according to experience. For example, and can both be set to 1.5. The speed update formula will be further simplified to: 。Through such simplification, the amount of calculation can be reduced to a certain extent. During the global path planning process, adopting this simplified formula can more effectively globally optimize the potential path points of the detection UAV, thereby obtaining a second safe flight path that has been globally optimized.

[0053] Furthermore, the specific way to fuse the first safe flight path obtained through local path adjustment and the second safe flight path obtained through global path planning to select the optimal path as the total safe flight path can be as follows. 1. Evaluate the safety of the two paths, including considering factors such as the density of obstacles on the path, the closest distance between the obstacles and the path, and whether the path passes through high-risk areas. The first safe flight path, being locally adjusted based on real-time obstacle detection, has high safety in avoiding immediate obstacles. The second safe flight path, on the other hand, is globally optimized and considers the safety of the path at a more macroscopic level. 2. Evaluate the efficiency of the two paths, including the length of the path, flight time, energy consumption, etc. Therefore, the two paths can be scored in terms of safety and efficiency, and the scores can be multiplied by the corresponding weights to obtain weighted scores. Compare the weighted scores of the two paths and select the path with the highest total score as the optimal path.

[0054] S102: After the ground station receives the on-site data transmitted by the detection UAV, analyze the life signal situation in the disaster area, and plan the material delivery route according to the analysis results.

[0055] S103: The material UAV flies to the target location with materials for delivery according to the planned material delivery route.

[0056] The planning steps of the material delivery route include: evaluating the pros and cons of each potential path of the material UAV to the target location according to the fitness formula, and taking the potential path with the largest fitness function value as the material delivery route.

[0057] It should be noted that before evaluating the pros and cons of each potential path of the material UAV to the target location according to the fitness formula, it also includes: generating a series of potential paths for each target location.

[0058] The fitness formula is: . Among them, is the fitness function value, and the larger the fitness function value, the better the potential path. is the weight coefficient of the potential path length. is the length of the potential path. is the weight coefficient of the obstacle avoidance safety factor. is the obstacle avoidance safety factor. is the time weight coefficient. is the time required to complete the task.

[0059] The calculation formula for the obstacle avoidance safety factor is as follows: ; where is the obstacle avoidance safety factor, is the number of obstacles detected by the second optical flow sensor, is the distance between the material drone and the th obstacle, is the th weight coefficient of the obstacle. The weight coefficient is used to adjust the influence degree of different obstacles on the obstacle avoidance safety factor.

[0060] Specifically, the determination method of the weight coefficient is as follows. Obstacles in motion (such as falling gravel, flying birds) pose a greater threat to the material drone, so a higher weight should be assigned. For dynamic obstacles, that is, obstacles in motion, the weight coefficient can be determined according to the motion speed and direction of the obstacle. If the obstacle approaches the material drone, at this time , is the motion speed of the th obstacle detected by the second optical flow sensor, is the evaluation coefficient, which is used to evaluate the danger of dynamic obstacles. If the danger of dynamic obstacles in the scene is too great, the evaluation coefficient can be appropriately increased. If the obstacle is stationary or moving away, at this time tends to 0.

[0061] Furthermore, in practical applications, for the characteristics of a specific rescue scene, if the time factor is regarded as relatively fixed and has little impact on path planning in the current material delivery task, the original fitness formula can be simplified. The specific approach is to first set the time weight coefficient to 0, so as to remove the influence of this time weight term on the fitness function. After such a simplification process, when the material drone selects the optimal material delivery route, it will no longer consider the time factor required to complete the task. Therefore, the simplified particle fitness function becomes: . Through such a simplification process, the material drone can focus more on the two key factors of path length and obstacle avoidance safety, so as to more effectively plan the material delivery route suitable for the current rescue scene.

[0062] S104: The ground station continuously monitors the flight status and task execution status of the detection drone and the material drone.

[0063] It should be noted that the monitoring of the flight state includes, but is not limited to, detecting key parameters such as the speed, altitude, heading, and flight attitude of the detection UAV and the supply UAV. The ground station also closely monitors the task execution of the detection UAV and the supply UAV. For the detection UAV, the ground station checks whether it flies along the total safe flight path, whether it successfully captures the key information of the disaster area, and transmits this information back to the ground station in real time for analysis. For the supply UAV, the ground station monitors whether it accurately delivers the supplies to the target location according to the planned supply delivery route and confirms the success or failure of the supply delivery.

[0064] S105: After the detection UAV and the supply UAV complete their tasks, they both return to the designated location according to the planned return route.

[0065] Specifically, the planning of the return route can be the same as the method for determining the total safe flight path, except that the target location is replaced with the designated location. It is also possible to directly use the first optical flow sensor or the second optical flow sensor for obstacle avoidance.

[0066] Specifically, after the return is completed, quickly unplug the battery of the UAV and cool down the motor to prevent damage or performance degradation caused by overheating of the motor. After ensuring that the UAV is in the best state, repeat the flight operation to improve the search and rescue efficiency and quality.

[0067] Furthermore, each UAV in the UAV group is equipped with a wireless communication module, and these modules adopt communication protocols with extremely strong anti-interference capabilities. These protocols ensure that the UAVs can stably transmit data in the complex disaster area environment, even when facing signal interference and transmission obstacles. This powerful communication ability enables the UAVs to share environmental data in real time, including the precise position, size, and motion state of obstacles, as well as the detailed information of the scanned area, such as whether a life signal is detected and the terrain characteristics. This information sharing provides a solid foundation for the collaborative operation of the UAV group. When a UAV discovers a new obstacle or a better path, it will share this information with other UAVs in real time. Other UAVs will refer to these shared path information and dynamically adjust their own path planning. This mechanism effectively avoids path conflicts between UAVs and realizes more efficient and collaborative operation. Taking the detection UAV discovering a suspected life sign area as an example, its position information and path adjustment information will be immediately shared with the supply UAV. The supply UAV can accordingly plan a more reasonable supply delivery route in advance, thus significantly improving the rescue efficiency. This information sharing and path coordination not only enhance the rescue speed but also ensure the accurate delivery of rescue resources.

[0068] During the collaborative operation of the UAV swarm, the present application also establishes a perfect task reallocation mechanism. When a sudden situation such as insufficient battery power or sensor failure occurs to a certain UAV, the task reallocation process will be quickly initiated. This process will comprehensively consider factors such as the current positions, task progress, and remaining battery power of each UAV, and calculate the optimal task allocation plan. Through this mechanism, it can be ensured that even in the face of sudden situations, the UAV swarm can quickly adjust the task allocation to ensure that the rescue task is not affected and continues to be carried out efficiently. This task reallocation mechanism not only improves the emergency response ability of the UAV swarm but also ensures the continuity and efficiency of the rescue task. In the complex and changeable disaster area environment, this ability is particularly important, and it can provide strong support and guarantee for the rescue operation.

[0069] The present application introduces the real-time detection function of the optical flow sensor and combines local path adjustment and global path planning to select the total safe flight path, so as to significantly improve the obstacle avoidance efficiency of the detection UAV. Compared with the traditional obstacle avoidance algorithm that only plans the path based on the static map, the solution of the present application greatly reduces the path redundancy and improves the timeliness and accuracy of obstacle avoidance. For example, in a collapsed building, the detection UAV can detect the movement trend of the wall crack through the optical flow sensor and plan a detour path in advance, so as to effectively avoid collisions. In addition, the present application also combines the data of the millimeter-wave radar and the ultrasonic sub-module to further improve the accuracy of obstacle detection. The present application can adapt to complex and changeable terrain environments, such as collapsed buildings, dense forests, etc. At the same time, the system can also make a fast and effective response to dynamic obstacles, such as moving gravel, fallen trees, etc. This stability ensures that the UAV can stably perform rescue tasks under various harsh conditions. In terms of communication and information sharing, the present application designs a lightweight communication protocol to only transmit key information, such as obstacle coordinates, vital sign positions, etc., to reduce bandwidth occupancy. In addition, a distributed decision-making mechanism is also adopted, enabling the UAV to autonomously adjust the path according to the shared information and reducing the dependence on the ground station.

[0070] Some modules in the device described in the present application can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, classes, etc. that perform specific tasks or implement specific abstract data types. The present application can also be practiced in a distributed computing environment, where tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules can be located in local and remote computer storage media including storage devices.

[0071] The devices or modules described in the above application embodiments can be specifically implemented by computer chips or entities, or by products with certain functions. For the convenience of description, when describing the above devices, they are divided into various modules according to functions and described separately. When implementing the application embodiments, the functions of each module can be implemented in the same or multiple software and / or hardware. Of course, the module for implementing a certain function can also be implemented by combining multiple sub-modules or sub-units.

[0072] The methods, devices or modules described in this application can be implemented in the form of computer-readable program codes. The controller can be implemented in any appropriate manner. For example, the controller can take the form of, for example, a microprocessor or a processor, and a computer-readable medium storing computer-readable program codes (such as software or firmware) executable by the (micro)processor, logic gates, switches, application specific integrated circuits (ASICs), programmable logic controllers, and embedded microcontrollers. Examples of controllers include, but are not limited to, the following microcontrollers: ARC 625D, Atmel AT91SAM, Microchip PIC18F26K20, and Silicone Labs C8051F320. The memory controller can also be implemented as part of the control logic of the memory. Those skilled in the art also know that in addition to implementing the controller in the form of pure computer-readable program codes, the method steps can be logically programmed to enable the controller to be implemented in the form of logic gates, switches, application specific integrated circuits, programmable logic controllers, and embedded microcontrollers to achieve the same function. Therefore, such a controller can be regarded as a hardware component, and the devices included therein for implementing various functions can also be regarded as the structures within the hardware component. Or even, the devices for implementing various functions can be regarded as both software modules for implementing the method and the structures within the hardware component.

[0073] As Figure 3 shown, the embodiment of the present application also provides a drone life detection and rescue server, including a memory 301 and a processor 302; the memory 301 is used to store computer-executable instructions; the processor 302 is used to execute the computer-executable instructions to implement the detection and rescue method of a drone life detection and rescue system described above in the embodiment of the present application.

[0074] The embodiment of the present application also provides a computer-readable storage medium, and the computer-readable storage medium stores executable instructions. When a computer executes the executable instructions, it can implement the detection and rescue method of a drone life detection and rescue system described above in the embodiment of the present application.

[0075] As can be seen from the description of the above embodiments, those skilled in the art can clearly understand that the present application can be implemented by means of software plus necessary hardware. Based on such an understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product or can also be embodied in the implementation process of data migration. This computer software product can be stored in a storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions for causing a computer device (which can be a personal computer, a mobile terminal, a server, or a network device, etc.) to execute the method described in the embodiments of the present application.

[0076] The various embodiments in this specification are described in a progressive manner. For the same or similar parts among the various embodiments, reference can be made to each other. The key point of each embodiment is to illustrate the differences from other embodiments. All or part of the present application can be used in many general or special computer system environments or configurations.

[0077] The above embodiments are only used to illustrate the technical solutions of the present application and are not intended to limit the present application. Although the present application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements for some or all of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the present application.

Claims

1. A drone life detection and rescue system, characterized in that: Includes drone swarms and ground stations; The drone swarm includes detection drones and supply drones; The detection drone is configured to detect life signals in the disaster area to determine the target location and transmit the on-site data to the ground station in real time; The ground station is configured to receive on-site data transmitted by the detection drone, analyze the life signal situation in the disaster area, and plan the route for material delivery based on the analysis results; The material delivery drone is configured to carry the materials and fly to the target location for delivery according to the planned material delivery route.

2. The drone life detection and rescue system according to claim 1, characterized in that: The detection drone includes a body module, a life detection module, a transmission and positioning module, and a data processing module; The body module adopts a quad-rotor drone design and is equipped with antennas to ensure stable signal transmission and reception; The life detection module includes a human pyroelectric infrared sensor, a human infrared pyroelectric motion sensor, a millimeter wave radar, and an ultrasonic submodule, which are used to determine whether there are life signals in the disaster area; The transmission and positioning module includes a first optical flow sensor, a first GPS module and an image transmission submodule; the first GPS module is used to detect the positioning of the UAV, the first optical flow sensor is used to assist the flight control system in attitude adjustment and position maintenance, and the image transmission submodule includes a first image transmission device, a first camera, a first microphone and a first speaker, which are used to transmit field data to the ground station in real time; The data processing module includes a microcomputer controller, a first flight control system and a buzzer; the microcomputer controller receives detection data from the life detection module, stimulates the buzzer, processes and analyzes the detection data, and transmits the processed detection data to the first flight control system, which is used to control the flight operation of the detection UAV.

3. The drone life detection and rescue system according to claim 1, characterized in that: The material drone adopts a fixed-wing drone design and is equipped with a second GPS module, a second flight control system, a second camera, a second image transmission device, a receiver, a second optical flow sensor and a storage rack; The second GPS module is used for positioning the material UAV, the second flight control system is used to control the flight operation of the material UAV, the second camera and the second image transmission device are used to shoot and transmit image data to the ground station, the receiver is used to receive remote control signals to ensure that the material UAV can fly and deliver materials according to the material delivery route, the second optical flow sensor is used to assist the flight control system in attitude adjustment and position maintenance, and the storage rack is used to place materials.

4. The detection and rescue method of the unmanned aerial vehicle life detection and rescue system according to any one of claims 1 to 3, characterized in that: include: The detection drone detects life signals in the disaster area to determine the target location and transmits the on-site data to the ground station in real time; After receiving the on-site data transmitted by the detection drone, the ground station analyzes the life signal situation in the disaster area and plans the route for material delivery based on the analysis results; The material delivery drone flies to the target location for delivery according to the planned material delivery route; The ground station continuously monitors the flight status and mission execution of the detection drone and the material drone; After completing their missions, the reconnaissance drones and material drones will return to the designated location according to the planned return route.

5. The detection and rescue method of the drone life detection and rescue system according to claim 4, characterized in that: The detection drone detects life signals in the disaster area to determine the target location, including determining the total safe flight path; The determining of the total safe flight path includes fusing a first safe flight path obtained by local path adjustment and a second safe flight path obtained by global path planning to select an optimal path as the total safe flight path.

6. The detection and rescue method of the unmanned aerial vehicle life detection and rescue system according to claim 5, characterized in that: The local path adjustment includes: Using the first optical flow sensor to detect obstacles in the environment in real time, and obtain the position and radius information of the obstacles; For each potential path point of the detection drone, calculate the distance from its current position to the center of each obstacle; Execute the update step; The update steps include: If the current position or updated position of a potential path point of the detection drone is within the radius of an obstacle, a path adjustment operation is performed; The path adjustment operation is: starting from the current position of the potential path point and deflecting at the minimum angle to avoid obstacles to obtain the updated position of the potential path point; The updated position of potential waypoints is calculated as: , ;in, is the horizontal coordinate of the current position of the potential path point, is the ordinate of the current position of the potential waypoint, is the horizontal coordinate of the updated position of the potential path point, is the ordinate of the updated position of the potential path point, is the minimum deflection angle, is the radius of the obstacle, is the safety margin; The updating step is continued to be iteratively performed using the updated positions of the potential waypoints after the adjustment operation until all potential waypoints are outside the radius of the obstacle, so as to plan a first safe flight path that avoids the obstacle.

7. The detection and rescue method of the unmanned aerial vehicle life detection and rescue system according to claim 6, characterized in that: The global path planning includes: Global optimization of potential path points of the detection UAV based on the first safe flight path; The global optimization of the potential path points of the detection UAV includes the calculation steps of the velocity update formula and the calculation steps of the position update formula; The calculation steps of the speed update formula are: use the speed update formula to calculate the speed vector of each potential path point at the next iteration; The speed update formula is: ;in, For the Potential path points in The velocity vector at the iteration, which determines the movement direction and step size of the potential path of the detection drone in the next iteration, is the inertia weight, For the Potential path points in The velocity vector at the iteration, is the cognitive learning factor, is the first random number between [0,1], For the The historical optimal position of potential path points, For the Potential path points in The position at the iteration, is the social learning factor, is the second random number between [0,1], is the global optimal position found by the potential path set in the update step; The calculation steps of the position update formula are: use the position update formula to calculate the position of each potential path point at the next iteration; The position update formula is: ;in, For the Potential path points in The position at the iteration; The calculation steps of the speed update formula and the calculation steps of the position update formula are iteratively executed until a preset number of iterations is reached to obtain a globally optimized second safe flight path.

8. The detection and rescue method of the unmanned aerial vehicle life detection and rescue system according to claim 4, characterized in that: The steps for planning the material delivery route include: The fitness formula is used to evaluate the quality of each potential path from the material drone to the target location, and the potential path with the largest fitness function value is used as the material delivery route; The fitness formula is: ;in, is the fitness function value. The larger the fitness function value, the better the potential path. is the weight coefficient of potential path length, is the length of the potential path, is the weight coefficient of obstacle avoidance safety factor, is the obstacle avoidance safety factor, is the time weight coefficient, The time required to complete the task.

9. The detection and rescue method of the unmanned aerial vehicle life detection and rescue system according to claim 8, characterized in that: The calculation formula of the obstacle avoidance safety factor is: ;in, is the obstacle avoidance safety factor, is the number of obstacles detected by the second optical flow sensor, For the material drone and The distance between obstacles, For the The weight coefficient of each obstacle.

Images