Unmanned aerial vehicle scheduling method and system for emergency rescue, terminal and storage medium

Abstract

The invention relates to an unmanned aerial vehicle scheduling method and system for emergency rescue, a terminal and a storage medium, and belongs to the technical field of emergency rescue, the unmanned aerial vehicle scheduling method comprises the following steps: sending an inspection instruction to a front-end unmanned aerial vehicle cluster, and the front-end unmanned aerial vehicle cluster performing inspection according to a preset inspection path; after the front-end unmanned aerial vehicle cluster finds the disaster site, receiving a preliminary assessment report of the disaster site sent by the front-end unmanned aerial vehicle cluster; the front-end unmanned aerial vehicle cluster generates and uploads a preliminary evaluation report after discovering a disaster site; inputting the preliminary evaluation report into a pre-constructed scoring model to obtain a score value of the preliminary evaluation report; calling a current dispatching scheme matched with the score value from a historical dispatching database; and sending a rescue instruction to the standby unmanned aerial vehicle cluster and the rescue terminal according to the current dispatch scheme. The method has the beneficial effects that the response time of the rescue unmanned aerial vehicle is shortened, so that the search and rescue efficiency is improved.

Description

Technical Field

[0001] The present application relates to the technical field of emergency rescue, and in particular to a method, system, terminal and storage medium for dispatching drones for emergency rescue. Background Art

[0002] With the continuous development of drone technology, its application in the field of emergency rescue has gradually received attention, especially in search and rescue missions under complex terrain conditions.

[0003] The current emergency rescue drone system lacks a rapid response mechanism, resulting in the inability to quickly take action at critical moments of rescue, seriously affecting the rescue efficiency and the success rate of life-saving. Summary of the Invention

[0004] In order to shorten the response time of rescue drones and thus improve search and rescue efficiency, the present application provides a method, system, terminal and storage medium for dispatching drones for emergency rescue.

[0005] In a first aspect, the present application provides a method for dispatching drones for emergency rescue, which adopts the following technical solutions: A method for dispatching a drone for emergency rescue, comprising: Send inspection instructions to the front-end drone cluster, and the front-end drone cluster conducts inspections according to the pre-set inspection path; After the front-end drone cluster finds the disaster site, receiving a preliminary assessment report of the disaster site sent by the front-end drone cluster; after the front-end drone cluster finds the disaster site, generating and uploading the preliminary assessment report; Inputting the preliminary evaluation report into a pre-built scoring model to obtain a scoring value of the preliminary evaluation report; Retrieving a current dispatch plan that matches the score value from a historical dispatch database; According to the current dispatch plan, a rescue command is sent to the standby drone cluster and the rescue terminal.

[0006] By adopting the above technical solution, the front-end drone cluster patrols along preset inspection routes, promptly discovers disaster-stricken areas, and generates preliminary assessment reports. This allows for rapid acquisition of key information in the early stages of a disaster or as soon as the disaster situation first appears, eliminating the need to wait for manual investigation or feedback from other traditional methods. This significantly shortens the time it takes to understand the disaster situation and enables subsequent rescue operations to be carried out rapidly. The preliminary assessment report is input into a scoring model to obtain a score, and the corresponding current dispatch plan is then retrieved from a historical dispatch database. This process automates and precisely allocates rescue resources, shortens drone response time, and improves search and rescue efficiency. Rescue resources (such as standby drone clusters and rescue terminals) are rationally deployed based on the actual severity and urgency of the disaster site, achieving precise mobilization and rapid response. This eliminates resource waste in less severely affected areas and ensures sufficient resource investment in severely affected areas that urgently need a large number of rescue forces. This achieves scientific allocation of limited resources and improves resource utilization efficiency within the entire rescue system.

[0007] Optionally, the scoring model construction method includes: The area of the disaster-affected region, the rate of building damage, and the number of casualties were selected as scoring features; According to the scoring features, a scoring model is constructed. The scoring model is ; where y is the score value, is the intercept, is the coefficient of the scoring feature, is the area of the disaster-affected area, is the building damage rate, The number of casualties, is the error term; Collecting historical scoring values and related data of the scoring features; Dividing the historical scoring values and the associated data of the scoring features into a training set and a test set; Inputting the training set into the initially constructed scoring model to obtain the coefficients of the scoring features and the intercept and error term of the scoring model; The test set is input into the trained scoring model to adjust the coefficients of the scoring features and the intercept and error term of the scoring model.

[0008] Optionally, the scheduling method further includes: During the flight of the standby UAV toward the disaster site, obtaining the altitude change rate, horizontal resistance, horizontal force, and vertical force of the standby UAV; Inputting the mass, weight, altitude change rate, and vertical force of the standby UAV into a pre-built vertical speed regulation model to obtain a first vertical adjustment amount of the vertical engine speed; Obtaining a first vertical rotation speed according to the current rotation speed and the first vertical adjustment amount; Inputting the mass, current horizontal acceleration, horizontal resistance, and horizontal force of the standby UAV into a pre-built horizontal speed regulation model to obtain a first horizontal adjustment amount of the horizontal engine speed; A first horizontal rotation speed is obtained according to the current rotation speed and the first horizontal adjustment amount.

[0009] By adopting the above technical solution, the flight altitude and direction can be dynamically adjusted to avoid collision with dangerous areas. At the same time, according to the feedback of the altitude change rate, the engine speed can be intelligently adjusted to maintain stable lift output, ensuring that the UAV can maintain a stable flight posture in strong wind environments; it can effectively improve the search coverage and survival rate of UAVs in complex terrain areas such as mountains, forests, and canyons, and reduce the probability of mission failure due to misjudgment risks.

[0010] Optionally, the vertical speed regulation model is ;in, is the first vertical adjustment amount, m is the mass of the standby UAV, is the altitude change rate, G is the weight of the standby UAV, is the vertical force, is the lift coefficient; The horizontal speed regulation model is ;in, is the first level adjustment, Current horizontal acceleration, D is the horizontal resistance, is the horizontal force, is the thrust coefficient.

[0011] Optionally, the scheduling method further includes: When the standby drone is flying, obtaining environmental information around the standby drone; Determine, based on the environmental information, whether there is an obstacle ahead of the standby UAV; If so, further determine the type of the obstacle; According to the type of the obstacle, select a corresponding adjustment coefficient; Obtaining a second vertical adjustment amount according to the adjustment coefficient, the vertical force, and the lift coefficient; Obtaining a second vertical rotation speed according to the current rotation speed of the standby drone and the second vertical adjustment amount; Obtaining a second horizontal adjustment amount according to the adjustment coefficient, the horizontal force, and the thrust coefficient; A second horizontal rotation speed is obtained according to the current rotation speed of the standby drone and the second horizontal adjustment amount.

[0012] By adopting the above technical solution, the standby drone can obtain environmental information around it, knowing in advance whether there are obstacles ahead of it, thereby greatly reducing the risk of collision. Further, the obstacle type can be determined, allowing the drone to adopt differentiated response strategies for obstacles with different characteristics. For example, for solid obstacles (such as buildings and large rocks), which pose a greater obstruction and potential damage to the drone's flight, the drone can adjust its vertical and horizontal rotation speeds more quickly and significantly to effectively avoid collisions. For soft obstacles (such as branches and small floating objects), the corresponding adjustment coefficient will be smaller, and the drone will make relatively gentle adjustments, avoiding obstacles while maintaining a relatively stable flight attitude and avoiding other risks caused by excessive maneuvering. Overall, this significantly improves flight safety in complex environments, ensuring that the standby drone can successfully perform its mission without being damaged by accidental collisions.

[0013] Optionally, after determining that there is an obstacle ahead of the standby UAV, the method further includes: Determine whether there are multiple obstacles and whether they are continuous; If not, further determine the type of obstacle; If so, a new path is generated based on the current position of the standby drone, the target position, and the position of the obstacle; Obtaining the height difference, distance, and direction deviation between the current position of the standby drone and the first path point of the new path; Inputting the height difference and distance into a pre-built vertical steering speed control model to obtain a vertical steering adjustment amount; Obtaining vertical steering speed control according to the current rotation speed and the vertical steering adjustment amount; Inputting the directional deviation into a pre-built horizontal steering speed regulation model to obtain a horizontal steering adjustment amount; The horizontal steering speed regulation is obtained according to the current rotation speed and the horizontal steering adjustment amount.

[0014] By adopting the above technical solution, when the obstacles are discontinuous, the standby drone can return to the established path after avoiding the obstacles; however, when the obstacles are continuous, it means that the standby drone will not return to the established path in a short time, so a new path needs to be generated so that it can fly on the new path.

[0015] Optionally, the vertical steering speed control model is ;in, is the vertical steering adjustment, is the path vertical adjustment coefficient, d is the distance between the current position of the standby UAV and the first path point of the new path, and h is the height difference; The horizontal steering speed regulation model is: ;in, is the horizontal steering adjustment, is the path level adjustment coefficient, is the direction deviation, is the maximum allowable steering angle.

[0016] Secondly, this application provides a drone dispatching system for emergency rescue, which adopts the following technical solutions: A drone dispatching system for emergency rescue, comprising: An instruction sending module is used to send inspection instructions to the front-end drone cluster, and the front-end drone cluster conducts inspections according to a pre-set inspection path; An information receiving module is configured to receive a preliminary assessment report of the disaster site sent by the front-end drone cluster after the front-end drone cluster finds the disaster site; after the front-end drone cluster finds the disaster site, generate and upload the preliminary assessment report; A model scoring module inputs the preliminary evaluation report into a pre-built scoring model to obtain a scoring value of the preliminary evaluation report; A dispatch plan retrieval module is used to retrieve a current dispatch plan that matches the score value from a historical dispatch database; The instruction sending module is used to send rescue instructions to the standby drone cluster and rescue terminal according to the current dispatch plan.

[0017] By adopting the above technical solution, the front-end drone cluster patrols along preset inspection routes, promptly discovers disaster-stricken areas, and generates preliminary assessment reports. This allows for rapid acquisition of key information in the early stages of a disaster or as soon as the disaster situation first appears, eliminating the need to wait for manual investigation or feedback from other traditional methods. This significantly shortens the time it takes to understand the disaster situation and enables subsequent rescue operations to be carried out rapidly. The preliminary assessment report is input into a scoring model to obtain a score, and the corresponding current dispatch plan is then retrieved from a historical dispatch database. This process automates and precisely allocates rescue resources, shortens drone response time, and improves search and rescue efficiency. Rescue resources (such as standby drone clusters and rescue terminals) are rationally deployed based on the actual severity and urgency of the disaster site, achieving precise mobilization and rapid response. This eliminates resource waste in less severely affected areas and ensures sufficient resource investment in severely affected areas that urgently need a large number of rescue forces. This achieves scientific allocation of limited resources and improves resource utilization efficiency within the entire rescue system.

[0018] In a third aspect, the present application provides a terminal that adopts the following technical solution: A terminal, comprising: a memory storing a dispatching program for a drone used for emergency rescue; The processor is used to execute the program stored in the memory to implement the steps of the above-mentioned emergency rescue drone dispatching method.

[0019] In a fourth aspect, the present application provides a computer-readable storage medium, which adopts the following technical solution: A computer-readable storage medium stores a computer program that can be loaded by a processor and execute the above-mentioned emergency rescue drone dispatching method.

[0020] In summary, this application has at least the following beneficial effects: 1. Inputting the preliminary assessment report into the scoring model to obtain a score, then retrieving the current dispatch plan that matches the score from the historical dispatch database. Based on the current dispatch plan, rescue instructions are sent to the standby drone cluster and rescue terminals. The goal is to quickly grasp key information at the beginning of a disaster or when the disaster situation first appears, without waiting for manual investigation or other traditional feedback methods. This greatly shortens the time to understand the disaster situation and enables subsequent rescue operations to be carried out quickly. Inputting the preliminary assessment report into the scoring model to obtain a score, and then retrieving the current dispatch plan that matches it from the historical dispatch database, this process realizes the automation and precision of rescue resource allocation, shortens drone response time, and improves search and rescue efficiency. Rescue resources (such as the standby drone cluster and rescue terminals) are rationally allocated according to the actual disaster severity and urgency of the disaster site, achieving precise mobilization and rapid response. This avoids wasting resources in less affected areas and ensures sufficient resources for severely affected areas that urgently need a large number of rescue forces. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Figure 1 This is the structural diagram of the emergency rescue drone architecture of this application; Figure 2 It is a flowchart of an embodiment of the method of the present application; Figure 3 This is a flowchart of the flight speed control of the standby UAV in this application; Figure 4 This is a flowchart of the obstacle avoidance process of the standby drone in this application; Figure 5 It is a flowchart of the steps that can be executed after S320; Figure 6 It is a structural block diagram of an embodiment of the system of the present application.

[0022] Explanation of the accompanying reference numerals: 100, front-end drone cluster; 200, rescue terminal; 300, standby drone cluster; 400, rescue platform; 401, command sending module; 402, information receiving module; 403, model scoring module; 404, dispatch plan retrieval module. DETAILED DESCRIPTION

[0023] To make the purpose, technical solutions and advantages of the embodiments of the present application clearer, the following will be combined with the appended drawings of the embodiments of the present invention. Figure 1 -Attached Figure 6 The technical solutions in the embodiments of the present invention are clearly and completely described. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of them. All other embodiments derived by persons of ordinary skill in the art based on the embodiments of the present invention without inventive effort are within the scope of protection of the present invention.

[0024] This application provides an emergency rescue drone architecture, referring to Figure 1 The drone architecture may include a front-end drone cluster 100, a rescue terminal 200, a standby drone cluster 300, and a rescue platform 400. The drone dispatch system is integrated into the rescue platform 400. The front-end drone cluster 100 inspects a certain area along a set inspection route based on inspection instructions sent by the rescue platform 400. If a disaster site is discovered during the inspection, it automatically enters an alert state, uses GPS positioning technology and image recognition algorithms to determine the coordinates of the disaster site and collect image information of the disaster site. The image recognition algorithm processes the image to determine the affected area, type of disaster, building damage rate, and number of casualties. The coordinates of the disaster site, image information of the disaster site, affected area, type of disaster, building damage rate, and number of casualties are then correlated to generate a preliminary assessment report, which is uploaded to the rescue platform 400. The rescue platform 400 processes the preliminary assessment report and synchronously sends rescue instructions to the standby drone cluster 300 and the rescue terminal 200 via mobile base stations and satellite communications. The rescue terminal 200 is a personal terminal for rescue personnel, such as a laptop, smartphone, or smart wearable device.

[0025] The drones in both the front-end drone cluster 100 and the standby drone cluster 300 are constructed with carbon fiber composite frames, offering both high strength and low weight. The maximum takeoff weight of the entire drone is under 3kg, making it easy for a single soldier to carry. The drones feature quadcopters with a maximum wingspan of 0.8m and a folded dimensions of just 0.4m x 0.4m x 0.2m, making them easy to carry and conceal. Equipped with a high-efficiency brushless motor and lithium battery pack, the drones have a flight time of up to 45 minutes when fully loaded and a maximum horizontal speed of 25km / h. A built-in obstacle avoidance system combining lidar and vision sensors can identify obstacles ahead and automatically adjust course within a distance of 5 meters to ensure flight safety. Equipped with a two-way wireless communication module, they maintain real-time voice and data communication with the rescue platform 400 within a range of 10km, supporting high-definition video streaming and remote control commands.

[0026] The first embodiment of the present application discloses a method for dispatching a drone for emergency rescue. Figure 2 As an implementation of the drone scheduling method, the drone scheduling method may include S110-S150: S110, sending an inspection instruction to the front-end drone cluster, and the front-end drone cluster performs inspection according to a pre-set inspection path; S120, after the front-end UAV cluster discovers the disaster site, receiving a preliminary assessment report of the disaster site sent by the front-end UAV cluster; S130, inputting the preliminary evaluation report into a pre-built scoring model to obtain a scoring value of the preliminary evaluation report; S140, retrieving a current dispatch plan that matches the score value from a historical dispatch database; S150: Send rescue instructions to the standby drone cluster and rescue terminal according to the current dispatch plan.

[0027] Specifically, the rescue platform will regularly send inspection instructions to the front-end drone cluster, which will then conduct inspections according to the set inspection path. If, during the inspection process, the front-end drone cluster discovers a disaster site, it will collect and process images of the disaster site, generating a preliminary assessment report based on the disaster site and the images of the disaster site. The front-end drone cluster will then upload the preliminary assessment report to the rescue platform, which will then input the preliminary assessment report into the scoring model to obtain a score for the preliminary assessment report. The rescue platform will then retrieve the current dispatch plan that matches the score from the historical dispatch database, and based on the current dispatch plan, send rescue instructions to the standby drone cluster and rescue terminal. The dispatch plan includes the number of standby drones participating in the rescue, the type and quantity of supplies required, and the number of rescue personnel. The score is then associated with the dispatch plan based on matching rules.

[0028] Furthermore, when constructing a scoring model, you can first select scoring features. For example, the scoring features selected in this application are the area of the disaster-stricken area, the building damage rate, and the number of casualties. Then, based on the scoring features, you can construct a scoring model. The scoring model is ; where y is the score value, is the intercept, is the coefficient of the scoring feature, is the area of the disaster-affected area, is the building damage rate, The number of casualties, is the error term. After the preliminary scoring model is constructed, the historical scoring values and the associated scoring features are statistically analyzed. These statistical data are then divided into a training set and a test set. The training set is input into the scoring model to obtain the coefficients of the scoring features, the intercept of the scoring model, and the error term. The test set is then input into the trained scoring model to further adjust the coefficients of the scoring features, the intercept of the scoring model, and the error term. The scoring model after testing is the final scoring model.

[0029] For example, the matching rule may be: if the score value is within a preset score value range, and the disaster type is flood, and the area of the disaster area is smaller than the preset value, then the dispatch plan may be to dispatch a small water standby drone cluster for preliminary investigation, and so on.

[0030] The matching rules can also be: for example, (score value ≥ 30 && score value < 60) && (disaster type == "earthquake") && (affected area area > 1000 square meters) && (number of casualties > 100 people). The dispatch plan can then be to dispatch medium-sized multi-functional drones, including a reconnaissance standby drone cluster and a rescue material delivery standby drone cluster, etc.

[0031] Reference Figure 3 In order to further improve the search and rescue efficiency in complex terrain, the flight trajectory and adaptive speed control mechanism of the UAV are optimized to ensure that good navigation performance can be maintained in rugged environments; the scheduling method may also include S210-S250: S210, while the standby UAV is flying toward the disaster site, obtaining the altitude change rate, horizontal resistance in the horizontal direction, horizontal force, and vertical force of the standby UAV; S220, inputting the mass, weight, altitude change rate, and vertical force of the standby UAV into a pre-built vertical speed control model to obtain a first vertical adjustment amount of the vertical engine speed; S230, obtaining a first vertical rotation speed according to the current rotation speed and the first vertical adjustment amount; S240, inputting the mass, current horizontal acceleration, horizontal resistance, and horizontal force of the standby UAV into a pre-built horizontal speed regulation model to obtain a first horizontal adjustment amount of the horizontal engine speed; S250: Obtain a first horizontal rotation speed according to the current rotation speed and the first horizontal adjustment amount.

[0032] Specifically, the altitude change rate of the drone can be measured with the help of a barometer. The horizontal force can be obtained based on the airspeed sensor and the body attitude data; the airspeed sensor is used to measure the speed of the drone relative to the surrounding air; combined with the drone's body attitude information (such as pitch angle, roll angle and heading angle, provided by the inertial measurement unit IMU), the effective velocity component of the drone in the horizontal direction can be determined. Then, according to aerodynamic theory, the air resistance encountered by the drone during flight is mainly related to the air density ( ),airspeed( ), the reference area of the drone (S, such as the equivalent area of the wing or fuselage), and the drag coefficient ( ). The resistance formula is With the known geometry and flight conditions of the drone, basic air resistance (horizontal force) can be estimated.

[0033] Horizontal drag (additional drag) can be obtained from the data of wind direction and speed sensor. Wind direction and speed sensor measures the speed and direction of external wind. When the wind direction is not parallel to the flight direction of the drone, additional horizontal drag will be generated. Through vector decomposition, the wind speed is decomposed into components parallel to the flight direction of the drone and perpendicular to the flight direction. The headwind component will increase the horizontal drag of the drone, while the tailwind component will reduce the drag. For example, if the wind speed is , the angle between wind direction and the flight direction of the UAV is , then, the additional horizontal resistance calculate.

[0034] Vertical force can be measured using a barometer. In the vertical direction, when the drone is in stable flight, lift equals weight. Lift is primarily related to air density, the vertical component of airspeed, wing or rotor area, and the lift coefficient. By measuring changes in atmospheric pressure and combining them with other flight parameters, information about vertical force (lift) can be indirectly derived. For example, during a drone's accelerated ascent or descent, the changes in air pressure measured by the barometer can reflect changes in vertical velocity, which can then be calculated using aerodynamic formulas.

[0035] The horizontal acceleration of a drone can be obtained through the accelerometer on it. When the drone accelerates in the horizontal direction, the mass block in the accelerometer will be displaced due to the inertial force. By detecting this displacement and undergoing a series of signal processing and conversion, the value of the horizontal acceleration is obtained.

[0036] The vertical speed regulation model is ;in, is the first vertical adjustment amount, m is the mass of the standby UAV, is the altitude change rate, G is the weight of the standby UAV, is the vertical force, is the lift coefficient; the first vertical rotation speed is the sum of the first vertical adjustment amount and the current rotation speed.

[0037] The horizontal speed regulation model is ;in, is the first level adjustment, Current horizontal acceleration, D is the horizontal resistance, is the horizontal force, The first level speed is the sum of the first level adjustment amount and the current speed.

[0038] Reference Figure 4 Furthermore, the scheduling method may further include S310-S380: S310, when the standby UAV is flying, obtaining environmental information around the standby UAV; S320, judging whether there is an obstacle ahead of the standby UAV based on the environmental information; S330, if yes, further determine the type of obstacle; S340, selecting a corresponding adjustment coefficient according to the type of obstacle; S350, obtaining a second vertical adjustment amount according to the adjustment coefficient, the vertical force, and the lift coefficient; S360, obtaining a second vertical rotation speed according to the current rotation speed of the standby UAV and the second vertical adjustment amount; S370, obtaining a second horizontal adjustment amount according to the adjustment coefficient, the horizontal force, and the thrust coefficient; S380: Obtain a second horizontal rotation speed according to the current rotation speed of the standby UAV and the second horizontal adjustment amount.

[0039] Specifically, the laser radar can be used to obtain the environmental information around the drone, thereby determining whether there are obstacles in front of the drone and judging the type of obstacles. Among them, the obstacle types are divided into solid obstacles and soft obstacles. The adjustment coefficient of solid obstacles can be set as , the adjustment coefficient for soft obstacles is For solid obstacles, the second vertical adjustment , the second vertical speed = n + the second vertical adjustment amount, n is the current speed; the second horizontal adjustment amount , the second horizontal speed = n + the second horizontal adjustment amount. For soft obstacles, the second vertical adjustment amount , the second level adjustment amount .

[0040] Reference Figure 5 , further, after determining that there is an obstacle in front of the standby UAV, S321-S328 can be executed: S321, determining whether there are multiple obstacles and whether they are continuous; S322, if not, further determine the obstacle type; S323, if yes, then generate a new path based on the current position of the standby UAV, the target position, and the position of the obstacle; S324, obtaining the height difference, distance, and direction deviation between the current position of the standby UAV and the first path point of the new path; S325, inputting the height difference and the distance into a pre-built vertical steering speed control model to obtain a vertical steering adjustment amount; S326, obtaining a vertical steering speed adjustment according to the current rotation speed and the vertical steering adjustment amount; S327, inputting the direction deviation into a pre-built horizontal steering speed control model to obtain a horizontal steering adjustment amount; S328, obtaining horizontal steering speed control according to the current rotation speed and the horizontal steering adjustment amount.

[0041] Specifically, the vertical steering speed control model is: ;in, is the vertical steering adjustment, is the path vertical adjustment coefficient, d is the distance between the current position of the standby UAV and the first path point of the new path, and h is the height difference.

[0042] The horizontal steering speed control model is ;in, is the horizontal steering adjustment, is the path level adjustment coefficient, is the direction deviation, is the maximum allowable steering angle.

[0043] The vertical steering speed is the sum of the current speed and the vertical steering adjustment amount, and the horizontal steering speed is the sum of the current speed and the horizontal steering adjustment amount.

[0044] A new path can be generated by using a rapidly expanding random tree (RRT) algorithm, starting from the drone's initial position and constructing a tree by randomly sampling in the state space (including position, velocity, attitude, etc.). Each time a new point is sampled, the tree finds the node closest to that point and attempts to extend a branch from this closest node toward the new sampled point. The extension of this branch needs to consider the drone's kinematic constraints, such as maximum speed and minimum turning radius. During the extension process, the branch is checked for collisions with obstacles. If not, the new node is added to the tree. When the new node reaches the target position or is close enough to the target position, it is reached along the tree path from the initial position, resulting in a feasible path.

[0045] It should be noted that the speed control method of the standby UAV during flight is applicable to the speed control of the front-end UAV during flight.

[0046] The implementation principle of this embodiment is: Send inspection instructions to the front-end drone cluster. After the front-end drone cluster finds the disaster site, upload the preliminary assessment report of the disaster site. After receiving the preliminary assessment report, input the preliminary assessment report into the scoring model to obtain the score value of the preliminary assessment report. According to the score value, retrieve the corresponding current dispatch plan from the historical dispatch database, and send rescue instructions to the standby drone cluster and rescue terminal according to the current dispatch plan.

[0047] Based on the above method embodiment, the second embodiment of the present application discloses a drone dispatching system for emergency rescue. Figure 6 , the scheduling system may include: The command sending module 401 is used to send inspection instructions to the front-end drone cluster 100, and the front-end drone cluster 100 conducts inspections according to a pre-set inspection path; The information receiving module 402 is used to receive the preliminary assessment report of the disaster site sent by the front-end drone cluster 100; after the front-end drone cluster 100 finds the disaster site during the inspection process, it generates and uploads the preliminary assessment report; The model scoring module 403 inputs the preliminary evaluation report into a pre-built scoring model to obtain a scoring value of the preliminary evaluation report; The dispatch plan retrieval module 404 is used to retrieve the current dispatch plan that matches the score value from the historical dispatch database; The instruction sending module 401 is used to send rescue instructions to the standby drone cluster 300 and the rescue terminal 200 according to the current dispatch plan.

[0048] The modules of the emergency rescue drone dispatching system correspond one-to-one to the emergency rescue drone dispatching method, and no further details will be given here.

[0049] The third embodiment of the present application provides a terminal. As an implementation of the terminal, the terminal may include: a memory and a processor; wherein, The memory is used to store the above-mentioned emergency rescue drone dispatching program; The processor is used to execute the program stored in the memory to implement the steps of the above-mentioned emergency rescue drone dispatching method.

[0050] The memory may be communicatively connected to the processor via a communication bus, and the communication bus may be an address bus, a data bus, a control bus, or the like.

[0051] In addition, the memory may include a random access memory (RAM) and may also include a non-volatile memory (NVM), such as at least one disk storage.

[0052] The processor can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc.

[0053] The fourth embodiment of the present application provides a computer-readable storage medium storing a computer program that can be loaded by a processor and execute the above-mentioned emergency rescue drone dispatching method.

[0054] Computer-readable storage media can be any available medium that can be accessed by a computer, or a data storage device such as a server or data center that includes one or more available media. Available media can include magnetic media (e.g., floppy disks, hard disks, magnetic tapes), optical media (e.g., DVDs), or semiconductor media (e.g., solid-state drives).

[0055] The above are all preferred embodiments of the present application and are not intended to limit the scope of protection of the present application. Unless otherwise specified, any feature disclosed in this specification (including the abstract and drawings) may be replaced by other equivalent or similar features. In other words, unless otherwise specified, each feature is merely an example of a series of equivalent or similar features.

Claims

1. A method for dispatching drones for emergency rescue, characterized in that: include: Send inspection instructions to the front-end drone cluster, and the front-end drone cluster conducts inspections according to the pre-set inspection path; After the front-end drone cluster finds the disaster site, receiving a preliminary assessment report of the disaster site sent by the front-end drone cluster; after the front-end drone cluster finds the disaster site, generating and uploading the preliminary assessment report; Inputting the preliminary evaluation report into a pre-built scoring model to obtain a scoring value of the preliminary evaluation report; Retrieving a current dispatch plan that matches the score value from a historical dispatch database; According to the current dispatch plan, a rescue command is sent to the standby drone cluster and the rescue terminal.

2. The method for dispatching a drone for emergency rescue according to claim 1, characterized in that: The method for constructing the scoring model includes: The area of the disaster-affected region, the rate of building damage, and the number of casualties were selected as scoring features; According to the scoring features, a scoring model is constructed. The scoring model is ; where y is the score value, is the intercept, is the coefficient of the scoring feature, is the area of the disaster-affected area, is the building damage rate, The number of casualties, is the error term; Collecting historical scoring values and related data of the scoring features; Dividing the historical scoring values and the associated data of the scoring features into a training set and a test set; Inputting the training set into the initially constructed scoring model to obtain the coefficients of the scoring features and the intercept and error term of the scoring model; The test set is input into the trained scoring model to adjust the coefficients of the scoring features and the intercept and error term of the scoring model.

3. The method for dispatching a drone for emergency rescue according to claim 1, characterized in that: The scheduling method further includes: During the flight of the standby UAV toward the disaster site, obtaining the altitude change rate, horizontal resistance, horizontal force, and vertical force of the standby UAV; Inputting the mass, weight, altitude change rate, and vertical force of the standby UAV into a pre-built vertical speed regulation model to obtain a first vertical adjustment amount of the vertical engine speed; Obtaining a first vertical rotation speed according to the current rotation speed and the first vertical adjustment amount; Inputting the mass, current horizontal acceleration, horizontal resistance, and horizontal force of the standby UAV into a pre-built horizontal speed regulation model to obtain a first horizontal adjustment amount of the horizontal engine speed; A first horizontal rotation speed is obtained according to the current rotation speed and the first horizontal adjustment amount.

4. The method for dispatching a drone for emergency rescue according to claim 3, characterized in that: The vertical speed regulation model is: ;in, is the first vertical adjustment amount, m is the mass of the standby UAV, is the altitude change rate, G is the weight of the standby UAV, is the vertical force, is the lift coefficient; The horizontal speed regulation model is ;in, is the first level adjustment, Current horizontal acceleration, D is the horizontal resistance, is the horizontal force, is the thrust coefficient.

5. The method for dispatching a drone for emergency rescue according to claim 4, characterized in that: The scheduling method further includes: When the standby drone is flying, obtaining environmental information around the standby drone; Determine, based on the environmental information, whether there is an obstacle ahead of the standby UAV; If so, further determine the type of the obstacle; According to the type of the obstacle, select a corresponding adjustment coefficient; Obtaining a second vertical adjustment amount according to the adjustment coefficient, the vertical force, and the lift coefficient; Obtaining a second vertical rotation speed according to the current rotation speed of the standby drone and the second vertical adjustment amount; Obtaining a second horizontal adjustment amount according to the adjustment coefficient, the horizontal force, and the thrust coefficient; A second horizontal rotation speed is obtained according to the current rotation speed of the standby drone and the second horizontal adjustment amount.

6. The method for dispatching a drone for emergency rescue according to claim 5, characterized in that: After determining that there is an obstacle in front of the standby UAV, the method includes: Determine whether there are multiple obstacles and whether they are continuous; If not, further determine the type of obstacle; If so, a new path is generated based on the current position of the standby drone, the target position, and the position of the obstacle; Obtaining the height difference, distance, and direction deviation between the current position of the standby drone and the first path point of the new path; Inputting the height difference and distance into a pre-built vertical steering speed control model to obtain a vertical steering adjustment amount; Obtaining vertical steering speed control according to the current rotation speed and the vertical steering adjustment amount; Inputting the directional deviation into a pre-built horizontal steering speed regulation model to obtain a horizontal steering adjustment amount; The horizontal steering speed regulation is obtained according to the current rotation speed and the horizontal steering adjustment amount.

7. The method for dispatching a drone for emergency rescue according to claim 6, characterized in that: The vertical steering speed regulation model is: ;in, is the vertical steering adjustment, is the path vertical adjustment coefficient, d is the distance between the current position of the standby UAV and the first path point of the new path, and h is the height difference; The horizontal steering speed regulation model is: ;in, is the horizontal steering adjustment, is the path level adjustment coefficient, is the direction deviation, is the maximum allowable steering angle.

8. An emergency rescue drone dispatching system, characterized in that: include: An instruction sending module (401) is used to send an inspection instruction to the front-end drone cluster (100), and the front-end drone cluster (100) inspects according to a pre-set inspection path; An information receiving module (402) is configured to receive a preliminary assessment report of the disaster site sent by the front-end drone cluster (100) after the front-end drone cluster (100) discovers the disaster site; after the front-end drone cluster (100) discovers the disaster site, generate and upload the preliminary assessment report; A model scoring module (403) inputs the preliminary evaluation report into a pre-built scoring model to obtain a scoring value of the preliminary evaluation report; A dispatch plan retrieval module (404) is used to retrieve a current dispatch plan that matches the score value from a historical dispatch database; The instruction sending module (401) is used to send a rescue instruction to the standby drone cluster (300) and the rescue terminal (200) according to the current dispatch plan.

9. A terminal, characterized in that: include: a memory storing a dispatching program for a drone used for emergency rescue; A processor is used to execute the program stored in the memory to implement the steps of the emergency rescue drone dispatching method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that A computer program is stored which can be loaded by a processor and execute the method for dispatching a drone for emergency rescue as claimed in any one of claims 1 to 7.

Images