Medical low-altitude service intelligent management and control method

Abstract

The application belongs to the technical field of space-air communication, and particularly relates to an intelligent management and control method for medical area low-altitude service, which comprises the following steps: S1, obtaining refined medical area low-altitude obstacle distribution through medical area terrain deduction; S2, constructing a medical area distribution scene graph through collaborative weighting and dynamic iterative optimization of multi-source data; S3, completing four-dimensional data linkage collection of flight state, environmental interference, material state and constraint data, and generating a dynamic perception data set; S4, constructing a city medical area whole-process scene adaptive unmanned aerial vehicle closed-loop control model through fusion of deep feature extraction, scene quantitative grading, flight parameter adaptive regulation and multi-machine collaborative scheduling mechanism; and S5, designing a closed-loop calibration collaborative control function module to perform flight parameter deviation identification and material transfer state linkage matching. The application aims to improve the problems of insufficient medical area low-altitude service scene adaptability and imperfect management and control system, and promote the upgrading of the intelligent hospital service system.

Description

Technical Field

[0001] This invention belongs to the field of aerospace communication technology, specifically relating to an intelligent management and control method for low-altitude medical services. Background Technology

[0002] Compared to traditional delivery methods, drones can effectively avoid physical limitations such as ground congestion and building obstructions, enabling point-to-point direct delivery between hospital buildings and functional departments, as well as cross-regional direct transfers between hospitals. However, urban hospital areas are characterized by high building density, high population density, and limited airspace. During flight, drones need to cope with complex scenarios such as urban airflow interference, dynamic obstacles in high-traffic areas, and hospital building obstructions in real time. Traditional general-purpose drone flight control algorithms are difficult to adapt to the accuracy, safety, and timeliness requirements of medical scenarios. Therefore, developing dedicated flight control technology for low-altitude medical services in smart hospitals is a core breakthrough for the application of drone technology in the medical field and an inevitable trend to promote the deep integration of the low-altitude economy and smart healthcare.

[0003] Currently, the dedicated technologies for low-altitude medical services in smart hospitals have the following limitations: First, insufficient scenario adaptability. Existing algorithms are mostly designed based on open airspace and do not fully consider the dynamic scene characteristics of complex building layouts and high-traffic areas within hospitals, which can easily lead to problems such as unreasonable flight path planning and untimely obstacle avoidance. Second, mismatched constraints. Medical supply delivery has strict constraints on transport volume, range, timeliness, and material protection. Existing algorithms do not embed these constraints into the flight control logic, making it difficult to balance delivery efficiency and material safety. Third, an imperfect management and control system. There is a lack of management and control mechanisms for collaborative delivery of multiple drones within hospitals, linkage of emergency landing points, and synchronous calibration of material status and flight status, making it difficult to ensure the orderly operation of medical delivery.

[0004] Therefore, this application provides an intelligent management and control method for low-altitude medical services. By innovatively integrating technologies such as multimodal perception and closed-loop feedback control, it carries out intelligent management and control of low-altitude medical services for smart hospitals, realizing efficient and safe transfer of materials within and between hospitals, thereby promoting the upgrading of the smart hospital service system.

[0005] The information disclosed in this background section is intended only to enhance the understanding of the overall background of the invention and should not be construed as an admission or in any way implying that the information constitutes prior art known to those skilled in the art. Summary of the Invention

[0006] The purpose of this invention is to provide an intelligent management and control method for low-altitude medical services, based on medical domain terrain simulation, multimodal perception, and closed-loop feedback control, to solve the problems of insufficient adaptability to existing low-altitude medical service scenarios and imperfect management and control systems.

[0007] To achieve the above objectives, the present invention provides the following technical solution: A method for intelligent management and control of low-altitude medical services includes the following steps: S1. Obtain a detailed distribution of low-altitude obstacles in the medical domain through terrain simulation. S2. Construct a medical delivery scenario diagram through collaborative weighting and dynamic iterative optimization of multi-source data; S3. Collect all flight data of the UAV and simultaneously complete the four-dimensional data linkage collection of flight status, environmental interference, material status and constraint data to generate dynamic perception dataset. S4. By integrating deep feature extraction, scene quantification and grading, adaptive control of flight parameters and multi-aircraft collaborative scheduling mechanism, a scene-adaptive UAV closed-loop control model for the entire process of urban medical care is constructed. S5. Design a closed-loop calibration and collaborative control function module to identify flight parameter deviations and match them with the status of material transfer.

[0008] As a preferred method, the medical domain terrain simulation is performed in S1, including the following steps: Collect signal attenuation coefficients at different sampling points in a low-altitude scene within a hospital. Signal propagation angle Multi-dimensional spectral terrain sampling maps are generated based on sampling locations; to distinguish between valid sampled data and zero values ​​(no data), a medical domain low-altitude sampling mask map is additionally constructed. By embedding medical low-altitude flight constraints into a hospital scene decoder, the high-dimensional feature map is gradually restored into a single-channel refined terrain projection map with obstacle layers and pedestrian flow boundaries; the projection formula is as follows: ; in, To deduce the three-dimensional coordinates in the diagram Pixel value at that location, It is the Sigmoid activation function. The feature weight matrix, For bias terms, This is a multi-dimensional feature fusion function.

[0009] As a preferred approach, a medical domain delivery scenario graph is constructed in S2. To eliminate data dimensionality differences, a dynamic medical domain scenario function is introduced, with the following formula: ; in, for Time 3D coordinates Feature values ​​of the scene graph at that location, These are static geographic data feature values. These are the feature values ​​of dynamic road network data. Thermal characteristic values ​​for high-traffic areas This is the priority coefficient for medical delivery; The weights are for the four types of data, and satisfy the following conditions: .

[0010] As a preferred option, S3 simultaneously completes the four-dimensional data linkage acquisition of flight status, environmental interference, material status, and constraint data, as detailed below: The UAV flight status data is collected through a GPS positioning module and an inertial measurement unit. Environmental interference data is collected using millimeter-wave radar and thermal infrared sensors. Material status data is collected through weight sensors, temperature sensors, and a visual recognition module; Delivery constraint data is collected through the route monitoring module.

[0011] As a preferred approach, S4 constructs a scenario-adaptive closed-loop control model for the entire urban medical process, which quantitatively evaluates the real-time flight status of the drone, using the following formula: ; In the formula, This is a comprehensive assessment value for flight status, with a range of values ​​ranging from [value missing]. ; The scene is quantified and graded, with a value range of [value range missing]. ; To evaluate the weights, satisfy the following conditions: ; This represents the percentage of the drone's remaining flight range. This represents the percentage of remaining delivery time. The model is based on Based on the threshold range and scene classification results, a differentiated scene adaptive control strategy is automatically matched, specifically: when At the same time, maintain the current optimal flight parameters and delivery route; when At the same time, dynamically adjust parameters such as flight speed, altitude, and heading to optimize local delivery routes; when At that time, it triggers global path replanning and simultaneously links with the emergency landing point for low-altitude delivery scenarios in smart hospitals to activate the emergency flight plan.

[0012] As a preferred option, a closed-loop calibration and collaborative control function module is designed in S5, with the following formula: ; In the formula, The values ​​are for the dual-closed-loop collaborative calibration coefficients, ranging from [value range missing]. ; This is the comprehensive deviation value of flight parameters. This is to verify the deviation value of the material transfer status; These are the maximum permissible deviations between flight parameters and cargo transfer status, respectively. For collaborative weights, satisfying When the flight deviation is large Increased to 0.6, when there is a large deviation in materials Increased to 0.6; Calibration control center according to The value dynamically adjusts the dual-ring calibration priority to achieve synchronous calibration of flight status and material transfer status.

[0013] Compared with the prior art, the present invention has the following beneficial effects: (1) The intelligent management and control method for low-altitude medical services of the present invention breaks through the limitations of traditional static scene maps by constructing a low-altitude medical delivery scene map, and can realize the dynamic fusion and real-time iteration of multi-source scene data.

[0014] (2) The intelligent control method for low-altitude medical services of the present invention constructs a scene-adaptive UAV closed-loop control model, and realizes the accurate mapping between scene features and flight control through deep learning algorithms. It can dynamically optimize flight parameters, plan delivery routes, and allocate delivery tasks according to real-time scene changes in hospitals, realize autonomous flight adaptation in complex environments of urban hospitals, and ensure the safety, timeliness and efficiency of medical supplies such as test samples, medicines, and medical devices.

[0015] (3) The intelligent control method for medical low-altitude services of the present invention, by designing a dual closed-loop collaborative calibration method for medical low-altitude transportation, deeply binds the flight attitude, speed, and path calibration of UAVs with the transportation status of medical supplies, and can correct flight deviations and material loading deviations in real time, providing accurate calibration technical support for flight control of medical low-altitude services in smart hospitals. Attached Figure Description

[0016] Figure 1 This is a schematic diagram of the method flow according to an embodiment of the present invention; Figure 2 This is a schematic diagram illustrating the medical domain terrain simulation principle of an embodiment of the present invention; Figure 3 This is a scene hierarchy diagram according to an embodiment of the present invention; Figure 4 This is a schematic diagram of the medical domain low-altitude transport dual closed-loop collaborative calibration principle according to an embodiment of the present invention. Detailed Implementation

[0017] The technical solution of this invention patent will be clearly and completely described below. Obviously, the described embodiments are only some, not all, of the embodiments of this invention. Based on the embodiments of this invention, all other embodiments obtained by those skilled in the art without inventive effort are within the scope of protection of this invention.

[0018] In the description of this invention, it should be noted that the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer", etc., indicating the orientation or positional relationship are based on the orientation or positional relationship shown in the accompanying drawings. They are only for the convenience of describing this invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on the invention.

[0019] In the description of this invention, it should be noted that, unless otherwise explicitly specified and limited, the terms "installation," "connection," and "joining" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to a connection within two components. Those skilled in the art will understand the specific meaning of the above terms in this invention based on the specific circumstances.

[0020] See attached document Figure 1 A method for intelligent management and control of low-altitude medical services includes the following steps: S1. By coupling training of signal propagation patterns and geographical features in low-altitude scenarios, a precise mapping relationship between the two is established to realize medical domain terrain projection and obtain the refined distribution of low-altitude obstacles in the hospital area.

[0021] In complex urban environments, the diverse shapes and varied locations of buildings cause varying degrees of interference with radio signals. This is based on the signal attenuation coefficient of low-altitude sampling points, the signal propagation angle, and the three-dimensional spatial coordinates of the UAV. The correlation is used to calculate the received power P during transmission through the non-line-of-sight transmission loss and gain function. obs : In the formula, For signal transmission power, The location for signal transmission. For signal attenuation coefficient, For the angle of signal propagation, represents the UAV's position coordinates, and β is the non-line-of-sight propagation path loss parameter; This is the loss coefficient caused by factors such as shading and phase superposition in the environment.

[0022] Based on this, a multi-dimensional spectral terrain sampling map is generated. The smaller the signal attenuation coefficient of the sampling point, the closer the grayscale image is to white. The greater the deviation of the signal propagation angle from the standard value, the closer the grayscale image is to black. This can accurately predict the types of obstacles and spatial structures in the low-altitude environment inside / in the hospital.

[0023] Due to the obstruction of hospital buildings and the shielding of equipment, there are blind spots with no sampling data. To distinguish between valid sampling data and zero values ​​with no data, an additional low-altitude sampling mask map of the medical domain is constructed. Its value is only 0 or 1. When a medical drone is effectively sampling at a certain low-altitude location, the corresponding pixel value in the mask image is... It is white and there is no sampling. .

[0024] In the training of low-altitude obstacle distribution prediction, a multi-dimensional spectral terrain sampling map and a medical-domain low-altitude sampling mask map are used as algorithm inputs. A neural network analyzes the relationship between data feature information and spatial domain data distribution to predict an obstacle distribution map that closely approximates the actual terrain. Further parameter adjustments are made through training with the predicted terrain map to reduce terrain prediction errors. The underlying principle is detailed in the appendix. Figure 2 As shown, the core derivation formula is: ; in, To deduce the three-dimensional coordinates in the diagram Pixel value at that location, It is the Sigmoid activation function. The feature weight matrix, For bias terms, This is a multi-dimensional feature fusion function.

[0025] S2. Through collaborative weighting and dynamic iterative optimization of multi-source data such as 3D architecture, real-time thermal data, and road conditions, a high-precision, real-time updated medical delivery scenario map is constructed.

[0026] Core scene data was collected, including static geographic data such as the 3D coordinates of hospital buildings and the distribution of functional departments, dynamic road network data such as urban road network congestion and traffic control, and real-time heat map data of high-traffic areas such as hospital outpatient entrances and intersections. For each sub-scene, 20 sub-scene maps with different locations were constructed, and real-time data was collected every 5 minutes. The feature values ​​of the scene maps were iteratively corrected, invalid data was removed, and new scene information was added. The sub-scene data was binarized to obtain grayscale images, and a core scene dataset was established. The dataset clearly distinguishes between intra-hospital delivery sub-scenes (flight altitude ≤ 50 meters) and inter-hospital cross-regional delivery sub-scenes (flight altitude 50-120 meters).

[0027] A dynamic scenario function for the medical domain is introduced to eliminate data dimensional differences, and differentiated weights are assigned to different data types based on the priority of medical supply distribution. The formula is as follows: ; in, for Time 3D coordinates Feature values ​​of the scene graph at that location, These are static geographic data feature values. These are the feature values ​​of dynamic road network data. Thermal characteristic values ​​for high-traffic areas This is the priority coefficient for medical delivery; The weights are for the four types of data, and satisfy the following conditions: In emergency medical supply delivery scenarios, priority is given to delivery of regular supplies over that of regular supplies. The weight has been increased to 0.3 to prioritize the optimization of emergency material transfer routes.

[0028] During function training, an adaptive moment estimation optimizer was used to determine the behavior. Additionally, to test training effectiveness and avoid overfitting, 15 sub-scenes from the dataset were randomly selected for the training set, while the remaining 5 were used for performance testing.

[0029] S3. Collect all flight data of the UAV and simultaneously complete the four-dimensional data linkage collection of flight status, environmental interference, material status and constraint data to generate a dynamic perception dataset.

[0030] Based on the medical delivery scenario map, the coordinates of hospital buildings and functional departments, the layout of inter-hospital routes, the flight constraint thresholds, and the locations of two emergency landing points and the compatibility requirements of material transport boxes for each route are marked simultaneously.

[0031] The drone is equipped with multiple types of sensors to complete four-dimensional data acquisition: It collects flight status data, including speed, attitude, remaining battery power, and real-time location, through a GPS positioning module and inertial measurement unit; it collects environmental interference data through millimeter-wave radar and thermal infrared sensors; it collects material status data, including material weight, type, transport container type, and cold storage temperature, through a weight sensor, temperature sensor, and visual recognition module; and it collects delivery constraint data through a path monitoring module. During the acquisition process, requirements such as material weight and cold storage temperature are simultaneously verified, invalid data is eliminated, and a dynamic perception dataset covering the entire scenario is generated.

[0032] To eliminate dimensional differences among multi-source data, the four types of feature data are first standardized, and the objective entropy weights for each data dimension are calculated:

[0033] In the formula, Let be the information entropy of the i-th type of data, and let be the objective entropy weight of the i-th type of data.

[0034] By incorporating the subjective priority constraints of medical supply delivery scenarios, an analytic hierarchy process (AHP) is introduced to construct a judgment matrix, yielding comprehensive weights:

[0035] In the formula, Let be the coupling adjustment coefficient of the objective weight. This is a priority dynamic adjustment factor.

[0036] Based on multimodal sensing fusion technology, a four-dimensional data fusion formula is designed to achieve standardized fusion of multi-source data: ; in, This is the fused dynamic sensing feature set. These are characteristic values ​​of the flight state. These are environmental disturbance characteristic values. These are the characteristic values ​​of the material's state. For delivery constraint characteristics; in high-traffic areas and for emergency supplies delivery, , The weight was increased to 0.3 to ensure that the data fusion fits the needs of the scenario.

[0037] S4 integrates deep feature extraction, scene quantification and grading, adaptive control of flight parameters and multi-aircraft collaborative scheduling mechanism to construct a scene-adaptive UAV closed-loop control model for the entire process of urban hospital area.

[0038] A CLA model is established, with an overall architecture consisting of a perception layer, a feature layer, a decision layer, and an execution layer. The decision layer embeds a multi-drone collaborative scheduling module, enabling intelligent planning of delivery tasks and drone formation scheduling based on the volume of medical supply delivery tasks, the remaining flight range of drones, and the priority of supply delivery. The execution layer receives control commands from the decision layer, performs operations such as adjusting flight parameters and planning paths, and introduces a closed-loop feedback mechanism to feed the execution results and real-time scene data back to the perception layer, achieving dynamic iterative optimization of model parameters.

[0039] First, the dynamic perception feature set is used as the model input in the perception layer. The feature layer extracts static spatial features of the scene through 3DCNN, and strengthens the weights of key features such as high-traffic areas, building obstacles, and emergency material delivery through the attention mechanism to achieve deep feature extraction and generate a high-dimensional fused feature vector. ; in, For flight state feature vectors, For scene environment feature vectors, This is a feature vector for material distribution.

[0040] A scenario-based evaluation function is constructed to quantitatively classify hospital low-altitude delivery scenarios. The core classification formula is as follows: ; In the formula, The scene is quantified and graded, with a value range of [value range missing]. ; For the Sigmoid activation function, These are the weighting coefficients; For bias terms; when This is a normal, stable scenario. The scene was of medium complexity. The time was a highly complex scene.

[0041] Based on the scenario classification results, a comprehensive evaluation function for UAV flight status is constructed at the decision-making level to quantitatively evaluate the real-time flight status of the UAV. ; In the formula, This is a comprehensive assessment value of the flight status; For evaluation weights; This represents the percentage of the drone's remaining flight range. This represents the percentage of remaining delivery time.

[0042] The scene classification process is as follows: Figure 3 As shown. The model is based on Based on the threshold range and scene classification results, automatically match differentiated scene adaptive control strategies: when At the same time, maintain the current flight parameters and delivery route; when At the same time, dynamically adjust parameters such as flight speed, altitude, and heading to optimize local delivery routes; when At that time, it triggers global path replanning and simultaneously links with the emergency landing point for low-altitude delivery scenarios in smart hospitals to activate the emergency flight plan.

[0043] S5. Design a closed-loop calibration and collaborative control function module, which combines real-time monitoring data to perform linkage matching between flight parameter deviation identification and material transfer status monitoring, and construct a complete closed-loop system of "real-time monitoring - deviation identification - feedback optimization".

[0044] A flight parameter deviation identification function is constructed to accurately calculate the deviation between the actual flight parameters of the UAV and the flight parameters output by the scene-adaptive UAV closed-loop control model. The core deviation identification formula is as follows: ; In the formula, This is the comprehensive deviation value of flight parameters. These are the optimal pitch angle, roll angle, and yaw angle, respectively. For optimal flight speed, These are the optimal position coordinates.

[0045] A material transfer status verification function is constructed to quantitatively assess the stability and compliance of the material transfer process. The core verification formula is as follows: ; In the formula, This is the deviation value for verifying the status of material transfer. To address the stability deviation of the cargo loading, This refers to the actual temperature of the transport container. The standard temperature is used for the cold storage and transportation of medical samples. ; This refers to the actual weight of the goods, not the standard loading weight. ≤10kg, For verifying weights.

[0046] To achieve dual-loop synergistic optimization, a closed-loop calibration synergistic control function is constructed to realize the linkage and matching between flight calibration and material calibration. The core synergistic formula is: ; In the formula, The values ​​are for the dual-closed-loop collaborative calibration coefficients, ranging from [value range missing]. ; These are the maximum permissible deviations between flight parameters and cargo transfer status, respectively. For coordinated weighting, when the flight deviation is large Increased to 0.6, when there is a large deviation in materials Increased to 0.6.

[0047] according to The value dynamically adjusts the dual-loop calibration priority, activates the dual-closed-loop collaborative calibration mechanism, and dynamically outputs calibration commands to achieve synchronous calibration of flight status and material transfer status; when When, maintain the current loading state; when Using the conventional calibration mode, flight attitude, speed, and local path are corrected simultaneously; when In such cases, an emergency calibration mode is adopted, regular delivery is suspended, flight parameters are quickly adjusted, and emergency landing points are coordinated to ensure flight safety.

[0048] As attached Figure 4 As shown, the closed-loop calibration collaborative control function module can be embedded into the scene-adaptive UAV closed-loop control model. Through iterative learning, it optimizes the deviation identification function and calibration parameters, continuously improving calibration accuracy. Simultaneously, considering the hospital's building layout, functional department distribution, and inter-hospital flight path characteristics, it specifically optimizes calibration strategies to ensure the real-time performance and accuracy of UAV calibration in high-traffic areas and complex building environments, ultimately achieving the dual goals of stable UAV flight and safe material transport.

[0049] The foregoing description of specific exemplary embodiments of the invention is for illustrative and explanatory purposes. These descriptions are not intended to limit the invention to the precise forms disclosed, and it will be apparent that many changes and variations can be made in accordance with the foregoing teachings. The exemplary embodiments were chosen and described in order to explain the specific principles of the invention and its practical application, thereby enabling those skilled in the art to implement and utilize various different exemplary embodiments of the invention, as well as various different choices and variations. The scope of the invention is intended to be defined by the claims and their equivalents.

Claims

1. A method for intelligent management and control of low-altitude medical services, characterized in that, Includes the following steps: S1. Obtain a detailed distribution of low-altitude obstacles in the medical domain through terrain simulation. S2. Construct a medical delivery scenario diagram through collaborative weighting and dynamic iterative optimization of multi-source data; S3. Collect all flight data of the UAV and simultaneously complete the four-dimensional data linkage collection of flight status, environmental interference, material status and constraint data to generate dynamic perception dataset. S4. By integrating deep feature extraction, scene quantification and grading, adaptive control of flight parameters and multi-aircraft collaborative scheduling mechanism, a scene-adaptive UAV closed-loop control model for the entire process of urban medical care is constructed. S5. Design a closed-loop calibration and collaborative control function module to identify flight parameter deviations and match them with the status of material transfer.

2. The intelligent management and control method for low-altitude medical services according to claim 1, characterized in that, The medical domain terrain simulation in S1 includes the following steps: Collect signal attenuation coefficients at different sampling points in a low-altitude scene within a hospital. Signal propagation angle Multi-dimensional spectral terrain sampling maps are generated based on sampling locations; to distinguish between valid sampled data and zero values ​​(no data), a medical domain low-altitude sampling mask map is additionally constructed. By embedding medical low-altitude flight constraints into a hospital scene decoder, the high-dimensional feature map is gradually restored into a single-channel refined terrain projection map with obstacle layers and pedestrian flow boundaries; the projection formula is as follows: ； in, To deduce the three-dimensional coordinates in the diagram Pixel value at that location, It is the Sigmoid activation function. The feature weight matrix, For bias terms, This is a multi-dimensional feature fusion function.

3. The intelligent management and control method for low-altitude medical services according to claim 1, characterized in that, In S2, a medical domain delivery scenario graph is constructed. To eliminate data dimensionality differences, a dynamic medical domain scenario function is introduced, as shown in the following formula: ； in, for Time 3D coordinates Feature values ​​of the scene graph at that location, These are static geographic data feature values. These are the feature values ​​of dynamic road network data. Thermal characteristic values ​​for high-traffic areas This is a priority coefficient for medical delivery. The weights are for the four types of data, and satisfy the following conditions: .

4. The intelligent management and control method for low-altitude medical services according to claim 1, characterized in that, S3 synchronously completes the four-dimensional data linkage acquisition of flight status, environmental interference, material status, and constraint data, as detailed below: The UAV flight status data is collected through a GPS positioning module and an inertial measurement unit. Environmental interference data is collected using millimeter-wave radar and thermal infrared sensors. Material status data is collected through weight sensors, temperature sensors, and a visual recognition module; Delivery constraint data is collected through the route monitoring module.

5. The intelligent management and control method for low-altitude medical services according to claim 1, characterized in that, In S4, a scenario-adaptive closed-loop control model for drones across the entire urban medical process is constructed to quantitatively evaluate the real-time flight status of drones. The formula is as follows: ； In the formula, This is a comprehensive assessment value for flight status, with a range of values ​​ranging from [value missing]. ; The scene is quantified and graded, with a value range of [value range missing]. ; To evaluate the weights, satisfy the following conditions: ; This represents the percentage of the drone's remaining flight range. This represents the percentage of remaining delivery time. The model is based on Based on the threshold range and scene classification results, a differentiated scene adaptive control strategy is automatically matched, specifically: when At the same time, maintain the current optimal flight parameters and delivery route; when At the same time, dynamically adjust parameters such as flight speed, altitude, and heading to optimize local delivery routes; when At that time, it triggers global path replanning and simultaneously links with the emergency landing point for low-altitude delivery scenarios in smart hospitals to activate the emergency flight plan.

6. The intelligent management and control method for low-altitude medical services according to claim 1, characterized in that, The closed-loop calibration and collaborative control function module is designed in S5, and the formula is as follows: ； In the formula, The values ​​are for the dual-closed-loop collaborative calibration coefficients, ranging from [value range missing]. ; This is the comprehensive deviation value of flight parameters. This is for verifying the deviation value of the material transfer status; These are the maximum permissible deviations between flight parameters and cargo transfer status, respectively. For collaborative weights, satisfying When the flight deviation is large Increased to 0.6, when there is a large deviation in materials Increased to 0.6; Calibration control center according to The value dynamically adjusts the dual-ring calibration priority to achieve synchronous calibration of flight status and material transfer status.

Images