Emergency rescue system and method based on flying life buoy

Abstract

The invention belongs to the technical field of flight life buoy emergency rescue, and particularly relates to an emergency rescue system and method based on a flight life buoy. Through the arrangement of the multispectral sensor array integrated with the flying life buoy, high-precision identification and positioning of a to-be-rescued target are realized, environmental data can be rapidly analyzed, the real-time position of the to-be-rescued target can be accurately captured, and the flying life buoy can be ensured to follow the moving path of the to-be-rescued target by dynamically adjusting the flying track, so that the rescue effect is improved. Besides, the rescue confidence of each landing point is evaluated, and the landing point with the highest rescue confidence is selected as the final rescue landing position, so that rescue errors caused by a complex water surface environment are effectively avoided, and meanwhile, a slow descent mechanism and a fine adjustment function are started when the flight life buoy approaches the rescue landing position, so that the rescue accuracy is improved. Therefore, the life buoy can stably and accurately fall to the vicinity of a to-be-rescued target, and powerful support is provided for rescue actions.

Description

Technical Field

[0001] The present invention belongs to the technical field of emergency rescue of flight lifebuoys, and particularly relates to an emergency rescue system and method based on a flight lifebuoy. Background Art

[0002] With the rapid development of unmanned aerial vehicle (UAV) technology, its application in water rescue has gradually been promoted. In the traditional UAV-based rescue method, life-saving equipment is often carried by the UAV for dropping. However, this method has problems such as low dropping accuracy and being easily affected by environmental factors, which may lead to ineffective rescue and thus cannot guarantee the safety of rescue personnel. By combining the UAV with a lifebuoy, a new type of flight lifebuoy is formed, which can directly land near the drowning person for rescue. This not only improves the rescue accuracy but also reduces the impact of environmental factors on the rescue effect.

[0003] In the prior art, although there are flight lifebuoys that combine UAVs with lifebuoys, in actual applications, real-time operations by rescue personnel are often required, which requires rescue personnel to have a high level of operation skills. During this process, both the delay in video transmission and the response of rescue personnel will directly affect the rescue effect. At the same time, the stress behavior of the drowning person in the water poses great difficulties for the precise landing of the flight lifebuoy, and the operation feedback of rescue personnel will also be delayed due to various factors. For example, when operating the flight lifebuoy to land, the drowning person may suddenly change direction, and the operation delay of the rescue personnel may cause the flight lifebuoy to be unable to adjust the landing trajectory in time, which may lead to rescue failure. Based on this, this solution provides an emergency rescue method based on a flight lifebuoy to solve the above problems. Summary of the Invention

[0004] The purpose of the present invention is to provide an emergency rescue system and method based on a flight lifebuoy, which can automatically complete a series of rescue actions such as path planning, target recognition, trajectory optimization, predicted landing, and slow descent fine-tuning of the flight lifebuoy, so as to assist rescue personnel in more efficiently and accurately completing water rescue tasks.

[0005] The technical solution adopted by the present invention is specifically as follows: An emergency rescue method based on a flight lifebuoy, comprising: Obtaining fuzzy position information of a target to be rescued, and planning an initial flight path according to the fuzzy position information of the target to be rescued; The flight lifebuoy executes a flight mission according to the initial flight path, and when entering the rescue range, identifies the real-time position information of the target to be rescued; Adjusting the flight trajectory of the flight lifebuoy according to the real-time position information, and collecting the stress displacement behavior of the target to be rescued in real time; Predict the moving direction and speed of the target to be rescued based on its stress displacement behavior, generate a predicted landing area, and set multiple landing points within the predicted landing area; Evaluate the rescue confidence of each landing point, select the landing point with the highest rescue confidence as the rescue landing position, and when approaching the rescue landing position, the flying life buoy activates the slow descent mechanism and makes fine adjustments according to the real-time position of the target to be rescued until the flying life buoy lands stably near the target to be rescued.

[0006] In a preferred solution, the fuzzy position information is one or a combination of position information manually marked in a map application, geographical position information identified by satellite images, position information located by a mobile communication device, or position information orally reported by a witness.

[0007] In a preferred solution, the step of planning an initial flight path according to the fuzzy position information of the target to be rescued includes: Obtain the obstacle distribution between the fuzzy position information and the take-off point of the flying life buoy; Generate multiple candidate paths that avoid obstacles based on the obstacle distribution; Collect the flight time and obstacle avoidance difficulty level corresponding to each candidate path, and comprehensively evaluate each candidate path according to the flight time and obstacle avoidance difficulty level to obtain a comprehensive evaluation score, and then use the candidate path with the highest comprehensive evaluation score as the initial flight path; Among them, if there are multiple candidate paths with the same comprehensive evaluation score, use the candidate path with the shortest flight time as the initial flight path.

[0008] In a preferred solution, the step of identifying the real-time position information of the target to be rescued when entering the rescue range includes: Collect environmental data within the rescue range through an airborne multi-spectral sensor array, where the rescue range is the area covered by the maximum distance at which the flying life buoy can identify the target to be rescued; Perform running target edge detection on the visible light image within the rescue range and extract the contour of the target to be rescued; Construct a three-dimensional space topology map using radar point cloud data, map each point in the radar point cloud data into the three-dimensional space topology map to form a three-dimensional point cloud model of the target to be rescued; Perform spatial registration on the three-dimensional point cloud model and the geographical coordinate system to obtain the real-time position information of the target to be rescued in the geographical coordinate system.

[0009] In a preferred solution, the step of adjusting the flight trajectory of the flying life buoy according to the real-time position information and collecting the stress displacement behavior of the target to be rescued in real time includes: Obtain the three-dimensional spatial coordinates of the flying life buoy and update them in real time to form a dynamic motion trajectory diagram; Capture the stress displacement behavior characteristics of the target to be rescued, including identifying the vertical undulation action characteristics, horizontal swing action characteristics, and sudden turning action characteristics of the target to be rescued; Based on the stress displacement behavior characteristics of the target to be rescued, predict the moving area of the target to be rescued, and dynamically adjust the flying direction of the flying life buoy according to the moving area of the target to be rescued, so that the flying life buoy follows the moving path of the target to be rescued.

[0010] In a preferred solution, the step of predicting the moving direction and speed of the target to be rescued based on the stress displacement behavior of the target to be rescued and generating a predicted landing area includes: Analyze the stress displacement behavior of the target to be rescued to identify the main moving direction and speed of the target to be rescued; Based on the identified moving direction and speed, combined with the current position and speed of the flying life buoy, determine the probability moving path of the target to be rescued in the future period; Merge the overlapping parts between all probability moving paths to form the predicted landing area of the target to be rescued, and divide it into hexagonal grids within the predicted landing area, and set the center point of each hexagon as the landing point of the flying life buoy.

[0011] In a preferred solution, the step of evaluating the rescue confidence of each landing point and selecting the landing point with the highest rescue confidence as the rescue landing position includes: Obtain the water surface environment parameters around each landing point, and the water surface environment parameters include water flow direction, wave height, and surface water flow velocity; Dynamically assign corresponding weight coefficients to the water flow direction, wave height, and surface water flow velocity, and calculate the comprehensive environmental risk score of each landing point according to the weight coefficients; Take the landing point with the lowest comprehensive environmental risk score as the landing point with the highest rescue confidence and output it as the final rescue landing position.

[0012] In a preferred solution, the step of starting the slow descent mechanism of the flying life buoy when approaching the rescue landing position and making fine adjustments according to the real-time position of the target to be rescued until the flying life buoy stably lands near the target to be rescued includes: When the flying life buoy reaches above the rescue landing position and is lower than the preset height threshold, immediately start the slow descent mechanism; After the slow descent mechanism of the flying life buoy is started, the relative distance and azimuth angle between the target to be rescued and the flying life buoy are collected in real time; Based on the relative distance and azimuth angle, dynamically control the landing speed and horizontal displacement of the flying lifebuoy, gradually reduce the relative distance from the target to be rescued, converge the flight trajectory of the flying lifebuoy to a position close to the target to be rescued, and complete the landing; If the target to be rescued undergoes a sudden displacement during the landing process of the flying lifebuoy, immediately recalculate the relative distance and azimuth angle between the target to be rescued and the flying lifebuoy, and adjust the landing trajectory of the flying lifebuoy according to the recalculated relative distance and azimuth angle until the landing of the flying lifebuoy is completed.

[0013] The present invention also provides an emergency rescue system based on a flying lifebuoy, which uses the above-mentioned emergency rescue method based on a flying lifebuoy, and includes: A path planning module, which is used to obtain the fuzzy position information of the target to be rescued and plan an initial flight path according to the fuzzy position information of the target to be rescued; A target recognition module, which is used for the flying lifebuoy to execute a flight mission according to the initial flight path, and identify the real-time position information of the target to be rescued when entering the rescue range; A trajectory optimization module, which is used to adjust the flight trajectory of the flying lifebuoy according to the real-time position information and collect the stress displacement behavior of the target to be rescued in real time; A predicted landing module, which is used to predict the moving direction and speed of the target to be rescued according to the stress displacement behavior of the target to be rescued, generate a predicted landing area, and set a plurality of landing points in the predicted landing area; A slow descent fine-tuning module, which is used to evaluate the rescue confidence of each landing point, select the landing point with the highest rescue confidence as the rescue landing position, and when approaching the rescue landing position, the flying lifebuoy activates a slow descent mechanism and makes fine-tuning according to the real-time position of the target to be rescued until the flying lifebuoy stably lands near the target to be rescued.

[0014] And an electronic device, which includes: At least one processor; And a memory communicatively connected to the at least one processor; Wherein, the memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the above-mentioned emergency rescue method based on a flying lifebuoy.

[0015] The technical effects achieved by the present invention are: Through the setting of the multi-spectral sensor array integrated in the flying life buoy, the present invention realizes the high-precision identification and positioning of the target to be rescued. In a complex and changeable rescue environment, it can quickly analyze environmental data, accurately capture the real-time position of the target to be rescued, and ensure that the flying life buoy can closely follow the moving path of the target to be rescued by dynamically adjusting the flight trajectory. In addition, the present invention also fully considers the complexity of the water surface environment, evaluates the rescue confidence of each landing point, and selects the landing point with the highest rescue confidence as the final rescue landing position, thereby effectively avoiding rescue mistakes caused by the complex water surface environment, further improving the success rate and safety of the rescue. At the same time, the slow descent mechanism and fine-tuning function activated when the flying life buoy approaches the rescue landing position ensure that the life buoy can land smoothly and accurately near the target to be rescued, providing strong support for the rescue operation, thus improving the efficiency and quality of emergency rescue to a certain extent. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 is a schematic flowchart of the method of the present invention; Figure 2 is a schematic diagram of the system module of the present invention; Figure 3 is a schematic diagram of the structure of the electronic device of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0017] In order to make the above objects, features, and advantages of the present invention more obvious and understandable, the following detailed description of the specific embodiments of the present invention will be made with reference to the accompanying drawings of the specification.

[0018] In the following description, many specific details are set forth in order to fully understand the present invention. However, the present invention can also be implemented in other ways different from those described herein. Those skilled in the art can make similar generalizations without departing from the connotation of the present invention. Therefore, the present invention is not limited by the specific embodiments disclosed below.

[0019] Secondly, the so-called "one embodiment" or "embodiment" herein refers to a specific feature, structure, or characteristic that can be included in at least one implementation manner of the present invention. The "in a preferred embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor is it a separate or selectively exclusive embodiment from other embodiments.

[0020] Please refer to Figure 1 As shown, the present invention provides an emergency rescue method based on a flying life buoy, including: S1. Obtain the fuzzy position information of the target to be rescued, and plan an initial flight path according to the fuzzy position information of the target to be rescued; In step S1, the flying life buoy is mainly applied to water rescue scenarios, such as emergencies like being in distress at sea or drowning in a river. Since the target to be rescued may not be equipped with a positioning device, it is impossible for the rescue personnel to accurately obtain the precise location information of the target to be rescued, and only approximate fuzzy location information can be obtained. The fuzzy location information is one or a combination of the location information manually marked in the map application, the geographical location information identified through satellite images, the location information located by a mobile communication device, or the location information orally reported by eyewitnesses. After obtaining the fuzzy location information, a comprehensive analysis will be carried out based on the fuzzy location information of the target to be rescued, and an initial flight path will be planned to ensure that the flying life buoy can quickly approach the target area. Then, the flying life buoy will execute the flight mission according to the initial flight path. Among them, the steps of planning the initial flight path according to the fuzzy location information of the target to be rescued include: Obtain the obstacle distribution between the fuzzy location information and the take-off point of the flying life buoy; Generate multiple candidate paths that avoid obstacles based on the obstacle distribution; Collect the flight time and obstacle avoidance difficulty level corresponding to each candidate path, and based on the flight time and obstacle avoidance difficulty level, comprehensively evaluate each candidate path to obtain a comprehensive evaluation score, and then take the candidate path with the highest comprehensive evaluation score as the initial flight path; Among them, if there are multiple candidate paths with the same comprehensive evaluation score, take the candidate path with the shortest flight time as the initial flight path; Specifically, when planning the initial flight path according to the fuzzy location information of the target to be rescued, first, obtain the fuzzy location information of the target to be rescued and determine the take-off point of the flying life buoy. On this basis, it is also necessary to clarify the obstacle distribution between the take-off point of the flying life buoy and the fuzzy location information. Then, based on the obtained obstacle distribution data, generate multiple candidate flight paths that can effectively avoid these obstacles. For each candidate path, its corresponding flight time and the difficulty level faced during obstacle avoidance will be collected and recorded respectively. The difficulty level is related to factors such as the number and type of obstacles and the complexity of obstacle avoidance operations. The formula for determining the difficulty level is: ; In the above formula, represents the difficulty level, represents the total number of obstacles, reflecting the overall obstacle density, represents the number of the type of obstacles, such as the number of static obstacles and dynamic obstacles, represents the weight coefficient of the type of obstacles. The weight coefficient of dynamic obstacles is greater than that of static obstacles, Indicates the obstacle avoidance complexity index, such as the path curvature change rate and the frequency of heading adjustment, etc. , and respectively represent the comprehensive influence coefficients of obstacle density, obstacle type distribution, and obstacle avoidance operation complexity on the difficulty level; The higher the difficulty level, it means that higher technical levels and more complex operation processes may be required when performing obstacle avoidance operations. At the same time, it also means that the possibility of risks occurring during the flight of the flying life buoy is greater. Based on this, in this embodiment, the flight time and the obstacle avoidance difficulty level are comprehensively considered to conduct a comprehensive evaluation of each candidate path. Before performing the comprehensive evaluation, the flight time and the difficulty level will be quantified into evaluation indicators under the same dimension, and the comprehensive evaluation score of each candidate path can be calculated by the method of weighted summation. In this process, the candidate path with the highest comprehensive evaluation score is selected as the initial flight path. In addition, if there are multiple candidate paths with the same comprehensive evaluation score, then the flight times of the candidate paths under the same comprehensive evaluation score are further compared, and finally the candidate path with the shortest flight time is selected as the initial flight path to ensure that the flying life buoy can quickly reach the location of the target to be rescued under the premise of safe flight.

[0021] S2. The flying life buoy executes the flight mission according to the initial flight path, and when it enters the rescue range, it identifies the real-time position information of the target to be rescued; In step S2, after the initial flight path is determined, the flying life buoy will immediately start flying according to the preset flight parameters and path planning information. During the flight, once the flying life buoy can fully identify the target to be rescued, it means that the flying life buoy has entered the rescue range. At this time, the real-time position information of the target to be rescued will be identified to provide precondition data support for subsequent landing and rescue. Among them, when entering the rescue range, the steps of identifying the real-time position information of the target to be rescued include: Collect the environmental data within the rescue range through the airborne multi-spectral sensor array, where the rescue range is the area covered by the maximum distance at which the flying life buoy can identify the target to be rescued; Perform running target edge detection on the visible light image within the rescue range and extract the contour of the target to be rescued; Construct a three-dimensional space topology map using the radar point cloud data, map each point in the radar point cloud data to the three-dimensional space topology map, and form a three-dimensional point cloud model of the target to be rescued; Perform spatial registration on the three-dimensional point cloud model and the geographic coordinate system to obtain the real-time position information of the target to be rescued in the geographic coordinate system; Specifically, when the flying life buoy enters the rescue range, first, through the multi-spectral sensor array carried on the flying life buoy, the water surface environment data within the rescue range is comprehensively collected. Then, efficient target edge detection processing is performed on the visible light images within the collected rescue range to extract the contour information of the target to be rescued, providing basic data for further analysis. Then, using the radar point cloud data, a corresponding three-dimensional space topology map is constructed, and each point in the radar point cloud data is accurately mapped into the three-dimensional space topology map, thereby forming a three-dimensional point cloud model of the target to be rescued that is three-dimensional and intuitive. Then, the constructed three-dimensional point cloud model is subjected to spatial registration operation with the geographic coordinate system. Specifically, noise reduction processing is performed on the three-dimensional point cloud model and static geographic features are extracted. By matching the elevation data in the pre-stored geographic information database, the corresponding relationship between the local coordinate system and the geographic coordinate system is established. Based on this corresponding relationship, the feature points of the dynamic target in the point cloud are identified and matched with the feature points of the preset landmarks in the geographic coordinate system, and the spatial transformation parameters are determined. Then, the spatial transformation parameters are iteratively optimized, and at the same time, the inertial navigation data and satellite positioning data of the flying life buoy are fused to correct the sensor errors. Finally, the optimized three-dimensional point cloud coordinates are mapped to the geographic coordinate system through affine transformation to generate real-time position information including longitude, latitude, and elevation, thereby obtaining the accurate real-time position information of the target to be rescued in the geographic coordinate system.

[0022] S3. Adjust the flight trajectory of the flying life buoy according to the real-time position information, and collect the stress displacement behavior of the target to be rescued in real time; In the step S3, after the real-time position information of the target to be rescued is output, the flying life buoy will adjust the flight trajectory in real time according to the real-time position information of the target to be rescued, so as to ensure that the flying life buoy can quickly and accurately approach the target to be rescued. Since the target to be rescued may have a stress response in the water area and its movement trajectory in the water area may change suddenly, therefore, during the process of the flying life buoy approaching the target to be rescued, it is also necessary to collect the stress displacement behavior of the target to be rescued in real time. Among them, the steps of adjusting the flight trajectory of the flying life buoy according to the real-time position information and collecting the stress displacement behavior of the target to be rescued in real time include: Obtain the three-dimensional space coordinates of the flying life buoy and update them in real time to form a dynamic movement trajectory map; Capture the stress displacement behavior characteristics of the target to be rescued, including identifying the vertical undulation action characteristics, horizontal swing action characteristics, and sudden turning action characteristics of the target to be rescued; Based on the stress displacement behavior characteristics of the target to be rescued, predict the moving area of the target to be rescued, and dynamically adjust the flight direction of the flying life buoy according to the moving area of the target to be rescued, so that the flying life buoy closely follows the moving path of the target to be rescued Specifically, when adjusting the flight trajectory of the flying life buoy according to the real-time position information, it is first necessary to determine and obtain the coordinates of the flying life buoy in the three-dimensional space and continuously update them in real time, so as to construct a dynamic motion trajectory map of the flying life buoy, so as to keep track of its flight state and position changes at any time. In addition, when updating the dynamic motion trajectory of the flying life buoy, the displacement behavior characteristics of the target to be rescued in the stress state will also be captured in real time, specifically including identifying the vertical undulation action characteristics, horizontal swing action characteristics and sudden turning action characteristics of the target to be rescued. Through the comprehensive analysis of the vertical undulation action characteristics, horizontal swing action characteristics and sudden turning action characteristics of the target to be rescued, a comprehensive understanding of the dynamic behavior pattern of the target to be rescued can be obtained. Finally, based on the stress displacement behavior characteristics of the target to be rescued, the possible moving area of the target to be rescued can be predicted. The boundary equation of the moving area is: ; In the formula, represents the boundary of the moving area, represents the prediction time window, represents the time integration variable, represents the initial position coordinates of the target to be rescued, represents the predicted moving speed of the target to be rescued, represents the safety expansion coefficient, represents the standard deviation of axial perturbation, which is used to describe the perturbation intensity in the x, y, and z directions, represents the unit sphere space, indicating the uniform distribution of the perturbation direction in the three-dimensional space; Generally speaking, in the water area, the target to be rescued will move along with the direction of the water flow, but the target to be rescued in the stress state may make abnormal movements, such as suddenly changing direction, etc. Therefore, it is very necessary to consider the stress displacement behavior characteristics, and then dynamically adjust the flight direction and trajectory of the flying life buoy according to the range of the moving area to ensure that the flying life buoy can closely follow the moving path of the target to be rescued, thereby improving the rescue efficiency and success rate.

[0023] S4. Predict the moving direction and speed of the target to be rescued according to the stress displacement behavior of the target to be rescued, generate a predicted landing area, and set multiple landing points in the predicted landing area; In the step S4, after collecting the moving area of the target to be rescued, the flying life buoy will further predict its moving direction and speed according to the stress displacement behavior characteristics of the target to be rescued. In order to more accurately locate the landing position, the flying life buoy will set multiple possible landing points in the predicted moving area to determine the next flight trajectory. Among them, the step of predicting the moving direction and speed of the target to be rescued according to the stress displacement behavior of the target to be rescued and generating a predicted landing area includes: Analyze the stress displacement behavior of the rescue target to identify the main moving direction and speed of the rescue target; Based on the identified moving direction and speed, combined with the current position and speed of the flying life buoy, determine the probable movement path of the rescue target within the future time period; Merge the overlapping parts between all probable movement paths to form the predicted landing area of the rescue target, and divide it into hexagonal grids within the predicted landing area, setting the center point of each hexagon as the landing point of the flying life buoy.

[0024] Specifically, when determining the final landing position of the flying life buoy, it is first necessary to identify the main moving direction and speed of the rescue target to ensure the accuracy and reliability of subsequent analysis. Then, based on the identified moving direction and speed, considering the current position and speed of the flying life buoy, determine the probable movement path of the rescue target within the future time period, which can be specifically achieved through methods such as Monte Carlo simulation or Markov chain prediction, and thus obtain multiple possible movement paths. To improve the accuracy of the rescue, the overlapping parts between all probable movement paths will be merged to form a coherent and reliable predicted landing area of the rescue target. The path overlapping and merging formula is: ; In the formula, represents the spatial range covered by all probable movement paths, that is, the range set of the predicted landing area, represents the total number of the predicted probable movement paths of the rescue target, is used to describe the planar coordinates of the predicted area, and are used to represent the center point coordinates of the th probable movement path, represents the maximum coverage range of the predicted landing area in the x-axis direction, represents the maximum coverage range of the predicted landing area in the y-axis direction; After the predicted landing area is determined, it is also necessary to set multiple landing points within the predicted landing area for the flying life buoy to select. Specifically, it is finely divided according to hexagonal grids, and the center point of each hexagon is set as the potential landing point of the flying life buoy, in this way to improve the accuracy of the rescue.

[0025] S5. Evaluate the rescue confidence level of each landing point, select the landing point with the highest rescue confidence level as the rescue landing position, and when approaching the rescue landing position, the flying life buoy activates the slow descent mechanism and makes fine adjustments according to the real-time position of the rescue target until the flying life buoy stably lands near the rescue target; In step S5, after the landing points within the predicted landing area are determined, the confidence levels of each landing point will be further evaluated to select the most suitable landing position for the flying life buoy. When the flying life buoy approaches the selected rescue landing position, a descent slow-down mechanism will be activated to reduce the descent speed. While ensuring a safe landing, it can also continue to make fine adjustments based on the real-time position information of the target to be rescued, ensuring that the flying life buoy can land precisely and stably near the target to be rescued, thereby maximizing the rescue success rate. Among them, the steps of evaluating the rescue confidence levels of each landing point and selecting the landing point with the highest rescue confidence level as the rescue landing position include: Obtain the water surface environment parameters around each landing point. The water surface environment parameters include the water flow direction, wave height, and surface water flow velocity; Dynamically assign corresponding weight coefficients to the water flow direction, wave height, and surface water flow velocity, and calculate the comprehensive environmental risk score of each landing point based on the weight coefficients; Take the landing point with the lowest comprehensive environmental risk score as the landing point with the highest rescue confidence level and output it as the final rescue landing position; It should be noted that after each landing point is set up, the rescue confidence levels of each landing point will be evaluated accordingly, and the landing point with the highest rescue confidence level will be selected as the final rescue landing position. First, it is necessary to obtain the water surface environment parameters around each landing point, including key information such as the water flow direction, wave height, and surface water flow velocity. Then, corresponding weight coefficients will be dynamically assigned for dynamic factors such as the water flow direction, wave height, and surface water flow velocity. Generally speaking, because the water flow direction has the most direct impact on the rescue, the weight coefficient of the water flow direction is higher than that of the wave height and surface water flow velocity. However, there may also be situations where the wave height is too high or the surface water flow velocity is too fast. At this time, the weight coefficients need to be adjusted flexibly to reflect the actual situation and ensure the accuracy of the evaluation. Specifically, the dynamic assignment of weight coefficients can be achieved through a preset weight coefficient distribution table. Then, based on the weight coefficients of the water flow direction, wave height, and surface water flow velocity, the comprehensive environmental risk score of each landing point will be calculated. The comprehensive environmental risk score can comprehensively reflect the complexity and potential risks of the environment around the landing point, thereby improving the accuracy of the rescue. In this embodiment, the landing point with the lowest comprehensive environmental risk score will be selected as the landing point with the highest rescue confidence level and output this landing point as the rescue landing position, and the flying life buoy will land according to this position and carry out rescue operations.

[0026] Secondly, when approaching the rescue landing position, the steps for the flying life buoy to activate the descent slow-down mechanism and make fine adjustments according to the real-time position of the target to be rescued until the flying life buoy stably lands near the target to be rescued include: When the flying life buoy reaches above the rescue landing position and is lower than the preset height threshold, the descent mechanism is immediately activated; After the descent mechanism of the flying life buoy is activated, the relative distance and azimuth angle between the target to be rescued and the flying life buoy are collected in real time; Based on the relative distance and azimuth angle, dynamically control the descent speed and horizontal displacement of the flying life buoy, gradually reduce the relative distance from the target to be rescued, and make the flight trajectory of the flying life buoy converge to a position close to the target to be rescued and complete the landing; If the target to be rescued has a sudden displacement during the descent of the flying life buoy, immediately recalculate the relative distance and azimuth angle between the target to be rescued and the flying life buoy, and adjust the descent trajectory of the flying life buoy according to the recalculated relative distance and azimuth angle until the landing of the flying life buoy is completed.

[0027] Specifically, during the process of approaching the rescue landing position, the flying life buoy will activate its descent mechanism, that is, when the flying life buoy reaches directly above the rescue landing position and its height drops below the preset height threshold, the descent mechanism will be immediately triggered to start slowly reducing the height of the flying life buoy. For example, the preset height threshold can be set to 5 meters above the water surface. Then, when the flying life buoy is 5 meters above the water surface, the descent mechanism will be activated to ensure that the life buoy approaches the water surface at a safe speed. The activation of the descent mechanism not only helps to reduce the impact force during landing, but also allows the rescue personnel to have a more stable perspective to observe the situation of the target to be rescued. After the descent mechanism is activated, the relative distance and azimuth angle data between the target to be rescued and the flying life buoy will be collected and updated in real time. At this time, the flying life buoy can dynamically adjust its descent speed and horizontal displacement, gradually reduce the relative distance from the target to be rescued, and make the flight trajectory of the flying life buoy gradually converge, and finally approach and reach the position of the target to be rescued and successfully complete the landing. In addition, if the target to be rescued has a sudden displacement during the descent of the flying life buoy, the relative distance and azimuth angle between the target to be rescued and the flying life buoy will be recalculated immediately, and the descent trajectory of the flying life buoy will be quickly updated according to the recalculated results to ensure that the flying life buoy can accurately land near the target to be rescued until the entire landing process is successfully completed.

[0028] Please refer to Figure 2 , an emergency rescue system based on a flying life buoy, using the above-mentioned emergency rescue method based on a flying life buoy, including: A path planning module, which is used to obtain the fuzzy position information of the target to be rescued and plan an initial flight path according to the fuzzy position information of the target to be rescued; A target recognition module, which is used for the flying life buoy to execute a flight mission according to the initial flight path, and when entering the rescue range, identify the real-time position information of the target to be rescued; A trajectory optimization module, which is used to adjust the flight trajectory of the flying life buoy according to the real-time position information, and collect the stress displacement behavior of the target to be rescued in real time; A predicted landing module, which is used to predict the moving direction and speed of the target to be rescued according to the stress displacement behavior of the target to be rescued, generate a predicted landing area, and set multiple landing points in the predicted landing area; A controlled descent fine-tuning module, which is used to evaluate the rescue confidence of each landing point, select the landing point with the highest rescue confidence as the rescue landing position, and when approaching the rescue landing position, the flying life buoy activates the controlled descent mechanism and makes fine-tuning according to the real-time position of the target to be rescued until the flying life buoy stably lands near the target to be rescued.

[0029] Among the above, the main function of the path planning module is to obtain the fuzzy position information of the target to be rescued, and plan an initial flight path according to the fuzzy position information, so as to provide preliminary navigation guidance for the flight mission of the flying life buoy. The target recognition module is activated during the process of the flying life buoy executing the flight mission according to the initial flight path, and is used to identify the target to be rescued and determine the rescue range. After entering the rescue range, it collects the real-time position information of the target to be rescued. The function of the trajectory optimization module is to dynamically adjust the flight trajectory of the flying life buoy according to the real-time position information provided by the target recognition module, and at the same time, it will also collect the stress displacement behavior of the target to be rescued in real time to better adapt to the changes in the rescue environment and ensure that the flying life buoy can approach the target to be rescued efficiently. The function of the predicted landing module is to intelligently predict its moving direction and speed according to the stress displacement behavior of the target to be rescued, generate a predicted landing area, and set multiple potential landing points in the predicted landing area. The controlled descent fine-tuning module is responsible for comprehensively evaluating the rescue confidence of each landing point in the predicted landing area, selecting the landing point with the highest rescue confidence as the final rescue landing position. When the flying life buoy approaches the rescue landing position, the system will activate the controlled descent mechanism and make fine adjustments according to the real-time position of the target to be rescued to ensure that the flying life buoy can land smoothly and safely near the target to be rescued, so as to successfully complete the rescue mission.

[0030] Please refer to Figure 3 , an electronic device, the electronic device includes: At least one processor; And a memory communicatively connected to at least one processor; Among them, the memory stores a computer program executable by at least one processor. The computer program is executed by at least one processor so that the at least one processor can execute the above-mentioned emergency rescue method based on a flying life buoy.

[0031] The processor of the above electronic device can be a central processing unit (CPU), a microcontroller unit (MCU), a digital signal processor (DSP), or other programmable logic devices. The memory can include a random access memory (RAM), a read-only memory (ROM), a flash memory, or other types of non-volatile memory for storing the computer programs and data required for the processor to execute. In addition, the electronic device can also include an arithmetic unit and input / output devices. The arithmetic unit is used to perform various arithmetic and logical operations to assist the processor in completing complex calculation tasks. The input / output devices include a keyboard, a display screen, a network interface, etc.

[0032] It should be noted that in this article, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, device, article or method including a series of elements not only includes those elements, but also includes other elements not expressly listed, or further includes elements inherent to such process, device, article or method. Without further limitations, an element defined by the statement "including one..." does not exclude the existence of additional identical elements in the process, device, article or method including that element.

[0033] The above are only the preferred embodiments of the present invention. It should be pointed out that for those of ordinary skill in the art, without departing from the principle of the present invention, several improvements and refinements can be made, and these improvements and refinements should also be regarded as the protection scope of the present invention. The structures, devices, and operation methods not specifically described and explained in the present invention are implemented according to the conventional means in the art without special description and limitation.

Claims

1. An emergency rescue method based on a flying life buoy, characterized in that: include: Obtaining the fuzzy position information of the target to be rescued, and planning an initial flight path according to the fuzzy position information of the target to be rescued; The flying lifebuoy performs the flight mission according to the initial flight path and identifies the real-time location information of the target to be rescued when entering the rescue range; Adjust the flight trajectory of the flying lifebuoy according to the real-time position information, and collect the stress displacement behavior of the rescue target in real time; Predict the moving direction and speed of the target to be rescued according to the stress displacement behavior of the target to be rescued, generate a predicted landing area, and set multiple landing points in the predicted landing area; The rescue confidence of each landing point is evaluated, and the landing point with the highest rescue confidence is selected as the rescue landing position. When approaching the rescue landing position, the flying lifebuoy starts the slow-descent mechanism and makes fine adjustments according to the real-time position of the target to be rescued until the flying lifebuoy lands stably near the target to be rescued.

2. The emergency rescue method based on a flying life buoy according to claim 1, wherein: The fuzzy location information is one or more combinations of location information manually marked in a map application, geographic location information identified by satellite images, location information located by a mobile communication device, or location information orally reported by an eyewitness reporter.

3. The emergency rescue method based on a flying life buoy according to claim 1, characterized in that: The step of planning the initial flight path according to the fuzzy position information of the target to be rescued includes: Obtain the obstacle distribution between the fuzzy position information and the take-off point of the flying lifebuoy; Generate multiple candidate paths to avoid obstacles based on the obstacle distribution; The corresponding flight time and obstacle avoidance difficulty level of each candidate path are collected, and each candidate path is comprehensively evaluated based on the flight time and obstacle avoidance difficulty level to obtain a comprehensive evaluation score, and then the candidate path with the highest comprehensive evaluation score is used as the initial flight path; Among them, if there are multiple candidate paths with the same comprehensive evaluation score, the candidate path with the shortest flight time will be used as the initial flight path.

4. The emergency rescue method based on a flying life buoy according to claim 1, characterized in that: The step of identifying the real-time location information of the target to be rescued when entering the rescue range includes: Collect environmental data within the rescue range through an onboard multispectral sensor array, where the rescue range is the area covered by the maximum distance at which the flying lifebuoy can identify the target to be rescued; Perform target edge detection on the visible light image within the rescue range and extract the outline of the target to be rescued; Use radar point cloud data to build a three-dimensional space topology map, map each point in the radar point cloud data to the three-dimensional space topology map, and form a three-dimensional point cloud model of the target to be rescued; The three-dimensional point cloud model is spatially registered with the geographic coordinate system to obtain the real-time position information of the rescue target in the geographic coordinate system.

5. The emergency rescue method based on a flying life buoy according to claim 1, characterized in that: The step of adjusting the flight trajectory of the flying lifebuoy according to the real-time position information and collecting the stress displacement behavior of the target to be rescued in real time includes: Obtain the three-dimensional spatial coordinates of the flying lifebuoy and update them in real time to form a dynamic motion trajectory diagram; Capture the stress displacement behavior characteristics of the target to be rescued, including identifying the vertical fluctuation action characteristics, horizontal swing action characteristics and sudden turning action characteristics of the target to be rescued; Predict the moving area of the target to be rescued according to the stress displacement behavior characteristics of the target to be rescued, and dynamically adjust the flight direction of the flying life buoy according to the moving area of the target to be rescued, so that the flying life buoy follows the moving path of the target to be rescued.

6. The emergency rescue method based on a flying life buoy according to claim 1, characterized in that: The step of predicting the moving direction and speed of the target to be rescued according to the stress displacement behavior of the target to be rescued and generating a predicted landing area includes: Analyze the stress displacement behavior of the target to be rescued to identify the main moving direction and speed of the target to be rescued; According to the identified moving direction and speed, combined with the current position and speed of the flying life buoy, determine the probable moving path of the target to be rescued in the future period; Merge the overlapping parts between all probable moving paths to form the predicted landing area of the target to be rescued, and divide it into hexagonal grids within the predicted landing area, and set the center point of each hexagon as the landing point of the flying life buoy.

7. A method for emergency rescue based on a flying life buoy according to claim 1, characterized in that: The step of evaluating the rescue confidence of each landing point and selecting the landing point with the highest rescue confidence as the rescue landing position includes: Obtain the water surface environment parameters around each landing point, and the water surface environment parameters include the water flow direction, wave height and surface water flow speed; Dynamically assign corresponding weight coefficients to the water flow direction, wave height and surface water flow speed, and calculate the comprehensive environmental risk score of each landing point according to the weight coefficients; Take the landing point with the lowest comprehensive environmental risk score as the landing point with the highest rescue confidence and output it as the final rescue landing position.

8. The emergency rescue method based on a flying life buoy according to claim 1, characterized in that: The step of starting the slow descent mechanism of the flying life buoy and making fine adjustments according to the real-time position of the target to be rescued when approaching the rescue landing position includes: When the flying life buoy reaches above the rescue landing position and is lower than the preset height threshold, immediately start the slow descent mechanism; After the slow descent mechanism of the flying life buoy is started, collect the relative distance and azimuth angle between the target to be rescued and the flying life buoy in real time; Based on the relative distance and azimuth angle, dynamically control the descent speed and horizontal displacement of the flying life buoy, gradually reduce the relative distance from the target to be rescued, and make the flight trajectory of the flying life buoy converge to a position close to the target to be rescued and complete the landing; If the target to be rescued has a sudden displacement during the landing of the flying life buoy, immediately recalculate the relative distance and azimuth angle between the target to be rescued and the flying life buoy, and adjust the landing trajectory of the flying life buoy according to the recalculated relative distance and azimuth angle until the landing of the flying life buoy is completed.

9. An emergency rescue system based on a flying life buoy, characterized in that: Using the emergency rescue method based on a flying life buoy according to any one of claims 1 to 8, includes: A path planning module for obtaining the fuzzy position information of the target to be rescued and planning an initial flight path according to the fuzzy position information of the target to be rescued; A target recognition module for the flying life buoy to execute a flight mission according to the initial flight path and identify the real-time position information of the target to be rescued when entering the rescue range; A trajectory optimization module, which is used to adjust the flight trajectory of the flying life buoy according to real-time position information and collect the stress displacement behavior of the target to be rescued in real time; A predicted landing module, which is used to predict the moving direction and speed of the target to be rescued according to the stress displacement behavior of the target to be rescued, generate a predicted landing area, and set multiple landing points in the predicted landing area; A slow descent fine-tuning module, which is used to evaluate the rescue confidence of each landing point, select the landing point with the highest rescue confidence as the rescue landing position, and when approaching the rescue landing position, the flying life buoy activates the slow descent mechanism and makes fine-tuning according to the real-time position of the target to be rescued until the flying life buoy stably lands near the target to be rescued.

10. An electronic device, characterized in that: The electronic device includes: At least one processor; And a memory communicatively connected to the at least one processor; Wherein, the memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the emergency rescue method based on a flying life buoy according to any one of claims 1 to 8.

Images