An air-ground task intersection point prediction method for emergency rescue

Abstract

The application discloses a kind of air-ground task intersection point prediction methods for emergency rescue, belong to unmanned aerial vehicle control technical field.To solve the problem of accurately predicting air-ground task intersection point of reachability and energy efficiency requirement, the present application includes unmanned aerial vehicle path prediction;Ground vehicle path prediction;Candidate intersection point generation;Calculate the time cost of rescue task, the energy consumption cost of flight, environmental risk cost;Build comprehensive cost function;Through topographic relief, path node complexity and communication blockage score, build confidence factor, risk correction is carried out to comprehensive cost function, and the modified comprehensive cost function is obtained;Introduce ground slope angle, wind speed value, ground passability score, unmanned aerial vehicle flight distance factor for penalty correction, extract the optimal air-ground task intersection point coordinate for emergency rescue.The application is suitable for various emergency rescue, multi-platform cooperation and intelligent scheduling task, with wide application prospect and popularization value.

Description

Technical Field

[0001] This invention belongs to the field of unmanned aerial vehicle (UAV) control technology, specifically relating to a method for predicting the intersection point of air-ground missions for emergency rescue. Background Technology

[0002] Emergencies are typically complex and urgent, placing higher demands on response time for rescue missions. Traditional rescue methods rely on ground vehicles to enter the emergency area, which not only suffers from uncertain routes but also has its response speed severely constrained by road conditions, traffic congestion, and terrain complexity. With the rapid development of drone technology, its advantages such as rapid deployment, strong aerial accessibility, and strong obstacle-crossing capabilities have demonstrated enormous application potential in emergencies. By introducing drones to coordinate with ground rescue vehicles, response times for information gathering, material delivery, and personnel rescue can be significantly shortened, improving overall rescue efficiency and operational coverage, thus becoming an important development direction for modern emergency response.

[0003] In air-ground coordinated rescue missions, the rendezvous point between drones and ground vehicles is a critical node for mission coordination. Whether it's the delivery of supplies, the exchange of information, or the transfer of personnel, both parties must achieve precise docking at the same location and time. If the rendezvous point is chosen inappropriately, such as being in a remote location, having a complex route, or being out of sync with the timing, it will lead to drones hovering and waiting, ground vehicles taking long detours, or even failed handovers, severely impacting rescue efficiency. Therefore, scientifically and rationally predicting and selecting rendezvous points not only ensures mission timeliness but also reduces energy consumption risks, avoids redundant routes, and improves the efficiency of coordinated use of air and ground resources, making it a core technical challenge for improving rescue success rates.

[0004] Most current air-to-ground collaborative rescue systems rely on fixed rendezvous points or manually designated handover locations, failing to fully consider key factors such as drone flight trajectories, dynamic ground paths, environmental risks, and spatiotemporal synchronization. On one hand, fixed rendezvous points limit mission flexibility and make it difficult to adapt to unforeseen circumstances such as road blockages or weather changes. On the other hand, manual point selection is highly subjective, ignoring dynamic changes in system latency, energy consumption constraints, and rendezvous accessibility. This approach is prone to rendezvous failures, excessive energy consumption, or response delays in complex environments, lacking intelligence and reliability. Summary of the Invention

[0005] The problem this invention aims to solve is to rationally predict and select air-ground mission intersection points that meet the requirements of spatiotemporal synchronization, safety, accessibility and energy efficiency in dynamic and complex environments during emergency rescue missions. This invention proposes a method for predicting air-ground mission intersection points for emergency rescue.

[0006] To achieve the above objectives, the present invention provides the following technical solution:

[0007] A method for predicting the intersection point of air-ground missions for emergency rescue includes the following steps:

[0008] S1. UAV Path Prediction: Flight speed, heading angle, external wind speed disturbance and navigation error are set as influencing factors. An integral method is used for modeling to predict the two-dimensional position of the UAV at any time and obtain the UAV path trajectory during the mission execution process.

[0009] S2. Ground vehicle path prediction: Considering the speed changes caused by vehicle turning behavior in the ground path, the ground path is discretized into multiple road segments, an angle-penalized path model is constructed, and the time required for a vehicle to pass through any road segment is calculated to obtain the ground vehicle path.

[0010] S3. Candidate Intersection Point Generation: Based on the UAV path predicted in step S1 and the ground vehicle path predicted in step S2, an initial set of candidate intersection points is generated.

[0011] S4. For the intersection points in the candidate intersection point set obtained in step S3, determine the accessibility of the intersection points through a sliding time window, and proceed to the next step for the candidate intersection points that are determined to meet the accessibility index;

[0012] S5. Based on the candidate intersection points obtained in step S4, calculate the time cost, flight energy cost, and environmental risk cost of the rescue mission;

[0013] S6. A comprehensive cost function is constructed by weighted linear combination of the time cost of the rescue mission, the energy cost of flight, and the environmental risk cost;

[0014] S7. Construct confidence factors using terrain elevation difference, path node complexity, and communication obstruction scores, and perform risk correction on the comprehensive cost function to obtain the corrected comprehensive cost function;

[0015] S8. For the modified comprehensive cost function obtained in step S7, ground slope angle, wind speed, ground accessibility score, and UAV flight distance factors are introduced for penalty correction, and the optimal coordinates of the air-ground mission intersection point for emergency rescue are extracted.

[0016] Furthermore, step S1 yields... , Let x and y be the x and y coordinates of the UAV's position at time t, respectively.

[0017] Furthermore, in step S2, the speed adjustment range of the vehicle on the ground path is estimated by analyzing the angle between adjacent road segments, thus obtaining the time required for the ground vehicle to pass through the j-th road segment. The expression is:

[0018]

[0019]

[0020] in, Let be the time required for ground vehicles to pass through the j-th road segment; The path length of the j-th segment is obtained from map data; The theoretical speed of ground vehicles is set manually; This is the speed attenuation factor corresponding to the j-th road segment; The specific penalty coefficient is determined by expert experience; , These are the directional angles corresponding to the (j+1)th and jth road segments, respectively, obtained from map data.

[0021] Furthermore, in step S3, based on the path trajectory predicted by the UAV, the positions and arrival times of the UAV and ground vehicles are compared time by time. The maximum spatial tolerance conditions and the maximum time error conditions for the UAV and ground vehicles are set, and all points that meet the maximum spatial tolerance conditions and the maximum time error conditions for the UAV and ground vehicles are found to form an initial candidate intersection point set.

[0022] Furthermore, in step S4, by using a sliding time window, the relative positional relationship between the UAV and the ground vehicle is compared frame by frame within a certain time range before and after the initial candidate intersection point to determine whether the two can achieve spatial proximity within the error tolerance range for a period of time, thereby obtaining the candidate intersection point.

[0023] Furthermore, the specific implementation method of step S5 includes the following steps:

[0024] S5.1. For each candidate intersection point, calculate the time required for both the UAV and the ground vehicle to travel from their current locations to the candidate intersection point, and take the maximum value as the time cost of the candidate intersection point. The calculation formula is as follows:

[0025]

[0026] in, For time cost, , These represent the time required for the drone and ground vehicle to reach the candidate intersection point, respectively.

[0027] S5.2. By modeling the horizontal distance and vertical landing distance of the UAV to the candidate intersection point, a weighted method is used to evaluate the energy consumption cost of the flight. The calculation formula is as follows:

[0028]

[0029] in, The energy cost of flight; The horizontal unit energy consumption coefficient is obtained from the UAV parameters; The vertical unit energy consumption coefficient is obtained from the UAV parameters; The drone's flight altitude is obtained from the flight control system. The altitude at which the drone and ground vehicle meet is set according to the rescue mission. , These are the x and y coordinates corresponding to the candidate intersection points, respectively;

[0030] S5.3. Based on historical wind field data or real-time wind speed sensor information, establish a risk integral model to quantify the environmental risk cost from wind speed change rate, wind direction fluctuation, spatial gradient, and sudden wind energy. The calculation formula is as follows:

[0031]

[0032] in, Environmental risk costs; The wind speed value is obtained from measurements by a weather sensor. The time window for risk assessment is determined by expert experience; The spatial wind speed gradient is calculated from the wind speed value. This is the wind direction angle, measured by a meteorological sensor. The degree of abrupt change in wind direction is calculated from the wind angle. The sudden wind speed intensity is measured by meteorological sensors; μ0, μ1, μ2, and μ3 are the weighting coefficients for environmental risk, spatial wind speed gradient, degree of wind direction change, and sudden wind speed intensity, respectively, and also serve to adjust the dimensions.

[0033] Furthermore, the specific implementation method of step S7 includes the following steps:

[0034] S7.1. Construct the confidence factor, calculated using the following formula:

[0035]

[0036] in, Confidence factor; The elevation difference between the candidate intersection point and the ground is obtained from GIS data; This represents the maximum difference in elevation between the candidate intersection point and the ground among all candidate points. This is the path complexity index, determined by experts in conjunction with the path itself; This represents the maximum value of the path complexity exponent for all candidate points. The signal obstruction score is determined by experts based on the actual environment. The maximum value of the signal occlusion score corresponding to all candidate points; , , These are the weighting coefficients for elevation difference, path complexity index, and signal obstruction score, respectively, and they also have the function of adjusting the units of measurement.

[0037] S7.2. Risk correction is performed on the comprehensive cost function based on the confidence factor. The calculation formula is as follows:

[0038]

[0039] in, This is the corrected comprehensive cost function. This is the overall cost function.

[0040] Furthermore, the specific implementation method of step S8 includes the following steps:

[0041] S8.1. A penalty correction value is constructed by incorporating ground slope angle, wind speed, ground accessibility score, and UAV flight distance factors. The expression is as follows:

[0042]

[0043] in, This is a penalty correction value. The ground slope angle is obtained from GIS data. The wind speed value is obtained from measurements by a weather sensor. Ground accessibility is scored based on expert experience combined with the route; , Let x and y be the x and y coordinates of the UAV's position at time t, respectively. , These are the x and y coordinates corresponding to the candidate intersection points, respectively; , , , These are the penalty weights corresponding to ground slope angle, wind speed value, ground accessibility score, and drone flight distance, respectively, and they also have the function of adjusting the dimensions.

[0044] S8.2. Optimize based on the penalty correction value combined with the corrected comprehensive cost function to obtain the optimal intersection point.

[0045] The beneficial effects of this invention are:

[0046] This invention presents a highly intelligent and adaptable method for predicting rendezvous points in air-to-ground missions for emergency response. Compared to traditional methods, this invention simultaneously considers multiple key factors, including UAV flight prediction, dynamic ground path estimation, energy consumption assessment, environmental risk determination, and rendezvous accessibility verification. It constructs a unified comprehensive cost model and applies penalty corrections, thereby improving the scientific rigor and reliability of rendezvous point selection. This method not only enhances the efficiency of air-to-ground collaborative missions but also strengthens the system's robustness in complex terrain, severe weather, or unstable communication environments. It is applicable to various emergency rescue, multi-platform collaboration, and intelligent scheduling missions, and has broad application prospects and promotional value. Attached Figure Description

[0047] Figure 1 This is a flowchart of a method for predicting the intersection point of air and ground missions for emergency rescue, as described in this invention.

[0048] Figure 2 This is a prediction result diagram of a method for predicting the intersection point of air and ground missions for emergency rescue, as described in this invention. Detailed Implementation

[0049] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are only for explaining the invention and are not intended to limit the invention; that is, the described specific embodiments are merely a part of the embodiments of the invention, and not all of them. The components of the specific embodiments of the invention described and shown in the accompanying drawings can generally be arranged and designed in various different configurations, and the invention may also have other embodiments.

[0050] Therefore, the following detailed description of specific embodiments of the invention provided in the accompanying drawings is not intended to limit the scope of the claimed invention, but merely to illustrate selected specific embodiments of the invention. All other specific embodiments obtained by those skilled in the art based on these specific embodiments without inventive effort are within the scope of protection of this invention.

[0051] To further understand the invention's content, features, and effects, the following specific embodiments are provided, along with accompanying drawings. Figure 1 - Appendix Figure 2 Detailed explanation is as follows:

[0052] Example 1:

[0053] A method for predicting the intersection point of air-ground missions for emergency rescue includes the following steps:

[0054] S1. UAV Path Prediction: Flight speed, heading angle, external wind speed disturbance and navigation error are set as influencing factors. An integral method is used for modeling to predict the two-dimensional position of the UAV at any time and obtain the UAV path trajectory during the mission execution process.

[0055] Furthermore, step S1 yields... , Let x and y be the x and y coordinates of the UAV's position at time t, respectively.

[0056] Furthermore, in rescue missions, drones are typically used for rapid transportation, site reconnaissance, or supply delivery. These drones must traverse complex terrain and variable weather conditions during operation. Their flight paths are influenced not only by their own control strategies but also by wind disturbances, navigation errors, and attitude control accuracy. Therefore, accurate trajectory prediction is crucial for mission success. The formulas for calculating the x-coordinate and y-coordinate of the drone's position at time t are:

[0057]

[0058]

[0059] in, , Let x and y be the x and y coordinates of the UAV's position at time t, respectively. , The x and y coordinates of the drone's starting position are obtained from the GPS sensor; The initial flight speed of the drone is obtained from the flight control system. The heading angle at time t is obtained from the flight control system; The navigation error at time t is determined by expert evaluation; , The values ​​represent the disturbances in wind speed at time t along the horizontal and vertical axes, respectively, and are measured by meteorological sensors.

[0060] S2. Ground vehicle path prediction: Considering the speed changes caused by vehicle turning behavior in the ground path, the ground path is discretized into multiple road segments, an angle-penalized path model is constructed, and the time required for a vehicle to pass through any road segment is calculated to obtain the ground vehicle path.

[0061] Furthermore, in step S2, the speed adjustment range of the vehicle on the ground path is estimated by analyzing the angle between adjacent road segments, thus obtaining the time required for the ground vehicle to pass through the j-th road segment. The expression is:

[0062]

[0063]

[0064] in, Let be the time required for ground vehicles to pass through the j-th road segment; The path length of the j-th segment is obtained from map data; The theoretical speed of ground vehicles is set manually; This is the speed attenuation factor corresponding to the j-th road segment; The specific penalty coefficient is determined by expert experience; , These are the directional angles corresponding to the (j+1)th and jth road segments, respectively, obtained from map data.

[0065] Furthermore, when ground rescue vehicles are performing missions, their route planning is constrained by factors such as road accessibility, building obstructions, traffic rules, and turning radii. To accurately predict future positional changes, a simple uniform speed model is insufficient; the speed reduction and delay caused by turning actions must be considered. Therefore, this step proposes an angle-penalized path model, discretizing the ground path into multiple segments and estimating the vehicle's speed adjustment range within each segment by analyzing the angle between adjacent segments. After speed adjustment, the time required for each segment can be estimated more accurately, thus obtaining the temporal trajectory of the ground vehicle during mission execution and providing a time reference for subsequent air-ground coordination and rendezvous point matching.

[0066] S3. Candidate Intersection Point Generation: Based on the UAV path predicted in step S1 and the ground vehicle path predicted in step S2, an initial set of candidate intersection points is generated.

[0067] Furthermore, in step S3, based on the path trajectory predicted by the UAV, the positions and arrival times of the UAV and ground vehicles are compared time by time. The maximum spatial tolerance conditions and the maximum time error conditions for the UAV and ground vehicles are set, and all points that meet the maximum spatial tolerance conditions and the maximum time error conditions for the UAV and ground vehicles are found to form an initial candidate intersection point set.

[0068] Furthermore, the initial candidate intersection point is generated based on the principle of spatiotemporal synchronization, and the calculation formula is as follows:

[0069]

[0070]

[0071]

[0072]

[0073] in, , Let x and y be the x and y coordinates of the ground vehicle's position at time t, respectively. , These are the estimated arrival times of the drone and the ground vehicle at that point, respectively. The maximum permissible time difference is determined by expert experience; Let t be the spatial distance between the UAV and the ground vehicle at time t; The maximum permissible intersection distance is determined by expert experience; , These represent the time required for the drone and the ground vehicle to reach the intersection point, respectively. , These are the x and y coordinates of the intersection point, respectively. Spatial tolerance is determined by expert experience; The total number of road segments traversed by ground vehicles to reach the junction point is obtained from map data; Let be the time required for a ground vehicle to pass through the j-th road segment.

[0074] S4. For the intersection points in the candidate intersection point set obtained in step S3, determine the accessibility of the intersection points through a sliding time window, and proceed to the next step for the candidate intersection points that are determined to meet the accessibility index;

[0075] Furthermore, in step S4, by using a sliding time window, the relative positional relationship between the UAV and the ground vehicle is compared frame by frame within a certain time range before and after the initial candidate intersection point to determine whether the two can achieve spatial proximity within the error tolerance range for a period of time, thereby obtaining the candidate intersection point.

[0076] Furthermore, even if the rendezvous point theoretically possesses spatiotemporal synchronization and exhibits low energy consumption and risk indicators, this does not guarantee its practical reachability. Due to system delays, positioning errors, and control uncertainties during execution, the dynamic reachability of the rendezvous point must be further verified. (Definition: If within a time window...) Within the range, there is a time when the condition is satisfied. Then define ;otherwise, ,in, The time window range for accessibility is set by expert experience; The maximum permissible spatial error is set in conjunction with communication and operational accuracy. This is an accessibility indicator.

[0077] S5. Based on the candidate intersection points obtained in step S4, calculate the time cost, flight energy cost, and environmental risk cost of the rescue mission;

[0078] Furthermore, the specific implementation method of step S5 includes the following steps:

[0079] S5.1. For each candidate intersection point, calculate the time required for both the UAV and the ground vehicle to travel from their current locations to the candidate intersection point, and take the maximum value as the time cost of the candidate intersection point. The calculation formula is as follows:

[0080]

[0081] in, For time cost, , These represent the time required for the drone and ground vehicle to reach the candidate intersection point, respectively.

[0082] Furthermore, response time is a core metric for evaluating the efficiency of rendezvous points. In rescue missions, delays on either side can lead to delivery failure or disrupt subsequent mission coordination. Therefore, for each candidate rendezvous point, the time required for both the drone and the ground vehicle to travel from their current locations to that point must be calculated separately, and the maximum value should be taken as the response time cost for that rendezvous point. This ensures that the selection of rendezvous points takes into account the movement characteristics of both parties, avoiding prolonged waiting times for one party that arrives early, and improving overall mission efficiency.

[0083] S5.2. By modeling the horizontal distance and vertical landing distance of the UAV to the candidate intersection point, a weighted method is used to evaluate the energy consumption cost of the flight. The calculation formula is as follows:

[0084]

[0085] in, The energy cost of flight; The horizontal unit energy consumption coefficient is obtained from the UAV parameters; The vertical unit energy consumption coefficient is obtained from the UAV parameters; The drone's flight altitude is obtained from the flight control system. The altitude at which the drone and ground vehicle meet is set according to the rescue mission. , These are the x and y coordinates corresponding to the candidate intersection points, respectively;

[0086] Furthermore, drones have limited battery capacity during missions, and their flight distance and altitude directly affect their endurance. Therefore, energy consumption must be considered when selecting rendezvous points. This step models the horizontal distance and vertical landing distance of the drone to the rendezvous point and uses a weighted approach to evaluate its energy consumption. This metric is crucial for aircraft power management, mission planning, and multi-mission collaboration, helping to select rendezvous points with high energy efficiency.

[0087] S5.3. Based on historical wind field data or real-time wind speed sensor information, establish a risk integral model to quantify the environmental risk cost from wind speed change rate, wind direction fluctuation, spatial gradient, and sudden wind energy. The calculation formula is as follows:

[0088]

[0089] in, Environmental risk costs; The wind speed value is obtained from measurements by a weather sensor. The time window for risk assessment is determined by expert experience; The spatial wind speed gradient is calculated from the wind speed value. This is the wind direction angle, measured by a meteorological sensor. The degree of abrupt change in wind direction is calculated from the wind angle. The sudden wind speed intensity is measured by meteorological sensors; μ0, μ1, μ2, and μ3 are the weighting coefficients for environmental risk, spatial wind speed gradient, degree of wind direction change, and sudden wind speed intensity, respectively, and also serve to adjust the dimensions.

[0090] Furthermore, in the context of rescue missions, the stability of drones is highly susceptible to environmental factors, especially wind speed changes, sudden wind direction shifts, and terrain-guided winds, which pose significant threats to flight safety. Even if the rendezvous points are synchronized in time and space and have low energy consumption, the presence of strong winds, turbulence, or sudden weather phenomena nearby can still lead to mission failure. Therefore, this step establishes a risk integral model based on historical wind field data or real-time wind speed sensor information to quantify environmental risks from multiple dimensions, including wind speed change rate, wind direction fluctuations, spatial gradient, and sudden wind energy. This risk value will affect the final optimal ranking of rendezvous points.

[0091] S6. A comprehensive cost function is constructed by weighted linear combination of the time cost of the rescue mission, the energy cost of flight, and the environmental risk cost;

[0092] Furthermore, since each candidate intersection point exhibits different performance in terms of time cost, energy cost, and environmental risk, a unified evaluation of these indicators is necessary for ranking and selection. To this end, this step constructs a weighted linear combination comprehensive cost function, converting performance indicators of different dimensions into scalar values ​​with a unified dimension. By setting task priorities and adjusting the weight coefficients of each indicator, a ranking basis for intersection points under different task backgrounds is established, providing quantitative support for the final intersection point decision. The expression is:

[0093]

[0094] in, To provide comprehensive value; , , These are the weighting coefficients for time cost, energy cost, and environmental risk cost, respectively, and they also serve to adjust the dimensions.

[0095] S7. Construct confidence factors using terrain elevation difference, path node complexity, and communication obstruction scores, and perform risk correction on the comprehensive cost function to obtain the corrected comprehensive cost function;

[0096] While some intersection points may perform well in terms of time, energy consumption, and environmental costs, they may face the risk of failure in actual implementation due to issues such as terrain obstruction, excessive slope, path complexity, or communication barriers. Therefore, this step introduces a confidence factor mechanism to adjust the total cost function for risk. The confidence of an intersection point is jointly evaluated through multiple dimensions, including terrain elevation difference, path node complexity, and communication barrier scores. The smaller the factor, the worse the operability of the point, which will significantly increase its total cost, reduce its priority, and effectively avoid theoretically feasible but practically unenforceable solutions.

[0097] Furthermore, the specific implementation method of step S7 includes the following steps:

[0098] S7.1. Construct the confidence factor, calculated using the following formula:

[0099]

[0100] in, Confidence factor; The elevation difference between the candidate intersection point and the ground is obtained from GIS data; This represents the maximum difference in elevation between the candidate intersection point and the ground among all candidate points. This is the path complexity index, determined by experts in conjunction with the path itself; This represents the maximum value of the path complexity exponent for all candidate points. The signal obstruction score is determined by experts based on the actual environment. The maximum value of the signal occlusion score corresponding to all candidate points; , , These are the weighting coefficients for elevation difference, path complexity index, and signal obstruction score, respectively, and they also have the function of adjusting the units of measurement.

[0101] S7.2. Risk correction is performed on the comprehensive cost function based on the confidence factor. The calculation formula is as follows:

[0102]

[0103] in, This is the corrected comprehensive cost function. This is the overall cost function.

[0104] S8. For the modified comprehensive cost function obtained in step S7, ground slope angle, wind speed, ground accessibility score, and UAV flight distance factors are introduced for penalty correction, and the optimal coordinates of the air-ground mission intersection point for emergency rescue are extracted.

[0105] In complex environments, only the corrected comprehensive cost value Using the optimal rendezvous point selection criterion as a sole criterion may overlook some key safety and operability factors, such as excessive ground slope, strong winds, or excessive platform flight distance. To improve the robustness of the decision and the feasibility of the project, this step introduces physical quantities for penalty correction, comprehensively determining the optimal rendezvous point coordinates. This method balances optimality and operability, and is suitable for high-uncertainty mission scenarios such as emergency rescue and disaster response.

[0106] Furthermore, the specific implementation method of step S8 includes the following steps:

[0107] S8.1. A penalty correction value is constructed by incorporating ground slope angle, wind speed, ground accessibility score, and UAV flight distance factors. The expression is as follows:

[0108]

[0109] in, This is a penalty correction value. The ground slope angle is obtained from GIS data. The wind speed value is obtained from measurements by a weather sensor. Ground accessibility is scored based on expert experience combined with the route; , Let x and y be the x and y coordinates of the UAV's position at time t, respectively. , These are the x and y coordinates corresponding to the candidate intersection points, respectively; , , , These are the penalty weights corresponding to ground slope angle, wind speed value, ground accessibility score, and drone flight distance, respectively, and they also have the function of adjusting the dimensions.

[0110] S8.2. Optimization is performed based on the penalty correction value combined with the corrected comprehensive cost function to obtain the optimal intersection point:

[0111] Let the set of all candidate intersection points be denoted as: ,in, The set of intersection points of the candidate points; Let i be the coordinates of the i-th intersection point; Let x and y be the coordinates of the i-th intersection point;

[0112] For each candidate point, there is a corresponding corrected comprehensive cost. Penalty Modification Value Accessibility indicators ,

[0113] The optimal intersection point coordinates are determined as follows:

[0114]

[0115] in, Let be the coordinates of the optimal intersection point; argmin represents the input that minimizes the function. The meaning of the formula above is: among all reachable coordinates, The smallest intersection point corresponds to the optimal coordinates. .

[0116] The following is a practical application example of this embodiment:

[0117] The initial position of the drone is set to (0,0), the initial speed is 10m / s, the heading angle is 45 degrees, and the flight altitude is 100m; the initial position of the ground vehicle is (500,100), and the maximum speed is 15m / s.

[0118] There are now 5 candidate intersection points with corresponding coordinates: C1(300,200), C2(350,250), C3(400,300), C4(450,350), C5(500,400).

[0119] The horizontal flight distances of candidate intersection points C1 to C5 from the UAV are 361m, 430m, 500m, 570m, and 640m, respectively.

[0120] The distances from candidate intersection points C1 to C5 to ground vehicles are 224m, 212m, 223m, 255m, and 300m, respectively.

[0121] Using the method in this embodiment, the final evaluation values ​​corresponding to candidate intersection points C1 to C5 can be calculated as 174.2, 197.4, 199.5, 251.8, and 282.7, respectively.

[0122] It should be noted that relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0123] Although this application has been described above with reference to specific embodiments, various modifications can be made and components can be replaced with equivalents without departing from the scope of this application. In particular, as long as there is no structural conflict, the features in the specific embodiments disclosed in this application can be combined with each other in any way. The lack of an exhaustive description of these combinations in this specification is merely for the sake of brevity and resource conservation. Therefore, this application is not limited to the specific embodiments disclosed herein, but includes all technical solutions falling within the scope of the claims.

Claims

1. A method for predicting the intersection point of air-ground missions for emergency rescue, characterized in that, Includes the following steps: S1. UAV Path Prediction: Flight speed, heading angle, external wind speed disturbance and navigation error are set as influencing factors. An integral method is used for modeling to predict the two-dimensional position of the UAV at any time and obtain the UAV path trajectory during the mission execution process. S2. Ground vehicle path prediction: Considering the speed changes caused by vehicle turning behavior in the ground path, the ground path is discretized into multiple road segments, an angle-penalized path model is constructed, and the time required for a vehicle to pass through any road segment is calculated to obtain the ground vehicle path. S3. Candidate Intersection Point Generation: Based on the UAV path predicted in step S1 and the ground vehicle path predicted in step S2, an initial set of candidate intersection points is generated. S4. For the intersection points in the candidate intersection point set obtained in step S3, determine the accessibility of the intersection points through a sliding time window, and proceed to the next step for the candidate intersection points that are determined to meet the accessibility index; S5. Based on the candidate intersection points obtained in step S4, calculate the time cost, flight energy cost, and environmental risk cost of the rescue mission; The specific implementation method of step S5 includes the following steps: S5.

1. For each candidate intersection point, calculate the time required for both the UAV and the ground vehicle to travel from their current locations to the candidate intersection point, and take the maximum value as the time cost of the candidate intersection point. The calculation formula is as follows: ； in, For time cost, , , respectively, represent the time required for the drone and the ground vehicle to reach the candidate intersection point; max is the maximum value function; S5.

2. By modeling the horizontal distance and vertical landing distance of the UAV to the candidate intersection point, a weighted method is used to evaluate the energy consumption cost of the flight. The calculation formula is as follows: ； in, The energy cost of flight; The horizontal unit energy consumption coefficient is obtained from the UAV parameters; The vertical unit energy consumption coefficient is obtained from the UAV parameters; The drone's flight altitude is obtained from the flight control system. The altitude at which the drone and ground vehicle meet is set according to the rescue mission. , These are the x and y coordinates corresponding to the candidate intersection points, respectively; , Let x and y be the x and y coordinates of the UAV's position at time t, respectively. S5.

3. Based on historical wind field data or real-time wind speed sensor information, establish a risk integral model to quantify the environmental risk cost from wind speed change rate, wind direction fluctuation, spatial gradient, and sudden wind energy. The calculation formula is as follows: ； in, Environmental risk costs; The wind speed value is obtained from meteorological sensors. The time window for risk assessment is determined by expert experience; The spatial wind speed gradient is calculated from the wind speed value. This is the wind direction angle, measured by a meteorological sensor; The degree of abrupt change in wind direction is calculated from the wind angle; The sudden wind speed intensity is measured by meteorological sensors; μ0, μ1, μ2, and μ3 are the weighting coefficients for environmental risk, spatial wind speed gradient, degree of wind direction change, and sudden wind speed intensity, respectively, and also serve to adjust the dimensions. S6. A comprehensive cost function is constructed by weighted linear combination of the time cost of the rescue mission, the energy cost of flight, and the environmental risk cost; S7. Construct confidence factors using terrain elevation difference, path node complexity, and communication obstruction scores, and perform risk correction on the comprehensive cost function to obtain the corrected comprehensive cost function; S8. For the modified comprehensive cost function obtained in step S7, ground slope angle, wind speed, ground accessibility score, and UAV flight distance factors are introduced for penalty correction, and the optimal coordinates of the air-ground mission intersection point for emergency rescue are extracted.

2. The method for predicting the intersection point of air-ground missions for emergency rescue according to claim 1, characterized in that, Step S1 yields , Let x and y be the x and y coordinates of the UAV's position at time t, respectively.

3. The method for predicting the intersection point of air-ground missions for emergency rescue according to claim 2, characterized in that, In step S2, the speed adjustment range of the vehicle on the ground path is estimated by analyzing the angle between adjacent road segments, thus obtaining the time required for the ground vehicle to pass through the j-th road segment. The expression is: ； ； in, Let j be the time required for ground vehicles to pass through the j-th road segment; The path length of the j-th segment is obtained from map data; The theoretical speed of ground vehicles is set manually; This is the speed attenuation factor corresponding to the j-th road segment; The specific penalty coefficient is determined by expert experience; , These are the directional angles corresponding to the (j+1)th and jth road segments, respectively, obtained from map data.

4. The method for predicting the intersection point of air-ground missions for emergency rescue according to claim 3, characterized in that, In step S3, based on the path trajectory predicted by the UAV, the positions and arrival times of the UAV and ground vehicles are compared at each time step. The maximum spatial tolerance conditions and the maximum time error conditions for the UAV and ground vehicles are set, and all points that meet the maximum spatial tolerance conditions and the maximum time error conditions for the UAV and ground vehicles are found to form an initial candidate intersection point set.

5. The method for predicting the intersection point of air-ground missions for emergency rescue according to claim 4, characterized in that, In step S4, by using a sliding time window, the relative positional relationship between the UAV and the ground vehicle is compared frame by frame within a certain time range before and after the initial candidate intersection point to determine whether the two can achieve spatial proximity within the error tolerance range for a period of time, thus obtaining the candidate intersection point.

6. The method for predicting the intersection point of air-ground missions for emergency rescue according to claim 5, characterized in that, The specific implementation method of step S7 includes the following steps: S7.

1. Construct the confidence factor, calculated using the following formula: ； in, Confidence factor; The elevation difference between the candidate intersection point and the ground is obtained from GIS data; This represents the maximum difference in elevation between the candidate intersection point and the ground among all candidate points. This is the path complexity index, determined by experts in conjunction with the path itself; This represents the maximum value of the path complexity exponent for all candidate points. The signal obstruction score is determined by experts based on the actual environment. The maximum value of the signal occlusion score corresponding to all candidate points; , , These are the weighting coefficients for elevation difference, path complexity index, and signal obstruction score, respectively, and they also have the function of adjusting the units of measurement. S7.

2. Risk correction is performed on the comprehensive cost function based on the confidence factor. The calculation formula is as follows: ； in, This is the corrected comprehensive cost function. This is the overall cost function.

7. The method for predicting the intersection point of air-ground missions for emergency rescue according to claim 6, characterized in that, The specific implementation method of step S8 includes the following steps: S8.

1. A penalty correction value is constructed by incorporating ground slope angle, wind speed, ground accessibility score, and UAV flight distance factors. The expression is as follows: ； in, This is a penalty correction value. The ground slope angle is obtained from GIS data. The wind speed value is obtained from meteorological sensors. Ground accessibility is scored based on expert experience combined with the route; , Let x and y be the x and y coordinates of the UAV's position at time t, respectively. , These are the x and y coordinates corresponding to the candidate intersection points, respectively; , , , These are the penalty weights corresponding to ground slope angle, wind speed value, ground accessibility score, and drone flight distance, respectively, and they also have the function of adjusting the dimensions. S8.

2. Optimize based on the penalty correction value combined with the corrected comprehensive cost function to obtain the optimal intersection point.

Images