Airport surface aircraft taxiing conflict real-time prediction and dynamic scheduling method and system

Abstract

This invention relates to the field of air traffic management technology, specifically providing a method for real-time prediction and dynamic scheduling of aircraft taxiing conflicts at airports. The method includes: collecting aircraft motion status and airport road network data; generating the original trajectories of aircraft using a Hidden Markov Model; predicting the future taxiing trajectories of aircraft to obtain predicted trajectories; using dynamic R-Tree spatial indexing technology to filter potential conflicting aircraft and determining whether the trajectories of potential conflicting aircraft intersect, generating dynamic risk values; executing dynamic scheduling decisions based on the dynamic risk values ​​and generating aircraft detour paths using a path generation algorithm; and employing rolling time-domain control to replan local paths based on real-time acquired data. This invention fully considers predicting aircraft taxiing trajectories, anticipating the risk value of aircraft taxiing conflicts in advance, and dynamically adjusting paths, which helps reduce labor costs and improve the efficiency and safety of airport ground operations.

Description

Technical Field

[0001] This invention relates to the field of air traffic management technology, and more specifically, to a method and system for real-time prediction and dynamic scheduling of aircraft taxiing conflicts at airports. Background Technology

[0002] With the continuous growth of air traffic, the scale and operational complexity of modern airports have significantly increased, and ground taxiing conflicts have become a key bottleneck restricting operational efficiency and flight safety. Currently, although computer simulation-based airport operational efficiency assessment models are widely used, existing conflict detection technologies still have limitations.

[0003] Trajectory prediction refers to constructing the future taxiing path of an aircraft by integrating real-time status data and historical operational patterns, thereby achieving a priori assessment of conflict risk. Existing technologies for airport surface conflict detection and early warning mainly fall into two categories: one is conflict judgment based on real-time aircraft position data. This method can only identify explicit conflicts that have already occurred, lacking the ability to predict potential conflicts and providing insufficient early warning time for controllers, failing to offer adequate decision-making buffer time. The other is based on historical operational data, using machine learning or mathematical statistics methods to extract common conflict patterns from historical trajectory databases. Analysis methods based on historical data can identify common path conflict patterns through statistical models, but their prediction accuracy is limited when facing real-time dynamic scenarios, and they largely ignore the actual air traffic control situation at airports.

[0004] Most current research lacks the ability to predict taxiing conflicts in real time and replan routes. The vast majority of systems only provide conflict alarms and fail to form a closed loop with dynamic route replanning technology, making it difficult to meet the needs of large hub airports for real-time conflict resolution and proactive scheduling. Summary of the Invention

[0005] In view of this, the present invention proposes a method and system for real-time prediction and dynamic scheduling of aircraft taxiing conflicts at airport surfaces, in order to solve the problems existing in the prior art.

[0006] To achieve the above objectives, this invention proposes a method for real-time prediction and dynamic scheduling of aircraft taxiing conflicts at airport surfaces. This method is characterized by comprising:

[0007] Acquire airport digital road network data, real-time aircraft signals, air traffic control instructions, and flight plan data; perform data preprocessing; and use a hidden Markov model to generate the aircraft's original trajectory.

[0008] Based on the original trajectory, as well as the preprocessed real-time aircraft signals and airport digital road network data, the future taxiing trajectory of the aircraft is predicted to obtain the predicted trajectory.

[0009] Based on the predicted trajectory, dynamic R-Tree spatial indexing technology is used to screen potential conflicting aircraft and determine whether the trajectories of the potential conflicting aircraft intersect, generating dynamic risk values.

[0010] Dynamic scheduling decisions are made based on the dynamic risk values, and aircraft detour paths are generated based on the path generation algorithm.

[0011] Rolling time-domain control is employed to replan local paths based on real-time acquired data.

[0012] Furthermore, the airport digital road network data includes the latitude and longitude, structure, and length of taxiways and runways; the air traffic control instructions include holding instructions and path change instructions; and the flight plan data includes the pre-stored taxi paths for each aircraft.

[0013] Furthermore, the process of generating the aircraft's original trajectory using a Hidden Markov Model includes:

[0014] The deviation distance between the trajectory points and the center lines of each taxiway is input into the Gaussian probability density function to calculate the observation probability of the hidden Markov model; a state transition probability matrix is ​​constructed based on the transition frequency between nodes in the historical trajectory, and the original trajectory points are mapped to the taxiway center lines to generate the corrected trajectory; the corrected trajectory is linearly interpolated to generate the original trajectory.

[0015] Furthermore, the process of predicting the future taxiing trajectory of an aircraft includes:

[0016] When the predicted duration is not greater than the remaining travel time of the current taxiway segment, the trajectory is predicted based on the uniform linear motion model.

[0017] When the predicted duration exceeds the remaining travel time of the current taxiway segment, multiple topologically connected paths are selected for parallel prediction based on the airport road network topology, according to the following priorities: a. pre-stored paths matching the flight plan database, b. paths specified by real-time air traffic control instructions, and c. feasible paths that meet the minimum turning radius of the aircraft. Prediction is stopped when a target runway entrance or target parking stand entrance is detected.

[0018] Based on the prediction results, the trajectories of each aircraft in the future time are aggregated to generate a predicted trajectory.

[0019] Furthermore, the process of screening potential conflict aircraft using dynamic R-Tree spatial indexing technology includes:

[0020] Based on the dynamically expanded R-Tree index, the minimum bounding rectangle is used to cover the future trajectory of the aircraft within the prediction time window;

[0021] If the minimum bounding rectangles of the future trajectories of two aircraft are found to overlap, it is determined that there is a potential conflict between the two aircraft; otherwise, there is no potential conflict.

[0022] The dynamically expanded R-Tree index is constructed in time-sharded chunks, with each chunk updated independently to adapt to dynamic motion.

[0023] Furthermore, in the process of determining whether the trajectories of the potentially conflicting aircraft intersect, if there is an intersection, the absolute value of the time difference between the two aircraft reaching the intersection point is calculated; if there is no intersection, the minimum distance between the two aircraft and the absolute value of the time difference between the two aircraft reaching the closest point on their trajectories are calculated.

[0024] The method for calculating the dynamic risk value is as follows:

[0025]

[0026] Where ΔT is the absolute value of the time difference between the arrival of the two aircraft at the intersection point or the absolute value of the time difference between the arrival of the two aircraft at the closest point on their trajectories; if ΔT = 0, it is directly considered as the highest conflict risk and does not need to be calculated by formula; ΔD min α is the minimum separation distance between the two aircraft; β is the time urgency weight; γ is the distance sensitivity weight; γ is the time decay coefficient, controlling the rate at which ΔT affects the risk; ∈ is the smoothing factor parameter; δ is the fixed risk additive parameter for the intersection scenario; w direction For directional weights.

[0027] Furthermore, the process of making dynamic scheduling decisions based on the dynamic risk value includes:

[0028] Based on the dynamic risk value classification trigger response measures, logs are recorded without intervention in low-risk situations, warnings are pushed to the control tower for manual monitoring in medium-risk situations, and avoidance instructions are automatically generated in high-risk situations, including deceleration instructions or the detour path.

[0029] To determine the priority of aircraft avoidance, if the two aircraft are traveling in the same direction, the aircraft behind should be slowed down or its path adjusted first. Otherwise, the aircraft with the slower speed or heavier load should be slowed down or its path adjusted first. When both aircraft are heavy aircraft, the aircraft on the glide path should be adjusted first.

[0030] Furthermore, the process of generating an aircraft detour path based on the path generation algorithm includes:

[0031] The cost function is calculated based on the combined path length and real-time conflict risk value, and is shown below:

[0032] Total cost f(n) = g(n) + h(n) + μ·R(n)

[0033] Where g(n) is the path cost from the current aircraft position to node n; h(n) is the Manhattan distance from node n to the target node; R(n) is the risk cost from the current aircraft position to node n; μ is the risk weight coefficient; the calculation formulas for R(n) and g(n) are as follows:

[0034]

[0035] Where, Length i Let Risk be the physical length (in meters) of the i-th taxiway segment. i BaseWeight is the dynamic risk value for this taxiway section. i This is the basic weighting coefficient for this taxiway section;

[0036] Based on the calculated total cost, an improved A* algorithm is used to generate a detour path.

[0037] Furthermore, the process of generating detour paths using the improved A* algorithm includes:

[0038] Initialization phase: Load airport road network topology data, define path start point S and target point G; the open list is the set of nodes to be examined, initially containing only the start point, and the closed list is the set of nodes already examined, initially an empty set;

[0039] Path search loop: If the open list is empty, terminate the process and return no solution; otherwise, select the node n with the smallest total generation value f(n) from the open list and move it to the closed list; if the current node n is the target point G, backtrack and output the complete path.

[0040] Neighborhood node expansion and filtering: Generate all adjacent nodes of the current node n; filter out adjacent nodes that do not meet the minimum turning radius constraint of the aircraft; exclude nodes whose taxiway one-way passage direction conflicts with the current movement direction;

[0041] Node state update: If an adjacent node is not in the open or closed list, add it to the open list; if an adjacent node already exists in the open list and the newly calculated f(n) value is better, update its cost value and parent node; then return to the path search loop to continue searching until the target point is found or the open list is exhausted.

[0042] On the other hand, in order to achieve the above objectives, the present invention proposes a real-time prediction and dynamic scheduling system for aircraft taxiing conflicts at airport surfaces, characterized in that it includes a data processing module, a trajectory prediction engine, a conflict detection engine, a dynamic scheduling decision module, and a visualization and alarm terminal.

[0043] The data processing module is used to receive and preprocess data, and to generate the aircraft's original trajectory using a hidden Markov model.

[0044] The trajectory prediction engine is used to predict the future taxiing trajectory of the aircraft based on the original trajectory and preprocessed data, and obtain the predicted trajectory.

[0045] The conflict detection engine is used to filter potential conflicting aircraft using dynamic R-Tree spatial indexing technology, and to determine whether the trajectories of the potential conflicting aircraft intersect, thereby generating dynamic risk values.

[0046] The dynamic scheduling decision module is used to execute dynamic scheduling decisions based on the dynamic risk value and generate aircraft detour paths based on the path generation algorithm.

[0047] The visualization and alarm terminal is used for rendering airport digital road network heat maps, displaying risk levels, and displaying dynamic scheduling decision feedback.

[0048] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0049] This invention provides a real-time prediction and dynamic scheduling method for aircraft taxiing conflicts at airports, including a multimodal trajectory prediction method. By integrating airport digital road network topology, air traffic control instructions, flight plan data and aircraft ADS-B real-time signal data, a Hidden Markov Model (HMM) is used for trajectory probability correction, and multi-path parallel prediction is achieved by combining dynamic taxiing status.

[0050] The airport taxiing conflict real-time detection and early warning method proposed in this invention includes spatiotemporal conflict detection and risk assessment. It uses a dynamic R-Tree spatial index to screen aircraft pairs with potential conflicts and constructs a conflict risk assessment model that integrates spatiotemporal factors (including time difference, minimum interval distance, and direction weight).

[0051] This invention triggers response measures in stages based on the dynamic risk value of aircraft pairs with potential conflicts. In cases where path adjustments are required, an improved A* algorithm and rolling time-domain control (RHC) are used to generate detour paths, and local paths are periodically replanned based on the latest data.

[0052] This invention fully considers predicting aircraft taxiing trajectories, anticipating the risk of taxiing conflicts in advance, and making dynamic path adjustments, which helps reduce labor costs and improve the efficiency and safety of airport ground operations. Attached Figure Description

[0053] Various other advantages and benefits will become apparent to those skilled in the art upon reading the following detailed description of preferred embodiments. The accompanying drawings are for illustrative purposes only and are not intended to limit the invention. In the drawings:

[0054] Figure 1 This is a flowchart illustrating the real-time prediction and dynamic scheduling method for aircraft taxiing conflicts at airport surfaces as described in this invention.

[0055] Figure 2 This is a schematic diagram of the aircraft trajectory before and after trajectory processing in an embodiment of the present invention;

[0056] Figure 3 This is a flowchart of conflict filtering for the R-Tree index in an embodiment of the present invention;

[0057] Figure 4 This is a schematic diagram of the R-Tree layered structure in an embodiment of the present invention;

[0058] Figure 5 This is a schematic diagram of R-Tree time-segmented MBR overlap in an embodiment of the present invention;

[0059] Figure 6 This is a schematic diagram illustrating the specific implementation process of the improved A* algorithm in this embodiment of the invention;

[0060] Figure 7 This is a schematic diagram of the system framework provided in the embodiments of the present invention;

[0061] Figure 8 This is a schematic diagram of the hardware deployment architecture of the system provided in the embodiments of the present invention. Detailed Implementation

[0062] Exemplary embodiments of the present disclosure will now be described in more detail with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be implemented in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided to enable a more thorough understanding of the present disclosure and to fully convey the scope of the disclosure to those skilled in the art. It should be noted that, unless otherwise specified, the embodiments and features described herein can be combined with each other. The present invention will now be described in detail with reference to the accompanying drawings and embodiments.

[0063] This embodiment proposes a real-time prediction and dynamic scheduling method for aircraft taxiing conflicts at airport surfaces, such as... Figure 1 As shown, the specific steps include the following:

[0064] Step 1: Data reception and trajectory processing, acquiring airport digital road network data, air traffic control instructions, flight plan database, and aircraft ADS-B real-time signals, based on a preset acceleration threshold (set to ±3m / s²). 2 Outliers are removed using a heading change threshold (set to ±30° / s), and the original trajectory points are mapped to the taxiway centerline based on a Hidden Markov Model (HMM). The state transition probability matrix of the HMM is obtained by statistically analyzing the transition frequency between nodes in the historical trajectory.

[0065] Step 2: Real-time prediction of taxiing trajectory. Based on the processed aircraft motion status data and the airport's digital road network topology, the aircraft's taxiing trajectory within the future time window is predicted for two cases: the prediction time is less than the remaining passage time of the current taxiway segment and the prediction time is greater than or equal to the remaining passage time.

[0066] Step 3: Spatiotemporal conflict detection and risk assessment. Based on the predicted aircraft trajectory, aircraft pairs with potential conflicts are screened through dynamic R-Tree spatial indexing technology. The future trajectory intersection point or the closest point of the trajectory of the aircraft pair is calculated. Combined with time difference, minimum interval distance and motion direction weight, a dynamic risk value is generated.

[0067] Step 4: Dynamic scheduling decision-making, based on the dynamic risk value of aircraft pairs with potential conflicts, triggering response measures according to the preset three-level risk value threshold.

[0068] The aforementioned data reception and trajectory processing specifically include:

[0069] Step 1-1: Obtain airport digital road network data, including the latitude, longitude, structure, and length of taxiways and runways; air traffic control instructions, including holding instructions and route changes (taxiway switching, runway reallocation, and parking position adjustment instructions); and flight plan database, including pre-stored and taxi routes for each aircraft.

[0070] Steps 1-2: Receive real-time ADS-B signals from the aircraft, including position, speed, and heading angle, and remove outliers based on preset acceleration thresholds and heading change thresholds;

[0071] Steps 1-3: Using the taxiway node set S = {s1, s2, s3, ..., s n The Hidden Markov Model (HMM) in the state space is used to map the original trajectory points to the taxiway centerlines. The observation probability of the HMM is calculated by inputting the deviation distance between the trajectory points and the centerlines of each taxiway into a Gaussian probability density function. Where d is the deviation distance, the mean μ is set to 0 (ideal centerline), σ reflects the tolerance of actual deviation, and can be set to 2m; the state transition probability matrix A = [aij This is obtained by statistically analyzing the frequency of transitions between nodes in historical trajectories.

[0072]

[0073] Where N i→j This indicates that the historical data is from node s i Transfer to node s j The number of times;

[0074] Steps 1-4: Perform linear interpolation on the corrected trajectory data (e.g., generate an interpolation point every 0.5 seconds) to improve the accuracy of the trajectory data.

[0075] Figure 2 The diagram shows the aircraft's trajectory before and after trajectory processing.

[0076] The aforementioned real-time prediction of the gliding trajectory specifically includes:

[0077] Step 2-1: Trajectory prediction based on dynamic gliding state, with a prediction duration of 40 seconds:

[0078] ① When the prediction duration t ≤ the remaining travel time on the current taxiway segment, the trajectory is predicted based on the uniform linear motion model. Assuming the aircraft maintains uniform linear motion during the taxiing phase, the formula for calculating its future position is:

[0079]

[0080] Where (x0, y0) are the current coordinates of the aircraft, v is the minimum value between the aircraft's real-time speed and the taxiway speed limit, θ is the heading angle (relative to due north), and t is the future time (seconds).

[0081] ② When the prediction duration t > the remaining travel time of the current taxiway segment, based on the airport road network topology, multiple topologically connected paths are selected for parallel prediction according to the following priorities: a. pre-stored paths matching the flight plan database, b. paths specified by real-time air traffic control instructions, and c. feasible paths that meet the minimum turning radius of the aircraft.

[0082] ③ Stop distance prediction when the target runway entrance or target parking stand entrance is detected;

[0083] Step 2-2: Construct a set of trajectory time slices, which includes the trajectory of each aircraft in the future time t (t = 40s).

[0084] The spatiotemporal conflict detection and risk assessment specifically includes the following steps:

[0085] Step 3-1: Potential Conflict Screening: Use dynamic R-Tree spatial indexing technology to quickly screen aircraft pairs with potential conflicts, and process trajectory data in batches by time slices;

[0086] Step 3-2: Conflict detection technology: Traverse the filtered aircraft pairs with potential conflicts, and solve whether the predicted trajectories of the two aircraft in each pair at the future time t intersect. If the trajectories intersect, calculate the absolute value of the time difference between the two aircraft reaching the intersection point. If the trajectories do not intersect, calculate the minimum distance between the two aircraft and the absolute value of the time difference between the two aircraft reaching the closest point on the trajectory.

[0087] Step 3-3: Conflict Risk Assessment: Based on the future trajectory intersection point or the closest point of the trajectory of the aircraft pair, combined with the time difference, minimum interval distance and motion direction weight, a dynamic risk value is generated to quantify the risk level.

[0088] Figure 3 The R-Tree conflict screening flowchart is shown, and the potential conflict screening is specifically as follows:

[0089] First, input the time-sliced ​​set of trajectory based on the aircraft's predicted trajectory obtained in step 2. Then, generate minimum bounding rectangles (MBRs) from the slices. The minimum bounding rectangles (MBRs) indexed by the R-Tree cover the future trajectories within the aircraft's predicted time window, and construct a hierarchical R-Tree ( Figure 4 The diagram shows the R-Tree hierarchical structure. Then, overlap detection is performed. If the R-Tree index detects that the minimum bounding rectangles (MBRs) of the future trajectories of two aircraft overlap, then there is a potential conflict between the aircraft pair; otherwise, there is no potential conflict. Figure 5 The diagram shows the overlap of time-sliced ​​MBRs in the R-Tree diagram. The MBRs formed by the predicted trajectories of the two aircraft have overlapping areas, indicating that there is a potential conflict between the two aircraft. Finally, the output shows the aircraft pairs with potential conflicts.

[0090] The spatial indexing technology is a dynamically expanding R-Tree index, which is updated every 2 seconds. A forced update is triggered when the aircraft speed changes by more than ±10% or the heading changes by more than ±5°.

[0091] The aforementioned conflict risk assessment specifically includes:

[0092] The formula for calculating dynamic risk value is:

[0093]

[0094] Where ΔT is the absolute value of the time difference between the arrival points of the two aircraft (trajectory intersection) or the absolute value of the time difference between the arrival points of the two aircraft (trajectory non-intersection); if ΔT = 0, it is directly considered as the highest risk and does not need to be calculated by formula; ΔD min α is the minimum separation distance between the two aircraft; α is the time urgency weight, which is 1.0 in this example; β is the distance sensitivity weight, which is 1.5 in this example; γ is the time decay coefficient, which is 0.1 in this example, controlling the rate at which ΔT affects the risk; ∈ is the smoothing factor parameter, preventing ΔD min →0 indicates numerical overflow, and in this example, the value is 0.5; δ is a fixed risk bonus parameter for intersection scenarios, and in this example, the value is 0.3; w direction The directional weight is set in segments according to the heading angle θ: in the example, it is set to 0.2 when in the same direction (θ<30°), 1.0 when crossing (30°≤θ<150°), and 1.5 when in opposite directions (θ≥150°).

[0095] For example, a potential collision is detected between aircraft A and aircraft B. Aircraft A has a speed of 15 m / s and a heading of 30°, while aircraft B has a speed of 10 m / s and a heading of 210°. Their predicted trajectories intersect at point X on taxiway. Calculate intermediate quantities:

[0096] ΔT = |(Time from A to X) - (Time from B to X)| = |80s - 120s| = 40s

[0097] ΔD min =25m (the closest distance between the tracks of the two aircraft)

[0098] θ = |210° - 30°| = 180° → w direction =1.5 (opposite direction)

[0099] The final calculated risk value is 0.67.

[0100] The dynamic scheduling decision specifically includes:

[0101] Step 4-1: Based on the dynamic risk values ​​of aircraft pairs with potential conflicts, trigger response measures in a tiered manner. In low-risk situations (Risk < 0.3), log entries are made without intervention. In medium-risk situations (0.3 ≤ Risk < 0.7), a warning is sent to the control tower for manual monitoring. In high-risk situations (Risk ≥ 0.7), avoidance instructions are automatically generated, including deceleration instructions or detour paths generated based on path generation algorithms. Table 1 shows the risk level determination comparison table for this embodiment.

[0102] Table 1

[0103] Risk value range Risk level Response measures [0,0.3) Low risk Log the information, do not interfere. [0.3,0.7) Medium risk Send a yellow alert to the control tower ≥0.7 High risk Automatically generate deceleration / path modification instructions

[0104] According to Table 1, the risk value of aircraft A and aircraft B is 0.67, and a yellow warning should be sent to the control tower.

[0105] Step 4-2: Determine the priority of aircraft avoidance. If the two aircraft are traveling in the same direction, prioritize slowing down or adjusting the path of the aircraft behind. Otherwise, prioritize slowing down or adjusting the path of the aircraft with slower speed or heavier load. When both aircraft are heavy aircraft, prioritize adjusting the glide path of the aircraft.

[0106] The path generation algorithm uses an improved A* algorithm. Figure 6 The specific implementation process of the improved A* algorithm is demonstrated, including:

[0107] Initialization phase: Load airport road network topology data, define path start point S and target point G; the open list is the set of nodes to be examined, initially containing only the start point, and the closed list is the set of nodes already examined, initially an empty set;

[0108] Path search loop: If the open list is empty, terminate the process and return no solution; otherwise, select the node n with the smallest comprehensive cost function value f(n) from the open list and move it to the closed list; if the current node n is the target point G, backtrack and output the complete path.

[0109] Neighborhood node expansion and filtering: Generate all adjacent nodes of the current node n; filter out adjacent nodes that do not meet the minimum turning radius constraint of the aircraft; exclude nodes whose taxiway one-way passage direction conflicts with the current movement direction;

[0110] The cost function combines path length and real-time conflict risk; the formula for the combined cost function is:

[0111] Total cost f(n) = g(n) + h(n) + μ·R(n)

[0112] Where h(n) is the Manhattan distance from node n to the target node; R(n) is the risk cost from the current aircraft position to node n; g(n) is the path cost from the current aircraft position to node n; μ is the risk weight coefficient, which is dynamically adjusted according to the airport's operational status. In this embodiment, it is set to 1.2 during peak hours (when the airport's takeoff and landing frequency is >40 flights / hour), 0.8 during off-peak hours, and 2.0 in emergency mode (e.g., low visibility (<800m) or runway emergency events); the calculation formulas for R(n) and g(n) are as follows:

[0113]

[0114] Length i Let Risk be the physical length (in meters) of the i-th taxiway segment. iThe BaseWeight is the real-time risk value for this taxiway segment, provided in real-time by the conflict risk assessment method. i The basic weighting coefficients for this taxiway segment are set as follows in the embodiment: 1.0 for the apron, 1.2 for the taxiway, and 1.5 for the runway, according to the regional importance classification.

[0115] Node state update: If an adjacent node is not in the open list or closed list, add it to the open list; if an adjacent node already exists in the open list and the newly calculated f(n) value is better, update its cost value and parent node; then return to the path search loop to continue searching until the target point is found or the open list is exhausted.

[0116] The path generation algorithm integrates Rolling Time Control (RHC), which periodically replans local paths based on the latest data. The replanning period of the Rolling Time Control is adjustable from 5 to 30 seconds.

[0117] In this embodiment, during peak hours, the planned path of aircraft C conflicts with that of aircraft D (Risk = 0.8). C is currently located on taxiway S1, with its target parking position G. The candidate paths for aircraft C and their costs are as follows:

[0118] Candidate node 1: S1→S2 (length 200m, Risk = 0.8)

[0119] The cost is f(n) = 200 × 1.2 + 350 + 0.8 × 200 = 750

[0120] Candidate node 2: S1→S3 (length 240m, Risk=0),

[0121] The cost is f(n) = 240 × 1.2 + 390 = 678

[0122] Although S2 is shorter, it poses a risk of conflict. Therefore, aircraft C ultimately chose to travel from node S1 to node S3, thus achieving intersection avoidance during peak hours.

[0123] like Figure 7 , Figure 8 As shown, this embodiment provides a real-time prediction and dynamic scheduling system for aircraft taxiing conflicts at airport surfaces, used to implement the aforementioned real-time prediction and dynamic scheduling method for aircraft taxiing conflicts at airport surfaces, including the following modules:

[0124] Module 1: Data Processing Module. Loads airport taxiway configuration data, receives and parses multi-source data streams in real time, including aircraft ADS-B data (aircraft position, speed, heading angle), extracts motion status, performs trajectory map matching, air traffic control instruction data (holding area allocation, taxiway closure status), and outputs a standardized motion status dataset.

[0125] Module 2: Trajectory Prediction Engine, which performs real-time trajectory prediction based on motion state data and generates the gliding trajectory within the next time interval t.

[0126] Module 3: Conflict Detection Engine, including a dynamic spatial indexing unit that filters aircraft pairs with overlapping trajectory bounding boxes based on a dynamic R-Tree index. The dynamic R-Tree index is implemented through GPU parallel computing, with a single full update taking less than 50ms. A risk calculation unit is configured to calculate the time difference (ΔT) and minimum clearance distance (ΔD) for the filtered aircraft pairs. min and dynamic risk value (Risk);

[0127] Module 4: Dynamic scheduling decision module, including a graded response unit that triggers a three-level response (log recording / tower alarm / automatic avoidance instruction) based on the risk level and risk value; and an instruction issuance unit that issues instructions to the pilot or tower terminal via data link. The avoidance instruction requires secondary confirmation from the controller before it can be sent to the aircraft. The confirmation timeout is a configurable parameter, set to 5 seconds. After the timeout, a voice prompt will prompt manual handling.

[0128] Module 5: Visualization and Alarm Terminal, which aggregates risk values ​​by taxiway node and displays conflict heatmaps, risk levels, and scheduling instructions in real time.

[0129] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit it. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that modifications or equivalent substitutions can still be made to the specific implementation of the present invention. Any modifications or equivalent substitutions that do not depart from the spirit and scope of the present invention should be covered within the scope of protection of the claims of the present invention.

Claims

1. A method for real-time prediction and dynamic scheduling of aircraft taxiing conflicts at an airport surface, characterized in that, include: Acquire airport digital road network data, real-time aircraft signals, air traffic control instructions, and flight plan data; perform data preprocessing; and use a hidden Markov model to generate the aircraft's original trajectory. Based on the original trajectory, as well as the preprocessed real-time aircraft signals and airport digital road network data, the future taxiing trajectory of the aircraft is predicted to obtain the predicted trajectory. Based on the predicted trajectory, dynamic R-Tree spatial indexing technology is used to screen potential conflicting aircraft and determine whether the trajectories of the potential conflicting aircraft intersect, generating dynamic risk values. Dynamic scheduling decisions are made based on the dynamic risk values, and aircraft detour paths are generated based on the path generation algorithm. Rolling time-domain control is employed to replan local paths based on real-time acquired data; In determining whether the trajectories of the potentially conflicting aircraft intersect, if they do intersect, the absolute value of the time difference between the arrival of the two aircraft at the intersection point is calculated; if they do not intersect, the minimum distance between the two aircraft and the absolute value of the time difference between the arrival of the two aircraft at the closest point on their trajectories are calculated. The method for calculating the dynamic risk value is as follows: ， in, This is the absolute value of the time difference between the arrival of the two aircraft at the intersection point or the absolute value of the time difference between the arrival of the two aircraft at the closest point on their trajectories; if If it is, then it is directly regarded as the highest risk of conflict, and there is no need to calculate it using a formula; This is the minimum clearance between two aircraft. Weighted by time urgency; Distance-sensitive weights; The time decay coefficient is used to control... Rate of impact on risk; For smoothing factor parameters; Fixed risk-additional parameters for intersection scenarios; This represents the directional weight.

2. The method for real-time prediction and dynamic scheduling of aircraft taxiing conflicts at airport surfaces according to claim 1, characterized in that, The airport digital road network data includes the latitude, longitude, structure, and length of taxiways and runways; the air traffic control instructions include holding instructions and path change instructions; and the flight plan data includes the pre-stored taxi paths for each aircraft.

3. The method for real-time prediction and dynamic scheduling of aircraft taxiing conflicts at airport surfaces according to claim 1, characterized in that, The process of generating the aircraft's original trajectory using a Hidden Markov Model includes: The deviation distance between the trajectory points and the center lines of each taxiway is input into the Gaussian probability density function to calculate the observation probability of the hidden Markov model; a state transition probability matrix is ​​constructed based on the transition frequency between nodes in the historical trajectory, and the original trajectory points are mapped to the taxiway center lines to generate the corrected trajectory; the corrected trajectory is linearly interpolated to generate the original trajectory.

4. The method for real-time prediction and dynamic scheduling of aircraft taxiing conflicts at airport surfaces according to claim 1, characterized in that, The process of predicting the future taxiing trajectory of an aircraft includes: When the predicted duration is not greater than the remaining travel time of the current taxiway segment, the trajectory is predicted based on the uniform linear motion model. When the predicted duration exceeds the remaining travel time of the current taxiway segment, multiple topologically connected paths are selected for parallel prediction based on the airport road network topology, according to the following priorities: a. pre-stored paths matching the flight plan database, b. paths specified by real-time air traffic control instructions, and c. feasible paths that meet the minimum turning radius of the aircraft. Prediction is stopped when a target runway entrance or target parking stand entrance is detected. Based on the prediction results, the trajectories of each aircraft in the future time are aggregated to generate a predicted trajectory.

5. The method for real-time prediction and dynamic scheduling of aircraft taxiing conflicts at airport surfaces according to claim 1, characterized in that, The process of screening potential conflict aircraft using dynamic R-Tree spatial indexing technology includes: Based on the dynamically expanded R-Tree index, the minimum bounding rectangle is used to cover the future trajectory of the aircraft within the prediction time window; If the minimum bounding rectangles of the future trajectories of two aircraft are found to overlap, it is determined that there is a potential conflict between the two aircraft; otherwise, there is no potential conflict. The dynamically expanded R-Tree index is constructed in time-sharded chunks, with each chunk updated independently to adapt to dynamic motion.

6. The method for real-time prediction and dynamic scheduling of aircraft taxiing conflicts at airport surfaces according to claim 1, characterized in that, The process of making dynamic scheduling decisions based on the dynamic risk value includes: Based on the dynamic risk value classification trigger response measures, logs are recorded without intervention in low-risk situations, warnings are pushed to the control tower for manual monitoring in medium-risk situations, and avoidance instructions are automatically generated in high-risk situations, including deceleration instructions or the detour path. To determine the priority of aircraft avoidance, if the two aircraft are traveling in the same direction, the aircraft behind should be slowed down or its path adjusted first. Otherwise, the aircraft with the slower speed or heavier load should be slowed down or its path adjusted first. When both aircraft are heavy aircraft, the aircraft on the glide path should be adjusted first.

7. The method for real-time prediction and dynamic scheduling of aircraft taxiing conflicts at airport surfaces according to claim 1, characterized in that, The process of generating an aircraft detour path based on a path generation algorithm includes: The cost function is calculated based on the combined path length and real-time conflict risk value, and is shown below: ， in, The path cost from the current aircraft position to node n; Let n be the Manhattan distance from node n to the target node; The risk cost of the current aircraft position to node n; This refers to the risk weighting coefficient. and The calculation formula is as follows: ， ， in, Let be the physical length (in meters) of the i-th taxiway segment. This represents the dynamic risk value for this taxiway section. This is the basic weighting coefficient for this taxiway section; Based on the calculated total cost, an improved A* algorithm is used to generate a detour path.

8. The method for real-time prediction and dynamic scheduling of aircraft taxiing conflicts at airport surfaces according to claim 7, characterized in that, The process of generating detour paths using the improved A* algorithm includes: Initialization phase: Load airport road network topology data, define path start point S and target point G; the open list is the set of nodes to be examined, initially containing only the start point, and the closed list is the set of nodes already examined, initially an empty set; Path search loop: If the open list is empty, terminate the process and return "no solution"; otherwise, select the total agent value from the open list. The smallest node n is moved to the closed list; if the current node n is the target point G, backtrack and output the complete path. Neighborhood node expansion and filtering: Generate all adjacent nodes of the current node n; filter out adjacent nodes that do not meet the minimum turning radius constraint of the aircraft; exclude nodes whose taxiway one-way passage direction conflicts with the current movement direction; Node status update: If a neighboring node is not in the open or closed list, add it to the open list; if a neighboring node already exists in the open list, and the newly calculated state is... If the value is better, update its value and parent node; then return to the path search loop to continue searching until the target point is found or the open list is exhausted.

9. A real-time prediction and dynamic scheduling system for aircraft taxiing conflicts at airport surfaces based on the method of any one of claims 1-8, characterized in that, It includes a data processing module, a trajectory prediction engine, a conflict detection engine, a dynamic scheduling decision module, and a visualization and alarm terminal; The data processing module is used to receive and preprocess data, and to generate the aircraft's original trajectory using a hidden Markov model. The trajectory prediction engine is used to predict the future taxiing trajectory of the aircraft based on the original trajectory and preprocessed data, and obtain the predicted trajectory. The conflict detection engine is used to filter potential conflicting aircraft using dynamic R-Tree spatial indexing technology, and to determine whether the trajectories of the potential conflicting aircraft intersect, thereby generating dynamic risk values. The dynamic scheduling decision module is used to execute dynamic scheduling decisions based on the dynamic risk value and generate aircraft detour paths based on the path generation algorithm. The visualization and alarm terminal is used for rendering airport digital road network heat maps, displaying risk levels, and displaying dynamic scheduling decision feedback.

Images