Airport scene unmanned guide vehicle cluster commanding and dispatching system and method

Abstract

The invention discloses an airport scene unmanned guide vehicle cluster command and dispatch system and method, and belongs to the technical field of airport scene operation management, and the system comprises the steps that a data support system obtains multi-source data related to airport scene operation; the trajectory collaborative planning system generates an airport scene conflict-free guide trajectory based on the multi-source data; the scheduling decision execution system is used for matching unmanned guide vehicle team resources and guide tasks based on airport scene conflict-free guide tracks, distributing tasks to unmanned guide vehicles and transmitting scheduling instructions; the unmanned guiding vehicle team management system calls the guiding vehicle to execute a sliding guiding task according to the scheduling instruction, and feeds back the position, the speed, the electric quantity and the task execution state of the unmanned vehicle to the data support system; the airport control seat interactively senses the operation situation of the aircraft and the unmanned vehicle, and intervenes in emergency command when necessary. According to the system, intelligent scheduling and cooperative operation of the unmanned guided vehicle cluster are realized, and the airport scene management efficiency is improved.

Description

Technical Field

[0001] This application relates to the field of airport surface operation management technology, and in particular to an airport surface unmanned guided vehicle cluster command and dispatch system and method. Background Technology

[0002] Currently, aircraft guidance at airports primarily relies on manually driven guidance vehicles, with drivers performing taxiing guidance tasks according to air traffic control instructions. This model has the following shortcomings: 1) High human resource costs, and susceptibility to potential safety accidents caused by factors such as driver fatigue and visibility; 2) Manual command and dispatch during guidance vehicle operations rely on experience-based judgment, making it difficult to achieve multi-vehicle collaborative optimization, easily leading to high empty vehicle rates and untimely responses, especially during peak hours when dispatch efficiency cannot match guidance demand; 3) Manual command and dispatch during guidance vehicle operations rely on voice commands, lacking a precise dynamic trajectory coordination mechanism during interactions with other aircraft, posing safety hazards related to surface conflicts, and failing to achieve optimal global efficiency based on real-time surface traffic data.

[0003] With the development of autonomous driving technology, airports both domestically and internationally have begun to explore the application of unmanned guidance vehicles. However, existing unmanned scheduling systems still have the following shortcomings: First, insufficient accuracy in conflict prediction: Existing trajectory planning models mostly rely on simplified preset rules and do not accurately quantify the dynamic interaction between the guidance vehicle and the aircraft (such as the following distance during taxiing guidance), resulting in inaccurate prediction of spatiotemporal occupancy conflicts and low conflict resolution efficiency during large-scale scheduling; Second, limitations in scheduling scale and real-time performance: Traditional optimization algorithms (such as particle swarm optimization and simulated annealing) converge slowly in large-scale scenarios at large airports and are difficult to support dynamic adjustments in the rolling time domain, failing to meet the real-time scheduling needs of high-density airports; Third, lack of resource coordination mechanisms: Insufficient consideration of aircraft taxiing timing constraints, guidance vehicle power management, and balanced task allocation leads to insufficient fairness in vehicle assignment, with some vehicles overloaded while others are idle, reducing system robustness; Fourth, insufficient depth of data fusion: Failure to deeply integrate airport control and airport operation control related business data results in a disconnect between scheduling decisions and the actual needs of aircraft taxiing guidance.

[0004] Overall, while some airports worldwide have launched pilot projects, these are mostly limited to the verification and operation of single-vehicle autonomous driving technology, failing to provide systems and methods for scheduling and commanding autonomous guidance vehicle clusters. Domestic research has also focused on ensuring vehicle path planning, lacking systematic solutions for multi-vehicle cluster scheduling of guidance vehicles, especially for the command and dispatch of autonomous guidance vehicles during aircraft taxiing. This hinders the realization of unmanned airfield operations and guidance scenarios. Therefore, it is necessary to develop an integrated command and dispatch system for autonomous guidance vehicles, providing conflict prediction and efficient scheduling algorithms for guidance vehicle clusters to improve the safety and efficiency of unmanned guidance operations at airports. Summary of the Invention

[0005] To address the aforementioned shortcomings in the existing technology, this application provides an airport surface unmanned guidance vehicle cluster command and dispatch system and method, which solves the problems of the lack of an intelligent dispatch platform for unmanned guidance vehicle clusters in the guidance vehicle operation management department, as well as the deficiencies in surface monitoring data fusion and utilization, collaborative management and control of unmanned guidance vehicle fleet resources, high-precision conflict prediction, and large-scale dispatch optimization.

[0006] To achieve the aforementioned objectives, the technical solution adopted in this application is as follows: First aspect: This application provides an airport surface unmanned guided vehicle cluster command and dispatch system, including: a data support system, a trajectory collaborative planning system, a dispatch decision execution system, an unmanned guided vehicle fleet management system, and airport control positions; The data support system acquires multi-source data related to airport surface operations from external sources. The trajectory collaborative planning system generates conflict-free guidance trajectories for the airport surface based on multi-source data. The scheduling decision execution system, based on the airport surface conflict-free guidance trajectory, completes the matching of unmanned guided vehicle fleet resources and guidance tasks, dispatches guidance tasks to the unmanned guided vehicle fleet, generates scheduling instructions for the unmanned guided vehicle fleet, and transmits the scheduling instructions to the unmanned guided vehicle fleet management system. The unmanned guided vehicle fleet management system dispatches unmanned guided vehicles to perform taxiing guidance tasks according to the planned path based on the dispatch instructions, and feeds back the unmanned vehicle's position, speed, battery level, and task execution status to the data support system through the aviation network; The airport control station interacts with the data support system to perceive the operational status of aircraft and unmanned guided vehicles on the airport surface, and allows controllers to intervene and enter emergency command as needed.

[0007] Furthermore, the data support system includes: an airport collaborative decision-making system, an advanced surface surveillance, guidance and control system, and an unmanned vehicle status monitoring system; The airport collaborative decision-making system acquires flight dynamic data; The advanced surface monitoring, guidance and control system acquires airport surface topology network, taxiing guidance path and node, and operation time node information; The unmanned vehicle status monitoring system acquires the motion status information of the unmanned guide vehicle.

[0008] Furthermore, the trajectory collaborative planning system includes a spatiotemporal occupancy conflict prediction module, a scene-guided trajectory deduction module, and a swarm intelligence algorithm optimization module; The spatiotemporal occupancy conflict prediction module, based on the airport surface topology network and operational rules, quantifies the spatiotemporal occupancy status of the guidance vehicle-aircraft coupling unit. It includes a design protection zone modeling submodule, a design conflict prediction submodule, and a design conflict frequency statistics submodule. The design protection zone modeling submodule considers the protection zone parameters generated by the guidance unit size and movement speed to construct a dynamic geometric protection zone model. The design conflict prediction submodule predicts the spatial overlap between protection zones. The design conflict frequency statistics submodule establishes a spatiotemporal occupancy conflict database, records the frequency of conflict occurrences at each node on the surface, and generates a conflict distribution heatmap. The surface guidance trajectory derivation module generates speed profiles and spatiotemporal trajectories, including a design path analysis submodule, a design turning trajectory optimization submodule, a design following distance calculation submodule, and a design speed profile generation submodule. The design path analysis submodule analyzes the airport surface topology network and taxiing guidance path nodes obtained by the Advanced Surface Monitoring, Guidance and Control System (ASMS). The design turning trajectory optimization submodule performs trajectory smoothing and timestamp correction on turning points in the airport surface topology network and taxiing guidance path nodes obtained by ASMS. The design following distance calculation submodule calculates the safe following distance between the unmanned guided vehicle and the aircraft. The design speed profile generation submodule generates speed curves for each road segment based on vehicle dynamics parameters. The swarm intelligence algorithm optimization module generates a conflict-free guidance trajectory for the airport surface based on the spatiotemporal occupancy status, velocity profile, and spatiotemporal trajectory of the guidance vehicle-aircraft coupling unit. It includes a design coding strategy submodule, a design fitness function construction submodule, and a design optimization engine submodule. The design coding strategy submodule uses an integer coding strategy to handle path selection and departure time variables. The design fitness function construction submodule integrates the number of conflicts and total working time to construct a fitness function. The design optimization engine submodule executes an iterative optimization process based on the swarm intelligence optimization algorithm.

[0009] Furthermore, the scheduling decision execution system includes a vehicle assignment module, a vehicle scheduling module, and an instruction issuance module; The vehicle assignment module, based on the conflict-free guidance trajectory of the airport surface, matches guidance tasks with vehicles. It includes a time window conflict detection submodule, a power management submodule, and a fairness optimization submodule. The time window conflict detection submodule detects and avoids overlapping time windows of the same vehicle's guidance task and charging task. The power management submodule monitors the real-time power status of vehicles and dynamically plans charging windows to ensure vehicle range safety. The fairness optimization submodule aims to minimize the vehicle working time imbalance index and establishes a guidance task-vehicle pairing model to ensure that guidance tasks are evenly distributed among vehicles. The vehicle dispatching module generates dispatching instructions for the unmanned guided vehicle fleet based on the airport surface taxiing guidance requirements and the matching of guidance tasks and vehicles. This includes a vehicle resource integration submodule, an emergency re-dispatch submodule, and a redundant resource management submodule. The vehicle resource integration submodule integrates optimized vehicle assignment and trajectory planning schemes into executable dispatching instructions. The emergency re-dispatch submodule, in conjunction with airport control, performs re-dispatch for unexpected scenarios, enabling takeover in emergency situations. The redundant resource management submodule maintains a backup vehicle resource pool to ensure system robustness. The instruction issuing module transmits the dispatch instructions of the unmanned guided vehicle fleet to the unmanned vehicle fleet guidance system through aviation telecommunications technology.

[0010] Furthermore, the unmanned guided fleet management system includes a scheduling management module and an operation status feedback module; The scheduling management module receives trajectory control instructions from the scheduling decision execution system and drives the unmanned guided vehicle to perform gliding guidance tasks according to the planned path; The operational status feedback module feeds back the unmanned vehicle's location, speed, battery level, and mission execution status to the data support system via the aviation network.

[0011] Furthermore, the airport control position includes airport surface surveillance equipment and airport control communication equipment; The airport surface surveillance equipment integrates surface surveillance radar and a multi-point positioning system, interacts with the advanced surface surveillance guidance and control system of the data support system, and senses the operational status of airport surface aircraft and unmanned guided vehicles. The airport control communication equipment supports controllers to intervene in the dispatch system and enable manual intervention in emergency situations via voice or data commands.

[0012] The second aspect: This application provides a method for commanding and dispatching a cluster of unmanned guided vehicles on the airport surface, including: S1: Acquire and integrate externally sourced airport multi-source data, including flight dynamic data, airport surface topology network, taxiway guidance path nodes, operation time node information, and motion status information of unmanned guidance vehicles; S2: Generate conflict-free guidance trajectories for the airport surface based on multi-source airport data; S3: Generate dispatch instructions for unmanned guided convoys based on the conflict-free guidance trajectory of the airport surface; S4: Based on the dispatch instructions of the autonomous driving guidance vehicle fleet, the autonomous driving guidance vehicle is mobilized to perform the gliding guidance task according to the planned path, and the autonomous vehicle's position, speed, battery level and task execution status are reported back.

[0013] Furthermore, the generation of conflict-free guidance trajectories on the airport surface based on multi-source airport data includes: S201: Based on multi-source airport data, and according to the airport surface topology network and operating rules, quantify the spatiotemporal occupancy status of the guidance vehicle-aircraft coupling unit; S202: Generate velocity profiles and spatiotemporal trajectories based on the airport surface topology network and taxiing guidance path nodes; S203: Generate a conflict-free guidance trajectory for the airport surface based on the spatiotemporal occupancy status, velocity profile, and spatiotemporal trajectory of the guidance vehicle-aircraft coupling unit.

[0014] Furthermore, the generation of velocity profiles and spatiotemporal trajectories based on the airport surface topology network and taxiway guidance path nodes includes: A1: The current path node set included in the motion state information of the gliding guidance path nodes and the autonomous guided vehicle. Two adjacent nodes on the current path and Spacing A set consisting of speed limits at each node and vehicle acceleration and deceleration ,like According to the formula For nodes Each upstream node Calculate the boot path number The required speed of each node If yes, proceed to A2; otherwise, proceed to A3, where... To represent the first step of the bootstrap path The x and y coordinates of each node, For guiding path number Speed ​​limits on each node For guiding path number Speed ​​limits on each node To accelerate the guide car, Indicates the last node in the bootstrap path; A2: If each upstream node satisfies Then let If A4 is not selected, proceed to A4; otherwise, proceed to A3, where... For guiding path number Speed ​​limits on each node; A3: If Then let And proceed to A4; otherwise, set Enter A1, where, Indicates the guiding path node The previous node, Indicates the first One node; A4: If Then calculate and Otherwise, proceed to A5, where the calculation formula is:

[0015] in, and The first step is the guide path calculated using the formula. , The actual speed at which each node passes through the point. Indicates the path from the first The node to the first The distance to each node, and The activity objectives are guided through the following paths: , The moment of each node; A5: If Greater than the calculation formula The obtained guiding path starts from the first The node to the first The distance traveled during the speed adjustment process of each node Then let and calculate and Enter A6, the calculation formula is:

[0016] Otherwise, calculate according to the following formula and Enter A6, the calculation formula is:

[0017] A6: If Output the set of velocity profiles corresponding to each guide trajectory. ,in, For the first Velocity profile of each node; otherwise, let , then move to A4.

[0018] Furthermore, the aforementioned airport surface unmanned guided vehicle cluster command and dispatch method also includes: In response to emergencies, a new dispatch system is implemented, and emergency command is activated.

[0019] The beneficial effects of this application are: This application provides an airport surface unmanned guided vehicle cluster command and dispatch system and method, which integrates multi-source data related to airport surface operations from multiple sources to form a dynamic airport surface operation scenario. This facilitates airport control departments in conducting command and dispatch of automated unmanned guided vehicles during taxiing guidance. It transforms manual command and dispatch, which relies solely on the individual experience of airport controllers, into a command system based on swarm intelligence that assists airport control positions in making decisions. This helps to fully utilize the data generated during airport control and airport operation control processes, thereby improving the safety and efficiency of airport surface taxiing guidance processes and their automation. Attached Figure Description

[0020] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other embodiments can be obtained based on these drawings.

[0021] Figure 1 This is a schematic diagram of the structure of an airport surface unmanned guidance vehicle cluster command and dispatch system provided in an embodiment of this application.

[0022] Figure 2 This is a schematic diagram of an elliptical protected area model oriented towards a guiding unit, provided as an embodiment of this application. Detailed Implementation

[0023] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art based on this application are within the scope of protection of this application.

[0024] Example 1: Addressing the challenges of unmanned guided vehicles (UAVs) operating in airfields, and considering the lack of an intelligent scheduling platform for UAV clusters within UAV operation management departments, as well as shortcomings in areas such as surface surveillance data fusion and utilization, collaborative management and control of UAV fleet resources, high-precision conflict prediction, and large-scale scheduling optimization, this application provides an airport surface UAV cluster command and dispatch system. This system can be found in [reference needed]. Figure 1 , Figure 1 The diagram shown is a structural schematic of an airport surface unmanned guided vehicle cluster command and dispatch system provided in an embodiment of this application, including: a data support system, a trajectory collaborative planning system, a dispatch decision execution system, an unmanned guided vehicle fleet management system, and an airport control position; The data support system acquires multi-source data related to airport surface operations from external sources.

[0025] In one embodiment of this application, to achieve comprehensive utilization of airport surface operation-related data by the command and dispatch system, it is necessary to determine the relevant information systems and data to be imported from external sources based on the design of the relevant modules of the trajectory collaborative planning system and the dispatch decision execution system. When setting the types of data to be imported, factors such as the timeliness, accuracy, and ease of access of the data are mainly considered.

[0026] Furthermore, the data support system needs to obtain flight dynamic data such as estimated landing time (ELDT), estimated takeoff time (ETOT), estimated wheel chock removal time, estimated wheel chock removal time, and runway usage from the Airport Collaborative Decision Making System (A-CDM); it needs to obtain airport surface topology, taxiway guidance connection location spatial nodes, and operation time node information from the Advanced Surface Surveillance Guidance and Control System (A-SMGCS); and it needs to obtain information on the location, speed, battery level, and operating status (whether guidance tasks have been assigned, vehicle component operating status, etc.) of the unmanned vehicle status monitoring system.

[0027] The trajectory collaborative planning system generates conflict-free guidance trajectories for the airport surface based on multi-source data.

[0028] In one embodiment of this application, the trajectory collaborative planning system realizes real-time fusion processing of the guidance data to form a conflict-free guidance vehicle scheduling scheme. It mainly consists of a spatiotemporal occupancy conflict prediction module, a scene guidance trajectory deduction module, and a swarm intelligence algorithm optimization module.

[0029] (1) Spatiotemporal occupancy conflict prediction module. This module, based on the airport surface topology network and operating rules, accurately quantifies the spatiotemporal occupancy status of the guidance vehicle-aircraft coupling unit, specifically including: The design includes a protected area modeling submodule to construct a dynamic geometric protected area model, taking into account the size of the guiding unit (aircraft wingspan + guiding vehicle length) and movement speed to generate protected area parameters. The aforementioned guiding unit refers to a single unit formed by a combination of a manned aircraft and an unmanned guiding vehicle with a following relationship.

[0030] The design includes a conflict prediction submodule, which uses airport observation and numerical simulation to predict the spatial overlap between protected areas.

[0031] Design a conflict frequency statistics submodule: establish a spatiotemporal conflict database, record the frequency of conflict occurrences at each node in the scene, and generate a conflict distribution heatmap.

[0032] In one embodiment of this application, an example is provided for establishing an elliptical protected area model for a guide unit. The elliptical protected area is drawn with the positions of points on the trajectory as geometric centers, and the size and speed of the moving target (guide vehicle or guide unit) as the main variables.

[0033] Design an elliptical protected area, such as Figure 2 Major axis length With minor axis length Calculated by the following formula:

[0034] In the formula, For safety reasons, , These represent the length and width of the guide unit, respectively. Vehicle deceleration parameters The target speed is defined as the speed of movement of the target on the airport surface. During taxiing guidance, the target refers to the guidance unit; during the deployment or recovery phase, the target refers to the individual guidance vehicle. The specific calculation formula is as follows:

[0035]

[0036] In the formula, and These are the length of the guide vehicle and the length of the aircraft, respectively. This can be obtained by measuring from the front of the guide vehicle to the rear of the vehicle; It can be measured from the nose to the tail of the aircraft. The latter introduces the following distance between the aircraft and the guide vehicle. average This indicates the space occupied by the guiding unit. Measured from the nose of the aircraft to the rear of the guide vehicle. For the wingspan of the guided aircraft, To guide the width of the vehicle.

[0037] The parameters of the lead vehicle can be obtained from the fleet management system, and the parameters of the aircraft can be obtained by combining the aircraft type information provided by the A-CDM system.

[0038] Safety factor The purpose of this setting is to reduce the possibility of false alarms and missed alarms in conflict prediction, and it is selected based on the largest aircraft type currently operating at the airport. The selection principles are as follows: Figure 2 For the largest aircraft type (Category E aircraft) at a certain airport, if the protection zone shown by the black dashed line (with a safety factor of 1) is used, the ellipse cannot encompass the entire moving target, and the possibility of missed alarms cannot be ruled out. If the protection zone shown by the red solid line (with a safety factor of 1.2) is used, the entire moving target can be encompassed, minimizing the probability of false alarms while detecting potential conflicts. If the safety factor is further increased, there is still a possibility of false alarms.

[0039] (2) Scene guidance trajectory deduction module, which generates accurate velocity profiles and spatiotemporal trajectories, specifically including: Design a path parsing submodule to parse the taxiing path nodes and topology relationships provided by A-SMGCS.

[0040] The design includes a turning trajectory optimization submodule, which smooths the trajectory at turning points and corrects the timestamps.

[0041] Design a follow-altitude distance calculation submodule to calculate the safe follow-altitude distance (including visual distance correction) between the guide vehicle and the aircraft.

[0042] The design speed profile generation submodule generates speed curves for each road segment based on vehicle dynamics parameters (acceleration / deceleration).

[0043] In one embodiment of this application, a corresponding embodiment is provided for the scene guidance trajectory deduction module and its sub-modules, and the overall process is as follows: Step 1: Enter the current stage ,flight Location of the aircraft and the selected route Generate the point set corresponding to the guide path. ,in, Indicates the first step of the boot path The x and y coordinates of each point, x-axis The vertical coordinate is denoted by y. The horizontal and vertical coordinates can be obtained by converting the latitude and longitude of each point, or by establishing a Cartesian coordinate system with a key point on the airport surface as the origin.

[0044] Step 2: Input the departure time adjustment amount for each stage Departure times are determined from Table 1. .

[0045] Table 1 Guided Flights Details of departure times for driverless guided vehicles at each stage

[0046] To guide flights For example, the departure times of the three stages of the autonomous guided vehicle are shown in Table 1. ETOT and ELDT are obtained from the A-CDM system, representing the estimated landing time and estimated takeoff time, respectively; the remaining times can be obtained from the A-SMGCS statistics. and These correspond to the time from touchdown to the guidance start point for approaching aircraft, and the time for departing aircraft to wait at the runway gate and enter the runway, respectively. This refers to the time it takes for the guide vehicle to pass through the apron taxiway; This refers to the time required for the guide vehicle to turn around before guiding the incoming aircraft. and These respectively represent the guidance vehicles guiding flights. The required working time during the dispatch and guidance phases. , and Each vehicle guides the flight. The departure time is adjusted during the dispatch, guidance, and retrieval phases. The three phases mentioned above refer to the dispatch, guidance, and retrieval phases of the unmanned guide vehicle's coasting guidance, which correspond to the three stages of the unmanned guide vehicle moving from the standby position to the guidance starting point, the unmanned guide vehicle performing coasting guidance, and the unmanned guide vehicle moving from the guidance endpoint to the standby position.

[0047] Step 3: Traverse the nodes on the trajectory and determine the turning speed adjustment nodes using the vector dot product formula:

[0048] In the formula B The point is the point to be determined. A Dot and C The points are respectively B The two nodes before and after the point, Represents a vector. This represents the magnitude of the vector. When the turning angle... ,Will B The point is identified as the turning speed adjustment point.

[0049] Step 4: Determine the speed limit at each point based on the actual operation of the scene. :

[0050] In the formula, For guiding path number Speed ​​limits for movement at each point To guide vehicles through the next speed limit point, i.e., the current speed limit value for the road segment; These respectively represent the apron area (including service lanes), taxiway in the maneuvering area, and turning points.

[0051] Step 5: Use the algorithm described in Table 2 to generate the velocity profile. ,in and Indicates the first step of the boot path The guide vehicle's speed and passing time at each point.

[0052] Table 2. Pseudocode for the field guidance trajectory velocity profile generation algorithm

[0053] in, , and These are the boot path numbers. , , Speed ​​limits on each node The boot path calculated by the algorithm shown in Table 2 is the first... The required speed for each node, and The first step is the boot path calculated using the algorithm shown in Table 2. , The actual speed at which each node passes through the point. Indicates the path from the first The node to the first The distance to each node, and The activity objectives are guided through the following paths: , At each node's time, and These represent the last node and the node preceding it in the guiding path, respectively. Indicates the path from the first The node to the first The distance traveled during the speed adjustment process of each node. Indicates the first 1 node To guide the vehicle's acceleration, when the vehicle accelerates, Pick When the vehicle slows down, Pick(- ).

[0054] Step 6: Smooth the trajectories of turning points in the original topology network; for any topology network node that is a turning point ( ), execute the following formula to correct the turning point timing:

[0055] In the formula, For turning angle; The turning radius; This is the distance from the starting point of the turn, A, to the topological node B. The arc length corresponding to half the turning angle. The corrected time of the turning point. The time of the turning point before correction. The speed of the target at the turning point.

[0056] Step 7: Output the guiding trajectory .

[0057] Guided trajectory This allows us to obtain the guide vehicle's working time required to construct the submodule using the designed fitness function. express:

[0058] in, This indicates the specific locations along the guidance path. The guidance trajectory includes the location information of the guidance vehicle (horizontal and vertical coordinates). Speed ​​information at the point Time of passing , Guide flights with a guide vehicle At that time, in the The required working time for each stage and These represent the times when the guide vehicle passes the end and beginning of the guidance route, respectively. For the assembly of flights awaiting guidance, This refers to the set of stages in the operation of the guidance vehicle, including three stages: dispatch, guidance, and retrieval.

[0059] (3) Swarm intelligence algorithm optimization module, which realizes the rapid solution of the unmanned guided vehicle cluster scheduling scheme, including: The design includes an encoding strategy submodule that uses an integer encoding strategy to handle path selection and departure time variables.

[0060] Furthermore, the integer encoding strategy refers to the strategy based on the trajectory deduced by the module, oriented towards... Flight guidance mission, constructing a A dimensional integer space. At this point, the th... Individual correspondence dimensional vector The adjustment of the selected route and departure time can be divided into three stages. to In the above embodiments, to correspond to , to correspond to .

[0061] The fitness function construction submodule is designed to integrate the number of conflicts and total working time to construct the fitness function. Regularization and normalization methods are used to establish the fitness function formula. In principle, the weight of the conflict count term is one order of magnitude larger than that of the total working time term; this weight can be further balanced according to safety and efficiency objectives.

[0062] The design optimizes the engine submodule, which executes the iterative optimization process of swarm intelligence optimization algorithms such as the Grey Wolf Algorithm, Particle Swarm Optimization Algorithm, Whale Algorithm, and Artificial Neural Network Algorithm, by iteratively optimizing the integer space described in the module.

[0063] The scheduling decision execution system, based on the conflict-free guidance trajectory at the airport surface, completes the matching of unmanned guided vehicle fleet resources with guidance tasks, dispatches guidance tasks to the unmanned guided vehicle fleet, generates scheduling instructions for the unmanned guided vehicle fleet, and transmits the scheduling instructions to the unmanned guided vehicle fleet management system.

[0064] In one embodiment of this application, the scheduling decision execution system implements the functions of task allocation, scheduling execution, and instruction issuance for an unmanned guided vehicle cluster, and consists of the following modules: (1) Vehicle assignment module, which is responsible for optimizing the matching of tasks and vehicles based on the conflict-free guidance trajectory output by the trajectory collaborative planning system. The vehicle assignment module includes the following sub-modules: ① Time window conflict detection sub-module: detects and avoids time window overlap conflicts of the same vehicle guidance task and charging task; ② Battery management sub-module: monitors the real-time battery status of the vehicle, dynamically plans the charging window, and ensures the vehicle's range safety; ③ Fairness optimization sub-module: with the goal of minimizing the vehicle working time imbalance index, it establishes a pairing model based on large-scale combinatorial optimization, integer linear programming, dynamic programming and other methods to ensure that the guidance task is evenly distributed among the vehicles.

[0065] (2) Vehicle dispatching module, responsible for responding to the airport surface taxiing guidance needs and generating executable dispatching schemes, including: ① Vehicle resource integration sub-module: integrating the optimized vehicle assignment and trajectory planning schemes into executable dispatching schemes; ② Emergency re-dispatch sub-module: for sudden scenarios such as flight delays and vehicle failures, airport control positions can implement re-dispatch to realize takeover in emergency situations; ③ Redundant resource management sub-module: maintaining the backup vehicle resource pool to ensure system robustness.

[0066] (3) The instruction issuing module transmits unmanned vehicle control instructions to the unmanned vehicle fleet management system through aviation telecommunications technologies such as 5G-AeroMACS network.

[0067] The unmanned guided vehicle fleet management system dispatches unmanned guided vehicles to perform taxiing guidance tasks according to the planned path based on the dispatch instructions, and feeds back the unmanned vehicle's position, speed, battery level and task execution status to the data support system through the aviation network.

[0068] In one embodiment of this application, in order to achieve precise control of the unmanned guided vehicle cluster, the unmanned guided vehicle fleet management system is configured with the following modules: (1) a scheduling management module, which receives trajectory control instructions issued by the scheduling decision execution system and drives the unmanned guided vehicles to perform gliding guidance tasks according to the planned path; (2) an operation status feedback module, which provides real-time feedback on the unmanned vehicle's position, speed, battery level and task execution status, and feeds it back to the data support system through the aviation telecommunications network.

[0069] The airport control station interacts with the data support system to perceive the operational status of aircraft and unmanned guided vehicles on the airport surface, and allows controllers to intervene and enter emergency command as needed.

[0070] In one embodiment of this application, the airport control position serves as the core of the overall operation monitoring, responsible for dynamically verifying the scheduling plan and implementing emergency intervention, including: (1) airport surface monitoring equipment, which integrates surface monitoring radar, multi-point positioning system and other equipment, interacts with A-SMGCS, and senses the operating status of airport surface aircraft and unmanned guided vehicles; (2) airport control communication equipment: supports controllers to intervene in the scheduling system and realize manual intervention in emergency situations through voice / data commands.

[0071] Example 2: This application provides a method for commanding and dispatching a cluster of unmanned guided vehicles on an airport surface, including: S1: Acquire and integrate externally sourced airport multi-source data, including flight dynamic data, airport surface topology network, taxiway guidance path nodes, operation time node information, and motion status information of unmanned guidance vehicles; S2: Generate conflict-free guidance trajectories for the airport surface based on multi-source airport data; S3: Generate dispatch instructions for unmanned guided convoys based on the conflict-free guidance trajectory of the airport surface; S4: Based on the dispatch instructions of the autonomous driving guidance vehicle fleet, the autonomous driving guidance vehicle is mobilized to perform the gliding guidance task according to the planned path, and the autonomous vehicle's position, speed, battery level and task execution status are reported back.

[0072] Furthermore, the generation of conflict-free guidance trajectories on the airport surface based on multi-source airport data includes: S201: Based on multi-source airport data, and according to the airport surface topology network and operating rules, quantify the spatiotemporal occupancy status of the guidance vehicle-aircraft coupling unit; S202: Generate velocity profiles and spatiotemporal trajectories based on the airport surface topology network and taxiing guidance path nodes; S203: Generate a conflict-free guidance trajectory for the airport surface based on the spatiotemporal occupancy status, velocity profile, and spatiotemporal trajectory of the guidance vehicle-aircraft coupling unit.

[0073] Furthermore, the generation of velocity profiles and spatiotemporal trajectories based on the airport surface topology network and taxiway guidance path nodes includes: A1: The current path node set included in the motion state information of the gliding guidance path nodes and the autonomous guided vehicle. Two adjacent nodes on the current path and Spacing A set consisting of speed limits at each node and vehicle acceleration and deceleration ,like According to the formula For nodes Each upstream node Calculate the boot path number The required speed of each node If yes, proceed to A2; otherwise, proceed to A3, where... To represent the first step of the bootstrap path The x and y coordinates of each node, For guiding path number Speed ​​limits on each node For guiding path number Speed ​​limits on each node To accelerate the guide car, Indicates the last node in the bootstrap path; A2: If each upstream node satisfies Then let And enter A4, where, For guiding path number Speed ​​limits on each node; A3: If Then let And proceed to A4; otherwise, set Enter A1, where, Indicates the guiding path node The previous node, Indicates the first One node; A4: If Then calculate and Otherwise, proceed to A5, where the calculation formula is:

[0074] in, and The first step is the guide path calculated using the formula. , The actual speed at which each node passes through the point. Indicates the path from the first The node to the first The distance to each node, and The activity objectives are guided through the following paths: , The moment of each node; A5: If Greater than the calculation formula The obtained guiding path starts from the first The node to the first The distance traveled during the speed adjustment process of each node Then let and calculate and Enter A6, the calculation formula is:

[0075] Otherwise, calculate according to the following formula and Enter A6, the calculation formula is:

[0076] A6: If Output the set of velocity profiles corresponding to each guide trajectory. ,in, For the first Velocity profile of each node; otherwise, let , then move to A4.

[0077] Furthermore, the aforementioned airport surface unmanned guided vehicle cluster command and dispatch method also includes: In response to emergencies, a new dispatch system is implemented, and emergency command is activated.

[0078] In one embodiment of this application, firstly, multi-source data is integrated and fused to construct a collaborative operating environment for unmanned guided vehicles (UAVs) and manned aircraft. Airport surface operation data from various information systems within the data support system are integrated to provide a real-time decision-making basis for UAV scheduling. This mainly includes: the A-CDM system providing flight dynamic data; the A-SMGCS providing airport surface topology network, taxiway path nodes, and airport surface operation rules information; and the UAV status monitoring system providing real-time feedback on vehicle position, speed, battery level, and operating status. Secondly, collaborative planning forms conflict-free guidance trajectories on the airport surface, optimizing vehicle operating efficiency. Based on the fused data, the spatiotemporal occupancy status of both airport surface aircraft and UAVs is characterized; the trajectory collaborative planning system optimizes the taxiing guidance process for UAVs. Finally, vehicle resources are dynamically scheduled to achieve balanced task allocation. Based on the optimized trajectory after collaborative planning, the UAV guidance vehicle fleet resource allocation is completed through the scheduling decision execution system. The vehicle allocation module, with allocation fairness as its core objective, uses large-scale combinatorial optimization, integer linear programming, dynamic programming, and other operations research optimization models to match guidance tasks with UAV guidance vehicles.

[0079] This application provides an airport surface unmanned guided vehicle cluster command and dispatch system and method, which integrates multi-source data related to airport surface operations from multiple sources to form a dynamic airport surface operation scenario. This facilitates airport control departments in conducting command and dispatch of automated unmanned guided vehicles during taxiing guidance. It transforms manual command and dispatch, which relies solely on the individual experience of airport controllers, into a command system based on swarm intelligence that assists airport control positions in making decisions. This helps to fully utilize the data generated during airport control and airport operation control processes, thereby improving the safety and efficiency of airport surface taxiing guidance processes and their automation.

[0080] It should be noted that those skilled in the art will recognize that the embodiments described herein are for the purpose of helping readers understand the principles of this application, and should be understood as not limiting the scope of protection of this application to such specific statements and embodiments. Those skilled in the art can make various other specific modifications and combinations based on the technical teachings disclosed in this application without departing from the essence of this application, and these modifications and combinations are still within the scope of protection of this application.

Claims

1. An airport surface unmanned guided vehicle cluster command and dispatch system, characterized in that, include: Data support system, trajectory collaborative planning system, scheduling decision execution system, unmanned driving guided vehicle fleet management system, and airport control position; The data support system acquires multi-source data related to airport surface operations from external sources. The trajectory collaborative planning system generates conflict-free guidance trajectories for the airport surface based on multi-source data; The scheduling decision execution system, based on the airport surface conflict-free guidance trajectory, completes the matching of unmanned guided vehicle fleet resources and guidance tasks, dispatches guidance tasks to the unmanned guided vehicle fleet, generates scheduling instructions for the unmanned guided vehicle fleet, and transmits the scheduling instructions to the unmanned guided vehicle fleet management system. The unmanned guided vehicle fleet management system dispatches unmanned guided vehicles to perform taxiing guidance tasks according to the planned path based on the dispatch instructions, and feeds back the unmanned vehicle's position, speed, battery level, and task execution status to the data support system through the aviation network; The airport control station interacts with the data support system to perceive the operational status of aircraft and unmanned guided vehicles on the airport surface, and allows controllers to intervene and enter emergency command as needed.

2. The airport surface unmanned guided vehicle cluster command and dispatch system according to claim 1, characterized in that, The data support system includes: an airport collaborative decision-making system, an advanced surface surveillance, guidance and control system, and an unmanned vehicle status monitoring system; The airport collaborative decision-making system acquires flight dynamic data; The advanced surface monitoring, guidance and control system acquires airport surface topology network, taxiing guidance path and node, and operation time node information; The unmanned vehicle status monitoring system acquires the motion status information of the unmanned guide vehicle.

3. The airport surface unmanned guided vehicle cluster command and dispatch system according to claim 2, characterized in that, The trajectory collaborative planning system includes a spatiotemporal occupancy conflict prediction module, a scene-guided trajectory deduction module, and a swarm intelligence algorithm optimization module. The spatiotemporal occupancy conflict prediction module quantifies the spatiotemporal occupancy status of the guidance vehicle-aircraft coupling unit based on the airport surface topology network and operating rules. It includes a design protection zone modeling submodule, a design conflict prediction submodule, and a design conflict frequency statistics submodule. The design protection zone modeling submodule considers the protection zone parameters generated by the guide unit size and movement speed to construct a dynamic geometric protection zone model; the design conflict prediction submodule predicts the spatial overlap between protection zones; the design conflict frequency statistics submodule establishes a spatiotemporal occupancy conflict database, records the frequency of conflict occurrence at each node of the scene, and generates a conflict distribution heatmap. The surface guidance trajectory derivation module generates velocity profiles and spatiotemporal trajectories, including a design path analysis submodule, a design turning trajectory optimization submodule, a design following distance calculation submodule, and a design velocity profile generation submodule. The design path analysis submodule analyzes the airport surface topology network and taxiing guidance path nodes obtained by the Advanced Surface Monitoring, Guidance and Control System. The design turning trajectory optimization submodule performs trajectory smoothing processing and corrects timestamps for turning points in the airport surface topology network and taxiing guidance path nodes obtained by the Advanced Surface Monitoring, Guidance and Control System. The design following distance calculation submodule calculates the safe following distance between the unmanned guided vehicle and the aircraft; the design speed profile generation submodule generates speed curves for each road segment based on vehicle dynamics parameters. The swarm intelligence algorithm optimization module generates a conflict-free airport surface guidance trajectory based on the spatiotemporal occupancy status, velocity profile, and spatiotemporal trajectory of the guidance vehicle-aircraft coupling unit. It includes a design coding strategy submodule, a design fitness function construction submodule, and a design optimization engine submodule. The design coding strategy submodule uses an integer coding strategy to process path selection and departure time variables. The design fitness function construction submodule integrates the number of conflicts and the total working time to construct the fitness function; the design optimization engine submodule executes an iterative optimization process based on a swarm intelligence optimization algorithm.

4. The airport surface unmanned guided vehicle cluster command and dispatch system according to claim 1, characterized in that, The scheduling decision execution system includes a vehicle assignment module, a vehicle scheduling module, and an instruction issuance module; The vehicle assignment module, based on the conflict-free guidance trajectory of the airport surface, matches guidance tasks with vehicles. It includes a time window conflict detection submodule, a power management submodule, and a fairness optimization submodule. The time window conflict detection submodule detects and avoids overlapping time windows of the same vehicle's guidance task and charging task. The power management submodule monitors the real-time power status of vehicles and dynamically plans charging windows to ensure vehicle range safety. The fairness optimization submodule aims to minimize the vehicle working time imbalance index and establishes a guidance task-vehicle pairing model to ensure that guidance tasks are evenly distributed among vehicles. The vehicle dispatching module generates dispatching instructions for the unmanned guided vehicle fleet based on the airport surface taxiing guidance requirements and the matching of guidance tasks and vehicles. This includes a vehicle resource integration submodule, an emergency re-dispatch submodule, and a redundant resource management submodule. The vehicle resource integration submodule integrates optimized vehicle assignment and trajectory planning schemes into executable dispatching instructions. The emergency re-dispatch submodule, in conjunction with airport control, performs re-dispatch for unexpected scenarios, enabling takeover in emergency situations. The redundant resource management submodule maintains a backup vehicle resource pool to ensure system robustness. The instruction issuing module transmits the dispatch instructions of the unmanned guided vehicle fleet to the unmanned vehicle fleet guidance system through aviation telecommunications technology.

5. The airport surface unmanned guided vehicle cluster command and dispatch system according to claim 4, characterized in that, The unmanned guided fleet management system includes a scheduling management module and an operation status feedback module; The scheduling management module receives trajectory control instructions from the scheduling decision execution system and drives the unmanned guided vehicle to perform gliding guidance tasks according to the planned path; The operational status feedback module feeds back the unmanned vehicle's location, speed, battery level, and mission execution status to the data support system via the aviation network.

6. The airport surface unmanned guided vehicle cluster command and dispatch system according to claim 1, characterized in that, The airport control station includes airport surface surveillance equipment and airport control communication equipment; The airport surface surveillance equipment integrates surface surveillance radar and a multi-point positioning system, interacts with the advanced surface surveillance guidance and control system of the data support system, and senses the operational status of airport surface aircraft and unmanned guided vehicles. The airport control communication equipment supports controllers to intervene in the dispatch system and enable manual intervention in emergency situations via voice or data commands.

7. A method for commanding and dispatching a cluster of unmanned guided vehicles at an airport, characterized in that, include: S1: Acquire and integrate externally sourced airport multi-source data, including flight dynamic data, airport surface topology network, taxiway guidance path nodes, operation time node information, and motion status information of unmanned guidance vehicles; S2: Generate conflict-free guidance trajectories for the airport surface based on multi-source airport data; S3: Generate dispatch instructions for unmanned guided convoys based on the conflict-free guidance trajectory of the airport surface; S4: Based on the dispatch instructions of the autonomous driving guidance vehicle fleet, the autonomous driving guidance vehicle is mobilized to perform the gliding guidance task according to the planned path, and the autonomous vehicle's position, speed, battery level and task execution status are reported back.

8. The airport surface unmanned guided vehicle cluster command and dispatch method according to claim 7, characterized in that, The generation of conflict-free guidance trajectories on the airport surface based on multi-source airport data includes: S201: Based on multi-source airport data, and according to the airport surface topology network and operating rules, quantify the spatiotemporal occupancy status of the guidance vehicle-aircraft coupling unit; S202: Generate velocity profiles and spatiotemporal trajectories based on the airport surface topology network and taxiing guidance path nodes; S203: Generate a conflict-free guidance trajectory for the airport surface based on the spatiotemporal occupancy status, velocity profile, and spatiotemporal trajectory of the guidance vehicle-aircraft coupling unit.

9. The airport surface unmanned guided vehicle cluster command and dispatch method according to claim 8, characterized in that, The generation of velocity profiles and spatiotemporal trajectories based on the airport surface topology network and taxiway guidance path nodes includes: A1: The current path node set included in the motion state information of the coasting guidance path nodes and the autonomous guided vehicle. Two adjacent nodes on the current path and Spacing A set consisting of speed limits at each node and vehicle acceleration and deceleration ,like According to the formula For nodes Each upstream node Calculate the boot path number The required speed of each node If yes, proceed to A2; otherwise, proceed to A3, where... To represent the first step of the bootstrap path The x and y coordinates of each node, For guiding path number Speed ​​limits on each node For guiding path number Speed ​​limits on each node To accelerate the guide car, Indicates the last node in the bootstrap path; A2: If each upstream node satisfies Then let If A4 is not selected, proceed to A4; otherwise, proceed to A3, where... For guiding path number Speed ​​limits on each node; A3: If Then let And proceed to A4; otherwise, set Enter A1, where, Indicates the guiding path node The previous node, Indicates the first One node; A4: If Then calculate and Otherwise, proceed to A5, where the calculation formula is: in, and The first step is the guide path calculated using the formula. , The actual speed at which each node passes through the point. Indicates the path to be guided, starting from the first... The node to the first The distance to each node, and The activity objectives are guided through the following paths: , The moment of each node; A5: If Greater than the calculation formula The obtained guiding path starts from the first The node to the first The distance traveled during the speed adjustment process of each node Then let and calculate and Enter A6, the calculation formula is: Otherwise, calculate according to the following formula and Enter A6, the calculation formula is: A6: If Output the set of velocity profiles corresponding to each guide trajectory. ,in, For the first Velocity profile of each node; otherwise, let , then move to A4.

10. The airport surface unmanned guided vehicle cluster command and dispatch method according to claim 7, characterized in that, Also includes: In response to emergencies, a new dispatch system is implemented, and emergency command is activated.

Images