An intelligent dynamic traffic management method and system for future urban air traffic

Abstract

The application relates to the field of intelligent traffic management, and discloses an intelligent dynamic traffic management method and system for future urban air traffic, which constructs a basic airway network based on urban traffic comprehensive data, realizes fine airspace management in three-dimensional space, avoids planar management of future urban air traffic, makes the management scheme more in line with actual demands, carries out airway optimization processing, avoids multiple risks caused by three-dimensional planar schemes, realizes airway optimization with multiple weight constraints, improves the intelligence and accuracy of the traffic management scheme, carries out hierarchical regulation, realizes dynamic regulation of the traffic management scheme, avoids dynamic risks caused by fixed routes, designs a take-off and landing scheduling model for take-off and landing optimization, improves traffic management efficiency, avoids congestion and superposition risks of traffic hubs, and improves the intelligence and dynamicity of the traffic management method for future urban air traffic.

Description

Technical Field

[0001] This invention relates to the field of intelligent traffic management, and in particular to an intelligent and dynamic traffic management method and system for future urban air traffic. Background Technology

[0002] With the rapid development of the transportation industry, the number of diverse urban transportation vehicles and complex transportation facilities is increasing year by year. Among them, urban aircraft (such as small and medium-sized helicopters), flying cars and unmanned low-altitude aircraft, as participants in future urban air traffic, have gradually become an indispensable part. Therefore, intelligent traffic management for future urban air traffic has become a crucial link.

[0003] In existing technologies, urban intelligent traffic management often only targets planar road traffic and lacks targeted design solutions for the three-dimensional scenarios of future urban air traffic. Furthermore, existing traffic facilities (such as traffic lights and signs) are difficult to apply to future urban air traffic management scenarios, making it impossible to achieve full-process management of pre-planning, real-time scheduling, and subsequent adjustments.

[0004] Therefore, how to design a traffic management method for future urban air traffic to achieve intelligent and dynamic traffic management has become an urgent problem to be solved. Summary of the Invention

[0005] Based on this, the present invention proposes an intelligent and dynamic traffic management method and system for future urban air traffic. By constructing a basic airway network based on comprehensive urban traffic data, it achieves refined airspace management in three-dimensional space, avoiding planar management of future urban air traffic and making the management scheme more in line with actual needs. Furthermore, it designs a loss function to minimize the airway optimization process, avoiding the multiple risks caused by the three-dimensionalization of the planar scheme, and realizing multi-weighted constraint airway optimization, which improves the intelligence and accuracy of the traffic management scheme. It also designs a hierarchical adjustment based on time adjustment and safety adjustment items, realizing dynamic adjustment of the traffic management scheme, avoiding the dynamic risks caused by fixed routes. In addition, it designs a takeoff and landing scheduling model for takeoff and landing optimization, improving traffic management efficiency and avoiding the risk of congestion superposition at transportation hubs. The present invention improves the intelligence and dynamism of traffic management methods for future urban air traffic.

[0006] This invention proposes an intelligent and dynamic traffic management method for future urban air traffic, comprising:

[0007] Collect comprehensive urban traffic data and construct a basic waterway network. The comprehensive urban traffic data includes urban geographic information data, urban traffic information data, and urban environmental information data. The basic waterway network is constructed based on three-dimensional regional grids.

[0008] The target traffic demand is obtained and the waterway optimization process is performed based on minimizing the loss function to obtain basic waterway information. The waterway optimization is based on multiple constraint weights.

[0009] The target status parameters are acquired in real time to perform hierarchical adjustment processing on the basic waterway information to obtain updated waterway information, and waterway adjustments are made according to the updated waterway information. The hierarchical adjustment processing is based on time adjustment items and safety adjustment items.

[0010] When in takeoff and landing mode, takeoff and landing optimization is performed according to the takeoff and landing scheduling model to obtain the final takeoff and landing instructions. The takeoff and landing scheduling model is based on time isolation and spatial isolation.

[0011] In summary, based on the aforementioned intelligent and dynamic traffic management method for future urban air traffic, this invention constructs a basic airway network based on comprehensive urban traffic data, achieving refined airspace management in three-dimensional space. This avoids planar management of future urban air traffic, making the management scheme more aligned with actual needs. Furthermore, a loss function is designed for airway optimization, avoiding the multiple risks arising from the three-dimensional transformation of planar schemes. This achieves multi-weighted constraint airway optimization, improving the intelligence and accuracy of the traffic management scheme. A hierarchical adjustment based on time and safety adjustment terms is also designed, enabling dynamic adjustment of the traffic management scheme and avoiding dynamic risks caused by fixed routes. Finally, a takeoff and landing scheduling model is designed for takeoff and landing optimization, improving traffic management efficiency and avoiding the risk of congestion at transportation hubs. This invention enhances the intelligence and dynamism of traffic management methods for future urban air traffic. Specifically, this involves collecting comprehensive urban traffic data and constructing a basic airway network. The comprehensive urban traffic data includes urban geographic information data, urban traffic information data, and urban environmental information data. The basic airway network is constructed based on three-dimensional regional grids, enabling refined airspace management in three-dimensional space. This avoids planar management of future urban air traffic, making the management scheme more aligned with actual needs. Target traffic demand is obtained, and airway optimization is performed based on minimizing a loss function to acquire basic airway information. This airway optimization is based on multi-constraint weights, avoiding the multiple risks arising from the three-dimensionalization of planar schemes, and achieving multi-weight constraint-based airway optimization. This invention optimizes the airway system, improving the intelligence and accuracy of traffic management solutions. It acquires target state parameters in real time and performs tiered adjustments to the basic airway information to obtain updated information. These tiered adjustments, based on time and safety factors, enable dynamic adjustment of the traffic management system, avoiding dynamic risks associated with fixed routes. Furthermore, it optimizes takeoff and landing operations based on a takeoff and landing scheduling model to obtain final instructions. This model, based on time and spatial isolation, improves traffic management efficiency and avoids the risk of congestion at transportation hubs. This invention enhances the intelligence and dynamism of future urban air traffic management methods.

[0012] Furthermore, the step of collecting comprehensive urban traffic data and constructing a basic waterway network specifically includes:

[0013] Collect comprehensive urban traffic data, which includes urban geographic information data, urban traffic information data, and urban environmental information data;

[0014] Three-dimensional spatial modeling is performed based on urban geographic information data to obtain a three-dimensional urban spatial model. Then, the urban three-dimensional spatial model is divided into grids, and each urban three-dimensional spatial grid is numbered. The coordinates of all outer edge points of the urban three-dimensional spatial grid are labeled according to the three-dimensional spatial coordinate system.

[0015] The urban three-dimensional spatial grid is labeled with state based on the urban traffic information data and urban environmental information data to construct a basic waterway network. The state labeling is based on binary state markers.

[0016] Furthermore, the step of obtaining the target traffic demand and performing channel optimization processing based on minimizing the loss function to obtain basic channel information specifically includes:

[0017] Obtain target traffic demand, which includes take-off and landing area demand information, traffic equipment demand information, and personnel demand information;

[0018] A directed graph is constructed in the basic waterway network based on the target traffic demand. The directed graph is based on the path start point and path end point. The basic paths in the directed graph are straight paths based on the shortest path principle. The probability of path collision is determined based on the directed graph. If the current basic path passes through a city 3D spatial grid where collision is possible, waterway optimization is performed by minimizing the loss function. The specific algorithm for waterway optimization is as follows:

[0019] ,

[0020] in, Indicates the total loss. Indicates the time of the path's endpoint. Indicates the start time of the path. Indicates time, , , , , , These represent the time cost, noise impact, energy consumption, safety penalty, airspace capacity cost, and fairness cost, respectively. , , , , , These represent time weight, noise weight, energy weight, security weight, spatial capacity weight, and fairness weight, respectively. , , , , , Let these represent the noise level function, noise sensitivity coefficient, energy consumption rate function, safety penalty function, airspace congestion function, and fairness function, respectively. Indicates the time of the aircraft velocity scalar, Indicates the time of the aircraft height, Indicates the time of the aircraft The position vector, Indicates the time of the aircraft acceleration vector, Indicates time The wind speed vector, This represents the distance from the aircraft at position r(t) to the nearest obstacle. Represents a constant term;

[0021] Then, the flight path instructions are optimized using a graph convolutional neural network.

[0022] Furthermore, the step of optimizing flight route instructions based on the graph convolutional neural network specifically includes:

[0023] A directed graph is input into a graph convolutional neural network, and the minimized loss function is used as the loss term of the graph convolutional neural network to optimize flight path instructions, thereby obtaining an optimized directed graph G. out =(V out E out ), where V out This represents an optimized directed graph G. out The vertex set, E out This represents an optimized directed graph G. out The set of edges, each vertex in the vertex set represents a key command point, the key command point includes command point time, command point location, flight speed and flight path execution action, each edge in the edge set represents a flight segment, the flight segment includes command point target, segment duration, segment consumption and segment constraints.

[0024] Furthermore, the step of acquiring target state parameters in real time and performing graded adjustment processing on the basic waterway information to obtain updated waterway information specifically includes:

[0025] Real-time acquisition of target state parameters, including aircraft state parameters, environmental state parameters, and airspace state parameters;

[0026] The target state parameters are used for graded adjustment processing, which includes general cases, special cases, and severe cases.

[0027] If the current situation is determined to be normal, no course change will be made, and a deceleration or stop instruction will be sent to the designated aircraft.

[0028] If a special situation is determined to be in place, a special route change will be carried out to obtain updated route information;

[0029] The special waterway change is based on a time adjustment factor, and the specific algorithm for the special waterway change is as follows:

[0030] ,

[0031] in, This represents the time cost item. Indicates time weighting, Indicates the time adjustment item. Indicates the original loss;

[0032] If the current situation is determined to be critical, a critical channel change will be made to obtain updated channel information.

[0033] Furthermore, the step of performing a severe channel change to obtain updated channel information when a severe situation is determined to be in effect specifically includes:

[0034] When a critical situation is determined, a critical channel change is initiated to obtain updated channel information. This critical channel change is based on safety adjustment items, and the specific algorithm for the critical channel change is as follows:

[0035] ,

[0036] in, This indicates a safety penalty item. Indicates safety weight, Let d(r(t)) represent the safety penalty function, and let d(r(t)) represent the distance from the aircraft at position r(t) to the nearest obstacle. Indicates the collision risk weight. This represents the collision risk function.

[0037] Furthermore, the step of optimizing takeoff and landing based on the takeoff and landing scheduling model to obtain the final takeoff and landing instructions specifically includes:

[0038] The takeoff and landing scheduling model is based on a multi-objective optimization model, and the specific algorithm of the takeoff and landing scheduling model is as follows:

[0039] ,

[0040] ,

[0041] ,

[0042] ,

[0043] ,

[0044] Where Minimize means to minimize, and J represents the optimization objective. , , These represent throughput weight, latency weight, and noise weight, respectively. , These represent the takeoff times of different aircraft. , These represent the landing times of different aircraft. Indicates the expected landing time. Indicates the expected takeoff time. Representing the noise model, Indicates the noise sensitivity coefficient. These represent the flight paths of different aircraft. , These represent the safe time intervals for landing and takeoff, respectively, with i and j representing different aircraft. Indicates a safe distance. Indicates the operation time.

[0045] This invention proposes an intelligent dynamic traffic management system for future urban air traffic, comprising:

[0046] The waterway construction module is used to collect comprehensive urban traffic data and construct a basic waterway network. The comprehensive urban traffic data includes urban geographic information data, urban traffic information data, and urban environmental information data. The basic waterway network is constructed based on three-dimensional regional grids.

[0047] The waterway optimization module is used to obtain the target traffic demand and perform waterway optimization processing according to the minimum loss function to obtain basic waterway information. The waterway optimization is based on multiple constraint weights.

[0048] The graded adjustment module is used to acquire target status parameters in real time and perform graded adjustment processing on the basic waterway information to obtain updated waterway information, and to adjust the waterway according to the updated waterway information. The graded adjustment processing is based on time adjustment items and safety adjustment items.

[0049] The takeoff and landing optimization module is used to optimize takeoff and landing according to the takeoff and landing scheduling model when in takeoff and landing state in order to obtain the final takeoff and landing instructions. The takeoff and landing scheduling model is based on time isolation and spatial isolation.

[0050] The present invention also provides a storage medium that stores one or more programs, which, when executed by a processor, implement the intelligent and dynamic traffic management method for future urban air traffic as described above.

[0051] The present invention also provides a computer device, the computer device including a memory and a processor, wherein:

[0052] The memory is used to store computer programs;

[0053] When the processor executes the computer program stored in the memory, it implements the intelligent and dynamic traffic management method for future urban air traffic as described above. Attached Figure Description

[0054] Figure 1 The flowchart shows the intelligent dynamic traffic management method for future urban air traffic proposed in the first embodiment of the present invention.

[0055] Figure 2 This is a schematic diagram of the intelligent dynamic traffic management system for future urban air traffic proposed in the second embodiment of the present invention.

[0056] Figure 3 This is the basic path diagram of the first embodiment of the present invention.

[0057] The following detailed description, in conjunction with the accompanying drawings, will further illustrate the present invention. Detailed Implementation

[0058] To facilitate understanding of the present invention, a more complete description will be given below with reference to the accompanying drawings. Several embodiments of the invention are illustrated in the drawings. However, the invention can be implemented in many different forms and is not limited to the embodiments described herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete.

[0059] It should be noted that when a component is said to be "fixed to" another component, it can be directly on the other component or there may be an intervening component. When a component is said to be "connected to" another component, it can be directly connected to the other component or there may be an intervening component. The terms "vertical," "horizontal," "left," "right," and similar expressions used in this document are for illustrative purposes only.

[0060] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains. The terminology used herein in the description of the invention is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. The term "and / or" as used herein includes any and all combinations of one or more of the associated listed items.

[0061] Please see Figure 1 The diagram shows a flowchart of the intelligent dynamic traffic management method for future urban air traffic proposed in the first embodiment of the present invention. This intelligent dynamic traffic management method for future urban air traffic includes steps S01 to S04, wherein:

[0062] Step S01: Collect comprehensive urban traffic data and construct a basic waterway network;

[0063] It should be noted that in this embodiment, the urban traffic integrated data includes urban geographic information data, urban traffic information data, and urban environmental information data, and the basic waterway network is constructed based on three-dimensional regional grids;

[0064] Collect comprehensive urban traffic data, which includes urban geographic information data, urban traffic information data, and urban environmental information data;

[0065] Three-dimensional spatial modeling is performed based on urban geographic information data to obtain a three-dimensional urban spatial model. Then, the urban three-dimensional spatial model is divided into grids, and each urban three-dimensional spatial grid is numbered. The coordinates of all outer edge points of the urban three-dimensional spatial grid are labeled according to the three-dimensional spatial coordinate system.

[0066] The urban three-dimensional spatial grid is labeled with state based on the urban traffic information data and urban environmental information data to construct a basic waterway network. The state labeling is based on binary state markers.

[0067] Step S02: Obtain the target traffic demand and perform channel optimization processing based on minimizing the loss function to obtain basic channel information;

[0068] It should be noted that in this embodiment, the waterway optimization is based on multiple constraint weights to obtain the target traffic demand, which includes take-off and landing area demand information, traffic equipment demand information, and personnel demand information.

[0069] A directed graph is constructed within the basic waterway network based on the target traffic demand. This directed graph is based on path start and end points, and the basic paths in the directed graph are straight-line paths based on the shortest path principle. For details on the basic paths in the directed graph, please refer to [link / reference needed]. Figure 3 Where points A, B, C, and D represent command points in the basic path of the city's three-dimensional spatial grid. The probability of path collision is determined based on the directed graph. If the current basic path passes through a city's three-dimensional spatial grid where a collision is possible, then channel optimization is performed by minimizing the loss function. The specific algorithm for channel optimization is as follows:

[0070] ,

[0071] in, Indicates the total loss. Indicates the time of the path's endpoint. Indicates the start time of the path. Indicates time, , , , , , These represent the time cost, noise impact, energy consumption, safety penalty, airspace capacity cost, and fairness cost, respectively. , , , , , These represent time weight, noise weight, energy weight, security weight, spatial capacity weight, and fairness weight, respectively. , , , , , Let these represent the noise level function, noise sensitivity coefficient, energy consumption rate function, safety penalty function, airspace congestion function, and fairness function, respectively. Indicates the time of the aircraft velocity scalar, Indicates the time of the aircraft height, Indicates the time of the aircraft The position vector, Indicates the time of the aircraft acceleration vector, Indicates time The wind speed vector, This represents the distance from the aircraft at position r(t) to the nearest obstacle. This represents a constant term, in this embodiment. =1;

[0072] Then, the flight path instructions are optimized using a graph convolutional neural network.

[0073] A directed graph is input into a graph convolutional neural network, and the minimized loss function is used as the loss term of the graph convolutional neural network to optimize flight path instructions, thereby obtaining an optimized directed graph G. out =(V out E out ), where V out This represents an optimized directed graph G. out The vertex set, E out This represents an optimized directed graph G. out The set of edges, each vertex in the vertex set represents a key command point, the key command point includes command point time, command point location, flight speed and flight path execution action, each edge in the edge set represents a flight segment, the flight segment includes command point target, segment duration, segment consumption and segment constraints.

[0074] Step S03: Real-time acquisition of target status parameters to perform hierarchical adjustment processing on basic channel information to obtain updated channel information, and channel adjustment based on the updated channel information;

[0075] It should be noted that in this embodiment, the graded adjustment process is based on time adjustment items and safety adjustment items to obtain target state parameters in real time. The target state parameters include aircraft state parameters, environmental state parameters and airspace state parameters.

[0076] The target state parameters are used for graded adjustment processing, which includes general cases, special cases, and severe cases.

[0077] If the current situation is determined to be normal, no course change will be made, and a deceleration or stop instruction will be sent to the designated aircraft.

[0078] If a special situation is determined to be in place, a special route change will be carried out to obtain updated route information;

[0079] The special waterway change is based on a time adjustment factor, and the specific algorithm for the special waterway change is as follows:

[0080] ,

[0081] in, This represents the time cost item. Indicates time weighting, Indicates the time adjustment item. Indicates the original loss;

[0082] If the current situation is determined to be critical, a critical channel change will be made to obtain updated channel information;

[0083] When a critical situation is determined, a critical channel change is initiated to obtain updated channel information. This critical channel change is based on safety adjustment items, and the specific algorithm for the critical channel change is as follows:

[0084] ,

[0085] in, This indicates a safety penalty item. Indicates safety weight, Let d(r(t)) represent the safety penalty function, and let d(r(t)) represent the distance from the aircraft at position r(t) to the nearest obstacle. Indicates the collision risk weight. This represents the collision risk function.

[0086] Step S04: When in takeoff and landing mode, perform takeoff and landing optimization according to the takeoff and landing scheduling model to obtain the final takeoff and landing instructions;

[0087] It should be noted that in this embodiment, the takeoff and landing scheduling model is based on time isolation and spatial isolation, and is based on a multi-objective optimization model. The specific algorithm of the takeoff and landing scheduling model is as follows:

[0088] ,

[0089] ,

[0090] ,

[0091] ,

[0092] ,

[0093] Where Minimize means to minimize, and J represents the optimization objective. , , These represent throughput weight, latency weight, and noise weight, respectively. , These represent the takeoff times of different aircraft. , These represent the landing times of different aircraft. Indicates the expected landing time. Indicates the expected takeoff time. Representing the noise model, Indicates the noise sensitivity coefficient. These represent the flight paths of different aircraft. , These represent the safe time intervals for landing and takeoff, respectively, with i and j representing different aircraft. Indicates a safe distance. Indicates the operation time.

[0094] In summary, based on the aforementioned intelligent and dynamic traffic management method for future urban air traffic, this invention constructs a basic airway network based on comprehensive urban traffic data, achieving refined airspace management in three-dimensional space. This avoids planar management of future urban air traffic, making the management scheme more aligned with actual needs. Furthermore, a loss function is designed for airway optimization, avoiding the multiple risks arising from the three-dimensional transformation of planar schemes. This achieves multi-weighted constraint airway optimization, improving the intelligence and accuracy of the traffic management scheme. A hierarchical adjustment based on time and safety adjustment terms is also designed, enabling dynamic adjustment of the traffic management scheme and avoiding dynamic risks caused by fixed routes. Finally, a takeoff and landing scheduling model is designed for takeoff and landing optimization, improving traffic management efficiency and avoiding the risk of congestion at transportation hubs. This invention enhances the intelligence and dynamism of traffic management methods for future urban air traffic. Specifically, this involves collecting comprehensive urban traffic data and constructing a basic airway network. The comprehensive urban traffic data includes urban geographic information data, urban traffic information data, and urban environmental information data. The basic airway network is constructed based on three-dimensional regional grids, enabling refined airspace management in three-dimensional space. This avoids planar management of future urban air traffic, making the management scheme more aligned with actual needs. Target traffic demand is obtained, and airway optimization is performed based on minimizing a loss function to acquire basic airway information. This airway optimization is based on multi-constraint weights, avoiding the multiple risks arising from the three-dimensionalization of planar schemes, and achieving multi-weight constraint-based airway optimization. This invention optimizes the airway system, improving the intelligence and accuracy of traffic management solutions. It acquires target state parameters in real time and performs tiered adjustments to the basic airway information to obtain updated information. These tiered adjustments, based on time and safety factors, enable dynamic adjustment of the traffic management system, avoiding dynamic risks associated with fixed routes. Furthermore, it optimizes takeoff and landing operations based on a takeoff and landing scheduling model to obtain final instructions. This model, based on time and spatial isolation, improves traffic management efficiency and avoids the risk of congestion at transportation hubs. This invention enhances the intelligence and dynamism of future urban air traffic management methods.

[0095] Please see Figure 2 The diagram shows a schematic representation of the intelligent dynamic traffic management system for future urban air traffic proposed in the second embodiment of the present invention. The system includes:

[0096] The waterway construction module 10 is used to collect comprehensive urban traffic data and construct a basic waterway network. The comprehensive urban traffic data includes urban geographic information data, urban traffic information data, and urban environmental information data. The basic waterway network is constructed based on three-dimensional regional grids.

[0097] The waterway optimization module 20 is used to obtain the target traffic demand and perform waterway optimization processing according to the minimum loss function to obtain basic waterway information. The waterway optimization is based on multiple constraint weights.

[0098] The graded adjustment module 30 is used to acquire target status parameters in real time to perform graded adjustment processing on the basic waterway information to obtain updated waterway information, and to adjust the waterway according to the updated waterway information. The graded adjustment processing is based on time adjustment items and safety adjustment items.

[0099] The takeoff and landing optimization module 40 is used to perform takeoff and landing optimization according to the takeoff and landing scheduling model when in takeoff and landing state in order to obtain the final takeoff and landing instruction. The takeoff and landing scheduling model is based on time isolation and spatial isolation.

[0100] The present invention also proposes a computer storage medium storing one or more programs that, when executed by a processor, implement the aforementioned intelligent and dynamic traffic management method for future urban air traffic.

[0101] The present invention also proposes a computer device, including a memory and a processor, wherein the memory is used to store computer programs, and the processor is used to execute the computer programs stored in the memory to realize the above-mentioned intelligent and dynamic traffic management method for future urban air traffic.

[0102] Those skilled in the art will understand that the logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-included system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can mean any means that can contain stored, communicated, propagated, or transmitted programs for use by, or in conjunction with, an instruction execution system, apparatus, or device.

[0103] More specific examples of computer-readable media (a non-exhaustive list) include: electrical connections (electronic devices) having one or more wires, portable computer disk drives (magnetic devices), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Furthermore, computer-readable media can even be paper or other suitable media on which the program can be printed, because the program can be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in computer memory.

[0104] It should be understood that various parts of the present invention can be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0105] In the description of this specification, references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of the invention. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0106] The embodiments described above are merely illustrative of several implementations of the present invention, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of the present invention. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of the present invention, and these modifications and improvements all fall within the scope of protection of the present invention. Therefore, the scope of protection of this patent should be determined by the appended claims.

Claims

1. A method for intelligent dynamic traffic management of future urban air traffic, characterized by The application relates to a method for constructing a city traffic route network, and belongs to the field of city traffic route network construction. The method comprises the following steps: Collecting city traffic comprehensive data and constructing a basic route network, wherein the city traffic comprehensive data comprises city geographic information data, city traffic information data and city environment information data, and the basic route network is constructed based on a three-dimensional regional grid; Obtaining target traffic demand and performing route optimization processing according to a minimum loss function to obtain basic route information, wherein the route optimization is based on a multi-constraint weight; The step of obtaining target traffic demand and performing route optimization processing according to a minimum loss function to obtain basic route information specifically comprises the following steps: Obtaining target traffic demand, wherein the target traffic demand comprises take-off and landing area demand information, traffic equipment demand information and personnel demand information; ， wherein, denotes the total loss, denotes the path end time, denotes the path start time, denotes the time, , , , , , denote the time cost term, the noise impact term, the energy consumption term, the safety penalty term, the airspace capacity cost term, the fairness cost term, respectively, , , , , , denote the time weight, the noise weight, the energy weight, the safety weight, the airspace capacity weight, the fairness weight, respectively, , , , , , denote the noise level function, the noise sensitivity coefficient, the energy consumption rate function, the safety penalty function, the airspace congestion degree function, the fairness function, respectively, denotes the speed scalar of the aircraft at time , denotes the altitude of the aircraft at time , denotes the position vector of the aircraft at time , denotes the acceleration vector of the aircraft at time , denotes the wind speed vector at time , denotes the distance of the aircraft at position r(t) to the nearest obstacle, denotes a constant term; Constructing a directed graph in the basic route network according to the target traffic demand, wherein the directed graph is based on a path starting point and a path ending point, a basic path in the directed graph is a straight line path based on a shortest path principle, and path collision possibility is judged according to the directed graph; if a current basic path passes through a city three-dimensional space grid where collision may occur, route optimization processing is performed according to a minimum loss function, and a specific algorithm of the route optimization processing is as follows: Then, route instruction optimization is performed according to a graph convolutional neural network; The directed graph is input into a graph convolutional neural network, and a loss function is minimized as a loss term of the graph convolutional neural network, and flight route instruction optimization is performed to obtain an optimized directed graph G out =(V out , E out ), wherein V out represents a vertex set of the optimized directed graph G out , E out represents an edge set of the optimized directed graph G out , each vertex in the vertex set represents a key instruction point, the key instruction point includes an instruction point time, an instruction point position, a flight speed and a route execution action, and each edge in the edge set represents a flight segment, the flight segment includes an instruction point target, a segment duration, a segment consumption and a segment constraint. The step of performing route instruction optimization according to a graph convolutional neural network specifically comprises the following steps: Obtaining target state parameters in real time, performing hierarchical adjustment processing on the basic route information to obtain updated route information, and performing route adjustment according to the updated route information, wherein the hierarchical adjustment processing is based on a time adjustment item and a safety adjustment item; 2. The intelligent dynamic traffic management method of future city air traffic according to claim 1, characterized in that, When being in a take-off and landing state, take-off and landing optimization is performed according to a take-off and landing scheduling model to obtain final take-off and landing instructions, wherein the take-off and landing scheduling model is based on time isolation and space isolation. The step of collecting city traffic comprehensive data and constructing a basic route network specifically comprises the following steps: Collecting city traffic comprehensive data, wherein the city traffic comprehensive data comprises city geographic information data, city traffic information data and city environment information data; Performing three-dimensional space modeling according to the city geographic information data to obtain a city three-dimensional space model, performing grid division on the city three-dimensional space model, numbering each city three-dimensional space grid, and marking coordinates of all outer edge points of the city three-dimensional space grid according to a three-dimensional space coordinate system; 3. The intelligent dynamic traffic management method of future city air traffic according to claim 1, characterized in that, Marking states of the city three-dimensional space grid according to the city traffic information data and the city environment information data to construct a basic route network, wherein the state marking is based on a binary state mark. The step of obtaining target state parameters in real time and performing hierarchical adjustment processing on the basic route information to obtain updated route information specifically comprises the following steps: Obtaining target state parameters in real time, wherein the target state parameters comprise aircraft state parameters, environment state parameters and airspace state parameters; Performing hierarchical adjustment processing according to the target state parameters, wherein the hierarchical adjustment processing comprises a general case, a special case and a serious case; When it is determined that the current situation is the general case, no route change is performed, and a speed reduction or stay instruction is sent to a specified aircraft; When it is determined that the current situation is the special case, special route change is performed to obtain updated route information. The special route change is based on a time adjustment term, and a specific algorithm of the special route change is as follows: ， wherein, denotes a time cost term, denotes a time weight, denotes a time adjustment term, denotes an original loss; When it is determined that the current situation is serious, a serious route change is performed to obtain updated route information.

4. The intelligent dynamic traffic management method of future city air traffic according to claim 3, characterized in that, The step of performing the serious route change to obtain the updated route information when it is determined that the current situation is serious specifically includes: When it is determined that the current situation is serious, a serious route change is performed to obtain updated route information, the serious route change is based on a safety adjustment term, and a specific algorithm of the serious route change is as follows: ， wherein, represents a safety penalty term, represents a safety weight, represents a safety penalty function, d(r(t)) represents the distance of the aircraft at position r(t) to the nearest obstacle, represents a collision risk weight, represents a collision risk function.

5. The intelligent dynamic traffic management method of future city air traffic according to claim 1, characterized in that, The step of performing the take-off and landing optimization according to the take-off and landing scheduling model to obtain the final take-off and landing instruction specifically includes: The take-off and landing scheduling model is based on a multi-objective optimization model, and a specific algorithm of the take-off and landing scheduling model is as follows: ， ， ， ， ， wherein Minimize denotes minimization, J denotes an optimization objective, , , denote a throughput weight, a delay weight, a noise weight, respectively, , denote a take-off time of different aircrafts, respectively, , denote a landing time of different aircrafts, respectively, denote a desired landing time, denote a desired take-off time, denote a noise model, denote a noise sensitivity coefficient, denote a flight path of different aircrafts, respectively, , denote a safety time interval for landing and take-off, respectively, i, j denote different aircrafts, denote a safety distance, denote an operation time.

6. An intelligent dynamic traffic management system for future urban air traffic, characterized by The method comprises the following steps: The route construction module is configured to collect city traffic comprehensive data and construct a basic route network, the city traffic comprehensive data comprises city geographic information data, city traffic information data and city environment information data, and the basic route network is constructed based on a three-dimensional regional grid; The route optimization module is configured to obtain target traffic demand and perform route optimization processing according to a minimum loss function to obtain basic route information, and the route optimization is based on a multi-constraint weight; The step of obtaining the target traffic demand and performing the route optimization processing according to the minimum loss function to obtain the basic route information specifically includes: The target traffic demand comprises take-off and landing area demand information, traffic equipment demand information and personnel demand information; The target traffic demand is used to construct a directed graph in the basic route network, the directed graph is based on a path starting point and a path ending point, a basic path in the directed graph is a straight line path based on a shortest path principle, and path collision possibility is determined according to the directed graph, if a current basic path passes through a city three-dimensional space grid in which a collision may occur, route optimization processing is performed according to a minimum loss function, and a specific algorithm of the route optimization processing is as follows: ， wherein denotes the total loss, denotes the path end time, denotes the path start time, denotes the time, , , , , , denote the time cost term, the noise impact term, the energy consumption term, the safety penalty term, the airspace capacity cost term, the fairness cost term, respectively, , , , , , denote the time weight, the noise weight, the energy weight, the safety weight, the airspace capacity weight, the fairness weight, respectively, , , , , , denote the noise level function, the noise sensitivity coefficient, the energy consumption rate function, the safety penalty function, the airspace congestion function, the fairness function, respectively, denotes the speed scalar of the aircraft at time , denotes the altitude of the aircraft at time , denotes the position vector of the aircraft at time , denotes the acceleration vector of the aircraft at time , denotes the wind speed vector at time , denotes the distance of the aircraft at position r(t) to the nearest obstacle, denotes a constant term; The route instruction optimization is further performed according to the graph convolutional neural network. The step of performing the route instruction optimization according to the graph convolutional neural network specifically includes: The directed graph is input into the graph convolutional neural network, and a loss function is minimized as a loss term of the graph convolutional neural network, and flight route instruction optimization is performed to obtain an optimized directed graph G out =(V out , E out ), wherein V out represents a vertex set of the optimized directed graph G out , E out represents an edge set of the optimized directed graph G out , each vertex in the vertex set represents a key instruction point, the key instruction point includes an instruction point time, an instruction point position, a flight speed and a route execution action, and each edge in the edge set represents a flight leg, the flight leg includes an instruction point target, a leg duration, a leg consumption and a leg constraint. The hierarchical adjustment module is configured to obtain target state parameters in real time, perform hierarchical adjustment processing on the basic route information to obtain updated route information, and perform route adjustment according to the updated route information, and the hierarchical adjustment processing is based on a time adjustment term and a safety adjustment term. The take-off and landing optimization module is configured to perform take-off and landing optimization according to a take-off and landing scheduling model to obtain a final take-off and landing instruction when in a take-off and landing state, and the take-off and landing scheduling model is based on time isolation and space isolation.

7. A storage medium, characterized by The storage medium stores one or more programs, and the programs are executed by the processor to implement the intelligent dynamic traffic management method for future city air traffic according to any one of claims 1-5.

8. A computer device, comprising: The computer device comprises a memory and a processor. The memory is configured to store a computer program. The processor is configured to execute the computer program stored in the memory to implement the intelligent dynamic traffic management method for future city air traffic according to any one of claims 1-5.

Images