Air-ground collaborative path planning method and system for dynamic congestion-oriented flying car

Abstract

This invention discloses a method and system for air-ground cooperative route planning for flying cars under dynamic congestion, belonging to the field of air traffic route planning technology. Addressing the temporal variation of urban road network congestion and the travel process of flying cars switching between ground driving and flight, this invention establishes a unified air-ground cost metric. Under the constraint of ensuring that different candidate routes experience comparable congestion impacts, a constraint search method based on reference path alignment is constructed to efficiently enumerate and search for takeoff / landing switching points within congested road segments. Finally, by scanning the time preference weight parameter, an energy-time Pareto solution set is generated and a compromise solution is output. This invention achieves optimal trade-off decisions for air-ground cooperative travel of flying cars under dynamic congestion conditions, reducing total energy consumption or shortening total travel time and improving planning interpretability. It has significant application value for improving the operational efficiency and user experience of urban air traffic and intelligent transportation systems.

Description

Technical Field

[0001] This invention relates to the field of air traffic route planning technology, specifically to a method and system for air-ground cooperative route planning for flying cars in the face of dynamic congestion. Background Technology

[0002] With the development of transportation electrification and urban air mobility, electric flying cars, through a collaborative "ground driving + air flight" approach, are expected to provide door-to-door services and alleviate urban traffic congestion. However, in dynamic congestion scenarios, existing air-ground collaborative planning typically suffers from the following shortcomings: (1) Large deviation in ground energy consumption estimation. Many methods use linear "distance-energy consumption" or rely solely on the simplified assumption of average speed, which makes it difficult to characterize the inertial loss caused by vehicles stopping and going in urban congestion, as well as the energy consumption increase caused by the cumulative effect of vehicle auxiliary loads (such as air conditioners and electronic devices) over driving time, thus affecting the rational decision-making on "whether to take off and where to take off / land".

[0003] (2) Insufficient comparability of candidate solutions and high search complexity. Near congested road sections, if candidate solutions are allowed to avoid congestion by detouring, the congestion impact experienced by different candidate solutions will be inconsistent, resulting in distortion of the energy and time comparison caliber; at the same time, the enumeration range of air-to-ground switching points is large and the search space expands, making it difficult to balance optimality and real-time performance.

[0004] To address this, the present invention proposes a method and system for air-ground cooperative path planning for flying cars in the context of dynamic congestion. Summary of the Invention

[0005] The purpose of this invention is to provide a method for air-ground cooperative path planning for flying cars under dynamic congestion, so as to solve the problems of inaccurate energy consumption assessment, incomparable congestion impact of candidate schemes, and complex switching point search in air-ground cooperative planning under dynamic congestion conditions.

[0006] According to a first aspect of the present invention, in order to achieve the above-mentioned objective, the present invention provides the following technical solution: a method for air-ground cooperative path planning for flying cars in dynamic congestion, comprising the following steps: Acquire dynamic traffic information and vehicle task parameters, and identify the congestion edge set Ω and its congestion interval range on the ground reference path based on the dynamic traffic information. The dynamic traffic information includes at least time-varying speed information of the roadside, and the vehicle task parameters include at least the starting point, the destination, and vehicle parameters for subsequent calculations. A ground segment energy consumption time model and a flight segment energy consumption time model are constructed. Based on vehicle mission parameters, ground energy consumption time data and flight energy consumption time data under a unified dimension are calculated and output respectively. The ground segment energy consumption time model introduces an inertial loss term and an auxiliary load power term. The flight segment energy consumption time model decomposes the flight process into three stages: vertical takeoff, horizontal cruise, and vertical landing, and models them respectively. Based on ground energy consumption time data and flight energy consumption time data, the constraint search algorithm CASA based on ground reference path alignment is adopted. Within the congested area, candidate take-off points are enumerated, and for each candidate take-off point, a corresponding candidate air-ground coordination scheme is generated to form a set of candidate schemes. A time preference parameter α is introduced to construct a comprehensive cost function. For each option in the candidate set, its comprehensive cost evaluation value is calculated to form a comprehensive cost set. Based on the candidate solution set and the corresponding comprehensive cost set, an energy-time Pareto front is constructed by scanning time preference parameters. Based on the ideal point distance, a recommended compromise solution is selected from the Pareto front, and the air-ground collaborative planning result is output.

[0007] Furthermore, defining and identifying the set of congested edges Ω includes: Congestion ratio parameters are calculated based on road time-varying speed information. The equivalent velocity factor is defined as: For each edge e in the road network, calculate its equivalent speed under congested conditions: In the formula, ξ represents the congestion ratio parameter, c represents the equivalent speed factor, and e represents the roadside in the road network. This represents the velocity of road edge e in free flow. This represents the equivalent speed of roadside e under congested conditions; Calculated Roadsides with speeds below a preset speed threshold are marked as congested edges, forming a congested edge set Ω. A ground reference path is calculated based on the starting point and destination, and the continuous roadside subsequences on the ground reference path corresponding to the congested edge set Ω are determined as the congested interval range.

[0008] Furthermore, in the ground segment energy consumption time model, the inertial loss term is positively correlated with the congestion ratio parameter ξ, and is used to characterize the additional energy loss caused by the stop-and-go nature of vehicles due to congestion; the auxiliary load power term is used to characterize the energy consumption of on-board auxiliary equipment accumulated over time.

[0009] Furthermore, a ground segment energy consumption time model is constructed, as follows: Define the power of ground traction machinery as: Among them, rolling resistance power Air resistance power With inertial loss power They are respectively: Considering transmission efficiency and non-traction load, the total electrical power is: For length of The passage time for the roadside or section of road is described as follows: Ground segment energy consumption is measured by the change in electrical power over ground travel time. The integral yields: In the formula, The rolling resistance coefficient is... For vehicle quality, air density, The air resistance coefficient, For windward area, To improve efficiency, To assist load power, For the minimum effective speed, These are parameters related to congestion intensity.

[0010] Furthermore, the flight segment energy consumption time model decomposes the flight process into three stages: vertical takeoff, horizontal cruise, and vertical landing, which are modeled separately as follows: Hovering power is obtained based on rotor momentum theory: Let the cruising altitude be The vertical speed of takeoff or climb is The takeoff phase time and energy consumption are as follows: Let the horizontal cruising distance be Cruise speed is Then the cruise phase time and energy consumption are as follows: Let the vertical velocity of descent be... The landing phase time and energy consumption are as follows: In the formula, Indicates hovering power. Indicates the mass of the flying car. Represents gravitational acceleration. Indicates air density, Indicates the number of rotors. Indicates the rotor radius. This represents the overall efficiency parameter of the flight propulsion system. Indicates cruising altitude. Indicates the vertical speed at takeoff or climb. Indicates the time of takeoff. This indicates the energy consumption during the takeoff phase. Indicates horizontal cruising distance. Indicates horizontal cruising speed. Indicates the cruise phase time. Indicates energy consumption during the cruise phase. Indicates the vertical velocity of descent. Indicates the time of the descent phase. This indicates energy consumption during the descent phase. This represents the equivalent windward area of ​​the aircraft. This represents the air drag coefficient.

[0011] Furthermore, the constraint search algorithm CASA based on ground reference path alignment... Includes the following steps: Calculate the shortest ground path from the starting point to the destination as a reference path, identify the continuous edge subsequence on the reference path that intersects with the congested edge set Ω, and determine the starting and ending nodes of the congested interval. Construct a state augmentation graph G', whose state space is defined as a triple S=(n,m,f), where n is the geographic node index, m is the motion mode, and f is the flight execution flag, which is used to characterize whether a flight has been executed to satisfy the single flight constraint. Within the congestion interval of the reference path from the start edge to the end edge, a set of takeoff point indices is constructed according to a preset step size. Each takeoff point is enumerated only once. For each takeoff point, the candidate air-ground cooperative scheme is decomposed into a ground sub-path before congestion, a single flight segment, and a ground sub-path after congestion. The energy consumption and time are calculated for each sub-path, and the total energy consumption is obtained by summing them up. Total Time ; The landing node of the candidate air-ground coordination scheme is constrained to be the head node of the terminating edge of the congestion interval to ensure that different candidate schemes experience the same congestion impact.

[0012] Furthermore, a time preference parameter α is introduced to construct the comprehensive cost function, as follows: Let the total time and total energy consumption corresponding to the energy-priority ground reference solution be respectively. and The total time and total energy consumption corresponding to the time-first extreme solution are respectively and ; Calculate the ground-based baseline solution prioritizing energy consumption and the extreme solutions prioritizing time consumption, and define the normalization factor accordingly: Then, a scalarized synthesis cost function is constructed: In the formula, Indicates the first The comprehensive cost-effectiveness of the candidate air-ground coordination solutions Indicates the first The total time for each candidate air-ground coordination scheme Indicates the first Total energy consumption of the candidate air-ground collaborative schemes Indicates the time normalization factor. This represents the energy consumption normalization factor. This represents the time preference weight parameter, and ;when When it indicates that pure energy consumption takes priority, when "Time" indicates pure time priority.

[0013] Furthermore, based on the ideal point distance, a recommended compromise solution is selected from the Pareto front, and the air-ground cooperative planning result is output as follows: A global scan is performed on the time preference weight parameter α within a preset interval [0,1] with a preset step size to obtain a set of candidate solutions for different values ​​of α. ; For any two candidate solutions and If satisfied If at least one inequality is strictly true, then it is called a candidate solution. Dominant candidate solutions ; Delete collection Given all dominated solutions, we obtain the set of non-dominated solutions. The non-dominated solution set Constructing an energy-time Pareto front, mapping the Pareto front to a dimensionless space, and considering any solution in the Pareto front... Its dimensionless time and dimensionless energy are respectively: in, and These represent the minimum total time and the maximum total time in the Pareto front, respectively. and These represent the minimum and maximum total energy consumption in the Pareto front, respectively; Calculate the Euclidean distance from each Pareto solution to the ideal point (0, 0): When candidate solutions satisfy: Then the candidate solutions This is output as a recommended compromise solution.

[0014] According to a second aspect of the present invention, the present invention provides a flying car air-ground cooperative path planning system for dynamic congestion, used to implement the flying car air-ground cooperative path planning method for dynamic congestion described in the first aspect, characterized in that it includes: The data receiving module is used to receive dynamic traffic information and vehicle task parameters, acquire dynamic traffic information and vehicle task parameters, and identify the congestion edge set Ω and its congestion interval range on the ground reference path based on the dynamic traffic information. The dynamic traffic information includes at least time-varying speed information of the roadside, and the vehicle task parameters include at least the starting point, destination, and vehicle parameters used for calculation of the ground segment energy consumption time model and the flight segment energy consumption time model. The model building module is used to build the ground segment energy consumption time model and the flight segment energy consumption time model. Based on the vehicle mission parameters, it calculates and outputs ground energy consumption time data and flight energy consumption time data under a unified dimension. The ground segment energy consumption time model introduces an inertial loss term and an auxiliary load power term. The flight segment energy consumption time model decomposes the flight process into three stages: vertical takeoff, horizontal cruise, and vertical landing, and models them separately. The constraint search solution module is used to solve the constraint search algorithm CASA based on ground reference path alignment, using ground energy consumption time data and flight energy consumption time data. Within the congested area, candidate take-off points are enumerated, and for each candidate take-off point, a corresponding candidate air-ground coordination scheme is generated to form a set of candidate schemes. The comprehensive cost function construction module is used to introduce the time preference parameter α to construct the comprehensive cost function, calculate the comprehensive cost evaluation value of each solution in the candidate solution set, and form a comprehensive cost set. The Pareto decision module is used to construct an energy-time Pareto front based on a set of candidate solutions and a set of corresponding comprehensive costs by scanning time preference parameters, select a recommended compromise solution from the Pareto front based on the ideal point distance, and output the air-ground collaborative planning results.

[0015] According to a third aspect of the present invention, the present invention provides a terminal device, including a memory, a processor, and a computer program stored in the memory and capable of running on the processor, characterized in that, when the processor loads and executes the computer program, it employs the air-ground cooperative path planning method for flying cars oriented towards dynamic congestion described in the first aspect.

[0016] This invention has at least the following beneficial effects: 1. This invention constructs a normalized linear scalarized comprehensive cost function by introducing a time preference parameter α, and combines this with a global scan to construct an energy-time Pareto front, thus achieving a systematic characterization of the energy-time trade-off. Compared to existing technologies that only output a single optimal solution, this invention can provide a complete trade-off decision space based on different user preferences, and automatically output recommended compromise solutions through ideal point distance calculation, making the planning results more flexible and interpretable, and meeting the diverse needs of different travel scenarios.

[0017] 2. This invention, by constructing a state-enhanced graph G', incorporates motion modes and flight execution flags into the state space definition, effectively realizing the expression of single-flight constraints and the management of mode switching during the search process. This state space design enables CASA... The algorithm can efficiently handle mode switching between ground driving and air flight, ensuring that the search process obtains a globally optimal or near-optimal air-ground cooperative solution while satisfying physical constraints. 3. This invention decomposes the flight segment energy consumption time model into three stages: vertical takeoff, horizontal cruise, and vertical landing, and models them separately. These stages are then compared with the ground segment model under a unified dimensional framework. This overcomes the problem of the lack of a unified metric benchmark in existing technologies for air-to-ground mode switching decisions. This phased modeling method can accurately depict the energy consumption characteristics of each stage of the flight process, making the energy consumption and time comparison of air-to-ground cooperative schemes more physically based and interpretable, and significantly improving the reliability of mode switching decisions.

[0018] 4. This invention employs a constraint search algorithm, CASA, based on ground reference path alignment. This approach limits the enumeration range of takeoff points to within congested intervals and constrains landing nodes to be the head nodes of the terminating edges of congested intervals. This effectively solves the problems of incomparable congestion impacts and search space expansion caused by different candidate solutions avoiding congestion in existing technologies. This congestion consistency constraint strategy ensures that all candidate solutions experience the same congestion impacts, making energy and time comparisons consistent. Simultaneously, by narrowing the enumeration range of switching points, it significantly reduces search complexity, balancing optimal solution and real-time computation.

[0019] 5. This invention addresses the problem of inaccurate energy consumption assessment under dynamic congestion conditions caused by the use of linear "distance-energy consumption" or average speed simplification assumptions in existing technologies by introducing an inertial loss term and an auxiliary load power term into the ground segment energy consumption time model. Specifically, the inertial loss term accurately characterizes the additional energy loss caused by the stop-and-go nature of vehicles in congested traffic, while the auxiliary load power term reflects the nonlinear energy consumption deviation caused by the cumulative effect of onboard auxiliary equipment (such as air conditioning and electronic systems) over travel time. This makes the ground segment energy consumption assessment closer to actual operating conditions, providing an accurate physical basis for optimizing takeoff and landing points.

[0020] Of course, any product implementing this invention does not necessarily need to achieve all of the advantages described above at the same time. Attached Figure Description

[0021] 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, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0022] Figure 1 This is a flowchart illustrating the method described in this invention; Figure 2 This is the pattern selection phase diagram of the present invention under different congestion ratios and time preference weights; Figure 3 This is a schematic diagram of the energy-time Pareto front and recommended trade-off point under different congestion intensities according to the present invention; Figure 4 This is a schematic diagram illustrating the relationship between the time preference weight and total travel time and total energy consumption in this invention; Figure 5 This is a schematic diagram of the air-ground coordinated path under the 50% congestion scenario of this invention with time preference α=0.6. 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 without creative effort are within the scope of protection of this application.

[0024] Example 1: Please see Figure 1 and Figure 2 This invention provides a technical solution: a method for air-ground cooperative path planning for flying cars in dynamic congestion, comprising the following steps: Step 1: Obtain dynamic traffic information and vehicle and mission parameters. The dynamic traffic information includes at least time-varying speed information along the roadside. The vehicle and mission parameters include at least the starting point, destination, and vehicle parameters used for calculating the ground segment energy consumption time model and the flight segment energy consumption time model. Vehicle parameters include vehicle mass, number of rotors, rotor radius, etc. Based on dynamic traffic information, the set of congested edges Ω and the range of congested intervals on the ground reference path are identified, which provides a basis for subsequent reference path alignment and consistency constraints. Define and identify the congested edge set Ω, including: Congestion ratio parameters are calculated based on road time-varying speed information. The equivalent velocity factor is defined as: For each edge e in the road network, calculate its equivalent speed under congested conditions: In the formula, ξ represents the congestion ratio parameter, c represents the equivalent speed factor, and e represents the roadside in the road network. This represents the velocity of road edge e in free flow. This represents the equivalent speed of roadside e under congested conditions; Calculated Roadsides with speeds below a preset threshold are marked as congested edges, forming a congested edge set Ω. A ground reference path is calculated based on the starting point and destination, and the continuous roadside subsequences on the ground reference path corresponding to the congested edge set Ω are determined as the congested interval range. Step 2: Establish energy consumption and travel time models for the ground and flight segments within a unified physical metric framework, and form the energy-time basis for subsequent optimization, namely, ground energy consumption time data and flight energy consumption time data, as detailed below: Step 2-1: Establish a ground segment energy-time model: Ground congestion causes additional inertial losses due to stop-and-go traffic, and the onboard auxiliary load accumulates over time, causing nonlinear energy consumption deviations. Therefore, a ground traction power model is constructed, and the total ground electrical power is obtained after considering efficiency and auxiliary load. Then, the travel time is calculated from the road segment length and equivalent speed, and the ground energy consumption is obtained from the power integration, as follows: Considering that dynamic congestion leads to stop-and-go traffic and thus generates additional inertial losses, and that the power of onboard auxiliary loads accumulates over time, causing nonlinear energy consumption deviations, the power of ground traction machinery is defined as follows: Among them, the rolling resistance power, air resistance power, and inertial loss power are respectively: Considering transmission efficiency and non-traction load, the total electrical power is: For length of The passage time for roadside / sections can be described as follows: Energy consumption on the ground road section is obtained by integrating electrical power over time.

[0025] In the formula, The rolling resistance coefficient is... For vehicle quality, air density, The air resistance coefficient, For windward area, To improve efficiency, To assist load power, For the minimum effective speed, A parameter related to congestion intensity; Step 2-2: Flight Segment Energy Consumption Time Model. The flight process is decomposed into three stages: "vertical takeoff - horizontal cruise - vertical landing," each modeled separately. Hovering power is obtained based on rotor momentum theory, and the time and energy consumption of each stage are calculated to obtain the total flight segment time and total energy consumption, as detailed below: Hovering power is obtained based on rotor momentum theory: Let the cruising altitude be Takeoff / climb vertical speed is The takeoff phase time and energy consumption are as follows: Let the horizontal cruising distance be Cruise speed is Then the cruise phase time and energy consumption are as follows: Let the vertical velocity of descent be... The landing phase time and energy consumption are as follows: In the formula, Indicates hovering power. Indicates the mass of the flying car. Represents gravitational acceleration. Indicates air density, Indicates the number of rotors. Indicates the rotor radius. This represents the overall efficiency parameter of the flight propulsion system. Indicates cruising altitude. Indicates the vertical speed at takeoff or climb. Indicates the time of takeoff. This indicates the energy consumption during the takeoff phase. Indicates horizontal cruising distance. Indicates horizontal cruising speed. Indicates the cruise phase time. Indicates energy consumption during the cruise phase. Indicates the vertical velocity of descent. Indicates the time of the descent phase. This indicates energy consumption during the descent phase. This represents the equivalent windward area of ​​the aircraft. Indicates the air drag coefficient; Step 3: Based on ground energy consumption time data and flight energy consumption time data, the constraint search algorithm CASA based on ground reference path alignment is used. Within the congested area, candidate takeoff points are enumerated, and for each candidate takeoff point, a corresponding candidate air-ground coordination scheme is generated, forming a set of candidate schemes, as follows: Calculate the shortest ground path from the starting point to the destination as a reference path, identify the continuous edge subsequence on the reference path that intersects with the congested edge set Ω, and determine the starting and ending nodes of the congested interval. Construct a state augmentation graph G', whose state space is defined as a triple S=(n,m,f), where n is the geographic node index, m is the motion mode, and f is the flight execution flag, which is used to characterize whether a flight has been executed to satisfy the single flight constraint. Within the congestion interval of the reference path, from the start edge to the end edge, a set of takeoff point indices is constructed according to a preset step size. Each takeoff point is enumerated only once. For each takeoff point, the candidate air-ground cooperative scheme is decomposed into a ground sub-path before congestion, a single flight segment, and a ground sub-path after congestion. The energy consumption and time are calculated separately for each sub-path, and the total energy consumption is obtained by summing them up. Total Time ; The landing node of the candidate air-ground coordination scheme is constrained to the head node of the congestion interval termination edge to ensure that different candidate schemes experience the same congestion impact. Step 4: To achieve single-objective heuristic search while preserving the energy-time tradeoff, a normalized linear scalarization is used to construct the comprehensive cost function. Let the total time and total energy consumption corresponding to the energy-priority ground benchmark solution be respectively... and The total time and total energy consumption corresponding to the time-first extreme solution are respectively and ; Calculate the ground-based baseline solution prioritizing energy consumption and the extreme solutions prioritizing time consumption, and define the normalization factor accordingly: Then, a scalarized synthesis cost function is constructed: In the formula, Indicates the first The comprehensive cost-effectiveness of the candidate air-ground coordination solutions Indicates the first The total time for each candidate air-ground coordination scheme Indicates the first Total energy consumption of the candidate air-ground collaborative schemes Indicates the time normalization factor. This represents the energy consumption normalization factor. This represents the time preference weight parameter, and ;when When it indicates that pure energy consumption takes priority, when Time indicates pure time priority; Then, under the reference path alignment strategy, a set of takeoff points is constructed only within the congested section of the reference path, and each takeoff point is enumerated once. The candidate air-ground coordination scheme is decomposed into "ground sub-path before congestion - single flight segment - ground sub-path after congestion", and the energy consumption and time are calculated separately and summed to obtain the total energy consumption. Total Time Then calculate the overall cost. Output the candidate air-ground coordination scheme with the best overall cost, such as Figure 4 The diagram shows the relationship between time preference weights and total travel time and total energy consumption. Step 5: As Figure 3 As shown, based on the candidate solution set and the corresponding comprehensive cost set, an energy-time Pareto front is constructed by scanning the time preference parameter. Based on the ideal point distance, a recommended compromise solution is selected from the Pareto front, and the air-ground collaborative planning results are output, as follows: A global scan is performed on the time preference weight parameter α within a preset interval [0,1] with a preset step size to obtain a set of candidate solutions for different values ​​of α. ; For any two candidate solutions and If satisfied If at least one inequality is strictly true, then it is called a candidate solution. Dominant candidate solutions ; Delete collection Given all dominated solutions, we obtain the set of non-dominated solutions. The non-dominated solution set Construct an energy-time Pareto front; map the Pareto front to a dimensionless space, and for any solution in the Pareto front... Its dimensionless time and dimensionless energy are respectively: in, and These represent the minimum total time and the maximum total time in the Pareto front, respectively. and These represent the minimum and maximum total energy consumption in the Pareto front, respectively; Calculate the Euclidean distance from each Pareto solution to the ideal point (0, 0): Choose the option that satisfies: Choose the one with the smallest distance. The solution is output as a recommended compromise solution. The output results include at least the Pareto front and the recommended air-ground cooperative solution (including the ground segment path, takeoff point, air segment, landing point and subsequent ground segment path) and their corresponding total energy consumption and total time indices.

[0026] In summary, this invention first addresses the issue of varying urban road network congestion over time and the travel process of flying cars switching between ground driving and air flight, establishing a unified air-ground cost metric. The ground component considers speed changes caused by congestion, stop-and-go inertial losses, and energy consumption of onboard auxiliary loads, while the air component considers energy and time consumption during vertical take-off and landing and horizontal cruise phases.

[0027] Then, under the constraint of ensuring that different candidate solutions experience comparable congestion effects, a constraint search method (CASA) based on reference path alignment is constructed. This allows for efficient enumeration and search solutions for takeoff / landing switching points within congested road sections.

[0028] Finally, by scanning the time preference weight parameters, an energy-time Pareto solution set is generated and a compromise solution is output to achieve the optimal trade-off decision for air-ground cooperative travel of flying cars under dynamic congestion conditions, thereby reducing total energy consumption or shortening total travel time and improving the interpretability of the plan.

[0029] The technical solution of this embodiment will be further elaborated below with reference to specific simulation experiments: To verify the effectiveness of the air-ground cooperative path planning method for flying cars in dynamic congestion as described in this invention, experimental verification was conducted in the SUMO-Python co-simulation environment. SUMO was used to simulate the microscopic traffic dynamics of urban roads and output the actual travel time of vehicles, while the Python side was used to execute the path planning algorithm described in this invention and calculate the total time and total energy consumption of candidate air-ground cooperative schemes.

[0030] The simulated road network adopts the Manhattan-grid urban grid road network. To ensure that different candidate schemes experience comparable congestion effects, the planning layer constrains candidate paths to include continuous road edge subsequences corresponding to the congestion edge set; in the simulation layer, congestion is imposed by reducing the maximum speed limit of each lane in the congested section, thereby ensuring that the planning layer and the simulation layer interpret congestion intensity consistently.

[0031] Simulation parameters include vehicle mass, air density, drag coefficient, rolling drag coefficient, frontal area, ground propulsion efficiency, auxiliary load power, inertial loss coefficient, number of rotors, rotor radius, and takeoff speed, cruising speed, and landing speed. Specifically, the vehicle mass is taken as 450 kg, air density as 1.225 kg / m³, drag coefficient as 0.35, rolling drag coefficient as 0.015, frontal area as 2.6 m², ground propulsion efficiency as 0.85, auxiliary load power as 2000 W, inertial loss coefficient as 1.2 m / s², number of rotors as 4, rotor radius as 0.3 m, takeoff speed as 8 m / s, cruising speed as 25 m / s, and landing speed as 8 m / s. These parameters serve as unified input parameters for both the ground segment energy consumption time model and the flight segment energy consumption time model to ensure consistency in evaluation criteria across different travel modes.

[0032] Nine congestion intensities were set up, and the time preference parameter α was scanned at a preset step size to obtain a set of candidate air-ground coordination schemes for each scenario. Based on this, an energy-time Pareto front and a recommended compromise scheme were constructed.

[0033] Experimental results show that: Figure 5 The diagram shows an air-ground cooperative path with a time preference α=0.6 under a 50% congestion scenario. In the high-congestion scenario, the recommended compromise mode switching threshold is approximately α ≈0.5. As the congestion level decreases, the threshold gradually shifts to α ≈0.8~0.9, indicating that the present invention can adaptively suppress unnecessary flights based on the congestion intensity. At the same time, the Pareto front shrinks as the congestion decreases, and the typical path gradually transitions from flight-based to ground-based, verifying that the present invention can adaptively adjust air-ground switching decisions under different congestion intensities, achieving a trade-off optimization of total time and total energy consumption, and improving the interpretability of path planning results.

[0034] Example 2: This embodiment provides a flying car air-ground cooperative path planning system for dynamic congestion, used to implement the flying car air-ground cooperative path planning method for dynamic congestion described in the first aspect, characterized by including: The data receiving module is used to receive dynamic traffic information and vehicle task parameters, and to identify the congestion edge set Ω and its congestion interval range on the ground reference path based on the dynamic traffic information. The dynamic traffic information includes at least time-varying speed information of the roadside, and the vehicle task parameters include at least the starting point, the destination, and vehicle parameters used for calculation of the ground segment energy consumption time model and the flight segment energy consumption time model. The model building module is used to build the ground segment energy consumption time model and the flight segment energy consumption time model. Based on the vehicle mission parameters, it calculates and outputs ground energy consumption time data and flight energy consumption time data under a unified dimension. The ground segment energy consumption time model introduces an inertial loss term and an auxiliary load power term. The flight segment energy consumption time model decomposes the flight process into three stages: vertical takeoff, horizontal cruise, and vertical landing, and models them separately. The constraint search solution module is used to solve the constraint search algorithm CASA based on ground reference path alignment, using ground energy consumption time data and flight energy consumption time data. Within the congested area, candidate take-off points are enumerated, and for each candidate take-off point, a corresponding candidate air-ground coordination scheme is generated to form a set of candidate schemes. The comprehensive cost function construction module is used to introduce the time preference parameter α to construct the comprehensive cost function, calculate the comprehensive cost evaluation value of each solution in the candidate solution set, and form a comprehensive cost set. The Pareto decision module is used to construct an energy-time Pareto front based on a set of candidate solutions and a set of corresponding comprehensive costs by scanning time preference parameters, select a recommended compromise solution from the Pareto front based on the ideal point distance, and output the air-ground collaborative planning results.

[0035] Example 3: The present invention provides a terminal device, including a memory, a processor, and a computer program stored in the memory and capable of running on the processor. The memory stores the computer program capable of running on the processor. When the processor loads and executes the computer program, it adopts the flying car air-ground cooperative path planning method for dynamic congestion described in Embodiment 1.

[0036] It should be noted that the terminal device can be a computer device such as a desktop computer, a laptop computer, or a cloud server, and the terminal device includes, but is not limited to, a processor and a memory. For example, the terminal device may also include input / output devices, network access devices, and buses.

[0037] Furthermore, the processor can be a central processing unit (CPU). Of course, depending on the actual use, other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), off-the-shelf programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. can also be used. The general-purpose processor can be a microprocessor or any conventional processor, etc., and this application does not limit it in this regard.

[0038] In the description of this specification, the references to terms such as "an embodiment," "example," "specific example," 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 this application. 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.

[0039] The foregoing has shown and described the basic principles, main features, and advantages of this application. Those skilled in the art should understand that this application is not limited to the above embodiments. The embodiments and descriptions in the specification are merely illustrative of the principles of this application. Various changes and modifications can be made to this application without departing from the spirit and scope thereof, and all such changes and modifications fall within the scope of the claims of this application.

Claims

1. A dynamic congestion-oriented air-ground cooperative path planning method for flying cars, characterized in that, Includes the following steps: Acquire dynamic traffic information and vehicle task parameters, and identify the congestion edge set Ω and its congestion interval range on the ground reference path based on the dynamic traffic information. The dynamic traffic information includes at least time-varying speed information of the roadside, and the vehicle task parameters include at least the starting point, the destination, and vehicle parameters for subsequent calculations. A ground segment energy consumption time model and a flight segment energy consumption time model are constructed. Based on vehicle mission parameters, ground energy consumption time data and flight energy consumption time data under a unified dimension are calculated and output respectively. The ground segment energy consumption time model introduces an inertial loss term and an auxiliary load power term. The flight segment energy consumption time model decomposes the flight process into three stages: vertical takeoff, horizontal cruise, and vertical landing, and models them respectively. According to the ground energy consumption time data and the flight energy consumption time data, a constraint search algorithm CASA based on ground reference path alignment is adopted Enumerate candidate takeoff points in the congestion interval range, and generate corresponding candidate air-ground coordination schemes for each candidate takeoff point to form a candidate scheme set. A time preference parameter α is introduced to construct a comprehensive cost function. For each option in the candidate set, its comprehensive cost evaluation value is calculated to form a comprehensive cost set. Based on the candidate solution set and the corresponding comprehensive cost set, an energy-time Pareto front is constructed by scanning time preference parameters. Based on the ideal point distance, a recommended compromise solution is selected from the Pareto front, and the air-ground collaborative planning result is output.

2. The air-ground coordinated path planning method for flying cars in dynamic congestion according to claim 1, characterized in that: Define and identify the congested edge set Ω, including: Calculating congestion proportion parameter according to road time-varying speed information An equivalent speed factor is defined as: For each edge e in the road network, the equivalent speed in the congested state is computed: wherein ξ denotes a congestion proportionality parameter, c denotes an equivalent speed factor, e denotes a road edge in the road network, denotes a speed of the road edge e in a free flow state, denotes an equivalent speed of the road edge e in a congested state; Calculated Roadsides with speeds below a preset speed threshold are marked as congested edges, forming a congested edge set Ω. A ground reference path is calculated based on the starting point and destination, and the continuous roadside subsequences on the ground reference path corresponding to the congested edge set Ω are determined as the congested interval range.

3. The method for air-ground cooperative path planning for flying cars in dynamic congestion according to claim 1, characterized in that: In the ground segment energy consumption time model, the inertial loss term is positively correlated with the congestion ratio parameter ξ, and is used to characterize the additional energy loss caused by the stop-and-go nature of vehicles due to congestion; the auxiliary load power term is used to characterize the energy consumption of on-board auxiliary equipment accumulated over time.

4. The method for air-ground cooperative path planning for flying cars in dynamic congestion according to claim 1, characterized in that: The ground segment energy consumption time model is constructed as follows: Define the power of ground traction machinery as: Among them, rolling resistance power Air resistance power With inertial loss power They are respectively: Considering transmission efficiency and non-traction load, the total electrical power is: For length of The passage time for the roadside or section of road is described as follows: Ground segment energy consumption is measured by the change in electrical power over ground travel time. The integral yields: In the formula, The rolling resistance coefficient is... For vehicle quality, air density, The air resistance coefficient, For windward area, To improve efficiency, To assist load power, For the minimum effective speed, These are parameters related to congestion intensity.

5. The method for air-ground cooperative path planning for flying cars in dynamic congestion according to claim 4, characterized in that: The flight segment energy consumption time model decomposes the flight process into three stages: vertical takeoff, horizontal cruise, and vertical landing, and models them separately as follows: Hovering power is obtained based on rotor momentum theory: Let the cruising altitude be The vertical speed of takeoff or climb is The takeoff phase time and energy consumption are as follows: Let the horizontal cruising distance be Cruise speed is Then the cruise phase time and energy consumption are as follows: Let the vertical velocity of descent be... The landing phase time and energy consumption are as follows: In the formula, Indicates hovering power. Indicates the mass of the flying car. Represents gravitational acceleration. Indicates air density, Indicates the number of rotors. Indicates the rotor radius. This represents the overall efficiency parameter of the flight propulsion system. Indicates cruising altitude. Indicates the vertical speed at takeoff or climb. Indicates the time of takeoff. This indicates the energy consumption during the takeoff phase. Indicates horizontal cruising distance. Indicates horizontal cruising speed. Indicates the cruise phase time. Indicates energy consumption during the cruise phase. Indicates the vertical velocity of descent. Indicates the time of the descent phase. This indicates energy consumption during the descent phase. This represents the equivalent windward area of ​​the aircraft. This represents the air drag coefficient.

6. The method for air-ground cooperative path planning for flying cars in dynamic congestion according to claim 1, characterized in that: Constraint Search Algorithm CASA Based on Ground Reference Path Alignment Includes the following steps: Calculate the shortest ground path from the starting point to the destination as a reference path, identify the continuous edge subsequence on the reference path that intersects with the congested edge set Ω, and determine the starting and ending nodes of the congested interval. Construct a state augmentation graph G', whose state space is defined as a triple S=(n,m,f), where n is the geographic node index, m is the motion mode, and f is the flight execution flag, which is used to characterize whether a flight has been executed to satisfy the single flight constraint. Within the congestion interval of the reference path from the start edge to the end edge, a set of takeoff point indices is constructed according to a preset step size. Each takeoff point is enumerated only once. For each takeoff point, the candidate air-ground cooperative scheme is decomposed into a ground sub-path before congestion, a single flight segment, and a ground sub-path after congestion. The energy consumption and time are calculated for each sub-path, and the total energy consumption is obtained by summing them up. Total Time ; The landing node of the candidate air-ground coordination scheme is constrained to be the head node of the terminating edge of the congestion interval to ensure that different candidate schemes experience the same congestion impact.

7. The method for air-ground cooperative path planning for flying cars in dynamic congestion according to claim 1, characterized in that: A comprehensive cost function is constructed by introducing a time preference parameter α, as follows: Let the total time and total energy consumption corresponding to the energy-priority ground reference solution be respectively. and The total time and total energy consumption corresponding to the time-first extreme solution are respectively and ; Calculate the ground-based baseline solution prioritizing energy consumption and the extreme solutions prioritizing time consumption, and define the normalization factor accordingly: Then, a scalarized synthesis cost function is constructed: In the formula, Indicates the first The comprehensive cost-effectiveness of the candidate air-ground coordination solutions Indicates the first The total time for each candidate air-ground coordination scheme Indicates the first Total energy consumption of the candidate air-ground collaborative schemes Indicates the time normalization factor. This represents the energy consumption normalization factor. This represents the time preference weight parameter, and ;when When it indicates that pure energy consumption takes priority, when "Time" indicates pure time priority.

8. The method for air-ground cooperative path planning for flying cars in dynamic congestion according to claim 1, characterized in that: An energy-time Pareto front is constructed by scanning time preference parameters. Based on the ideal point distance, a recommended compromise scheme is selected from the Pareto front, and the air-ground collaborative planning result is output as follows: A global scan is performed on the time preference weight parameter α within a preset interval [0,1] with a preset step size to obtain a set of candidate solutions for different values ​​of α. ; For any two candidate solutions and If satisfied If at least one inequality is strictly true, then it is called a candidate solution. Dominant candidate solutions ; Delete collection Given all dominated solutions, we obtain the set of non-dominated solutions. The non-dominated solution set Constructing an energy-time Pareto front, mapping the Pareto front to a dimensionless space, and considering any solution in the Pareto front... Its dimensionless time and dimensionless energy are respectively: in, and These represent the minimum total time and the maximum total time in the Pareto front, respectively. and These represent the minimum and maximum total energy consumption in the Pareto front, respectively; Calculate the Euclidean distance from each Pareto solution to the ideal point (0, 0): When candidate solutions satisfy: Then the candidate solutions This is output as a recommended compromise solution.

9. A flying car air-ground cooperative path planning system for dynamic congestion, used to implement the flying car air-ground cooperative path planning method for dynamic congestion as described in any one of claims 1 to 8, characterized in that, include: The data receiving module is used to acquire dynamic traffic information and vehicle task parameters, and to identify the congestion edge set Ω and its congestion interval range on the ground reference path based on the dynamic traffic information. The dynamic traffic information includes at least time-varying speed information of the roadside, and the vehicle task parameters include at least the starting point, the destination, and vehicle parameters used for calculation of the ground segment energy consumption time model and the flight segment energy consumption time model. The model building module is used to build the ground segment energy consumption time model and the flight segment energy consumption time model, and calculate the ground segment energy consumption time data and the flight segment energy consumption time data under the unified evaluation framework based on the vehicle mission parameters. The ground segment energy consumption time model introduces an inertial loss term and an auxiliary load power term, and the flight segment energy consumption time model decomposes the flight process into three stages: vertical takeoff, horizontal cruise, and vertical landing, and models them separately. The constraint search solution module is used to perform a constraint search algorithm (CASA) based on the ground segment energy consumption time data and the flight segment energy consumption time data. Within the congested area, candidate takeoff points are enumerated, and for each candidate takeoff point, a corresponding candidate air-ground coordination scheme is generated to form a candidate scheme set. The comprehensive cost function construction module is used to introduce the time preference parameter α to construct the comprehensive cost function, and to calculate the comprehensive cost value for each candidate air-ground coordination scheme in the candidate scheme set, thus forming a comprehensive cost set; The Pareto decision module is used to construct an energy-time Pareto front based on the candidate solution set and the corresponding comprehensive cost set by scanning the time preference parameter α, and select a recommended compromise solution from the Pareto front based on the ideal point distance, and output the air-ground cooperative path planning result.

10. A terminal device, comprising a memory, a processor, and a computer program stored in the memory and capable of running on the processor, characterized in that, When the processor loads and executes the computer program, it employs the air-ground cooperative path planning method for flying cars oriented towards dynamic congestion, as described in any one of claims 1 to 8.

Images