Low altitude traffic control method and system for aircraft

Abstract

The present invention relates to the field of flight control technology, and specifically to a low-altitude traffic control method and system for aircraft. The steps of the control method include: building a wireless communication network, ensuring data exchange between aircraft through a multi-level topology structure and dynamic spectrum management technology, and the wireless communication network adopts a channel evaluation mechanism to adapt to the changing airspace environment and ensure a stable high-bandwidth connection. The present invention first solves the communication delay problem caused by reliance on ground infrastructure in traditional systems by building a wireless communication network and adopting a multi-level topology structure and dynamic spectrum management technology. Through the channel evaluation mechanism, the network can adapt to the changing airspace environment to ensure stable and reliable data transmission between aircraft, and the realization of high-bandwidth connection provides a solid guarantee for real-time monitoring and dynamic decision-making.

Description

Technical Field

[0001] The present invention relates to the field of flight control technology, and in particular to a low-altitude traffic control method and system for aircraft. Background Art

[0002] With the rise of drones and various low-altitude aircraft, the need for low-altitude traffic control is imminent. Currently, the low-altitude traffic control system is still in its early stages of development, facing many problems such as communication delays, low efficiency in flight conflict detection and resolution, and unable to meet the growing demand for low-altitude safe flight of aircraft.

[0003] The existing solution corresponding to this technical solution is that the existing low-altitude traffic control system mostly relies on ground infrastructure and personnel operations to monitor and control aircraft, and tracks the status and position of aircraft through radar, optoelectronic and other sensors. However, when faced with a large number of aircraft flying at the same time, such systems have limited processing capabilities and response speeds, making it difficult to ensure the safety of low-altitude flights.

[0004] In view of the above introduction to the current status of low-altitude flight and existing processing methods, the technical problem proposed by the present invention is: how to solve the problems of low-altitude traffic control such as insufficient and comprehensive flight monitoring, low efficiency of conflict detection and processing, and difficulty in adapting to the complex and changeable low-altitude flight environment. Summary of the invention

[0005] The present invention provides a low-altitude traffic control method and system for aircraft to solve the technical problems of real-time communication delay, insufficient efficiency in rapid detection and processing of flight conflicts, and poor system adaptability during low-altitude flight.

[0006] The technical solution of the present invention to solve the above technical problems is as follows:

[0007] In one aspect, a low-altitude traffic control method for an aircraft is provided, the steps of the control method comprising:

[0008] Build a wireless communication network to ensure data exchange between aircraft through multi-level topology and dynamic spectrum management technology. The wireless communication network adopts a channel assessment mechanism to adapt to the changing airspace environment and ensure stable high-bandwidth connections;

[0009] Integrate and process multi-modal sensor data from the aircraft, including positioning, navigation and control systems, optical radar and meteorological data, and use data fusion technology to improve the time synchronization of sensor data to provide a data basis for path planning;

[0010] Develop a path planning algorithm based on dynamic risk assessment, which combines static obstacles and dynamic targets to evaluate the risk cost of path planning to determine the optimal route;

[0011] Implement multi-target conflict detection and avoidance strategies, use prediction models to evaluate the aircraft's motion status in real time, and identify and avoid potential flight path conflicts;

[0012] Perform self-organizing adjustments to the flight path to respond to immediate changes in airspace conditions, monitor the flight process of the aircraft and provide real-time feedback to the path planning system, and continuously optimize the flight path through a feedback mechanism.

[0013] On the other hand, a low-altitude traffic control system for an aircraft is provided, the control system comprising:

[0014] Communication module, which realizes adaptive connection and data transmission between aircrafts, and can dynamically manage channels and fault recovery;

[0015] The data processing module is responsible for integrating multi-source sensor information, real-time error correction and using filtering mechanisms to ensure data quality;

[0016] The path planning module integrates a multi-objective optimization algorithm and combines static and dynamic environmental factors to provide real-time path suggestions for the aircraft;

[0017] Conflict avoidance module, which uses prediction and simulation techniques to ensure safe and effective flight path selection;

[0018] The self-organizing adjustment module performs path selection and real-time adjustment, and optimizes flight strategies through feedback mechanisms;

[0019] The learning and prediction module uses the reinforcement learning framework to accumulate and summarize historical flight path data and update it into the control strategy.

[0020] The beneficial effects of the present invention are:

[0021] The present invention first solves the communication delay problem caused by reliance on ground infrastructure in traditional systems by building a wireless communication network and adopting a multi-level topology and dynamic spectrum management technology. Through the channel evaluation mechanism, the network can adapt to the changing airspace environment to ensure stable and reliable data transmission between aircraft. The realization of high-bandwidth connections provides a solid guarantee for real-time monitoring and dynamic decision-making, thereby improving the response speed of the entire system to complex airspace conditions.

[0022] Furthermore, the present invention integrates and processes multimodal sensor data, improves data synchronization through data fusion technology, and solves the problem of incomplete information caused by isolation of sensor data and large time differences in existing systems. Especially in the path planning link, through the fusion analysis of positioning, navigation and control system, optical radar and meteorological data, it can provide a more accurate and comprehensive data foundation for the algorithm. Thus, the improvement of path planning is comprehensive and accurate.

[0023] Furthermore, the present invention introduces a path planning algorithm based on dynamic risk assessment and a multi-target conflict detection and avoidance strategy. Different from the traditional model that relies on ground personnel operation, the present invention combines static obstacles and dynamic targets to comprehensively evaluate the risk cost in path planning and intelligently determine the optimal route. It improves the processing efficiency of conflict detection and avoidance, ensuring that the system can still respond quickly to potential flight conflicts when multiple aircraft are flying at the same time.

[0024] In addition, the ability to perform self-organizing adjustments to the flight path enables the system to respond quickly to immediate changes in airspace conditions, and continuously optimize the flight path through real-time monitoring and feedback mechanisms. This not only improves the autonomy and flexibility of the aircraft, but also solves the problem that the existing system is difficult to adapt to the complex and changeable low-altitude flight environment, and ultimately achieves efficient, safe and intelligent management of low-altitude traffic control. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] Figure 1 A flowchart of a low-altitude traffic control method for an aircraft in one embodiment of the present invention;

[0026] Figure 2 A schematic diagram of a multi-layer topology structure of a wireless network in an embodiment of the present invention;

[0027] Figure 3 This is a schematic diagram of sensor multimodal data fusion synchronization in one embodiment of the present invention;

[0028] Figure 4 A schematic diagram of self-organized adjustment of a flight path in one embodiment of the present invention;

[0029] Figure 5 A schematic diagram of a flight path planning simulation in one embodiment of the present invention;

[0030] Figure 6 This is a simulation diagram of the flight path and avoidance strategy in one embodiment of the present invention. DETAILED DESCRIPTION

[0031] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0032] The term "comprise" and any variations thereof in the specification and claims of the present application are intended to cover non-exclusive inclusions. For example, a process, method, system, product or apparatus comprising a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to these processes, methods, products or apparatuses.

[0033] In the embodiments of the present invention, words such as "exemplary" or "for example" are used to indicate examples, illustrations or explanations. Any embodiment or design described as "exemplary" or "for example" in the embodiments of the present invention should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "exemplary" or "for example" is intended to present related concepts in a specific way.

[0034] The present invention provides the following preferred embodiments:

[0035] Embodiment 1

[0036] In order to solve the technical problems of real-time communication delay, insufficient efficiency of rapid detection and processing of flight conflicts, and poor system adaptability during low-altitude flight, this embodiment proposes a low-altitude traffic control method for aircraft to meet the safety and efficiency requirements of low-altitude aircraft in complex airspace environments. Figure 1 As shown, the steps of the low-altitude traffic control method in this embodiment include:

[0037] S101. Build a wireless communication network to ensure data exchange between aircraft through a multi-level topology structure and dynamic spectrum management technology. The wireless communication network adopts a channel assessment mechanism to adapt to the changing airspace environment and ensure a stable high-bandwidth connection.

[0038] S102. Integrate and process multimodal sensor data from the aircraft, including positioning, navigation and control systems, optical radar and meteorological data, and use data fusion technology to improve the time synchronization of sensor data to provide a data basis for path planning.

[0039] S103. Develop a path planning algorithm based on dynamic risk assessment. By combining static obstacles and dynamic targets, the risk cost of path planning is evaluated to determine the optimal route.

[0040] S104. Implement multi-target conflict detection and avoidance strategies, use prediction models to evaluate the motion state of the aircraft in real time, and identify and avoid potential flight path conflicts.

[0041] S105. Perform self-organizing adjustments to the flight path to respond to immediate changes in airspace conditions, monitor the flight process of the aircraft and provide real-time feedback to the path planning system, and continuously optimize the flight path through a feedback mechanism.

[0042] Specifically, this embodiment first builds a scalable wireless communication network, which adopts a multi-level topology structure and can realize flexible regional node configuration according to the density and distribution of aircraft, such as Figure 2 As shown. With the help of dynamic spectrum management technology, multiple communication channels can be selected to optimize bandwidth utilization and reduce communication interference. It should be understood that the wireless communication network further introduces a channel assessment mechanism, which allows the network to dynamically evaluate and adapt to frequency changes in the airspace environment, thereby ensuring that high-bandwidth stable connections are maintained between aircraft even under complex and changing conditions.

[0043] Furthermore, this embodiment integrates a processing module for multimodal sensor data, including positioning, navigation and control systems, optical radar sensors and meteorological sensor modules. By applying advanced data fusion technology, these multimodal data achieve efficient time synchronization, such as Figure 3 As shown in the figure, the coordination and real-time performance of various sensor information are improved. It can be understood that the fusion of multimodal data provides an accurate data basis for subsequent path planning, which can support more sophisticated route selection and adjustment.

[0044] Furthermore, in terms of path planning, this embodiment proposes an algorithm based on dynamic risk assessment. This path planning algorithm combines the geographic information of static obstacles and the real-time data of dynamic targets (such as other aircraft and weather changes), and continuously adjusts the route selection to obtain the optimal solution by evaluating potential risks and costs. It should be understood that this risk assessment-based path planning greatly enriches the adaptability and decision-making ability of the planning algorithm, enabling it to quickly adapt to changes in the airspace environment and effectively avoid potential dangerous areas.

[0045] Furthermore, to ensure that the aircraft can effectively avoid collisions during flight, the multi-target conflict detection and avoidance strategy introduced in this embodiment analyzes the movement trajectory and state of the aircraft through a real-time prediction model. It can be understood that through accurate evaluation of future flight paths, potential conflicts can be identified and avoided in a timely manner, thereby improving the safety of the overall aviation network.

[0046] Furthermore, if Figure 4 As shown, this embodiment also includes a self-organizing adjustment method for the flight path, which is used to respond to changes in the airspace conditions around the aircraft in real time, and transmit the monitoring data during the actual flight process back to the path planning system through a feedback mechanism for dynamic optimization. It should be understood that this real-time data feedback and the path adjustment mechanism work together to enable the aircraft to more flexibly adapt to various emergencies in the airspace.

[0047] Through this embodiment, the low-altitude traffic control method of this embodiment can maintain communication stability in a constantly changing airspace environment, and improve the path planning efficiency and safety management capabilities of the aircraft. It not only optimizes the coordination fluency between aircraft under complex airspace conditions, but also provides a reliable and efficient technical solution for the development of future low-altitude traffic management systems.

[0048] Embodiment 2

[0049] In order to solve the path planning optimization problem of low-altitude aircraft in complex environments, this embodiment further refines the steps of the path planning algorithm based on risk dynamic assessment. By defining static and dynamic obstacles as nodes, a risk graph is constructed under the graph theory framework to lay a structural foundation for path optimization, such as Figure 5 As shown in Figure 2, it can be understood that the construction of the risk graph enables the path planning problem to be intuitively represented through node connections, and the shortest path search and optimization can be conveniently performed through graph theory methods.

[0050] Furthermore, this embodiment introduces a cost function, which is expressed as follows:

[0051]

[0052] Among them, C(p) is the cost function, d i is the path distance, r i is the risk factor, v j is the speed variable, t j is the time adjustment factor, and α and β are adjustment parameters. It should be understood that the cost function comprehensively considers the distance, risk factor, speed variable and time adjustment factor of the path. By setting the dynamic penalty factor, it can achieve sensitive adjustment to various dynamic obstacles, thereby more accurately quantifying the risks and costs in path planning. Parameters α and β are adjustment parameters that can be adjusted according to environmental characteristics and different mission requirements to adapt to different flight optimization scenarios.

[0053] Furthermore, in the process of path optimization, this embodiment combines the genetic algorithm and the simulated annealing algorithm to find the optimal path planning that minimizes the cost function through iterative optimization. The introduction of the genetic algorithm provides a heuristic global search mechanism that can avoid the local optimal trap in the traditional optimization process; through the simulated annealing algorithm, the degree of random perturbation of the search path can be further controlled by simulating the physical annealing process, gradually approaching the optimal solution. It can be understood that the combination of the two algorithms works synergistically in the optimization process to ensure the global optimality and convergence speed of the path planning solution.

[0054] The benefit of this embodiment is that by constructing a risk assessment model based on graph theory and designing a cost function, the uncertainty and potential risks in low-altitude flight path planning can be greatly reduced. At the same time, the synergy of the genetic algorithm and the simulated annealing algorithm provides an efficient and reliable search method, so that the flight path can be adjusted and optimized in a timely manner, and a robust decision-making process is still maintained under dynamic conditions.

[0055] Embodiment 3

[0056] In order to solve the real-time and flexible adaptability of path planning in complex airspace, this embodiment further improves the path planning algorithm, introduces enhanced planning, and makes path planning more intelligent and dynamic through the combination of fuzzy logic and Bayesian reasoning.

[0057] Furthermore, by combining fuzzy logic to define fuzzy sets and reasoning about fuzzy inputs through a preset rule base, the path can be adjusted dynamically in real time and the planned path can be gradually corrected. It can be understood that this method uses the uncertainty characteristics of fuzzy logic processing to better cope with the path deviation of the aircraft caused by environmental changes, and timely perform path correction to keep the aircraft in the best route state. Therefore, the reasoning process based on fuzzy rules provides efficient path decision support, ensuring that the planned path can effectively cope with changes in the external environment.

[0058] In this embodiment, the use of Bayesian networks adds a probabilistic prediction layer to the environmental state and path selection process. Through Bayesian reasoning, the system can perform probabilistic evaluation of the path and environmental state, thereby dynamically adjusting the path priority. This makes path planning not only based on the current state, but also includes the prediction and response to future states. This probability-based approach enhances the forward-looking nature of planning and can effectively reduce the frequent problem of path replanning caused by emergencies.

[0059] Through this embodiment, intelligent dynamic updating of path planning schemes in complex environments is achieved. The combined use of fuzzy logic and Bayesian reasoning enhances the flexibility and adaptability of the planning system, allowing low-altitude aircraft to maintain efficient and safe flight routes in dynamic changes. The enhanced planning scheme of this embodiment improves the response speed of the path planning system and its ability to handle complex situations, providing an advanced technical framework for low-altitude aircraft traffic control.

[0060] Embodiment 4

[0061] In order to solve the problem of aircraft conflict detection and avoidance in complex airspace with multiple targets, this embodiment further optimizes the specific steps of the multi-target conflict detection and avoidance strategy. By initializing the spatial grid mapping, a Monte Carlo simulation of the three-dimensional risk area can be performed in real time, providing an accurate and efficient basis for conflict detection. It can be understood that the gridded spatial mapping not only simplifies the representation of the relationship between the flight path and the spatial obstacles, but also can efficiently perform dynamic simulation of risk assessment, such as Figure 6 shown.

[0062] Furthermore, in this embodiment, a density function estimation method is used to evaluate the possibility of intersection of flight paths. This method uses density estimation in a statistical sense to quantitatively analyze the intersection opportunities of different aircraft paths, and then make predictions and risk assessments. It should be understood that since flight paths in low-altitude airspace change rapidly and variably, density function estimation provides an agile computational framework for risk assessment, so that potential path conflicts can be identified in advance.

[0063] Furthermore, in terms of avoidance strategy generation, this embodiment generates multi-path avoidance instructions through maneuver constraint technology. In this process, not only the energy consumption of the aircraft is comprehensively considered, but also the avoidance effect is optimized. It can be understood that in the design of the avoidance strategy, the balance between energy consumption and avoidance effect affects the overall operating efficiency of the aircraft. By embedding energy constraint factors in the avoidance algorithm, the feasibility and efficiency of the avoidance instructions can be ensured, and the optimal avoidance decision can be achieved.

[0064] Through this embodiment, the multi-target conflict detection and avoidance strategy becomes more accurate and efficient. The combination of spatial grid mapping, density estimation and flexible maneuvering constraints improves the detection and avoidance capabilities of complex dynamic conflicts and effectively reduces the possibility of collisions between aircraft in low-altitude high-density traffic environments. It provides cutting-edge technical guarantees and strategic support for low-altitude aircraft navigation systems.

[0065] Embodiment 5

[0066] In order to solve the challenge of calculating effective avoidance strategies in complex airspace with multiple targets, this embodiment refines the calculation method of the avoidance strategy and describes the benefits of the avoidance action through the precise construction of a mathematical model. Specifically, the calculation formula for the avoidance benefit is:

[0067]

[0068] Among them, R avoidis the avoidance benefit of the avoidance strategy, γ is the gain adjustment coefficient, λ is the steepness parameter, x(t) is the position trajectory, and x0 is the optimal position to be avoided. It can be understood that the calculation formula of the avoidance benefit reflects the influence of optimizing the gain adjustment coefficient γ and the steepness parameter λ on the obstacle avoidance path selection. In this embodiment, the avoidance strategy not only considers the avoidance action at the physical position, but also integrates the influence of dynamic environmental changes on the avoidance strategy.

[0069] Furthermore, in the implementation of the avoidance strategy, this embodiment focuses on the optimization of the two parameters γ and λ. It should be understood that γ, as a gain adjustment coefficient, can be adjusted according to the specific aircraft performance and actual scenario requirements, so as to achieve an optimal balance between avoidance gain and control input. In addition, the steepness parameter λ controls the sensitivity of the avoidance strategy to path deviation. When the aircraft is close to the area to be avoided, the appropriate adjustment of λ can ensure the rapidity and smoothness of the avoidance action.

[0070] In this embodiment, the designed avoidance strategy has been repeatedly simulated and verified to ensure that the path can be adjusted in a dynamically changing airspace environment. The effectiveness of the avoidance strategy has been fully evaluated through participant simulation training and real environment testing. It can be understood that this design not only takes into account common relatively static obstacles, such as buildings and fixed flight areas, but also effectively responds to dynamic targets, such as other moving drones.

[0071] Through this embodiment, the aircraft can complete the obstacle avoidance task in complex weather conditions and high-density traffic environments, and the design of the avoidance strategy brings higher safety. It enhances the risk management ability of the aircraft during navigation and lays a solid foundation for future path avoidance technology.

[0072] Embodiment 6

[0073] In order to effectively respond to the demand for flight path adjustment caused by dynamic changes in the airspace environment, this embodiment optimizes the self-organizing adjustment module of the flight path, and realizes the dynamic adaptation function of the path through a dynamic adjustment method based on particle swarm optimization (PSO) and combined with an information feedback mechanism.

[0074] Specifically, particle swarm optimization, as an optimization algorithm that simulates the behavior of ecological groups, adjusts the flight path in real time through the coordinated actions of a group of intelligent nodes. It can be understood that each node represents a potential path solution, and through the cooperation and information exchange between nodes, the system quickly converges to the global optimal path. This mechanism ensures that the path adjustment always maintains the best direction and position during the flight to improve the robustness of the entire flight operation.

[0075] Furthermore, this embodiment uses an incremental learning method to integrate data on external environmental changes to enhance the precision adjustment capability of the flight path. Through continuously updated environmental information, the system can dynamically adjust path details to ensure the adaptability of path planning. It should be understood that incremental learning not only improves the system's sensitivity to sudden environmental changes, but also improves the ability to make decisions based on accumulated experience, providing lasting learning feedback for path optimization.

[0076] Furthermore, since all parameters of flight path adjustment are monitored, real-time corrections can be made during flight. It can be understood that this monitoring mechanism ensures that all responses during the path adjustment process are accurate and correct, not only compensating for path deviations, but also providing an effective means of monitoring the overall effect of path planning.

[0077] Through this embodiment, the aircraft can maintain the flexibility and stability of path adjustment in various complex environments, enhancing the intelligent characteristics of path planning. In addition, the self-organizing adjustment mechanism of this embodiment ensures that the low-altitude traffic control system can respond quickly and effectively when facing dynamic challenges, thereby continuously ensuring the safety of the aircraft and the accuracy of the track.

[0078] Embodiment 7

[0079] This embodiment further refines the self-organizing adjustment of the flight path by introducing machine learning models, especially deep neural networks and reinforcement learning algorithms, to improve the intelligence level of path adjustment in order to cope with the changing challenges of complex airspace.

[0080] Specifically, this embodiment designs a deep neural network architecture for high-complexity decision support in path planning. Through in-depth learning of historical path data and current environmental conditions, the network can accurately predict possible future path states and provide strong support for planning decisions. It should be understood that the deep network is not only a summary of existing path data, but also accumulates decision-making experience in dynamic airspace to ensure that path adjustments always target the safest and most efficient routes.

[0081] Furthermore, the reinforcement learning algorithm is used for continuous environment simulation learning to improve the strategy's ability to combat dynamic challenges. The reinforcement learning optimization objective expression is as follows:

[0082]

[0083] Among them, J(θ) is the optimization objective function, which represents the expected total return of the strategy under parameter θ. is the expected symbol, indicating that the distribution from the state ρ π and strategy π θR(s,a) is the reward function, which represents the benefit obtained from a given state s and action a. σ is the trade-off coefficient, which is used to balance the relationship between the reward function R(s,a) and the feature function. f(ϕ(s),ψ(a)) is the feature function, which is used to describe the relationship between the state feature ϕ(s) and the action feature ψ(a).

[0084] It is understandable that the reward function R(s, a) and the feature function f(ϕ(s),ψ(a)) work together to ensure that the strategy can still balance risks and benefits in a complex environment. Reinforcement learning is not only an algorithm optimization process, but also enhances the adaptability of the path adjustment strategy through continuous interaction and adjustment.

[0085] Furthermore, by feeding back the acquired historical path data to the strategy module, the accuracy of future path generation can be improved. It can be understood that this feedback mechanism realizes the reasonable accumulation and retrospective utilization of knowledge, thereby dynamically improving the path optimization effect and adaptability to cope with unknown scenarios.

[0086] Through this embodiment, the intelligence level of the aircraft path optimization process is improved, and it can autonomously generate and adjust the path in real time in dynamic airspace to ensure the safety and efficiency of the flight process. With the combination of deep neural networks and reinforcement learning, low-altitude traffic control will move towards a more adaptive and intelligent direction.

[0087] Embodiment 8

[0088] In order to solve the problem of complex multimodal sensor data processing and low accuracy in low-altitude aircraft, this embodiment further refines the integrated processing steps of sensor data, and adopts an adaptive weighting algorithm based on entropy weight assignment to dynamically adjust the weight of each sensor data, thereby improving the reliability of data fusion. It can be understood that the entropy weight assignment method can dynamically evaluate the validity of each sensor data based on the information entropy characteristics of real-time sensor data, thereby adaptively adjusting its contribution to the overall data fusion process. This process not only ensures the maximum utilization of data information, but also effectively reduces the negative impact caused by abnormal individual sensor data.

[0089] Specifically, in the data preprocessing stage, this embodiment uses wavelet transform technology to denoise the multimodal sensor data. It should be understood that wavelet transform, as a powerful signal processing tool, has multi-resolution analysis capabilities and can accurately separate the high-frequency noise and useful information of the signal in the frequency domain. Wavelet denoising of sensor data can effectively remove background noise while retaining key information in the signal, thereby laying a solid foundation for subsequent data fusion and analysis.

[0090] Furthermore, this embodiment uses collaborative Kalman filtering technology to perform multi-source data fusion to ensure navigation accuracy even when there is uncertainty in multimodal sensor data. Collaborative Kalman filtering enables the aircraft to extract consistent state estimates from sensor data from different sources by cyclically executing between time updates and measurement updates. It can be understood that the collaborative characteristics of Kalman filtering can still provide optimized estimates when multiple sensor information is inconsistent or even conflicting, thereby enhancing the navigation accuracy of the system.

[0091] Through this embodiment, the fusion processing of multimodal sensor data not only improves the system's ability to analyze the current aerodynamic environment of the aircraft, but also enhances the navigation accuracy under complex environmental conditions. This multi-level, multi-technical combination method improves the overall response efficiency and anti-interference ability of the low-altitude traffic management system, and provides strong support for the safe operation of aircraft in low-altitude complex airspace.

[0092] Embodiment 9

[0093] In order to solve the problem of insufficient communication stability of low-altitude aircraft in complex environments, this embodiment refines the steps of building a wireless communication network, and adopts adaptive spectrum allocation technology to dynamically adjust the available spectrum by measuring the channel interference level in real time to optimize bandwidth usage. It should be understood that adaptive spectrum allocation is a dynamic resource management strategy that can perform real-time adaptation and adjustment to different channel conditions at different time periods to ensure the stability and efficiency of the communication link. This technology not only improves network transmission performance, but also reduces communication interruption accidents caused by channel interference.

[0094] Furthermore, this embodiment uses multi-hop transmission technology to solve the data transmission problem when direct communication is not feasible, and establishes a reliable data channel with the participation of relay aircraft. It can be understood that multi-hop transmission technology breaks down the communication task into multiple short-distance transmissions and combines them into long-distance stable communication, thereby achieving accurate information transmission across obstacles and complex geographical restrictions. This technology is particularly suitable for deploying real-time and flexible communication architectures in complex terrain or large-scale network environments.

[0095] Furthermore, in order to solve the problem of communication path interruption, this embodiment introduces a fault recovery algorithm, which can automatically switch to the backup channel when the signal path interruption is detected to maintain the stability of the network connection. This algorithm accurately determines when to switch channels by monitoring the network connection status in real time, and ensures that data transmission is not interrupted under the condition of seamless transition. It can be understood that the fault recovery algorithm is not only a guarantee measure for network stability, but also a safety line to ensure cooperative communication between aircraft in complex airspace environments.

[0096] Through this embodiment, the designed wireless communication network has dynamic adaptability and high fault recovery capability, which effectively improves the quality and stability of low-altitude aircraft communication. This multi-level network structure design meets the needs of the ever-changing and frequently disturbed airspace environment, and provides a solid guarantee for the efficient operation of low-altitude aircraft in complex airspace environments.

[0097] Embodiment 10

[0098] In order to solve the problem of autonomous navigation and control of low-altitude aircraft in complex environments, this embodiment proposes a low-altitude traffic control system for aircraft, and refines multiple modules of the low-altitude traffic control system to ensure that aircraft can maintain efficient collaboration in changing airspace conditions.

[0099] In this embodiment, the communication module provides dynamic channel management and fault recovery functions between aircraft through adaptive connection and data transmission. It should be understood that channel conditions change frequently in airspace, and the adaptive connection mechanism can flexibly adjust the channel according to real-time interference and usage requirements to maintain the reliability of the communication link. Fault recovery is a safeguard. Even in the face of a communication link interruption, the system can quickly switch to a backup channel to ensure the continuity and effectiveness of data transmission.

[0100] Furthermore, the data processing module undertakes the task of integrating multi-source sensor information and real-time error correction. By introducing filtering mechanisms such as Kalman filtering or particle filtering, the module effectively optimizes data quality, thereby improving the accuracy and stability of the entire system. It can be understood that multi-source data fusion not only increases the accuracy of environmental perception, but also provides a more stable navigation foundation. The core of the data processing module is to make full use of heterogeneous data from multiple sensors to achieve real-time response to dynamic environments.

[0101] Furthermore, in the path planning module, this embodiment integrates a multi-objective optimization algorithm, which aims to combine static and dynamic factors in the environment to provide timely path suggestions for the aircraft. The multi-objective optimization algorithm covers multiple objectives such as shortest path, obstacle avoidance priority, and minimum energy consumption to ensure that path planning not only accelerates the generation of solutions but also responds quickly when unexpected obstacles occur and dynamically adjusts the navigation strategy. The path planning module ensures safety during flight by calculating potential path conflicts and optimizing path selection.

[0102] Furthermore, the conflict avoidance module uses prediction and simulation technology to ensure the safety and effectiveness of flight path selection. By scanning the surrounding airspace and analyzing potential conflicts, possible path intersections are predicted in advance, and avoidance strategies are adjusted in real time based on simulation results. This module is designed to improve the aircraft's responsiveness to emergencies, improve flight safety factors, and improve the timeliness of path adjustments.

[0103] Furthermore, the self-organizing adjustment module is responsible for real-time adjustment of path selection and optimization of flight strategy through feedback mechanism. The self-organizing adjustment module combines multi-sensor information, evaluates the deviation between the current path of the aircraft and environmental conditions, updates the navigation strategy in real time, and achieves highly adaptive adjustment during flight. It can be understood that this self-organizing adjustment capability enables the aircraft to maintain the optimal navigation path in a continuously changing environment.

[0104] Furthermore, the learning and prediction module achieves the accumulation and summary of historical flight path data through the application of the reinforcement learning framework. It is important to understand that historical data not only provides valuable experience, but also provides a reference basis for future decision-making. On this basis, the control strategy can be continuously updated and optimized to improve the system's foresight and handling capabilities for new environmental challenges.

[0105] Through this embodiment, the low-altitude traffic control system demonstrates an excellent level of intelligence and an optimized combination of diversified functional modules, providing solid technical support for the efficient operation of aircraft in complex airspace environments.

[0106] The above embodiments further illustrate the purpose, technical solutions and beneficial effects of the present invention. It should be understood that the above are only specific implementation methods of the present invention and are not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc. made on the basis of the technical solutions of the present invention should be included in the scope of protection of the present invention.

Claims

1. A low-altitude traffic control method for aircraft, characterized in that: The steps of the control method include: Building a wireless communication network to ensure data exchange between the aircraft through a multi-level topology structure and dynamic spectrum management technology, wherein the wireless communication network adopts a channel assessment mechanism to adapt to a changing airspace environment and ensure a stable high-bandwidth connection; Integrate and process multimodal sensor data from the aircraft, including positioning, navigation and control system, optical radar and meteorological data, and use data fusion technology to improve the time synchronization of the sensor data to provide a data basis for path planning; Develop a path planning algorithm based on dynamic risk assessment, which evaluates the risk cost of the path planning by combining static obstacles and dynamic goals to determine the optimal route; Implementing a multi-target conflict detection and avoidance strategy, using a predictive model to evaluate the motion state of the aircraft in real time, identifying and avoiding potential flight path conflicts; Perform self-organizing adjustments to the flight path to cope with real-time changes in airspace conditions, monitor the flight process of the aircraft and provide real-time feedback to the path planning system, and continuously optimize the flight path through a feedback mechanism; The steps of developing a path planning algorithm based on dynamic risk assessment include: Define static and dynamic obstacles in the environment as nodes and construct a risk graph in the graph theory framework; A cost function with a dynamic penalty factor is introduced, and the expression of the cost function is: , where C(p) is the cost function, d i is the path distance, r i is the risk factor, v j is the speed variable, t j is the time adjustment factor, α and β are adjustment parameters; Iterative optimization is performed through genetic algorithms and simulated annealing algorithms to find the optimal path planning that minimizes the cost function.

2. The low-altitude traffic control method for aircraft according to claim 1, characterized in that: The step of developing a path planning algorithm based on dynamic risk assessment also includes enhanced planning, and the steps of enhanced planning are: Combining fuzzy logic and Bayesian reasoning to dynamically update the path planning solution; Define fuzzy sets and reason about fuzzy inputs through rule bases to gradually correct the planned path; The Bayesian network is used to perform probability prediction of the environment and path status and adjust the priority of the planned path.

3. The low-altitude traffic control method for aircraft according to claim 1, characterized in that: The steps of implementing the multi-target conflict detection and avoidance strategy include: Initialize spatial grid mapping for real-time Monte Carlo simulation of 3D risk areas; Using density function estimation to evaluate the possibility of the flight path intersection is used to predict the risk of collision between aircraft; Multi-path avoidance instructions are generated through maneuver constraints, and energy consumption and avoidance effects are comprehensively considered to optimize the avoidance strategy.

4. The low-altitude traffic control method for aircraft according to claim 3, characterized in that: The calculation formula of the avoidance strategy is: , where R avoid is the avoidance benefit of the avoidance strategy, γ is the gain adjustment coefficient, λ is the steepness parameter, x(t) is the position trajectory, and x0 is the optimal position to be avoided.

5. The low-altitude traffic control method for aircraft according to claim 1, characterized in that: The steps of performing the self-organizing adjustment of the flight path are: Implementing dynamic adjustment based on particle swarm optimization to adjust the flight path in real time through cooperation and information feedback between intelligent nodes; Using an incremental learning method, integrating external environment change data to enhance the adjustment accuracy of the flight path; The adjustment parameters of the flight path are monitored to correct the flight path in real time during the flight.

6. The low-altitude traffic control method for aircraft according to claim 5, characterized in that: The performing of the self-organizing adjustment of the flight path further includes enhancing the path adjustment using a machine learning model, wherein the steps of enhancing the path adjustment are: Implementing a deep neural network architecture for making high-complexity decision support in the task of path planning; Continuously learn in environmental simulation based on reinforcement learning algorithms to improve the strategy's ability to combat dynamic challenges; The acquired historical path data is fed back to the strategy module to improve the accuracy of future path generation; The expression of the reinforcement learning algorithm is: , where J(θ) is the optimization objective function, which represents the expected total return of the strategy under parameter θ. is the expected symbol, indicating that the distribution from the state ρ π and strategy π θ R(s,a) is the reward function, which represents the benefit obtained from a given state s and action a. σ is the trade-off coefficient, which is used to balance the relationship between the reward function R(s,a) and the feature function. f(ϕ(s),ψ(a)) is the feature function, which is used to describe the relationship between the state feature ϕ(s) and the action feature ψ(a).

7. The low-altitude traffic control method for aircraft according to claim 1, characterized in that: The step of integrating and processing multimodal sensor data from the aircraft comprises: Using an adaptive weighting algorithm based on entropy weight assignment to dynamically adjust the weight of the sensor data to improve the reliability of the sensor data; In the data preprocessing stage, the sensor data is denoised using wavelet transform to retain key information and remove redundant background noise; Collaborative Kalman filtering is used to perform multi-source data fusion to ensure navigation accuracy under the uncertainty of the sensor data.

8. The low-altitude traffic control method for aircraft according to claim 1, characterized in that: The steps of establishing a wireless communication network include: Implement adaptive spectrum allocation to dynamically adjust available spectrum for bandwidth usage by measuring channel interference levels in real time; Using multi-hop transmission technology, a reliable data channel can be established through relay aircraft when the environment is complex or direct communication is not feasible; Through the fault recovery algorithm, when the detection signal path is interrupted, the backup channel is automatically switched to maintain the stability of network connectivity.

9. A low-altitude traffic control system for an aircraft, used to execute the low-altitude traffic control method for an aircraft as claimed in any one of claims 1 to 8, characterized in that: The control system comprises: A communication module, which realizes adaptive connection and data transmission between the aircraft, and can dynamically manage channels and fault recovery; The data processing module is responsible for integrating multi-source sensor information, real-time error correction and using filtering mechanisms to ensure data quality; The path planning module integrates a multi-objective optimization algorithm and provides real-time path suggestions for the aircraft based on static and dynamic environmental factors; Conflict avoidance module, which uses prediction and simulation techniques to ensure safe and effective flight path selection; The self-organizing adjustment module performs path selection and real-time adjustment, and optimizes flight strategies through feedback mechanisms; The learning and prediction module uses the reinforcement learning framework to accumulate and summarize historical flight path data and update it into the control strategy.

Images