Low-altitude unmanned aerial vehicle assisted peak period urban intersection coordinated control system and method

Abstract

The present application relates to a kind of low-altitude unmanned aerial vehicle assisted peak period city intersection coordination control system and method, belong to traffic control field.The system includes equipment deployment layer, perception layer, decision layer, control layer.Based on the infrastructure of equipment deployment layer deployment, unmanned aerial vehicle cruise shoots and preliminary analyzes image, structured data is transferred to edge computing device;Perception layer determines intersection state information and is transferred to decision layer, and decision layer generates signal timing strategy and regional scheduling scheme;Control layer controls signal light according to this, and feedback execution result, system can adaptive optimization and early warning.The method includes unmanned aerial vehicle obtains image and processes, data is transferred to decision layer optimization timing, strategy is issued to signal light controller and feedback execution effect.The scheme can enhance the perception range and accuracy, reduce communication load, optimize signal timing, support multi-intersection cooperation, build closed-loop control system, and deployment is flexible, strong adaptability.

Description

Technical Field

[0001] This invention belongs to the field of traffic control and relates to a low-altitude unmanned aerial vehicle (UAV)-assisted coordinated control system and method for urban intersections during peak hours. Background Technology

[0002] Traffic management at urban intersections is one of the most complex and critical aspects of the urban transportation system. With the continuous increase in the number of motor vehicles in cities, especially during weekday morning and evening rush hours, intersections have become traffic bottlenecks, and traffic congestion is particularly prominent. In order to alleviate congestion and improve traffic efficiency, various urban intersection control technologies have been developed and applied. Currently, the mainstream traffic signal control methods mainly include the following categories: (1) Adaptive signal light control technology: Real-time collection of traffic flow data through ground sensors or cameras to dynamically adjust the duration of red and green lights. This method can alleviate congestion to a certain extent, but the response time is limited by the coverage and processing speed of ground sensing equipment, making it difficult to adapt to sudden events or large-scale traffic changes. (2) Green wave control technology: Coordinating multiple traffic lights on continuous road sections and setting a "green wave" traffic strategy to improve the traffic efficiency of arterial roads. However, this technology has high requirements for vehicle speed consistency, is difficult to implement, and its effect is limited in densely populated intersection areas. (3) Speed ​​guidance and induction system: Guiding vehicles to choose reasonable routes and speeds through information release platforms (such as variable message signs, APPs, etc.). The system relies on driver cooperation, making it difficult to achieve mandatory intervention and rapid response. (4) Traffic police on-site control: During peak hours or in the event of an emergency, traffic is manually directed by traffic police. Although it has a certain degree of flexibility, it is costly, inefficient, and lacks timeliness, making it difficult to achieve large-scale coordination.

[0003] In summary, while existing urban intersection traffic management technologies have achieved some success, they still have significant shortcomings in addressing sudden congestion during peak hours and improving overall coordination efficiency. In particular, the lack of comprehensive situational awareness and dynamic decision-making capabilities from an "aerial perspective" hinders rapid response and coordinated control at the regional level.

[0004] Existing technology—a method for intersection signal timing based on drone aerial video—acquires intersection video information using drones and extracts vehicle trajectory data and road structure data using deep learning and image processing algorithms to assist in signal timing optimization. The key focus is on using image recognition to analyze historical and real-time traffic flow information, providing support for traffic management.

[0005] Another existing technology, a method for detecting dynamic signal timing schemes at intersections based on drone video, involves using a drone to capture traffic images, then constructing a dataset and a neural network model for information extraction and processing to detect and assist in signal timing optimization. It emphasizes automated recognition and timing analysis driven by video data.

[0006] Both solutions are based on drone aerial photography and image analysis, which realizes automated processing of data collection and timing detection, improving the efficiency and accuracy of data acquisition.

[0007] While the aforementioned existing technologies have introduced drones into urban intersection management, the following shortcomings remain: Limited to perception and auxiliary analysis, lacking a control loop: Existing patents focus on drone video acquisition and timing scheme detection, lacking direct intervention capabilities at the signal control end, and failing to achieve integrated "analysis-decision-control" linkage. Perception capabilities are biased towards offline processing, lacking real-time performance: Image data typically needs to be transmitted back to the center for in-depth processing, resulting in insufficient flexibility and timeliness in responding to sudden congestion events during peak hours. Lack of a systematic, layered architecture: Existing solutions do not clearly define the functions of perception, decision-making, and control at each level, lacking a comprehensive collaborative mechanism based on system architecture. Summary of the Invention

[0008] In view of this, the purpose of this invention is to provide a low-altitude unmanned aerial vehicle (UAV)-assisted coordinated control system and method for urban intersections during peak hours, aiming to achieve real-time dynamic optimization and regional collaborative control of traffic lights, construct a closed-loop architecture of "perception-decision-control" to achieve real-time full-process linkage response; adopting a fusion architecture of low-altitude UAV + edge computing + intelligent traffic light controller to ensure response speed and coverage; supporting coordinated scheduling of regional intersections, rather than isolated optimization, to achieve optimal global traffic efficiency; acting as an "electronic traffic police," supporting immediate intervention and emergency timing adjustments in the event of emergencies (such as accidents, temporary construction), and improving the robustness and adaptability of intersections.

[0009] To achieve the above objectives, the present invention provides the following technical solution:

[0010] On the one hand, a low-altitude unmanned aerial vehicle (UAV)-assisted coordinated control system for urban intersections during peak hours is proposed. This system includes: an equipment deployment layer, a perception layer, a decision-making layer, and a control layer. The perception layer, decision-making layer, and control layer implement corresponding data acquisition and data processing based on the infrastructure deployed in the equipment deployment layer.

[0011] The equipment deployment layer includes the deployment of low-altitude drones, intelligent traffic signal controllers, communication modules, and edge computing devices. The low-altitude drones and edge computing devices communicate through the communication modules. The drones acquire video information and front-end processing tasks, and the edge computing devices extract structured data and upload it to the perception layer.

[0012] The perception layer determines the intersection status information based on structured data and transmits it to the decision layer. The decision layer generates real-time signal timing strategies and regional scheduling schemes based on the intersection status information.

[0013] The control layer controls traffic lights based on the real-time signal timing scheme and regional scheduling scheme output by the decision layer, and the execution results of the traffic lights are fed back to the perception layer through ground equipment or drones; in case of continuous congestion or strategy execution failure, the system triggers an adaptive optimization and early warning mechanism to achieve dynamic correction.

[0014] Furthermore, the low-altitude drones deployed at the equipment deployment layer are equipped with high-definition cameras, embedded computing platforms, communication modules, and flight control systems. They use high-definition cameras to conduct aerial patrols and take pictures in the intersection and its surrounding areas, and use embedded computing platforms to perform preliminary image analysis, including vehicle detection and vehicle recognition, and generate structured data locally.

[0015] The intelligent traffic signal controller includes an external communication interface, through which it remotely receives control strategies and dynamically adjusts the duration and phase sequence of traffic lights according to the received control strategies.

[0016] Edge computing devices acquire structured information transmitted by drones through communication modules and perform time analysis and control strategy generation based on the structured information;

[0017] The communication module employs high-speed communication technology to support data synchronization between the UAV and MEC nodes, as well as information transmission in the event of command distribution between the MEC and traffic lights.

[0018] Furthermore, the perception layer performs corresponding operations based on the various infrastructures deployed in the basic equipment layer. The perception layer includes: a drone front-end video perception and preliminary analysis module, a multi-source data fusion module, and an event detection module.

[0019] The UAV front-end video perception and preliminary analysis module is deployed in the UAV's embedded computing platform. Based on the acquired video information, it completes vehicle target detection, traffic density estimation, and preliminary screening of abnormal behavior, and transmits the structured data to the edge computing node.

[0020] The multi-source data fusion module integrates structured perception data from different UAVs and perception data from various ground perception sources;

[0021] The event detection module determines whether there is a sudden event based on the structured data flow and rule model, and generates a description of the current intersection status.

[0022] Furthermore, in the UAV front-end video perception and preliminary analysis module, the structured data D output by the UAV is... l (t) is represented as:

[0023] D l (t)={n veh ,ρ lane E abn}

[0024]

[0025] Where: n veh ρ represents the number of vehicles on the road per unit of time. lane Lane occupancy rate reflects the degree of traffic congestion; L is the total length of the observed road segment. i E is the length of vehicle i; abn This serves as a marker for abnormal events, such as driving in the wrong direction or a traffic accident.

[0026] The structured sensing data from different sensing sources, integrated by the multi-source data fusion module, are as follows:

[0027] D k (t)={m veh D l (t)}

[0028] Where, m veh This refers to the number of vehicles allowed to pass upstream of the intersection.

[0029] The event detection module detects lane occupancy rate ρ lane The threshold for determining congestion at the intersection is used to identify and record whether congestion exists. The congestion threshold is set as ρ. thresh If ρ lane >ρ thresh If the result is positive, it is considered congested; otherwise, it is considered not congested. If the above detection result belongs to E... abn Then, abnormal events are recorded; structured sensing data D from different sensing sources k (t) is used to guide the decision-making level in specifying signal timing schemes.

[0030] Furthermore, the decision-making layer undertakes the task of generating traffic control strategies, which includes a timing optimization module and a strategy evaluation and adaptive feedback module. Among them, when the traffic lights are released in sequence according to the preset plan, the timing optimization module analyzes the current traffic status based on the perception data, uses a dynamic timing algorithm to generate the optimal timing strategy for the intersection, and adjusts the duration of each phase according to the optimal timing strategy.

[0031] The strategy evaluation and adaptive feedback module continuously evaluates the effectiveness of the current strategy and makes adaptive corrections based on signal control results and real-time traffic feedback.

[0032] Furthermore, in the configuration optimization module, the green light duration s of the traffic light corresponding to lane j under the optimal timing strategy is defined. j The calculation method is as follows:

[0033]

[0034] Where, n vehIndicates the number of vehicles in the queue; s m s1 is the distance the preceding vehicle has traveled when the following vehicle starts moving; v is the distance the vehicle has traveled from starting to accelerating to the required speed; d and t loss These represent the expected speed and the lost time, respectively. t represents startup acceleration; t represents system time; L represents startup acceleration. i The length of the vehicle is m. veh t represents the number of vehicles input from the upstream source. add This indicates the time delay of upstream vehicles being considered; Δτ k Indicates the policy adjustment amount; Δs * The safe following distance is described using an intelligent driver model, which includes predicting acceleration. Defined as:

[0035]

[0036]

[0037] Among them, a max v max s0, σ and b represent the maximum acceleration, maximum speed, congestion distance, safe travel distance and desired acceleration, respectively; Indicates the instantaneous speed of the vehicle; Δd n (t), Δv n (t), Δs * These represent the distance, speed difference, and safety distance between vehicle n and vehicle n-1, respectively.

[0038] Furthermore, the strategy evaluation and adaptive feedback module evaluates the effectiveness of the strategy according to the following formula:

[0039] E = n veh +α1m veh -n real

[0040] Where E represents the difference between the target number of vehicles passing through and the actual number of vehicles passing through after a green light cycle, α1 represents the upstream vehicle weight, and n real This indicates the actual number of vehicles that passed through.

[0041] Then, the signal timing strategy is corrected based on the strategy error feedback:

[0042] Δτ k (t)=γ·E

[0043] Where, Δτ k (t) represents the policy adjustment amount, and γ represents the feedback adjustment coefficient.

[0044] Furthermore, the control layer includes an instruction issuing module, a traffic light execution module, and a feedback confirmation module. The instruction issuing module, deployed in the edge computing device, sends the timing strategy generated by the decision layer to the traffic light controller at the corresponding intersection in real time via a wireless link. The traffic light execution module in the traffic light controller automatically completes the adjustment of the traffic light cycle, phase sequence, and phase according to the timing strategy received by the traffic light controller. The feedback confirmation module in the traffic light controller feeds back the execution results to the edge computing node and performs closed-loop verification through UAV perception to achieve closed-loop optimization of the strategy.

[0045] On the other hand, a low-altitude unmanned aerial vehicle (UAV)-assisted coordinated control method for urban intersections during peak hours is also proposed. This method is based on the aforementioned low-altitude UAV-assisted coordinated control system for urban intersections during peak hours, and includes:

[0046] The system uses drones to acquire video images of intersections, performs front-end perception and data processing at the perception layer, and then transmits the processed structured data to the decision-making layer.

[0047] Edge computing devices receive traffic status data from different drones, build an intersection status matrix, and determine whether the lane occupancy rate exceeds the threshold. If it does, a strategy optimization process is triggered.

[0048] At the decision-making level, signal timing optimization and coordinated scheduling are carried out based on the analysis of current traffic conditions using perception data, and dynamic timing algorithms are used to generate the optimal timing strategy for intersections.

[0049] The generated signal control strategy is sent to the traffic light controllers at each intersection; the controllers adjust the light control parameters in real time, and the controller execution status is fed back to the edge computing device through the status confirmation module, and the execution effect is sensed and verified by the drone.

[0050] The beneficial effects of this invention are as follows:

[0051] (1) Enhance the sensing range and accuracy; by deploying low-altitude unmanned aerial vehicle (UAV) systems, dynamic aerial photography is conducted in and around intersections, breaking through the sensing blind spots of traditional ground cameras and induction coils, and realizing real-time monitoring of traffic flow over a wide area, at high resolution, and from multiple angles. By combining ground sensing sources to construct an air-ground integrated sensing system, the completeness and accuracy of traffic information at urban intersections are significantly improved.

[0052] (2) Communication load is greatly reduced; the present invention adopts a “cooperative processing architecture”, which integrates an embedded computing module on the drone end to complete the local extraction of structured data such as traffic flow, queue length, and abnormal behavior, and only uploads the necessary information to the edge computing device, thereby effectively reducing the communication load, avoiding network congestion caused by large-scale high-definition video transmission, and improving the overall real-time performance and stability of the system.

[0053] (3) Optimize signal timing: By using edge computing devices to aggregate various structured data in real time, and combining current traffic conditions with historical data, the system uses a dynamic timing optimization algorithm to quickly generate the optimal signal control strategy. The system has a rapid response capability and can adjust traffic light timings according to emergencies (such as accidents or abnormal traffic flow) to alleviate queuing pressure and improve intersection throughput.

[0054] (4) Supports multi-intersection collaborative control; the decision layer of this invention supports signal timing coordination for multiple adjacent intersections to avoid phenomena such as "green light conflict" or "traffic flow conflict", improves the continuity and stability of regional traffic flow, and is particularly suitable for the management needs of dense road networks and areas with dense intersections of main roads.

[0055] (5) Construct a closed-loop control system; The system constructs a closed-loop mechanism for the entire process from the perception layer, decision-making layer to the control layer. The execution results of the traffic lights can be captured and fed back by the perception layer again, supporting strategy evaluation and automatic correction, ensuring continuous optimization of control effect, and having adaptive evolution capability.

[0056] (6) Flexible deployment and strong adaptability: This system supports zoned deployment according to urban road level and traffic flow changes. Low-altitude UAVs can be flexibly dispatched, do not rely on fixed infrastructure, adapt to various road types, and are easy for urban traffic management departments to promote and apply.

[0057] Other advantages, objectives, and features of the invention will be set forth in part in the description which follows, and in part will be apparent to those skilled in the art from the following examination, or may be learned from practice of the invention. The objectives and other advantages of the invention can be realized and obtained through the following description. Attached Figure Description

[0058] To make the objectives, technical solutions, and advantages of the present invention clearer, the preferred embodiments of the present invention will be described in detail below with reference to the accompanying drawings, wherein:

[0059] Figure 1 This is a schematic diagram of the architecture of a low-altitude unmanned aerial vehicle-assisted peak-hour urban intersection coordination control system according to an embodiment of the present invention;

[0060] Figure 2 This is a schematic diagram of the hierarchical structure of a low-altitude unmanned aerial vehicle-assisted urban intersection coordination control system during peak hours, according to an embodiment of the present invention.

[0061] Figure 3 This is a flowchart illustrating a low-altitude unmanned aerial vehicle (UAV)-assisted coordinated control method for urban intersections during peak hours, according to an embodiment of the present invention. Detailed Implementation

[0062] The following specific examples illustrate the implementation of the present invention. Those skilled in the art can easily understand other advantages and effects of the present invention from the content disclosed in this specification. The present invention can also be implemented or applied through other different specific embodiments, and various details in this specification can be modified or changed based on different viewpoints and applications without departing from the spirit of the present invention. It should be noted that the illustrations provided in the following embodiments are only schematic representations of the basic concept of the present invention. Unless otherwise specified, the following embodiments and features can be combined with each other.

[0063] The accompanying drawings are for illustrative purposes only and are schematic diagrams, not actual pictures. They should not be construed as limiting the invention. To better illustrate the embodiments of the invention, some parts in the drawings may be omitted, enlarged, or reduced, and do not represent the actual product dimensions. It is understandable to those skilled in the art that some well-known structures and their descriptions may be omitted in the drawings.

[0064] In the accompanying drawings of the embodiments of the present invention, the same or similar reference numerals correspond to the same or similar components. In the description of the present invention, it should be understood that if terms such as "upper," "lower," "left," "right," "front," and "rear" indicate the orientation or positional relationship based on the orientation or positional relationship shown in the drawings, they are only for the convenience of describing the present invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, the terms used to describe positional relationships in the drawings are only for illustrative purposes and should not be construed as limiting the present invention. For those skilled in the art, the specific meaning of the above terms can be understood according to the specific circumstances.

[0065] Please see Figures 1-3 This invention relates to a low-altitude unmanned aerial vehicle (UAV)-assisted coordinated control system and method for urban intersections during peak hours.

[0066] Example 1

[0067] This embodiment first describes in detail the specific structure of the low-altitude unmanned aerial vehicle-assisted urban intersection coordination control system during peak hours of the present invention, such as... Figure 1 The system architecture diagram shown illustrates that the system comprises a device deployment layer, a perception layer, a decision-making layer, and a control layer. The perception, decision-making, and control layers, based on the infrastructure deployed in the device deployment layer, implement corresponding data acquisition and processing.

[0068] The equipment deployment layer includes the deployment of low-altitude drones, intelligent traffic signal controllers, communication modules, and edge computing devices. The low-altitude drones and edge computing devices communicate through the communication modules. The drones acquire video information and front-end processing tasks, and the edge computing devices extract structured data and upload it to the perception layer.

[0069] The perception layer determines the intersection status information based on structured data and transmits it to the decision layer. The decision layer generates real-time signal timing strategies and regional scheduling schemes based on the intersection status information.

[0070] The control layer controls traffic lights based on the real-time signal timing scheme and regional scheduling scheme output by the decision layer, and the execution results of the traffic lights are fed back to the perception layer through ground equipment or drones; in case of continuous congestion or strategy execution failure, the system triggers an adaptive optimization and early warning mechanism to achieve dynamic correction.

[0071] In this embodiment, as Figure 2 The diagram illustrates the hierarchical structure of a low-altitude drone-assisted peak-hour urban intersection coordination control system. The equipment deployment layer forms the system's infrastructure support, primarily comprising: a low-altitude drone system equipped with a high-definition camera, an embedded computing platform (such as Jetson Nano), and a flight control system. It can cruise and capture images in and around the intersection, performing preliminary image analysis locally, such as vehicle detection and lane recognition, and generating some structured data locally. Drone deployment is mainly during peak traffic hours (e.g., morning and evening rush hours). An intelligent traffic light controller with an external communication interface supports remote reception of control strategies and dynamic adjustment of parameters such as traffic light duration and phase sequence. Edge computing devices (MEC nodes) deployed near the signal control center handle structured data aggregation, event analysis, and control strategy generation, possessing strong real-time processing capabilities. A communication module employing high-speed communication technologies such as 5G and V2X supports data synchronization between the drone and MEC nodes (uploading only structured information) and command distribution between the MEC and traffic lights, ensuring low-latency and highly reliable data interaction.

[0072] In this embodiment, the perception layer is responsible for real-time monitoring and data collection of traffic conditions, mainly including: a UAV front-end video perception and preliminary analysis module: This module uses embedded computing on the UAV to perform functions such as vehicle target detection, traffic density estimation, and preliminary screening of abnormal behavior. It only sends structured information (such as vehicle quantity, congestion level, and suspicious abnormal event markers) to the MEC node, significantly reducing the transmission load. Let D be the structured data output by UAV l. l (t) is:

[0073] D l (t)={n veh ,ρ lane E abn}

[0074]

[0075] Where: n vehρ represents the number of vehicles on the road per unit of time. lane Lane occupancy rate reflects the degree of traffic congestion; L is the total length of the observed road segment. i E is the length of vehicle i; abn It serves as a marker for abnormal events, such as driving in the wrong direction or a traffic accident.

[0076] Multi-source data fusion module: Integrates structured perception data from different UAVs, and can also incorporate ground perception sources such as ground induction coils, surveillance cameras, and RSUs to improve overall perception coverage and reliability. Let the structured perception data from different perception sources be:

[0077] D k (t)={m veh D l (t)}

[0078] Where m veh This refers to the number of vehicles allowed to pass upstream of the intersection.

[0079] Event Detection Module: The edge computing unit determines the presence of sudden events (such as severe queuing, wrong-way driving, accidents, etc.) based on structured data streams and rule models, and generates a description of the current intersection status. Specifically, the edge computing unit detects lane occupancy rate ρ... lane The threshold is used to determine whether there is congestion at the current intersection and to record it. If ρ lane >ρ thresh If ρ is the value of ρ, then it is considered congested. thresh This is the set congestion determination threshold. Furthermore, if the above detection result falls under E... abn Then, abnormal events are recorded; structured sensing data D from different sensing sources k (t) is used to guide the decision-making level in specifying signal timing schemes.

[0080] In this embodiment, the decision-making layer undertakes the task of generating traffic control strategies, mainly including:

[0081] Timing optimization module: First, the traffic lights are sequentially activated according to a preset plan. Then, the duration of each phase is determined based on the following scheme: Based on perception data analysis of the current traffic state, a dynamic timing algorithm is used to generate the optimal timing strategy for the intersection. Assume the green light duration s for lane j is... j The calculation formula is:

[0082]

[0083] Where, n veh Indicates the number of vehicles in the queue; s m =5m is the distance the preceding vehicle has traveled when the following vehicle starts; s1 is the distance the vehicle travels from starting to accelerating to the required speed; vd and t loss =3s represents the desired speed and the lost time, respectively; t represents startup acceleration; t represents system time; L represents startup acceleration. i The length of the vehicle is m. veh t represents the number of vehicles input from the upstream source. add =2s indicates that the delay time of upstream vehicles is taken into account; Δτ k The value of Δs represents the strategy adjustment amount, and is taken from formula (8); * Regarding safe following distance, this embodiment uses an Intelligent Driver Model (IDM) to describe the car's following behavior, where the predicted acceleration... Defined as:

[0084]

[0085]

[0086] Among them, a max v max s0, σ and b represent the maximum acceleration, maximum speed, congestion distance, safe travel distance and desired acceleration, respectively; Indicates the instantaneous speed of the vehicle; Δd n (t), Δv n (t), Δs * These represent the distance, speed difference, and safety distance between vehicle n and vehicle n-1, respectively.

[0087] Strategy Evaluation and Adaptive Feedback Module: Based on signal control results and real-time traffic feedback, this module continuously evaluates the effectiveness of the current strategy and makes adaptive corrections. The effectiveness of the strategy is evaluated according to the following formula, and the strategy parameters are adjusted based on actual conditions:

[0088] E = n veh +α1m veh -n real

[0089] E represents the difference between the target number of vehicles passing through and the actual number of vehicles passing through after a green light cycle. α1 represents the upstream vehicle weight, n real This indicates the actual number of vehicles passing through. Based on the strategy error, the signal timing strategy is corrected accordingly.

[0090] Δτ k (t)=γ·E

[0091] Where, Δτ k (t) represents the policy adjustment amount, and γ represents the feedback adjustment coefficient.

[0092] An adaptive feedback adjustment mechanism can ensure that the system has a strong ability to adapt to dynamic changes in traffic conditions, and guarantee the real-time performance and effectiveness of traffic control strategies.

[0093] In this embodiment, the control layer is responsible for executing control commands issued from the upper layer, specifically including: a command issuance module: the edge computing device sends the timing strategy generated by the decision layer to the traffic light controller at the corresponding intersection in real time via a wireless link. A traffic light execution module: automatically adjusts the traffic light cycle, phase sequence, and phase according to the timing strategy received by the traffic light controller. A feedback confirmation mechanism: the traffic light controller feeds back the execution results to the edge computing node and performs closed-loop verification through UAV perception to achieve closed-loop optimization of the strategy.

[0094] Example 2

[0095] This embodiment focuses on the system in Embodiment 1, taking two consecutive cross-shaped urban intersections (denoted as intersection A and intersection B respectively) as examples, and combines them with a typical morning rush hour traffic scenario to introduce the workflow and application effect of the system of the present invention.

[0096] 1) Implementation environment and parameter settings

[0097] Traffic Scenario: Intersections A and B are 300 meters apart, both are two-way six-lane roads, and both are located on urban arterial roads. During the morning rush hour (7:30-9:00), traffic flow is dense, with significant vehicle queuing and bottlenecks at arterial road junctions. Table 1 shows the traffic flow configuration of the intersections, and Table 2 shows the fixed signal timing schemes for intersections A and B:

[0098] Table 1

[0099]

[0100] Table 2

[0101]

[0102] Drone deployment: One low-altitude drone will be deployed at each intersection, with a flight altitude of 40 meters and a cruising path covering the intersection and the two lanes before and after it.

[0103] Drone hardware: Equipped with a 1080p HD camera, Jetson Nano embedded computing module, and 5G communication terminal.

[0104] Edge computing device (MEC): Deployed in the traffic management and control center near intersection B, it communicates with the outside world through the RSU, has a GPU acceleration module, and supports real-time policy generation.

[0105] Traffic light controller: Supports V2X communication interface and can receive remote signal timing control commands.

[0106] 2) Workflow

[0107] Figure 3 The overall control flowchart under the system collaborative processing architecture, namely the low-altitude UAV-assisted coordinated control method for urban intersections during peak hours proposed in this embodiment, includes the following steps:

[0108] Step 1: Front-end perception and data processing (perception layer)

[0109] The drone cruises at fixed points in an "S" shaped path over intersections A and B, capturing images of traffic flow. The embedded computing module analyzes the images in real time to identify lane conditions (number of vehicles, average speed, queue length, whether there is congestion, etc.). The extracted structured data is packaged into a "traffic status package" and sent to the MEC node via the 5G network.

[0110] Step 2: Data Fusion and Event Judgment (Edge-Aware Fusion)

[0111] The MEC node receives traffic status data from drones A and B; and establishes the intersection status matrix D. k (t), determine whether the following event exists: lane occupancy rate exceeds the threshold (e.g., ρ). lane ≥0.6) triggers the strategy optimization process.

[0112] The perception layer is responsible for real-time monitoring and data collection of traffic conditions. It mainly includes: UAV front-end video perception and preliminary analysis module: It realizes functions such as vehicle target detection, traffic density estimation and abnormal behavior screening through embedded computing on the UAV. It only sends structured information (such as the number of vehicles, congestion level and suspicious abnormal event flags) to the MEC node, which significantly reduces the transmission load.

[0113] The multi-source data fusion module integrates structured perception data from different UAVs, and can also incorporate ground perception sources such as ground induction coils, surveillance cameras, and RSUs to improve the overall perception coverage and reliability.

[0114] The event detection module's edge computing end determines the presence of sudden events (such as severe queuing, wrong-way driving, accidents, etc.) based on structured data streams and rule models, generating a description of the current intersection status. Specifically, the edge computing end uses lane occupancy rate ρ... lane The threshold is used to determine whether there is congestion at the current intersection and to record it. If ρ lane >ρ thresh If ρ is the value of ρ, then it is considered congested. thresh This is the set congestion determination threshold. Furthermore, if the above detection result falls under E... abn If so, then the abnormal event will be recorded.

[0115] Step 3: Signal Timing Optimization and Coordinated Scheduling (Decision-Making Level)

[0116] First, the traffic lights are released sequentially according to a preset plan. Then, the duration of each phase is determined based on the following scheme: the optimal timing strategy for the intersection is generated by analyzing the current traffic conditions based on perception data and using a dynamic timing algorithm.

[0117] Strategy evaluation and adaptive feedback module: Based on signal control results and real-time traffic feedback, it continuously evaluates the effectiveness of the current strategy and makes adaptive corrections. The adaptive feedback adjustment mechanism ensures that the system has a strong ability to adapt to dynamic changes in traffic conditions, guaranteeing the real-time performance and effectiveness of the traffic control strategy.

[0118] Step 4: Policy Distribution and Control Execution (Control Layer)

[0119] The generated signal control strategy is sent from the MEC to the traffic light controllers at each intersection; the controllers adjust the light control parameters in real time to achieve dynamic priority adjustment of traffic flow and extension of green light time; the controller's execution status is fed back to the MEC through the status confirmation module, and the execution effect is verified by the UAV.

[0120] 3) Experimental data and effect verification

[0121] To verify the control effect of the system of the present invention during peak hours, the following two indicators were selected for comparative experiments, and the comparison results are shown in Table 3:

[0122] Table 3

[0123] Test Items Traditional fixed time control solution Invention Solution Improvement rate Average queue length (meters) 110m 65m ↓40.9％ Number of vehicles passing through (30 minutes) 630 vehicles 880 vehicles ↑39.7％ Average vehicle speed (within the intersection) 12km / h 18km / h ↑50％

[0124] 4) Results Analysis and Summary

[0125] As shown in Table 3 of the experimental results, this invention effectively alleviates traffic bottlenecks during peak hours through a collaborative perception and control mechanism assisted by low-altitude unmanned aerial vehicles (UAVs). Its core advantages are reflected in:

[0126] Wider and more flexible perception: avoiding blind spots of ground sensors; more efficient communication: transmitting only structured data, reducing bandwidth pressure; more dynamic and intelligent policies: capable of responding to emergencies; more global and coordinated management and control: supporting unified scheduling of multiple intersections, avoiding policy conflicts.

[0127] This invention effectively alleviates traffic congestion during morning and evening rush hours: by using aerial drones to acquire real-time traffic flow data from multiple intersections, dynamically analyzing congestion trends, and adjusting signal timing in a timely manner, it effectively guides vehicle traffic and improves intersection efficiency. It also enhances the intelligence level of urban intersection signal control: by constructing a closed-loop system architecture from perception and analysis to control, it integrates drones, edge computing, and intelligent signal control equipment to achieve real-time generation and execution of signal timing schemes. Furthermore, it strengthens the responsiveness and adaptability of the traffic management system: it possesses a rapid response mechanism for sudden traffic events (such as accidents and abnormal traffic flow), allowing for temporary adjustments to signal strategies and the issuance of guidance instructions, thereby improving system robustness and traffic safety. Finally, it enables coordinated scheduling and control between intersections: through the mobile perception capabilities of drones and a regional data sharing mechanism, it supports unified coordinated control of multiple adjacent intersections, avoiding situations where local optimization leads to a decrease in overall efficiency.

[0128] This invention overcomes the limitations of traditional ground-based sensing methods in terms of field of view, information update frequency, and real-time performance; it compensates for the shortcomings of existing UAV sensing solutions in failing to form an automatic control closed loop and lacking a real-time control execution mechanism; and it establishes a traffic collaborative management and control system with rapid perception, intelligent decision-making, and precise control for peak hours, multiple intersections, and complex traffic conditions.

[0129] This embodiment fully verifies the practicality, innovation, and significant effects of the present invention in the field of intelligent control of urban traffic signals.

[0130] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.

Claims

1. A low-altitude unmanned aerial vehicle (UAV)-assisted peak-hour urban intersection coordination control system, characterized in that: The system comprises: a device deployment layer, a perception layer, a decision-making layer, and a control layer. The perception layer, decision-making layer, and control layer implement corresponding data acquisition and data processing based on the infrastructure deployed in the device deployment layer. The equipment deployment layer includes the deployment of low-altitude drones, intelligent traffic signal controllers, communication modules, and edge computing devices. The low-altitude drones and edge computing devices communicate through the communication modules. The drones acquire video information and front-end processing tasks, and the edge computing devices extract structured data and upload it to the perception layer. The perception layer determines the intersection status information based on structured data and transmits it to the decision layer. The decision layer generates real-time signal timing strategies and regional scheduling schemes based on the intersection status information. The control layer controls traffic lights based on the real-time signal timing scheme and regional scheduling scheme output by the decision layer, and the execution results of the traffic lights are fed back to the perception layer through ground equipment or drones; in case of continuous congestion or strategy execution failure, the system triggers an adaptive optimization and early warning mechanism to achieve dynamic correction. The decision-making layer is responsible for generating traffic control strategies, which includes a timing optimization module and a strategy evaluation and adaptive feedback module. When the traffic lights are released in sequence according to the preset plan, the timing optimization module analyzes the current traffic status based on the perception data, uses a dynamic timing algorithm to generate the optimal timing strategy for the intersection, and adjusts the duration of each phase according to the optimal timing strategy. The strategy evaluation and adaptive feedback module continuously evaluates the effectiveness of the current strategy and makes adaptive corrections based on signal control results and real-time traffic feedback. In the timing optimization module, the lanes under the optimal timing strategy Corresponding green light duration The calculation method is as follows: in, Indicates the number of vehicles in the queue; This represents the distance the preceding vehicle has traveled when the following vehicle starts moving. It is the distance the vehicle travels after starting and accelerating to the required speed; and These represent the expected speed and the lost time, respectively. To accelerate the start; System time; For vehicle length; This indicates the number of vehicles input from upstream. This indicates that the delay time of upstream vehicles has been taken into account. Indicates the amount of strategy adjustment; The safe following distance is described using an intelligent driver model, which includes predicting acceleration. Defined as: in, , , , and These represent maximum acceleration, maximum speed, congestion distance, safe travel distance, and desired acceleration, respectively. Indicates the instantaneous speed of the vehicle; , , These represent the distance, speed difference, and safety distance between vehicle n and vehicle n-1, respectively. The strategy evaluation and adaptive feedback module evaluates the effectiveness of the strategy according to the following formula: in, This represents the difference between the target number of vehicles that passed through and the actual number of vehicles that passed through after a green light cycle. Indicates the weight of upstream vehicles. This indicates the actual number of vehicles that passed through. Then, the signal timing strategy is corrected based on the strategy error feedback: in, For strategy adjustment amount, This is the feedback adjustment coefficient.

2. The low-altitude unmanned aerial vehicle-assisted peak-hour urban intersection coordination control system according to claim 1, characterized in that: The low-altitude drones deployed at the equipment layer are equipped with high-definition cameras, embedded computing platforms, and flight control systems. They use high-definition cameras to conduct aerial patrols and take pictures in the intersection and its surrounding areas, and use embedded computing platforms to perform preliminary image analysis, including vehicle detection and vehicle recognition, and generate structured data locally. The intelligent traffic signal controller includes an external communication interface, through which it remotely receives control strategies and dynamically adjusts the duration and phase sequence of traffic lights according to the received control strategies. Edge computing devices acquire structured information transmitted by drones through communication modules and perform time analysis and control strategy generation based on the structured information; The communication module employs high-speed communication technology to support data synchronization between the UAV and MEC nodes, as well as information transmission in the event of command distribution between the MEC and traffic lights.

3. The low-altitude unmanned aerial vehicle-assisted peak-hour urban intersection coordination control system according to claim 1, characterized in that: The perception layer performs corresponding operations based on the basic settings deployed by the device deployment layer. The perception layer includes: a drone front-end video perception and preliminary analysis module, a multi-source data fusion module, and an event detection module. The UAV front-end video perception and preliminary analysis module is deployed in the UAV's embedded computing platform. Based on the acquired video information, it completes vehicle target detection, traffic density estimation, and preliminary screening of abnormal behavior, and transmits the structured data to the edge computing node. The multi-source data fusion module integrates structured perception data from different drones; The event detection module determines whether there is a sudden event based on the structured data flow and rule model, and generates a description of the current intersection status.

4. A low-altitude unmanned aerial vehicle-assisted peak-hour urban intersection coordination control system according to claim 3, characterized in that: In the drone front-end video perception and preliminary analysis module, the drone Output structured data Represented as: in: The vehicle count represents the number of vehicles present on the road per unit of time. Lane occupancy rate reflects the degree of traffic congestion; The total length of the observed road segment, For vehicles Length; These are indicators of abnormal events, including wrong-way driving and traffic accidents. The structured sensing data from different sensing sources, integrated by the multi-source data fusion module, are as follows: in, This refers to the number of vehicles allowed to pass upstream of the intersection. The event detection module detects lane occupancy rate. The threshold for determining congestion at the intersection is used to identify and record whether congestion exists. The congestion threshold is set as follows: ,like If the above detection result is positive, it is considered congested; otherwise, it is considered that there is no congestion. Then, abnormal events are recorded; structured sensing data from different sensing sources. Used to guide decision-makers in specifying signal timing schemes.

5. A low-altitude unmanned aerial vehicle-assisted peak-hour urban intersection coordination control system according to claim 1, characterized in that: The control layer includes an instruction issuing module, a traffic light execution module, and a feedback confirmation module. The instruction issuing module, deployed in the edge computing device, sends the timing strategy generated by the decision layer to the traffic light controller at the corresponding intersection in real time via a wireless link. The traffic light execution module in the traffic light controller automatically adjusts the red and green light cycle, phase sequence, and phase according to the timing strategy received by the traffic light controller. The feedback confirmation module in the traffic light controller feeds back the execution results to the edge computing node and performs closed-loop verification through UAV perception to achieve closed-loop optimization of the strategy.

6. A method for coordinated control of urban intersections during peak hours assisted by low-altitude unmanned aerial vehicles (UAVs), characterized in that: Based on any one of the aforementioned claims 1-5, a low-altitude unmanned aerial vehicle (UAV)-assisted peak-hour urban intersection coordination control system, the method includes: The system uses drones to acquire video images of intersections, performs front-end perception and data processing at the perception layer, and then transmits the processed structured data to the decision-making layer. Edge computing devices receive traffic status data from different drones, build an intersection status matrix, and determine whether the lane occupancy rate exceeds the threshold. If it exceeds the threshold, a strategy optimization process is triggered. At the decision-making level, signal timing optimization and coordination are carried out. Based on the analysis of current traffic conditions using perception data, dynamic timing algorithms are used to generate the optimal timing strategy for intersections. The generated signal control strategy is sent to the traffic light controllers at each intersection; the controllers adjust the light control parameters in real time, and the controller execution status is fed back to the edge computing device through the status confirmation module, and the execution effect is sensed and verified by the drone.

Images