A traffic signal lamp cooperative control method and device and storage medium

Abstract

The application provides a traffic signal lamp cooperative control method and device and a storage medium, relates to the technical field of intelligent transportation, and the method comprises the following steps: acquiring running track data of each vehicle and traffic signal lamp state data; marking a space-time conflict point in a preset time period; setting a dynamic priority passing sequence; in the process of signal lamp phase switching, reconstructing a signal lamp phase time sequence of an intersection and issuing a cooperative control instruction; transmitting the cooperative control instruction to each traffic signal lamp controller in real time through a communication link; and simultaneously, dynamically correcting a phase time sequence deviation by using real-time position information of vehicles fed back through the communication link. The application solves the technical problem that traffic congestion occurs in a sudden situation due to the fact that traffic signal lamps rely on a fixed cycle, thereby affecting traffic efficiency, marks a space-time conflict point by using running track data of vehicles, dynamically adjusts signal lamps, effectively reduces traffic congestion, and improves traffic efficiency.

Description

Technical Field

[0001] This application relates to the field of intelligent transportation technology, and in particular to a method, device and storage medium for coordinated control of traffic lights. Background Technology

[0002] Traffic signal control systems play a crucial role in urban road management. A well-designed signal control strategy can effectively improve road efficiency and reduce traffic congestion. However, existing traffic signal control methods still have many limitations in practical applications, especially in responding promptly to sudden traffic situations, leading to traffic flow obstruction and impacting overall traffic efficiency. While some intelligent transportation systems can adjust traffic light durations based on past traffic flow data, they still suffer from response lag. In sudden situations, signal light adjustments often require a period of data collection and calculation, failing to immediately adapt to new traffic conditions. This can easily lead to severe congestion in some lanes while wasting green light time in other lanes, reducing overall traffic efficiency.

[0003] In summary, existing technologies suffer from the problem that traffic lights rely on fixed cycles, leading to traffic congestion in unexpected situations and thus affecting traffic efficiency. Summary of the Invention

[0004] The purpose of this application is to provide a traffic signal light coordinated control method, device and storage medium to solve the technical problem in the prior art that traffic lights rely on a fixed cycle, which leads to traffic congestion in sudden situations and thus affects traffic efficiency.

[0005] In view of the above problems, this application provides a traffic signal light coordinated control method, device and storage medium.

[0006] In a first aspect, this application provides a traffic signal coordinated control method, which is implemented through a traffic signal coordinated control device. The method includes: acquiring the trajectory data of each vehicle and the status data of traffic signals within a target area; based on the trajectory data, marking the spatiotemporal conflict points of each vehicle arriving at the intersection within a preset time period; setting a dynamic priority passage sequence according to the distribution of the spatiotemporal conflict points and the traffic signal status data; based on the dynamic priority passage sequence, reconstructing the traffic signal phase timing of the intersection and issuing coordinated control commands during traffic signal phase switching; the coordinated control commands are transmitted in real time to each traffic signal controller via a communication link, and simultaneously, the phase timing deviation is dynamically corrected using the real-time vehicle location information fed back from the communication link.

[0007] Optionally, within the target area, vehicle speed, acceleration, and turn signal status are collected using V2X communication via the onboard OBUs built into each vehicle; point cloud data from LiDAR and image data from cameras are fused to complete the trajectories of the remaining vehicles without OBUs; and the trajectory data is spatiotemporally aligned to obtain the running trajectory data of each vehicle within the target area.

[0008] Optionally, identify the types of vehicles with emergency passage rights and set priority rules; assess the passage urgency of each vehicle in the target area based on the remaining green light time and the vehicle's safe braking distance; and generate a dynamic priority passage sequence based on the priority rules, combined with the distribution of spatiotemporal conflict points and the passage urgency of each vehicle in the target area.

[0009] Optionally, based on the dynamic priority passage sequence, a reward function is configured to minimize the average vehicle delay time; based on the reward function, a buffer phase is introduced, the buffer phase including all-directional red light states and the estimated waiting time is positively correlated with the number of conflict points; before the traffic signal controller performs phase switching, a local change of phase timing is triggered by the buffer phase according to real-time traffic flow change events.

[0010] Optionally, phase difference coupling constraints are established; based on the phase difference coupling constraints, phase difference parameters of multiple intersections are determined; and green wave control parameters are generated according to the phase difference parameters of the multiple intersections.

[0011] Optionally, based on multiple intersections in the target area and combined with the dynamic priority passage sequence, a virtual twin model is configured; in the virtual twin environment, multiple candidate control strategies are run in parallel and the risk of congestion propagation is evaluated; a preset risk threshold is compared with the risk of congestion propagation to identify congested intersections and congestion phases in order to minimize congestion propagation, and the phase difference coupling constraint condition is established.

[0012] Optionally, between adjacent intersections, based on real-time traffic flow data, the congestion propagation path and impact range under different phase difference parameters are simulated; based on the congestion propagation path and impact range, multiple preset control strategies are generated; based on preset optimization objectives, the multiple preset control strategies are screened to obtain multiple candidate control strategies.

[0013] Secondly, this application also provides a traffic signal cooperative control device for executing a traffic signal cooperative control method as described in the first aspect. The traffic signal cooperative control device includes: a data acquisition module for acquiring the trajectory data of each vehicle within a target area and the status data of traffic signals; a conflict point marking module for marking spatiotemporal conflict points of each vehicle arriving at the intersection within a preset time period based on the trajectory data; a priority sequence setting module for setting a dynamic priority passage sequence based on the distribution of spatiotemporal conflict points and the traffic signal status data; a control command sending module for reconstructing the traffic signal phase timing of the intersection and issuing cooperative control commands during traffic signal phase switching based on the dynamic priority passage sequence; and a deviation correction module for transmitting the cooperative control commands to each traffic signal controller in real time via a communication link, and simultaneously dynamically correcting phase timing deviations using real-time vehicle location information fed back from the communication link.

[0014] Thirdly, a computer-readable storage medium storing a computer program that, when executed, implements the steps of the traffic signal light coordinated control method described in any one of the first aspects above.

[0015] One or more technical solutions provided in this application have at least the following beneficial effects:

[0016] By acquiring the trajectory data of each vehicle and the status data of traffic lights within the target area; based on the trajectory data, marking the spatiotemporal conflict points of each vehicle arriving at the intersection within a preset time period; setting a dynamic priority passage sequence based on the distribution of spatiotemporal conflict points and the traffic light status data; and reconstructing the traffic light phase timing sequence at the intersection and issuing coordinated control commands during traffic light phase switching based on the dynamic priority passage sequence; the coordinated control commands are transmitted in real time to each traffic light controller via a communication link, and the phase timing deviation is dynamically corrected using the real-time vehicle location information fed back from the communication link. In other words, by predicting the spatiotemporal conflict points of vehicles arriving at the intersection based on their trajectories, setting a priority passage sequence in conjunction with the traffic light status, and collecting real-time vehicle location information, intelligent and dynamic traffic light control effectively reduces traffic congestion and improves traffic management efficiency.

[0017] The above description is merely an overview of the technical solution of this application. To better understand the technical means of this application and to facilitate its implementation according to the description, and to make the above and other objects, features, and advantages of this application more apparent, specific embodiments of this application are described below. It should be understood that the content described in this section is not intended to identify key or important features of the embodiments of this application, nor is it intended to limit the scope of this application. Other features of this application will become readily apparent through the following description. Attached Figure Description

[0018] To more clearly illustrate the technical solutions in this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are merely exemplary. For those skilled in the art, other drawings can be obtained based on the provided drawings without creative effort.

[0019] Figure 1 This is a flowchart illustrating a traffic signal light coordinated control method according to this application;

[0020] Figure 2 This is a schematic diagram of the structure of a traffic signal light cooperative control system according to this application.

[0021] Figure labeling: Data acquisition module 11, conflict point marking module 12, priority sequence setting module 13, control command sending module 14, deviation correction module 15. Detailed Implementation

[0022] This application provides a traffic signal coordinated control method, device, and storage medium, solving the technical problem in the prior art where traffic signals rely on fixed cycles, leading to traffic congestion in sudden situations and thus affecting traffic efficiency. By predicting the spatiotemporal conflict points of vehicles arriving at intersections based on their travel trajectories, setting priority passage sequences in conjunction with traffic signal status, and collecting real-time vehicle location information, intelligent and dynamic traffic signal control effectively reduces traffic congestion and improves traffic management efficiency.

[0023] The technical solutions of this application will now be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. It should be understood that this application is not limited to the exemplary embodiments described herein. All other embodiments obtained by those skilled in the art based on the embodiments of this application without creative effort are within the scope of protection of this application. It should also be noted that, for ease of description, only the parts related to this application are shown in the accompanying drawings, not all of them.

[0024] Example 1, please refer to the appendix. Figure 1 This application provides a traffic light coordination control method, wherein the traffic light coordination control method is executed by a traffic light coordination control device, and the traffic light coordination control method specifically includes the following steps:

[0025] S100: Acquire the trajectory data of each vehicle and the status data of traffic lights within the target area.

[0026] Furthermore, this application S100 includes:

[0027] Within the target area, V2X communication using the onboard OBUs built into each vehicle is used to collect vehicle speed, acceleration, and turn signal status; point cloud data from LiDAR and image data from cameras are fused to complete the trajectories of the remaining vehicles without OBUs; the trajectory data is then spatiotemporally aligned to obtain the running trajectory data of each vehicle within the target area.

[0028] Specifically, the target area refers to the geographical range for collecting trajectory and traffic light data, such as a specific intersection, a main road, or an entire urban area. The vehicle's built-in On-Board Unit (OBU) utilizes V2X communication to collect data such as vehicle speed, acceleration, and turn signal status within the target area. The OBU is an on-board unit installed in the vehicle, primarily used for V2X communication, including vehicle-to-vehicle (V2V), vehicle-to-infrastructure (V2I), and vehicle-to-pedestrian (V2P) communication, enabling interconnection between vehicles and traffic infrastructure, other vehicles, and cloud platforms. V2X refers to wireless communication between vehicles and all (X) environments, namely the aforementioned vehicle-to-vehicle (V2V), vehicle-to-infrastructure (V2I), and vehicle-to-pedestrian (V2P) communication. The OBU communicates with other vehicles and infrastructure (RSUs) via DSRC or C-V2X to achieve data sharing between vehicles, enabling real-time collection of vehicle speed, acceleration, location information, turn signal status, etc., and interacting with the surrounding environment through wireless communication.

[0029] Some vehicles lack onboard units (OBUs), and their trajectory data needs to be supplemented using LiDAR and cameras. LiDAR acquires 3D spatial information about vehicles, pedestrians, and obstacles through laser pulse ranging, forming point cloud data (a 3D map composed of multiple points). Cameras (such as vehicle-mounted or roadside cameras) capture vehicle images and identify vehicle type, direction, lane markings, and other information. By combining the LiDAR point cloud data and camera images, the trajectory data of vehicles without OBUs is completed, ensuring the integrity of trajectory data for all vehicles within the target area.

[0030] Because OBU data, radar data, and camera data have different sampling frequencies (e.g., OBU samples every 100ms, while cameras sample every 30ms), spatiotemporal alignment is required, i.e., aligning data from different sensors at the same point in time. All trajectory data undergoes spatiotemporal alignment to ensure that the trajectory data of all vehicles are time-synchronized and coordinate-consistent for subsequent signal optimization. The collected vehicle trajectory data may contain time delays or spatial deviations. Data processing algorithms, such as time synchronization and spatial coordinate transformation, are used to align trajectory data from different sources. The trajectory data is time-aligned according to the acquisition timestamp, and interpolation algorithms (such as linear interpolation and spline interpolation) are used to adjust data with different timestamps to the same point in time. Data collected by different devices is transformed into a unified spatial coordinate system, and spatial deviations are eliminated through rotation and translation transformations. The time-synchronized and spatially transformed data are fused to form a complete and accurate vehicle trajectory. Through spatiotemporal alignment, the precise position and timestamp of each vehicle within the target area are obtained, such as vehicle A arriving at the southwest corner of the intersection at time T1.

[0031] The intelligent signal control center acquires data such as traffic light phase, duration, and change cycle, combines this data with roadside sensing devices to monitor traffic light status, and synchronizes it with the cloud to obtain traffic light status data, including traffic light color and switching time. Vehicle trajectory data and traffic light status data are then aligned using a unified timestamp.

[0032] Vehicle trajectory data includes the movement paths of all vehicles on the road within the target area, typically composed of a series of time-series data points, such as timestamps, latitude and longitude coordinates, speed, acceleration, and direction angle. Traffic light status data describes the operational status of traffic lights, including the duration, phase (direction), and periodic changes of red, green, and yellow lights. Obtaining accurate vehicle trajectory and traffic light status data helps traffic management systems promptly identify potential traffic conflict points, take measures, and improve road safety.

[0033] S200: Based on the running trajectory data, mark the spatiotemporal conflict points of each vehicle arriving at the intersection within a preset time period in the target area.

[0034] Specifically, based on the acquired trajectory data of each vehicle, the trajectory of each vehicle is analyzed to determine its position and speed within a preset time period. Based on the trajectory data, the arrival time of each vehicle at each lane intersection is calculated. Considering the vehicle's current position, speed, acceleration, direction of travel, intersection geometry, and possible acceleration or deceleration changes, the precise arrival time of each vehicle at the intersection is predicted. Typically, methods used include simple physical models based on vehicle speed and current position, such as constant speed models or acceleration models. These models can help predict the specific arrival time of each vehicle at the intersection. If the vehicle accelerates or decelerates during its journey, acceleration equations of motion are required for more accurate time prediction.

[0035] After obtaining the arrival time of each vehicle at the intersection, the next step is to mark spatiotemporal conflict points. A spatiotemporal conflict point is defined as a situation where two vehicles are expected to arrive at the same intersection or adjacent lanes of an intersection within a similar timeframe, and they are likely to collide or interfere with each other. To mark these conflict points, the time difference between the arrival times of every two vehicles at the intersection is calculated, and these time differences are compared to the vehicles' travel paths. If the arrival times of two vehicles are very close, and their travel paths overlap or are close, then they can be marked as potential conflict points. For example, assuming the traffic light cycle at the intersection is 30 seconds, and two vehicles are expected to arrive at the same intersection within 5 seconds, and their paths intersect, these two vehicles are automatically marked as high-conflict points, and traffic accidents may be avoided by adjusting the timing of the traffic lights.

[0036] By marking points of spatiotemporal conflict, potential traffic accident risks can be identified in advance, enabling preventative measures such as adjusting traffic light timings and issuing traffic warnings.

[0037] S300: Based on the distribution of spatiotemporal conflict points and the traffic light status data, set a dynamic priority passage sequence.

[0038] Furthermore, this application S300 includes:

[0039] Identify vehicle types with emergency passage permissions and set priority rules; assess the urgency of passage for each vehicle in the target area based on the remaining green light time and the vehicle's safe braking distance; and generate a dynamic priority passage sequence based on the priority rules, combined with the distribution of spatiotemporal conflict points and the urgency of passage for each vehicle in the target area.

[0040] Specifically, by analyzing vehicle trajectories and related sensor data, vehicles with emergency passage rights, such as ambulances, fire trucks, or police cars, are identified. These vehicles typically have specific emergency identification markings in their V2X information. Based on the vehicle type indicated by the emergency identification markings, a set of priority rules is established to grant emergency vehicles higher right-of-way.

[0041] Using the current traffic light status data at the intersection, determine the remaining green light time, i.e., the number of seconds remaining in the current green light phase. Based on the speed and reaction time of each vehicle within the target area, calculate the vehicle's safe braking distance, i.e., the distance a vehicle can safely stop in an emergency braking situation. For example, a vehicle traveling at 60 km / h might have a safe braking distance of approximately 40 meters. Based on the remaining green light time and the vehicle's safe braking distance, assess the urgency of passage for each vehicle within the target area. For example, if a vehicle is currently close to the intersection, but has only 3 seconds of remaining green light time, and its calculated safe braking distance is 40 meters, then the vehicle's urgency will be assessed as high.

[0042] By combining priority rules, the distribution of spatiotemporal conflict points, and the urgency of passage for each vehicle within the target area, a dynamic priority passage sequence is generated. This sequence dynamically adjusts the passage order of vehicles, determining which vehicles should have priority in the next phase. For example, suppose an ambulance is approaching an intersection when the traffic light is about to change from green to red. Vehicle identification determines that this is a vehicle with emergency passage rights. According to the priority rules, the ambulance is assigned the highest priority. The remaining green light time for the ambulance to reach the intersection is calculated to be 10 seconds, and the safe braking distance is 50 meters. The calculated urgency of passage for the ambulance is 0.2 (10 seconds / 50 meters), indicating that the traffic light needs to be adjusted immediately to ensure the ambulance's priority passage.

[0043] By accurately identifying emergency vehicles and assessing the urgency of all vehicles, a priority passage sequence is dynamically generated. This ensures that emergency vehicles can pass safely and prioritized, and optimizes traffic light scheduling based on real-time traffic conditions, thereby significantly improving the efficiency and safety of intersections.

[0044] Furthermore, this application also includes the following steps:

[0045] Based on the dynamic priority passage sequence, a reward function is configured to minimize the average vehicle delay time; based on the reward function, a buffer phase is introduced, which includes all-directional red light states and the estimated waiting time is positively correlated with the number of conflict points; before the traffic signal controller performs phase switching, a local change in phase timing is triggered by the buffer phase according to real-time traffic flow change events.

[0046] Specifically, based on the dynamically prioritized passage sequence generated above, a reward function is designed with the goal of reducing the average vehicle delay time. The average vehicle delay time refers to the average time a vehicle waits to pass through an intersection. The reward function is a mathematical model used to quantify the delay effect under different traffic light phase schemes, with the aim of minimizing this delay value. In other words, the optimization algorithm finds the optimal traffic light switching strategy by providing a higher reward for a lower average delay.

[0047] A buffer phase is introduced, which includes a red light state in all directions. Its estimated waiting time is positively correlated with the number of conflict points. The characteristic of the buffer phase is that the traffic lights in all directions show red simultaneously, that is, vehicles are prohibited from passing in all directions. Its design purpose is to provide a transition window. During this phase, the waiting time is estimated based on the number of currently detected conflict points (such as the location of vehicles about to collide at the intersection). The more conflict points, the longer the estimated waiting time, thus allowing sufficient reaction time for subsequent adjustments.

[0048] Before the traffic signal controller officially executes phase switching, it monitors sudden changes in traffic flow (such as sudden influx of vehicles or traffic changes caused by accidents) in real time. When such a change is detected, the buffer phase is used as a trigger to locally change the original phase sequence, thereby adjusting the signal light strategy in a timely manner and avoiding delays that could lead to more severe congestion or safety hazards.

[0049] For example, if a sudden 20% increase in traffic density in a certain direction is detected, causing the average waiting time for vehicles in that direction to rise from 3 seconds to 5 seconds, a buffer phase is activated before the phase switch, temporarily setting all directions to red. After reassessment, the original signal timing is locally adjusted, for example, increasing the green light duration for that direction by 2 seconds in the next phase, thereby quickly alleviating the sudden congestion. By constructing a reward function based on a dynamic priority passage sequence and introducing a buffer phase positively correlated with the number of conflict points, timely adjustments are made before sudden changes in traffic flow, thereby achieving local replacement of signal phases. This not only effectively reduces the average vehicle delay but also, in actual testing, demonstrates that the introduction of a buffer phase enables rapid response to sudden events, significantly improving the safety and traffic efficiency of intersections.

[0050] S400: Based on dynamic priority passage sequence, during the traffic light phase switching process, the traffic light phase timing of the intersection is reconstructed and coordinated control commands are issued.

[0051] Specifically, the effectiveness of the current traffic light phase sequence is reassessed based on the dynamic priority traffic sequence. Optimization algorithms (such as genetic algorithms, simulated annealing, linear programming, etc.) are used to adjust the phase sequence to minimize vehicle delays and maximize traffic flow efficiency. Factors such as intersection geometry, lane configuration, and traffic flow characteristics are considered to ensure that the new phase sequence strikes a balance between safety and efficiency.

[0052] A comprehensive objective function was designed, primarily aiming to minimize average vehicle delay time and maximize traffic flow efficiency, while embedding safety constraints, such as ensuring necessary safe intervals between directions to prevent conflicts caused by excessively short green light times. In the initial stage, an initial population consisting of several candidate signal timing sequences is randomly generated. Using real-time collected data on vehicle trajectories, conflict point distribution, and intersection geometry, the fitness of each candidate scheme is evaluated. Based on fitness, some candidate schemes are selected for cross-pollination, combining elements from two or more excellent schemes to generate new candidate schemes. For example, one scheme might set longer green light times for north and east directions, while another optimizes for south and west directions. After cross-pollination, the new scheme may achieve a more balanced adjustment of green light times in all directions, thereby further reducing average vehicle delay in the simulation.

[0053] To avoid local optima traps, the algorithm also mutates some genes, randomly adjusting the duration or order of a phase to ensure diversity in the search space. After multiple iterations, until the improvement of candidate solutions stabilizes, the algorithm eventually converges to one or more optimal solutions. This optimization yields the reconstructed traffic light phase sequence of the intersection, i.e., the optimal or near-optimal traffic light phase sequence scheme. The optimized phase sequence is converted into traffic light control commands and issued to the signal controllers at each intersection as coordinated control commands. These commands are generally real-time and coordinated, ensuring synchronized response of all traffic lights at the intersection and avoiding information delays or control conflicts caused by local adjustments. In other words, when a change in traffic flow is detected, new control commands are issued in real time during the traffic light phase switching process by adjusting the switching sequence of green, yellow, and red lights, thereby quickly adapting to actual traffic conditions and ensuring vehicle traffic efficiency and safety.

[0054] Dynamic reconfiguration and collaborative control not only reduced the average vehicle delay time and improved the intersection's capacity, but also effectively reduced safety hazards caused by sudden changes in traffic flow through the real-time issuance of collaborative control commands, thereby improving the overall operational efficiency and emergency response capability of the intersection.

[0055] S500: The coordinated control command is transmitted to each traffic light controller in real time through the communication link. At the same time, the phase timing deviation is dynamically corrected by using the real-time vehicle location information fed back by the communication link.

[0056] Specifically, coordinated control commands are signal light phase adjustment schemes determined based on real-time traffic data, dynamic priority sequences, and optimization algorithms. These commands are transmitted in real time to the traffic light controllers at each intersection via high-speed communication links. Coordinated control commands mean that the adjustment information received by the traffic lights at each intersection can work collaboratively throughout the entire traffic network to achieve overall scheduling optimization.

[0057] A communication link refers to the network channel used for data transmission, such as a network based on 5G, DSRC, or fiber optic communication. These links ensure low latency and high reliability in command transmission. Choose the appropriate communication technology based on actual needs and conditions, such as fiber optic, Dedicated Short Range Communication (DSRC), Wi-Fi, or 4G / 5G networks. Configure the communication network to ensure that all traffic light controllers can access the network and that the network has sufficient bandwidth and low latency.

[0058] To ensure the security and integrity of instructions, they are encrypted and transmitted using secure protocols such as TLS / SSL. Real-time transport protocols (such as TCP or UDP) are used to send instructions. TCP provides reliable transmission, while UDP, although less reliable, has lower latency and is suitable for scenarios with extremely high real-time requirements. The communication link is monitored in real time during transmission to ensure instructions arrive successfully.

[0059] Upon receiving a command, the traffic light controller first decrypts and verifies it. Commands that pass verification are executed by the controller to adjust the phase sequence of the traffic lights. After executing the command, the controller sends an execution confirmation message to the control center. The traffic light controller periodically or based on event triggers sends current status information to the control center, including traffic light phase and fault information.

[0060] Simultaneously, real-time vehicle location information is fed back via communication links and compared with the preset signal timing to determine if any deviation exists. If vehicles are expected to travel near the intersection at a set speed during the green light period, but actual monitoring data shows that vehicles arrive early or late, a phase timing deviation is considered to exist. The remaining time of the current signal phase is automatically adjusted, or subsequent phase switching strategies are modified to ensure that actual vehicle traffic better matches the expected plan. Based on the correction strategy, the signal timing at the intersection is dynamically adjusted. The adjusted signal timing information is fed back to the traffic signal controller. The signal controller adjusts the phase timing of the traffic lights in real time based on the new timing information. It also adjusts the signal timing of each intersection, including green light time, red light time, and all-red time, based on the phase difference parameters of multiple intersections. This ensures that the phase difference parameters of the traffic lights at adjacent intersections are coordinated to form a green wave, allowing vehicles exiting one intersection at a certain speed to encounter a green light when reaching the next intersection. By dynamically correcting phase timing deviations, the flexibility and efficiency of traffic signal control are improved, thereby further enhancing the overall performance of the traffic system.

[0061] Furthermore, this application S500 includes:

[0062] Establish phase difference coupling constraints; based on the phase difference coupling constraints, determine the phase difference parameters of multiple intersections; generate green wave control parameters according to the phase difference parameters of the multiple intersections.

[0063] Furthermore, this application also includes the following steps:

[0064] Based on multiple intersections in the target area and the dynamic priority passage sequence, a virtual twin model is configured. In the virtual twin environment, multiple candidate control strategies are run in parallel and the risk of congestion propagation is evaluated. The preset risk threshold is compared with the risk of congestion propagation to identify congested intersections and congestion phases in order to minimize congestion propagation and establish the phase difference coupling constraint condition.

[0065] Specifically, the process involves acquiring real-time traffic data from multiple intersections in the target area, including vehicle flow, speed, and traffic light timing. A virtual twin model is then constructed based on this data, representing a digital replica of the real-world traffic system and capable of simulating traffic flow and traffic light control. Dynamic priority sequences are integrated into the virtual twin model to ensure that the model can adjust traffic light control strategies according to real-time traffic demands.

[0066] In a virtual twin environment, multiple candidate control strategies are run simultaneously. These strategies may involve different traffic light switching sequences, green light extension schemes, or priority release rules. Through parallel simulation, the performance of each strategy in the face of congestion propagation risk is evaluated. The congestion propagation risk under each strategy is assessed, including the congestion initiation point, propagation speed, and scope of impact.

[0067] Based on traffic management objectives and historical data analysis, a risk threshold for congestion propagation is pre-set. The congestion propagation risk simulated in the virtual twin model is compared with the pre-set risk threshold. Which intersections and signal light phases might cause congestion propagation to exceed the risk threshold are identified. Situations exhibiting congestion at intersections and congested phases (i.e., severe delays at certain intersections under specific signal phases) are identified, and phase difference coupling constraints are established based on this. These constraints are used to synchronously adjust the signal phases between adjacent intersections in actual control, ensuring that congestion does not spread throughout the network, thereby achieving the goal of overall traffic flow optimization. The phase difference coupling constraint controls traffic flow and reduces congestion by adjusting the signal light phase difference between adjacent intersections.

[0068] For example, in a simulation experiment covering a 3-square-kilometer area in the city center, the experimental platform integrated data from 300 V2X vehicles, information collected by 10 LiDARs and 20 cameras. After virtual twin modeling, one of the candidate strategies running in parallel reduced the risk of congestion propagation at a certain intersection during peak hours from 0.75 (expressed as a risk index) to 0.35. The signal phases of adjacent intersections were also coordinated after phase difference coupling. The average vehicle delay in the entire area was reduced from 6.5 seconds to 4.2 seconds. Simulations also showed that this solution reduced the probability of congestion spread by 30%.

[0069] By running and evaluating multiple candidate control strategies in parallel in a virtual twin environment, traffic managers can quickly identify key intersections and phases that may lead to congestion and take corresponding control measures to ensure both safety and efficiency under various complex road conditions. This helps to significantly improve the capacity and emergency response of the entire traffic network.

[0070] Based on the established positional coupling constraints, the green light start time difference between multiple intersections is parametrically designed. A phase difference parameter is determined, representing the time offset between green lights at adjacent intersections. This ensures that when a vehicle exits one intersection at a certain speed, it can reach the next intersection when the light turns green. For example, in an experiment in a city center, real-time analysis of the intersection's geometric layout, lane configuration, and traffic flow characteristics determined the optimal phase difference from intersection A to B to be 5 seconds, and from B to C to be 6 seconds. This means that if a vehicle starts its journey from the green light at intersection A, it is expected to reach intersection B 5 seconds later, by which time intersection B will have switched to a green light, thus achieving seamless passage.

[0071] Based on the phase difference parameters, green wave control parameters are generated. This involves coordinating the signal timing at each intersection throughout the traffic corridor to form a continuous green wave, allowing vehicles to pass through green lights continuously at a predetermined speed. Using real-time vehicle trajectory data, conflict point detection results, and traffic flow information, the optimal signal start time and green light duration are determined through a virtual twin model and optimization tools, such as the aforementioned genetic optimization algorithm. Based on the determined phase difference parameters, the signal timing at each intersection is adjusted, including green light time, red light time, and all-red time. This ensures that the phase difference parameters of the signal lights at adjacent intersections are consistent, forming a green wave. Real-time traffic data feedback is used to fine-tune the green wave control parameters. For example, the green light start time at intersection A is set to 0 seconds, the green light start time at intersection B to 20 seconds, and so on, forming a green wave that allows vehicles to continuously encounter green lights while maintaining a certain speed.

[0072] By determining the phase difference parameters of multiple intersections based on phase difference coupling constraints and generating green wave control parameters, the waiting time of vehicles at intersections is reduced, and the continuity of traffic flow is improved. This not only significantly reduces the average delay time of vehicles, but also significantly reduces the risk of congestion spread, bringing a more efficient and intelligent solution to urban traffic management.

[0073] Furthermore, this application also includes the following steps:

[0074] Between adjacent intersections, based on real-time traffic flow data, the congestion propagation path and impact range under different phase difference parameters are simulated; based on the congestion propagation path and impact range, multiple preset control strategies are generated; based on preset optimization objectives, the multiple preset control strategies are screened to obtain multiple candidate control strategies.

[0075] Specifically, between two adjacent intersections, the congestion propagation path and its impact range under different phase difference parameters are simulated based on real-time traffic flow data. The phase difference parameter refers to the time offset between the traffic light phases of adjacent intersections. By collecting real-time traffic flow data (such as vehicle speed, flow rate, and density), a virtual twin model is used to evaluate the impact of different phase difference parameter settings on traffic flow and simulate the congestion propagation path from one intersection to the next. During the simulation, changes in traffic flow will affect the starting location, direction of spread, and range of congestion. For example, an excessively large phase difference may cause vehicle accumulation at one intersection, thus affecting the traffic efficiency of subsequent intersections. In this way, the potential congestion and its propagation path caused by each intersection or phase configuration are identified.

[0076] The congestion propagation path is the route by which traffic congestion spreads from one intersection to another, and the impact range is the extent to which the congestion propagates to the surrounding area. Based on the congestion propagation path and impact range, multiple preset control strategies are generated, including adjusting the signal light switching sequence, phase duration, and inter-phase relationships at each intersection to minimize or mitigate congestion propagation. The generated strategies ensure coverage of different traffic scenarios and demands, such as peak hours, off-peak hours, and special events. For example, under one strategy, if the phase difference parameter is too large, the resulting congestion might spread from intersection A to intersection B. However, if another strategy adjusts the phase difference and reasonably configures the green light time, the scope of this congestion propagation can be effectively controlled. The preset control strategies will consider factors such as different traffic flows, vehicle delay times, and traffic efficiency.

[0077] Define optimization objectives, such as minimizing overall delays, maximizing capacity, and reducing congestion propagation. Based on these objectives, determine evaluation metrics, such as average vehicle delay, queue length, and number of stops. Use these metrics to evaluate each preset control strategy, selecting multiple candidate control strategies that meet the optimization objectives. Candidate control strategies may include different traffic light timing schemes. After screening, select the strategies that effectively prevent congestion propagation while also ensuring safety and improving traffic efficiency.

[0078] One or more candidate control strategies are selected for real-world testing or implementation. During implementation, traffic conditions are monitored in real time, and feedback data is collected. Based on the real-time feedback, the control strategies are dynamically adjusted to adapt to changes in traffic flow. For example, in a test area in a city, by simulating traffic flow under different phase difference parameters, it was found that excessively long phase differences caused traffic congestion from intersection A to intersection B to affect traffic flow within a range of approximately 500 meters. By adjusting signal timing and simulating different control strategies, a solution was ultimately selected that could reduce the spread of traffic congestion and optimize traffic efficiency. This strategy, by setting reasonable phase difference and green wave control parameters, ultimately reduced the impact range of congestion propagation by approximately 30%.

[0079] By simulating and evaluating the congestion propagation path and impact range under different phase difference parameters, traffic flow can be optimized based on real-time traffic conditions, traffic congestion can be reduced, the responsiveness of the traffic management system can be enhanced, the system can better adapt to complex and ever-changing traffic environments, and traffic efficiency can be significantly improved.

[0080] In summary, the traffic signal coordinated control method provided in this application has the following beneficial effects:

[0081] By acquiring the trajectory data of each vehicle and the status data of traffic lights within the target area; based on the trajectory data, marking the spatiotemporal conflict points of each vehicle arriving at the intersection within a preset time period; setting a dynamic priority passage sequence based on the distribution of spatiotemporal conflict points and the traffic light status data; and reconstructing the traffic light phase timing sequence at the intersection and issuing coordinated control commands during traffic light phase switching based on the dynamic priority passage sequence; the coordinated control commands are transmitted in real time to each traffic light controller via a communication link, and the phase timing deviation is dynamically corrected using the real-time vehicle location information fed back from the communication link. In other words, by predicting the spatiotemporal conflict points of vehicles arriving at the intersection based on their trajectories, setting a priority passage sequence in conjunction with the traffic light status, and collecting real-time vehicle location information, intelligent and dynamic traffic light control effectively reduces traffic congestion and improves traffic management efficiency.

[0082] Example 2: Based on the same inventive concept as the traffic light coordination control method in Example 1, this application also provides a traffic light coordination control device. Please refer to the appendix. Figure 2 The traffic signal light coordination control device includes:

[0083] The data acquisition module 11 is used to acquire the running trajectory data of each vehicle and the traffic light status data within the target area; the conflict point marking module 12 is used to mark the spatiotemporal conflict points of each vehicle arriving at the intersection within a preset time period based on the running trajectory data; the priority sequence setting module 13 is used to set a dynamic priority passage sequence according to the distribution of spatiotemporal conflict points and the traffic light status data; the control command sending module 14 is used to reconstruct the traffic light phase timing sequence of the intersection and issue a coordinated control command during the traffic light phase switching process based on the dynamic priority passage sequence; the deviation correction module 15 is used to transmit the coordinated control command to each traffic light controller in real time through the communication link, and at the same time, dynamically correct the phase timing deviation using the real-time vehicle location information fed back by the communication link.

[0084] Furthermore, the data acquisition module 11 in the traffic signal light coordinated control device is also used for:

[0085] Within the target area, V2X communication using the onboard OBUs built into each vehicle is used to collect vehicle speed, acceleration, and turn signal status; point cloud data from LiDAR and image data from cameras are fused to complete the trajectories of the remaining vehicles without OBUs; the trajectory data is then spatiotemporally aligned to obtain the running trajectory data of each vehicle within the target area.

[0086] Furthermore, the priority sequence setting module 13 in the traffic signal light cooperative control device is also used for:

[0087] Identify vehicle types with emergency passage permissions and set priority rules; assess the urgency of passage for each vehicle in the target area based on the remaining green light time and the vehicle's safe braking distance; and generate a dynamic priority passage sequence based on the priority rules, combined with the distribution of spatiotemporal conflict points and the urgency of passage for each vehicle in the target area.

[0088] Furthermore, the priority sequence setting module 13 in the traffic signal light cooperative control device is also used for:

[0089] Based on the dynamic priority passage sequence, a reward function is configured to minimize the average vehicle delay time; based on the reward function, a buffer phase is introduced, which includes all-directional red light states and the estimated waiting time is positively correlated with the number of conflict points; before the traffic signal controller performs phase switching, a local change in phase timing is triggered by the buffer phase according to real-time traffic flow change events.

[0090] Furthermore, the deviation correction module 15 in the traffic signal light coordinated control device is also used for:

[0091] Establish phase difference coupling constraints; based on the phase difference coupling constraints, determine the phase difference parameters of multiple intersections; generate green wave control parameters according to the phase difference parameters of the multiple intersections.

[0092] Furthermore, the deviation correction module 15 in the traffic signal light coordinated control device is also used for:

[0093] Based on multiple intersections in the target area and the dynamic priority passage sequence, a virtual twin model is configured. In the virtual twin environment, multiple candidate control strategies are run in parallel and the risk of congestion propagation is evaluated. The preset risk threshold is compared with the risk of congestion propagation to identify congested intersections and congestion phases in order to minimize congestion propagation and establish the phase difference coupling constraint condition.

[0094] Furthermore, the deviation correction module 15 in the traffic signal light coordinated control device is also used for:

[0095] Between adjacent intersections, based on real-time traffic flow data, the congestion propagation path and impact range under different phase difference parameters are simulated; based on the congestion propagation path and impact range, multiple preset control strategies are generated; based on preset optimization objectives, the multiple preset control strategies are screened to obtain multiple candidate control strategies.

[0096] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on its differences from other embodiments. Figure 1The traffic light coordination control method and specific examples in Embodiment 1 are also applicable to the traffic light coordination control device in this embodiment. Through the foregoing detailed description of the traffic light coordination control method, those skilled in the art can clearly understand the traffic light coordination control device in this embodiment; therefore, for the sake of brevity, it will not be described in detail here. As for the device disclosed in the embodiments, since it corresponds to the method disclosed in the embodiments, the description is relatively simple; relevant details can be found in the method section.

[0097] In embodiment three, based on the same inventive concept as the traffic light coordination control method in embodiment one, this application also provides a computer-readable storage medium storing a computer program, which, when executed, implements the steps of the traffic light coordination control method described in any one of embodiments one above.

[0098] The above description of the disclosed embodiments enables those skilled in the art to make or use this application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of this application. Therefore, this application is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

[0099] Obviously, those skilled in the art can make several improvements and modifications to this application without departing from the principles of this application, and these improvements and modifications also fall within the protection scope of this application.

Claims

1. A method for coordinated control of traffic lights, characterized in that, include: Acquire the trajectory data of each vehicle and the status data of traffic lights within the target area; Based on the aforementioned trajectory data, mark the spatiotemporal conflict points of each vehicle arriving at the intersection within a preset time period in the target area; Based on the spatiotemporal conflict point distribution and the traffic light status data, a dynamic priority passage sequence is set. This step includes: Identify vehicle types with emergency passage permissions and set priority rules; Assess the urgency of passage for each vehicle within the target area by using the remaining green light time and the vehicle's safe braking distance; Based on the aforementioned priority rules, and combined with the distribution of spatiotemporal conflict points and the urgency of passage for each vehicle within the target area, a dynamic priority passage sequence is generated. Based on the dynamic priority passage sequence, a reward function is configured to minimize the average vehicle delay time. Based on the reward function, a buffer phase is introduced, which includes the omnidirectional red light state and the estimated waiting time is positively correlated with the number of conflict points. Before the traffic signal controller performs a phase switch, a local change in phase timing is triggered by the buffer phase based on real-time traffic flow change events. Based on the dynamic priority passage sequence, the traffic light phase timing of the intersection is reconstructed and coordinated control commands are issued during the traffic light phase switching process; The coordinated control commands are transmitted in real time to each traffic light controller via the communication link. At the same time, the phase timing deviation is dynamically corrected by using the real-time vehicle location information fed back from the communication link.

2. The traffic signal light coordinated control method as described in claim 1, characterized in that, Obtain the trajectory data of each vehicle within the target area, including: Within the target area, vehicle speed, acceleration, and turn signal status are collected using V2X communication via the onboard OBU built into each vehicle. By fusing point cloud data from LiDAR with image data from cameras, trajectory completion is performed for the remaining vehicles that do not have an OBU installed. The trajectory data is spatiotemporally aligned to obtain the running trajectory data of each vehicle within the target area.

3. The traffic signal light coordinated control method as described in claim 1, characterized in that, Using real-time vehicle location information fed back from the communication link, phase timing deviations are dynamically corrected, including: Establish phase difference coupling constraints; Based on the phase difference coupling constraint, the phase difference parameters of multiple intersections are determined; Green wave control parameters are generated based on the phase difference parameters of the multiple intersections.

4. The traffic signal light coordinated control method as described in claim 3, characterized in that, Between adjacent intersections, establish phase difference coupling constraints, including: Based on multiple intersections in the target area, and in conjunction with the dynamic priority passage sequence, a virtual twin model is configured; In a virtual twin environment, multiple candidate control strategies are run in parallel and the risk of congestion propagation is assessed; By comparing the preset risk threshold with the risk of congestion propagation, congested intersections and congestion phases are identified to minimize congestion propagation, and the phase difference coupling constraint condition is established.

5. The traffic signal light coordinated control method as described in claim 4, characterized in that, The traffic signal light coordinated control method further includes: Between adjacent intersections, based on real-time traffic flow data, the congestion propagation path and impact range under different phase difference parameters are simulated; Based on the congestion propagation path and the scope of impact, multiple preset control strategies are generated; Based on the preset optimization target, the multiple preset control strategies are screened to obtain multiple candidate control strategies.

6. A traffic signal light coordination control device, characterized in that, The step of implementing the traffic light coordination control method according to any one of claims 1 to 5, wherein the traffic light coordination control device comprises: The data acquisition module is used to acquire the trajectory data of each vehicle and the status data of traffic lights within the target area; The conflict point marking module is used to mark the spatiotemporal conflict points of each vehicle arriving at the intersection within a preset time period based on the running trajectory data. The priority sequence setting module is used to set a dynamic priority passage sequence based on the spatiotemporal conflict point distribution and the traffic light status data; The control command sending module is used to reconstruct the traffic light phase timing of the intersection and issue coordinated control commands during the traffic light phase switching process based on the dynamic priority passage sequence. The deviation correction module is used to transmit the coordinated control commands to each traffic light controller in real time via the communication link. At the same time, it uses the real-time vehicle location information fed back by the communication link to dynamically correct the phase timing deviation.

7. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed, implements the steps of the traffic signal light coordinated control method according to any one of claims 1 to 5.

Images