Traffic signal lamp control method based on vehicle path prediction under vehicle-road cooperation

Abstract

The invention relates to the technical field of intelligent traffic, in particular to a traffic signal lamp control method based on vehicle path prediction under vehicle-road cooperation, and the method comprises the steps: collecting the driving path data of each vehicle within a set distance range in front of a designated intersection in real time; predicting the traffic flow of each signal phase of the specified intersection in a set future time period based on the acquired driving path data of the vehicle; the signal phase refers to a time period which is divided according to a passing direction and a passing mode and allows vehicles to pass in a signal period; calculating total vehicle delay time of each signal phase based on the predicted traffic flow, traffic capacity, queuing length and saturation flow rate of each signal phase; dynamically optimizing and adjusting the green light time of each signal phase based on the vehicle total delay time of each signal phase to obtain an optimized green light timing scheme; and issuing the optimized green light timing scheme to a signal controller at a specified intersection in real time so as to execute a corresponding signal timing control action.

Description

Technical Field

[0001] The present invention relates to the field of intelligent transportation technology, and in particular to a traffic light control method based on vehicle path prediction under vehicle-road collaboration. Background Art

[0002] With the development of smart cities and intelligent transportation, traffic signal control systems are gradually evolving from traditional fixed timing methods to intelligent regulation driven by real-time data. In urban traffic environments, intersections serve as bottlenecks, and the way they control traffic lights directly impacts the overall efficiency and operational order of the road network.

[0003] In the existing technology, the control of traffic lights mainly relies on detection equipment such as ground sensors and cameras to obtain vehicle cross-sectional information, and combines historical data and traffic flow models to perform signal timing. However, this type of method has the following shortcomings: traditional detection methods can only obtain instantaneous traffic flow information on the road section, lack the perception of the vehicle's overall driving path, destination and arrival time, and it is difficult to accurately predict future traffic conditions. When traffic flow fluctuates frequently or emergencies occur (such as the passage of emergency vehicles), the existing signal control system is often unable to achieve rapid response and reasonable adjustment due to the lag in the adjustment mechanism, resulting in increased delays at intersections and even local congestion. Most current signal optimization strategies rely only on cross-sectional flow or queue length, fail to fully utilize the vehicle's own path information, and cannot perform fine-grained matching and control of signal phases.

[0004] Therefore, it is urgent to propose a signal control method that integrates vehicle-road cooperative communication and vehicle path prediction mechanism to achieve accurate prediction of signal phase flow and dynamically optimize green light time, thereby reducing vehicle delays and improving intersection traffic efficiency. Summary of the Invention

[0005] In view of the above-mentioned shortcomings and deficiencies of the prior art, the present invention provides a traffic light control method based on vehicle path prediction under vehicle-road collaboration.

[0006] In order to achieve the above objectives, the main technical solutions adopted by the present invention include:

[0007] An embodiment of the present invention provides a traffic light control method based on vehicle path prediction under vehicle-road collaboration, comprising the following steps:

[0008] S1. Real-time collection of driving path data for each vehicle within a set distance range before a designated intersection, wherein the driving path data includes: current vehicle position, current speed, driving path, driving direction, and estimated time of arrival at the designated intersection;

[0009] S2. Based on the collected vehicle travel path data, predict the traffic flow at each signal phase at a specified intersection within a set future time period;

[0010] The signal phase refers to the time period within the signal cycle during which vehicles are allowed to pass, divided by the direction and mode of travel;

[0011] S3. Calculate the total vehicle delay time for each signal phase based on the predicted traffic flow, capacity, queue length, and saturation flow rate of each signal phase;

[0012] The traffic capacity and queue length are calculated from the collected vehicle travel path data, and the saturation flow rate is a preset parameter or determined based on historical data;

[0013] S4. Based on the total vehicle delay time of each signal phase, dynamically optimize and adjust the green light time of each signal phase to obtain an optimized green light timing plan;

[0014] S5. Send the optimized green light timing plan to the signal controller at the designated intersection in real time to execute the corresponding signal timing control action.

[0015] Preferably, the driving path data of each vehicle is collected by the vehicle-mounted terminal of the vehicle and uploaded to the central control platform through wireless communication with the roadside unit installed at the designated intersection;

[0016] The central control platform is also connected to the signal controller at the designated intersection.

[0017] Preferably, the S2 specifically includes:

[0018] Based on the collected vehicle driving path data, the traffic flow of each signal phase at the specified intersection within the set future time period is predicted using formula (1);

[0019] The formula (1) is:

[0020]

[0021] Q p is the predicted traffic flow at the signal phase p of a specified intersection within a set future time period;

[0022] n is the total number of vehicles that may enter the designated intersection within the set future time period;

[0023] w i，p is the path matching weight of the i-th vehicle to the signal phase p, which takes a positive value when the vehicle path actually passes through this phase, otherwise it is 0;

[0024] γ is the time attenuation coefficient;

[0025] t is the current time;

[0026] t i is the estimated arrival time of the i-th vehicle at the designated intersection;

[0027] q i is the preset contribution value to traffic flow corresponding to the vehicle type of the i-th vehicle.

[0028] Preferably,

[0029] Among them, the path matching weight w of the i-th vehicle to the signal phase p is i,p Calculated by formula (2); the formula (2) is:

[0030]

[0031] δ i,p is the path ownership indicator function. When the expected travel direction of the i-th vehicle belongs to the travel direction allowed by the signal phase p, δ i,p is equal to 1, otherwise 0;

[0032] θ i，p is the angle between the current actual driving direction of the i-th vehicle and the direction allowed by the signal phase p;

[0033] ∈ is the direction deviation adjustment parameter, ∈>0.

[0034] Preferably, the S3 specifically includes:

[0035] Based on the predicted traffic flow, capacity, queue length, and saturation flow rate of each signal phase, the total vehicle delay time of each signal phase is calculated using formula (3); the formula (3) is:

[0036]

[0037] D p is the total delay time of signal phase p;

[0038] C p is the capacity of the signal phase p;

[0039] L p is the queue length of signal phase p;

[0040] S p is the saturation flow rate of the signal phase p;

[0041] α is the first weight parameter;

[0042] β is the second weight parameter.

[0043] Preferably,

[0044] The capacity C of the signal phase p p It is calculated by formula (4);

[0045] The formula (4) is:

[0046]

[0047] l p is the length of the drivable lane corresponding to the signal phase p;

[0048] T g is the time of the current signal phase p;

[0049] v p is the average speed of the traffic flow corresponding to the current phase p;

[0050] v ref It is a reference speed determined in advance according to the road type;

[0051] a p is the traffic adjustment factor.

[0052] Preferably,

[0053] The queue length L of the signal phase p p Calculated by formula (5);

[0054] The formula (5) is:

[0055]

[0056] N p Set the number of stationary vehicles within a specified distance before the intersection;

[0057] l v is the preset vehicle length value;

[0058] ΔT r The time required for the remaining vehicles in the queue at the intersection to pass through the previous red light.

[0059] β p It is a queue adjustment factor used to correct the signal delay to reflect the difference in vehicle starting.

[0060] Preferably, the saturation flow rate S of the signal phase p p It is calculated by formula (6);

[0061] The formula (6) is:

[0062]

[0063] n pis the total number of independent lanes that can be released simultaneously in all directions allowed to pass at signal phase p;

[0064] v p The current average speed of the lane corresponding to the signal phase p;

[0065] v0 is the pre-acquired average starting speed of the vehicle;

[0066] δ is the preset speed response sensitivity parameter;

[0067] is the correction factor.

[0068] Preferably, the S4 specifically includes:

[0069] Based on the total vehicle delay time of the signal phase, formula (7) is used to dynamically optimize and adjust the green light time of each signal phase to obtain the optimized green light timing plan;

[0070] The formula (7) is:

[0071]

[0072] G p is the optimized green time of signal phase p;

[0073] G min It is the lower limit of the pre-set green light time;

[0074] G max The upper limit of the pre-set green light time;

[0075] T is the total time length of the signal cycle;

[0076] m is the total number of signal phases at a given intersection.

[0077] Preferably, the method further comprises:

[0078] S6. When the central control platform detects the presence of an emergency vehicle at the designated intersection, the emergency priority control strategy is executed; the emergency priority control strategy includes:

[0079] S61. Obtain the travel direction and estimated arrival time of the emergency vehicle;

[0080] S62: Adjust the signal phase time in the direction of emergency vehicle traffic to ensure that the emergency vehicle has priority when arriving at the intersection;

[0081] S63. Shorten the non-priority signal phase time, but it must not be lower than the preset lower limit of the green light time G min .

[0082] The beneficial effects of the present invention are:

[0083] The present invention provides a traffic signal control method based on vehicle path prediction under vehicle-road collaboration. Since it collects the driving path data of each vehicle in real time through an on-board terminal and predicts the traffic flow of each signal phase in the future time period based on the vehicle's expected arrival time, compared with the existing technology, it can obtain more detailed and comprehensive traffic flow dynamic information, realize forward-looking prediction of signal phase flow changes, and thus improve the responsiveness and accuracy of traffic signal timing.

[0084] In addition, the present invention calculates the total vehicle delay time for each signal phase by comprehensively considering multiple factors such as traffic flow, capacity, queue length and saturation flow rate, and dynamically optimizes the green light time allocation accordingly. Compared with traditional fixed timing methods based on cross-sectional flow or historical models, it can effectively reduce vehicle delays in key traffic directions, alleviate congestion, and improve intersection traffic efficiency, achieving the technical effect of realizing refined traffic signal control based on vehicle path information.

[0085] Furthermore, due to the adoption of the vehicle-road cooperative communication mechanism, real-time data interaction between vehicles and intersection signal control systems is realized, so it also has good scalability and intelligent scheduling capabilities, and can provide a data basis and control interface for subsequent access to various applications such as emergency priority control, bus priority, and pedestrian crossing coordination, thereby improving the overall intelligence level and practical value of the system. BRIEF DESCRIPTION OF THE DRAWINGS

[0086] Figure 1 This is a flow chart of a traffic light control method based on vehicle path prediction under vehicle-road collaboration of the present invention. DETAILED DESCRIPTION

[0087] In order to better explain the present invention and facilitate understanding, the present invention is described in detail below through specific implementation methods in conjunction with the accompanying drawings.

[0088] To better understand the above technical solutions, exemplary embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. Although exemplary embodiments of the present invention are shown in the accompanying drawings, it should be understood that the present invention can be implemented in various forms and should not be limited by the embodiments described herein. Instead, these embodiments are provided to enable a clearer and more thorough understanding of the present invention and to fully convey the scope of the present invention to those skilled in the art.

[0089] Example 1

[0090] This embodiment provides a traffic signal control method based on vehicle path prediction in a vehicle-road collaborative environment. Specifically, it is applied to a typical intersection on a major urban road. Roadside units (RSUs) are installed within 150 meters of each of the four entrances to the intersection, enabling V2I communication with intelligent connected vehicles equipped with onboard units (OBUs). A signal controller is deployed at the intersection and connected to a central control platform via a wired network.

[0091] When the system is running, the on-board terminal collects the vehicle's driving path data in real time, including the current vehicle position, current speed, driving path, driving direction and estimated time of arrival at the intersection, and sends it to the central control platform through the RSU.

[0092] Based on all reported vehicle path data, the central control platform predicts traffic flow for each signal phase within a set future time period. This is combined with the signal phase's capacity, queue length (estimated from path data), and preset or historically calculated saturation flow rates to calculate the total vehicle delay for each signal phase.

[0093] The platform dynamically optimizes the green light time allocation based on the total delay time of each signal phase, generates the optimal green light timing plan, and sends it to the signal control machine in real time to execute the corresponding signal control strategy to achieve intelligent control of traffic lights.

[0094] This method effectively improves the traffic efficiency at intersections, reduces vehicle waiting time, and has good real-time and adaptability.

[0095] Example 2

[0096] See also Figure 1 This embodiment provides a traffic light control method based on vehicle path prediction under vehicle-road collaboration, including the following steps:

[0097] S1. Real-time collection of driving path data for each vehicle within a set distance range before a designated intersection, wherein the driving path data includes: current vehicle position, current speed, driving path, driving direction, and estimated time of arrival at the designated intersection;

[0098] In this embodiment, the driving path data of each vehicle is collected by the vehicle-mounted terminal of the vehicle and uploaded to the central control platform through wireless communication with the roadside unit installed at the designated intersection;

[0099] The central control platform is also connected to the signal controller at the designated intersection.

[0100] S2. Based on the collected vehicle travel path data, predict the traffic flow at each signal phase at a specified intersection within a set future time period;

[0101] The signal phase refers to the time period within the signal cycle during which vehicles are allowed to pass, divided by the direction and mode of travel;

[0102] The S2 specifically includes:

[0103] Based on the collected vehicle driving path data, the traffic flow of each signal phase at the specified intersection within the set future time period is predicted using formula (1);

[0104] The formula (1) is:

[0105]

[0106] Q p is the predicted traffic flow at the signal phase p of the designated intersection within the set future time period; n is the total number of vehicles that may enter the designated intersection within the set future time period; w i，p is the path matching weight of the i-th vehicle for the signal phase p, which takes a positive value when the vehicle path actually passes through the phase, otherwise it is 0; γ is the time attenuation coefficient; t is the current time; t i is the estimated time for the i-th vehicle to arrive at the designated intersection; q i is the preset contribution value to traffic flow corresponding to the vehicle type of the i-th vehicle.

[0107] In this embodiment, the path direction (whether it passes through phase p), expected arrival time t i , the current time t are all known; these data can be obtained in real time through the vehicle-road cooperative system (such as vehicle-mounted terminal + roadside unit), meeting the data requirements of the calculation of formula (1). i，p It is used to describe the probability of the i-th vehicle passing through signal phase p or the degree of path matching; if the vehicle will indeed pass through phase p, the weight is 1, otherwise it is 0 or close to 0 (fuzzy path decision can be considered); in the case of multipath, it can be defined as the path probability distribution, which has actual physical meaning. This term in formula (1) Indicates that the current time is t from the vehicle's estimated arrival time i The farther away, the smaller the weight, which is in line with the rule that traffic forecasts are more sensitive to "near-term information"; this is a modeling reflection of the dynamic and real-time nature of traffic flow, avoiding long-term forecasts misleading timing.

[0108] Formula (1) in this embodiment constructs a computational model that can predict traffic flow at a given intersection signal phase by introducing vehicle path matching weights, time decay factors, and traffic contribution weights. This model accurately predicts the traffic demand for each signal phase within a set future time period at the current moment, providing data support for subsequent signal timing optimization. This method overcomes the limitations of traditional methods that rely on fixed traffic models or historical statistical data, improves the responsiveness and accuracy of the timing system, effectively reduces intersection delays and congestion, and significantly improves the operating efficiency of urban roads.

[0109] In this embodiment, the path matching weight w of the i-th vehicle for the signal phase p is i，p Calculated by formula (2); the formula (2) is:

[0110]

[0111] δ i,p is the path ownership indicator function. When the expected travel direction of the i-th vehicle belongs to the travel direction allowed by the signal phase p, δ i，p is equal to 1, otherwise it is 0; θ i，p is the angle (direction deviation) between the current actual driving direction of the i-th vehicle and the direction allowed by the signal phase p; ∈ is the direction deviation adjustment parameter (used to control the degree of error attenuation), ∈>0. This indicates that the larger the angle (direction deviation) between the current actual driving direction of the i-th vehicle and the direction allowed by the signal phase p, the lower the credibility of the vehicle being considered as "belonging to this signal phase", showing a Gaussian decay.

[0112] S3. Calculate the total vehicle delay time for each signal phase based on the predicted traffic flow, capacity, queue length, and saturation flow rate of each signal phase;

[0113] The traffic capacity and queue length are calculated from the collected vehicle travel path data, and the saturation flow rate is a preset parameter or determined based on historical data;

[0114] Specifically, S3 specifically includes: based on the predicted traffic flow, traffic capacity, queue length and saturation flow rate of each signal phase, using formula (3) to calculate the total vehicle delay time of each signal phase; the formula (3) is:

[0115]

[0116] D p is the total delay time of signal phase p; C p is the capacity of the signal phase p; L p is the queue length of signal phase p; S pis the saturation flow rate of the signal phase p; α is the first weight parameter; β is the second weight parameter. (In this embodiment, the specific values ​​of α and β can be obtained by fitting historical data).

[0117] In this embodiment, the formula (3) The ratio of predicted traffic demand to traffic capacity reflects the pressure index. The larger the ratio, the greater the demand is, indicating that the demand is far greater than the capacity, and there will be a risk of congestion in the future. is the ratio of queue length to flow rate, which measures the current backlog. If the queue is long and the flow rate is low, it means that the vehicle traffic efficiency is low and the delay will increase. Formula (3) weightedly integrates the predicted traffic flow, queue length, traffic capacity, and saturation flow rate of the signal phase to construct a delay time prediction model. By comparing traffic demand and supply capacity and considering historical backlogs, a quantitative prediction of future signal phase traffic pressure is achieved. The model has the advantages of strong interpretability, high prediction accuracy, and strong adaptability. It can provide a reliable basis for traffic signal timing, phase scheduling, and intelligent control, significantly improving urban road traffic efficiency and traffic management level.

[0118] The capacity C of the signal phase p p It is calculated by formula (4);

[0119] The formula (4) is:

[0120]

[0121] l p is the length of the drivable lane corresponding to the signal phase p; T g is the time of the current signal phase p; v p is the average speed of traffic corresponding to the current phase p; v ref is the reference speed determined in advance according to the road type; a p is the traffic adjustment factor.

[0122] In this embodiment, the queue length Lx at signal phase p refers to the length of the queue of vehicles waiting to pass due to a red light or traffic jam in the lane corresponding to that signal phase at the current or predicted time. This length is dependent on factors such as the duration of the red light, traffic flow, departure delay, and headway. For example, if the left-turn lane at the west entrance is red at a certain moment and 15 vehicles are queued, with each vehicle occupying an average of 6 meters, the queue length is approximately 90 meters.

[0123] The signal phase p corresponds to the length of the drivable lane l pThis refers to the actual physical length of the accessible lane corresponding to signal phase p, extending upstream from the stop line, allowing for queuing. For example, a left-turn lane extending upstream from the stop line for a total of 120 meters is the accessible lane length for that phase.

[0124] In formula (4) of this embodiment, Reflects the ratio of the current traffic speed to the ideal speed. p Close to v ref , indicating that the traffic flow is smooth and the traffic capacity is high. Otherwise, there may be congestion and the phase time needs to be adjusted. Indicates the length of the lane that can be passed in unit time. The longer l p or a shorter T g It will increase traffic capacity, but a balance must be struck to avoid congestion. Traffic adjustment factor a p It can be obtained through historical data or real-time feedback (such as traffic flow, weather, accidents, etc.).

[0125] In this embodiment, the queue length L of the signal phase p p Calculated by formula (5);

[0126] The formula (5) is:

[0127]

[0128] N p The number of stationary vehicles within a set distance before the designated intersection; v is the pre-set vehicle length value; ΔT r The time required for all remaining vehicles in the queue at the intersection to pass through when the previous red light ends; β p It is a queue adjustment factor used to correct the signal delay to reflect the difference in vehicle starting.

[0129] In this embodiment, N p ·l v Directly calculate the physical space occupied by stationary vehicles (N p is the number of stationary vehicles, l v is the length of a bicycle), reflecting the current backlog of traffic demand. Capturing the delay effect when switching the red light phase, ΔT r It indicates the time required for the remaining queued vehicles at the intersection to pass through completely after the previous red light ends, reflecting the congestion impact of the historical phase that has not been eliminated; Normalize the delay time to the current green light phase time T g Avoid time scale bias.

[0130] In this embodiment, formula (5) is obtained by real-time monitoring of N p and ΔTr , combined with β trained with historical data p ,Formula (5) can dynamically predict the changes in queue length in the future period.

[0131] In this embodiment, the saturation flow rate S of the signal phase p p It is calculated by formula (6); the formula (6) is:

[0132]

[0133] n p is the total number of independent lanes that can be released simultaneously in all directions allowed by signal phase p; p The current average vehicle speed of the lane corresponding to the signal phase p; v0 is the pre-acquired average vehicle starting speed; δ is the pre-set speed response sensitivity parameter; is the correction factor (used to reflect the changes in maximum traffic capacity under different lane or terrain conditions).

[0134] In this embodiment Is a Sigmoid function used to characterize the traffic speed v p Effect on saturation flow rate; when v p When the speed approaches or exceeds the starting speed v0, the function value approaches 1, indicating that the traffic flow is smooth and the saturation flow rate is maximized; when v p When it is far lower than v0 (such as in congestion), the function value approaches 0, significantly reducing the saturation flow rate.

[0135] In this embodiment, the number of lanes n is monitored in real time. p and traffic speed v p , combined with a dynamically adjusted correction coefficient Formula (6) can predict the saturation flow rate S of each phase in the future period p . High S p Phase can allocate more green time, and low S p The phase needs to be optimized or congestion management strategies triggered.

[0136] S4. Based on the total vehicle delay time of each signal phase, dynamically optimize and adjust the green light time of each signal phase to obtain an optimized green light timing plan;

[0137] Specifically, the S4 specifically includes: based on the total vehicle delay time of the signal phase, using formula (7) to dynamically optimize and adjust the green light time of each signal phase to obtain an optimized green light timing plan; the formula (7) is:

[0138]

[0139] G pis the optimized green light time of signal phase p; G min The lower limit of the preset green light time; G max is the preset upper limit of the green light time; T is the total time length of the signal cycle; m is the total number of signal phases at the specified intersection.

[0140] In this embodiment, in formula (7) Calculate the proportion of the delay time of phase p to the total delay, and distribute the total signal cycle time T in proportion. If the D of a phase p p If the total delay time of signal phase p is large (such as severe congestion), more green light time G is allocated. p , to speed up the evacuation of traffic. If D p If the delay time D of each phase is smaller (such as when the traffic is smooth), the green light time is reduced to avoid wasting resources. p Formula (7) dynamically adjusts the green light time, thereby affecting the traffic flow distribution in the future period: the high-delay phase obtains more green light time, speeding up the passage of queued vehicles and reducing the probability of future congestion. The low-delay phase gives up some time to avoid the green light being left idle, thus improving overall efficiency.

[0141] S5. Send the optimized green light timing plan to the signal controller at the designated intersection in real time to execute the corresponding signal timing control action.

[0142] The method of this embodiment further includes:

[0143] S6. When the central control platform detects the presence of an emergency vehicle at the designated intersection, the emergency priority control strategy is executed; the emergency priority control strategy includes:

[0144] S61. Obtain the travel direction and estimated arrival time of the emergency vehicle;

[0145] S62: Adjust the signal phase time in the direction of emergency vehicle traffic to ensure that the emergency vehicle has priority when arriving at the intersection;

[0146] S63. Shorten the non-priority signal phase time, but it must not be lower than the preset lower limit of the green light time G min That is, the signal phase time of the non-priority direction is shortened, but the shortened phase time must not be lower than the preset green light minimum time threshold to ensure the basic traffic needs of non-emergency direction traffic flow and prevent traffic congestion and safety hazards.

[0147] This step can maintain the orderliness and safety of the overall traffic system while ensuring the efficiency of emergency vehicle traffic, improve the intelligence level of traffic control and emergency response capabilities, and is suitable for signal timing optimization control scenarios in intelligent transportation systems.

[0148] In the description of the present invention, it should be understood that the terms "first" and "second" are used for descriptive purposes only and should not be understood to indicate or imply relative importance or implicitly specify the number of the technical features indicated. Therefore, a feature specified as "first" or "second" may explicitly or implicitly include one or more of the features. In the description of the present invention, "plurality" means two or more, unless otherwise specifically defined.

[0149] In the present invention, unless otherwise expressly specified or limited, the terms "mounted," "connected," "connect," "fixed," etc. should be understood broadly. For example, they may refer to fixed connection, detachable connection, or integration; mechanical connection or electrical connection; direct connection or indirect connection through an intermediate medium; and internal communication between two components or interaction between two components. Those skilled in the art will understand the specific meanings of the above terms in the present invention based on specific circumstances.

[0150] In the present invention, unless otherwise expressly specified or limited, when a first feature is "above" or "below" a second feature, it may mean that the first and second features are in direct contact, or that the first and second features are in indirect contact through an intermediate medium. Furthermore, when a first feature is "above," "above," or "above" a second feature, it may mean that the first feature is directly above or obliquely above the second feature, or simply means that the first feature is at a higher level than the second feature. When a first feature is "below," "below," or "below" a second feature, it may mean that the first feature is directly below or obliquely below the second feature, or simply means that the first feature is at a lower level than the second feature.

[0151] In the description of this specification, the terms "one embodiment", "some embodiments", "embodiments", "examples", "specific examples" or "some examples" refer to the specific features, structures, materials or characteristics described in conjunction with the embodiment or example and included in at least one embodiment or example of the present invention. In this specification, the schematic expressions of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine different embodiments or examples described in this specification and features of different embodiments or examples, unless they are mutually inconsistent.

[0152] Although the embodiments of the present invention have been shown and described above, it will be understood that the above embodiments are illustrative and are not to be construed as limitations on the present invention. A person skilled in the art may alter, modify, replace and modify the above embodiments within the scope of the present invention.

Claims

1. A traffic light control method based on vehicle path prediction under vehicle-road collaboration, characterized in that: The steps include: S1. Real-time collection of driving path data for each vehicle within a set distance range before a designated intersection, wherein the driving path data includes: current vehicle position, current speed, driving path, driving direction, and estimated time of arrival at the designated intersection; S2. Based on the collected vehicle travel path data, predict the traffic flow at each signal phase at a specified intersection within a set future time period; The signal phase refers to the time period within the signal cycle during which vehicles are allowed to pass, divided by the direction and mode of travel; S3. Calculate the total vehicle delay time for each signal phase based on the predicted traffic flow, capacity, queue length, and saturation flow rate of each signal phase; The traffic capacity and queue length are calculated from the collected vehicle travel path data, and the saturation flow rate is a preset parameter or determined based on historical data; S4. Based on the total vehicle delay time of each signal phase, dynamically optimize and adjust the green light time of each signal phase to obtain an optimized green light timing plan; S5. Send the optimized green light timing plan to the signal controller at the designated intersection in real time to execute the corresponding signal timing control action.

2. The traffic light control method based on vehicle path prediction under vehicle-road collaboration according to claim 1 is characterized in that: The driving path data of each vehicle is collected by the vehicle-mounted terminal and uploaded to the central control platform through wireless communication with the roadside unit installed at the designated intersection; The central control platform is also connected to the signal controller at the designated intersection.

3. The traffic light control method based on vehicle path prediction under vehicle-road collaboration according to claim 1 is characterized in that: The S2 specifically includes: Based on the collected vehicle driving path data, the traffic flow of each signal phase at the specified intersection within the set future time period is predicted using formula (1); The formula (1) is: Q p is the predicted traffic flow at the signal phase p of a specified intersection within a set future time period; n is the total number of vehicles that may enter the designated intersection within the set future time period; w i,p is the path matching weight of the i-th vehicle to the signal phase p, which takes a positive value when the vehicle path actually passes through this phase, otherwise it is 0; γ is the time attenuation coefficient; t is the current time; t i is the estimated arrival time of the i-th vehicle at the designated intersection; q i is the preset contribution value to traffic flow corresponding to the vehicle type of the i-th vehicle.

4. The traffic light control method based on vehicle path prediction under vehicle-road collaboration according to claim 3, It is characterized by: Among them, the path matching weight w of the i-th vehicle to the signal phase p is i，p Calculated by formula (2); the formula (2) is: δ i，p is the path ownership indicator function. When the expected travel direction of the i-th vehicle belongs to the travel direction allowed by the signal phase p, δ i,p is equal to 1, otherwise 0; θ i,p is the angle between the current actual driving direction of the i-th vehicle and the direction allowed by the signal phase p; ∈ is the direction deviation adjustment parameter, ∈>0.

5. The traffic light control method based on vehicle path prediction under vehicle-road collaboration according to claim 4 is characterized in that: The S3 specifically includes: Based on the predicted traffic flow, capacity, queue length and saturation flow rate of each signal phase, the total vehicle delay time of each signal phase is calculated using formula (3); The formula (3) is: D p is the total delay time of signal phase p; C p is the capacity of the signal phase p; L p is the queue length of signal phase p; S p is the saturation flow rate of the signal phase p; α is the first weight parameter; β is the second weight parameter.

6. The traffic light control method based on vehicle path prediction under vehicle-road collaboration according to claim 5 is characterized in that: The capacity C of the signal phase p p It is calculated by formula (4); The formula (4) is: l p is the length of the drivable lane corresponding to the signal phase p; T g is the time of the current signal phase p; v p is the average speed of the traffic flow corresponding to the current phase p; v ref It is a reference speed determined in advance according to the road type; a p is the traffic adjustment factor.

7. The traffic light control method based on vehicle path prediction under vehicle-road collaboration according to claim 6 is characterized in that: The queue length L of the signal phase p p Calculated by formula (5); The formula (5) is: N p Set the number of stationary vehicles within a specified distance before the intersection; l v is the preset vehicle length value; ΔT r The time required for the remaining vehicles in the queue at the intersection to pass through the previous red light. β p It is a queue adjustment factor used to correct the signal delay to reflect the difference in vehicle starting.

8. The traffic light control method based on vehicle path prediction under vehicle-road collaboration according to claim 7 is characterized in that: The saturation flow rate S of the signal phase p p It is calculated by formula (6); The formula (6) is: n p is the total number of independent lanes that can be released simultaneously in all directions allowed to pass at signal phase p; v p The current average speed of the lane corresponding to the signal phase p; v0 is the pre-acquired average starting speed of the vehicle; δ is the preset speed response sensitivity parameter; is the correction factor.

9. The traffic light control method based on vehicle path prediction under vehicle-road collaboration according to claim 8 is characterized in that: The S4 specifically includes: Based on the total vehicle delay time of the signal phase, formula (7) is used to dynamically optimize and adjust the green light time of each signal phase to obtain the optimized green light timing plan; The formula (7) is: G p is the optimized green time of signal phase p; G min It is the lower limit of the pre-set green light time; G max The upper limit of the pre-set green light time; T is the total time length of the signal cycle; m is the total number of signal phases at a given intersection.

10. The traffic light control method based on vehicle path prediction under vehicle-road collaboration according to claim 6, characterized in that: The method further comprises: S6. When the central control platform detects the presence of an emergency vehicle at the designated intersection, the emergency priority control strategy is executed; the emergency priority control strategy includes: S61. Obtain the travel direction and estimated arrival time of the emergency vehicle; S62: Adjust the signal phase time in the direction of emergency vehicle traffic to ensure that the emergency vehicle has priority when arriving at the intersection; S63. Shorten the non-priority signal phase time, but it must not be lower than the preset lower limit of the green light time G min .

Images