An adaptive traffic light control method based on individual-level data

Abstract

An adaptive traffic signal control method based on individual-level data belongs to the field of traffic control technology. In order to achieve refined control of intersections, the present invention includes collecting vehicle status information, slow-moving traffic individual status information, and traffic signal status information; constructing the minimum sum of delay times of vehicles and slow-moving traffic individuals as the optimization objective function; constructing traffic signal structure constraints; constructing mutual constraints between vehicles; constructing mutual constraints between individual travel trajectories and traffic signals; forming an adaptive traffic signal control model based on individual trajectories; solving the obtained adaptive traffic signal control model based on individual trajectories, optimizing the traffic signal timing plan and phase sequence at the intersection, and optimizing the traffic signals of the current cycle and the following cycles each time to ensure that each travel individual can leave the intersection within the optimized time range. The present invention achieves the optimal comprehensive benefits of motor vehicles and slow-moving traffic passing through the intersection.

Description

Technical Field

[0001] The present invention belongs to the technical field of traffic control, and in particular relates to an adaptive traffic signal light control method based on individual-level data. Background Art

[0002] Intersection signal control is key to ensuring traffic safety and improving travel efficiency. The hardware facilities and control strategies of signal control systems are constantly evolving, and currently three main control strategies have been formed: timed control, sensor control, and adaptive control. Timed traffic signal control is based on historical traffic flow data, dividing the day into multiple time periods. It is assumed that traffic flow does not change much within a time period and adopts the same signal timing scheme. Sensor control uses detectors installed near the intersection to detect vehicle arrivals in real time and adopt control methods such as extending green lights and switching phases. Compared with static timed control schemes, it can better adapt to random fluctuations in traffic flow. Adaptive control is also a dynamic signal control strategy that relies on real-time detector data to predict future short-term traffic flow conditions. Then, it integrates the overall benefits of traffic flow in all directions and uses a specific optimization model to optimize the signal timing scheme.

[0003] Adaptive control typically relies on sensors such as coils, radars, and cameras fixed to roads near intersections to detect traffic flow and other data. These devices have limited detection ranges and high maintenance costs. With the development of technologies such as autonomous driving and vehicle-road-cloud integration, and the construction of new equipment, continuous data at the level of individual travel trajectories can be collected in real time through vehicle-side OBU (On Board Unit) devices, roadside RSU (Roadside Unit) facilities, and V2I (Vehicle to Infrastructure) communication technologies. This allows for wider coverage and more refined detection information. Furthermore, the vehicle-road-cloud environment provides more immediate communication capabilities and more powerful computing power, which is of great significance to the innovation of adaptive signal optimization technology.

[0004] This method uses individual vehicle data acquired through an intelligent connected environment to calculate efficiency indicators for signalized intersections and adjust signal schemes based on these efficiency indicators. Based on the continuous position information of individual vehicles acquired in real time within the intelligent connected environment, it can calculate efficiency indicators such as the cumulative travel time of vehicles corresponding to each current signal phase. This indicator reflects the level of traffic congestion corresponding to each signal phase and can be used as a criterion for phase extension or switching to dynamically adjust traffic signal timing schemes in real time. This method is relatively simple and easy to implement, but the control strategy only relies on indicators to simply adjust the green light time of the current phase. It does not comprehensively optimize the release time of each phase from the perspective of the entire traffic flow at the intersection, making it difficult to achieve optimal control results.

[0005] Using individual vehicle data collected through an intelligent connected environment, a dynamic programming-based approach for real-time rolling optimization of intersection signal control schemes can be used to complete the data of all individual vehicles approaching the intersection using a predictive estimation method based on the collected continuous position information of a subset of connected vehicles. This dynamic programming approach divides the signal cycle into time segments and searches for the optimal duration for each phase. Given the known arrival schedule of each vehicle, aggregated efficiency metrics such as queuing and delay can be derived by accumulating individual vehicle metrics, which are calculated based on whether the light is green. This allows for the optimization of signal schemes that minimize efficiency metrics such as delay and queuing. Signal timing schemes are optimized for several cycles each time, with real-time rolling updates based on specific time intervals or trigger conditions. This approach can comprehensively optimize signal phase and sequence schemes from the perspective of the entire traffic flow at the intersection. However, the individual vehicle metric calculation model is significantly simplified, making it difficult to account for inter-vehicle interference and rarely considering the benefits of slow-moving traffic such as pedestrians. Summary of the Invention

[0006] The problem to be solved by the present invention is to achieve refined control of intersections and improve traffic efficiency, and propose an adaptive traffic signal control method based on individual-level data.

[0007] To achieve the above object, the present invention is implemented through the following technical solutions:

[0008] An adaptive traffic signal control method based on individual-level data includes the following steps:

[0009] S1. Collect vehicle status information, slow-moving traffic status information, and traffic light status information;

[0010] S2. Construct the optimization objective function to minimize the sum of delays of vehicles and slow-moving traffic entities;

[0011] S3. Construct traffic signal structure constraints;

[0012] S4. Construct mutual constraints between vehicles;

[0013] S5. Construct the mutual constraints between individual travel trajectories and traffic signals;

[0014] S6. Based on steps S2-S5, an adaptive traffic light control model based on individual trajectories is formed;

[0015] S7. Solve the adaptive traffic signal control model based on individual trajectories obtained in step S6 to optimize the traffic signal timing and phase sequence at the intersection. Each time, the traffic signal is optimized for the current cycle and several cycles thereafter to ensure that each individual traveler can leave the intersection within the optimized time range. The optimization results are updated in real time.

[0016] Furthermore, the sum of the delay times of vehicles and slow-moving traffic individuals constructed in step S2 is the minimum min f The expression of the optimization objective function is:

[0017] (1)

[0018] in, Is the vehicle number, It is the pedestrian's number. is the time when the vehicle leaves the stop line, It is the time when the last traffic signal light turns green for pedestrians to cross the street.

[0019] Furthermore, step S3 constructs the traffic signal structure constraint conditions as follows:

[0020] The traffic signal adopts a double-loop control structure, which includes 8 motor vehicle phases and 6 pedestrian phases, of which 4 pedestrian phases are pedestrian secondary crossing phases and the motor vehicle phase In the The start time of the cycle is ,in Starting from 1, the maximum value of the cycle Determined based on intersection scope and desired speed;

[0021] The motor vehicle phase is set to meet the minimum duration requirement, as shown in formulas (2) and (3):

[0022] (2)

[0023] (3)

[0024] in, Motor vehicle phase The next phase start time, Motor vehicle phase The minimum green time, Motor vehicle phase Green light interval time, Motor vehicle phase In the A variable indicating whether a cycle is not skipped, If the value is 0, skip. If the value is 1, it will not be skipped;

[0025] When the traffic signal reaches the barrier, the phase time of each motor vehicle ends at the same time, as shown in formula (4):

[0026] (4)

[0027] Furthermore, step S4 constructs the mutual constraints between vehicles as follows:

[0028] Assume that vehicles leave during the green light period of any cycle, and each vehicle leaves the intersection during a certain cycle, as shown in equations (5) and (6):

[0029] (5)

[0030] (6)

[0031] in, Indicates vehicle Is it The variables of the cycle leaving the intersection, If the value is 0, then do not leave the intersection. If the value is 1, leave the intersection;

[0032] When a vehicle passes through the widening section junction, for the lane upstream of the widening section junction, the traffic flow on the same lane leaves the widening section junction in sequence, and the departure time meets the saturated headway constraint, as shown in formula (7):

[0033] (7)

[0034] in, The vehicle is in the lane The sequence number on is the time when the vehicle leaves the junction of the widening section, It's a lane saturated headway;

[0035] The time it takes for a vehicle to leave the widening section junction is set to be greater than the time it takes to travel to the widening section junction without stopping at the current position, as shown in formula (8):

[0036] (8)

[0037] in, It's a vehicle The distance to the stop line at the current moment, is the distance from the widening section junction to the stop line. is the desired speed of the vehicle;

[0038] For the lanes downstream of the widening section junction, the traffic on the same lane leaves the stop line in sequence and the departure time meets the saturated headway constraint, as shown in formula (9). The departure time of the vehicle downstream of the widening section junction is greater than the time it takes to drive from the widening section junction to the stop line without stopping, as shown in formula (10). The departure time of the vehicle downstream of the widening section junction is greater than the time it takes to drive from the current position to the stop line without stopping, as shown in formula (11):

[0039] (9)

[0040] (10)

[0041] (11)

[0042] Furthermore, step S5 constructs the mutual constraints between individual travel trajectories and traffic signals as follows:

[0043] Set pedestrian phase The minimum duration requirement is met, as shown in formulas (12) and (13):

[0044] (12)

[0045] (13)

[0046] in, Pedestrian phase The minimum green time, Pedestrian phase Green light interval time, Pedestrian phase In the A variable indicating whether a cycle is not skipped, A value of 0 means it is skipped. A value of 1 indicates that it is not skipped;

[0047] Set the pedestrian flow direction for a single crossing. Leave during the green light period of any cycle, and each pedestrian is determined to leave the intersection during a certain cycle, as shown in equations (14) and (15):

[0048] (14)

[0049] (15)

[0050] in, Indicates pedestrians Is it The variables of the cycle leaving the intersection, A value of 0 means not leaving the intersection. A value of 1 indicates leaving the intersection;

[0051] Assuming that pedestrians cross the street twice, the first pedestrian crossing time is during the green light period, as shown in formulas (16) and (17):

[0052] (16)

[0053] (17)

[0054] in, It is the time it takes for pedestrians crossing the street twice to leave the first pedestrian crossing section. Indicates pedestrians Is it The variable of the first pedestrian crossing is left in the cycle, A value of 0 means not leaving the first pedestrian crossing. A value of 1 indicates leaving the first pedestrian crossing;

[0055] Assuming that pedestrians cross the street twice, the time for the second pedestrian crossing is greater than the sum of the time for leaving the first pedestrian crossing and the length of the first pedestrian crossing, as shown in formula (18):

[0056] (18)

[0057] in, A pedestrian crossing the street twice The corresponding duration of the first pedestrian crossing.

[0058] Furthermore, the input of the adaptive traffic light control model based on individual trajectories in step S6 includes the following parameters:

[0059] Static parameters include travel speed, queue density, saturation flow rate, widening section length, and pedestrian or non-vehicle crossing time;

[0060] Real-time vehicle detection information includes distance to the stop line, lane, and direction;

[0061] Real-time pedestrian and non-vehicle detection information includes the direction of crossing; traffic signal related information includes phase sequence scheme, minimum phase duration, green light interval, and real-time operation status;

[0062] Status information of vehicles and slow-moving traffic entities, and traffic light status information;

[0063] The output of the adaptive traffic light control model based on individual-level data includes the phase sequence and duration plan of several signal cycles starting from the current cycle.

[0064] Beneficial effects of the present invention:

[0065] The adaptive traffic light control method based on individual-level data described in the present invention models individual vehicles at the trajectory level to describe the relationship between signal and vehicle efficiency indicators. This addresses issues such as inaccurate calculation delays caused by uneven traffic flow arrival distribution and the reduction of saturated flow rate when the green light duration is long in the presence of short lanes, which are difficult for traditional optimization models to describe.

[0066] The adaptive traffic signal control method based on individual-level data described in the present invention addresses issues such as the lack of consideration of slow-moving traffic such as pedestrians in signal optimization models, especially the continuity of secondary street crossings. By modeling pedestrians / non-vehicles at the trajectory level, it can describe their discontinuous passage delays in situations such as secondary street crossings. This is incorporated into the above-mentioned vehicle optimization model to construct an adaptive intersection signal optimization model that optimizes the combined benefits of vehicles and slow-moving traffic, thereby achieving the optimal combined benefits for vehicles and slow-moving traffic passing through the intersection. BRIEF DESCRIPTION OF THE DRAWINGS

[0067] Figure 1 This is a flow chart of a method for adaptively controlling traffic lights based on individual-level data according to the present invention;

[0068] Figure 2 This is a schematic diagram of the traffic signal dual-loop control structure of the present invention;

[0069] Figure 3 Schematic diagram of vehicle-related constraints of the present invention. DETAILED DESCRIPTION

[0070] In order to make the objectives, technical solutions, and advantages of the present invention more clearly understood, the present invention is further described in detail below with reference to the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are only intended to explain the present invention and are not intended to limit the present invention. That is, the specific embodiments described herein are only some embodiments of the present invention, not all embodiments. Generally, the components of the specific embodiments of the present invention described and illustrated in the drawings herein can be arranged and designed in various different configurations, and the present invention can also have other embodiments.

[0071] Therefore, the following detailed description of the specific embodiments of the present invention provided in the accompanying drawings is not intended to limit the scope of the invention as claimed, but is merely representative of selected specific embodiments of the present invention. All other specific embodiments obtained by those skilled in the art based on the specific embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0072] In order to further understand the content, features and effects of the present invention, the following specific embodiments are given as examples, and the attached Figure 1 -Attached Figure 3 The detailed instructions are as follows:

[0073] Example 1:

[0074] An adaptive traffic signal control method based on individual-level data includes the following steps:

[0075] S1. Collect vehicle status information, slow-moving traffic status information, and traffic light status information;

[0076] S2. Construct the optimization objective function to minimize the sum of delays of vehicles and slow-moving traffic entities;

[0077] Furthermore, the sum of the delay times of vehicles and slow-moving traffic individuals constructed in step S2 is the minimum min f The expression of the optimization objective function is:

[0078] (1)

[0079] in, Is the vehicle number, It is the pedestrian's number. is the time when the vehicle leaves the stop line, It is the time when the last traffic signal light turns green for pedestrians to cross the street.

[0080] S3. Construct traffic signal structure constraints;

[0081] Furthermore, step S3 constructs the traffic signal structure constraint conditions as follows:

[0082] The traffic signal adopts a double-loop control structure, which includes 8 motor vehicle phases and 6 pedestrian phases, of which 4 pedestrian phases are pedestrian secondary crossing phases and the motor vehicle phase In the The start time of the cycle is ,in Starting from 1, the maximum value of the cycle Determined based on intersection scope and desired speed;

[0083] The motor vehicle phase is set to meet the minimum duration requirement, as shown in formulas (2) and (3):

[0084] (2)

[0085] (3)

[0086] in, Motor vehicle phase The next phase start time, Motor vehicle phase The minimum green time, Motor vehicle phase Green light interval time, Motor vehicle phase In the A variable indicating whether a cycle is not skipped, If the value is 0, skip. If the value is 1, it will not be skipped;

[0087] When the traffic signal reaches the barrier, the phase time of each motor vehicle ends at the same time, as shown in formula (4):

[0088] (4)

[0089] S4. Construct mutual constraints between vehicles;

[0090] Furthermore, step S4 constructs the mutual constraints between vehicles as follows:

[0091] Assume that vehicles leave during the green light period of any cycle, and each vehicle leaves the intersection during a certain cycle, as shown in equations (5) and (6):

[0092] (5)

[0093] (6)

[0094] in, Indicates vehicle Is it The variables of the cycle leaving the intersection, If the value is 0, then do not leave the intersection. If the value is 1, leave the intersection;

[0095] When a vehicle passes through the widening section junction, for the lane upstream of the widening section junction, the traffic flow on the same lane leaves the widening section junction in sequence, and the departure time meets the saturated headway constraint, as shown in formula (7):

[0096] (7)

[0097] in, The vehicle is in the lane The sequence number on is the time when the vehicle leaves the junction of the widening section, It's a lane saturated headway;

[0098] The time it takes for a vehicle to leave the widening section junction is set to be greater than the time it takes to travel to the widening section junction without stopping at the current position, as shown in formula (8):

[0099] (8)

[0100] in, It's a vehicle The distance to the stop line at the current moment, is the distance from the widening section junction to the stop line. is the desired speed of the vehicle;

[0101] For the lanes downstream of the widening section junction, the traffic on the same lane leaves the stop line in sequence and the departure time meets the saturated headway constraint, as shown in formula (9). The departure time of the vehicle downstream of the widening section junction is greater than the time it takes to drive from the widening section junction to the stop line without stopping, as shown in formula (10). The departure time of the vehicle downstream of the widening section junction is greater than the time it takes to drive from the current position to the stop line without stopping, as shown in formula (11):

[0102] (9)

[0103] (10)

[0104] (11)

[0105] S5. Construct the mutual constraints between individual travel trajectories and traffic signals;

[0106] Furthermore, step S5 constructs the mutual constraints between individual travel trajectories and traffic signals as follows:

[0107] Set pedestrian phase The minimum duration requirement is met, as shown in formulas (12) and (13):

[0108] (12)

[0109] (13)

[0110] in, Pedestrian phase The minimum green time, Pedestrian phase Green light interval time, Pedestrian phase In the A variable indicating whether a cycle is not skipped, A value of 0 means it is skipped. A value of 1 indicates that it is not skipped;

[0111] Set the pedestrian flow direction for a single crossing. Leave during the green light period of any cycle, and each pedestrian is sure to leave the intersection during a certain cycle, as shown in equations (14) and (15):

[0112] (14)

[0113] (15)

[0114] in, Indicates pedestrians Is it The variables of the cycle leaving the intersection, A value of 0 means not leaving the intersection. A value of 1 indicates leaving the intersection;

[0115] Assuming that pedestrians cross the street twice, the first pedestrian crossing time is during the green light period, as shown in formulas (16) and (17):

[0116] (16)

[0117] (17)

[0118] in, It is the time it takes for pedestrians crossing the street twice to leave the first pedestrian crossing section. Indicates pedestrians Is it The variable of the first pedestrian crossing is left in the cycle, A value of 0 means not leaving the first pedestrian crossing. A value of 1 indicates leaving the first pedestrian crossing;

[0119] Assuming that pedestrians cross the street twice, the time for the second pedestrian crossing is greater than the sum of the time for leaving the first pedestrian crossing and the length of the first pedestrian crossing, as shown in formula (18):

[0120] (18)

[0121] in, A pedestrian crossing the street twice The corresponding duration of the first pedestrian crossing.

[0122] S6. Based on steps S2-S5, an adaptive traffic light control model based on individual trajectories is formed;

[0123] Furthermore, the input of the adaptive traffic light control model based on individual trajectories in step S6 includes the following parameters:

[0124] Static parameters include travel speed, queue density, saturation flow rate, widening section length, and pedestrian or non-vehicle crossing time;

[0125] Real-time vehicle detection information includes distance to the stop line, lane, and direction;

[0126] Real-time pedestrian and non-vehicle detection information includes the direction of crossing; traffic signal related information includes phase sequence scheme, minimum phase duration, green light interval, and real-time operation status;

[0127] Status information of vehicles and slow-moving traffic entities, and traffic light status information;

[0128] The output of the adaptive traffic light control model based on individual-level data includes the phase sequence and duration plan of several signal cycles starting from the current cycle.

[0129] S7. Solve the adaptive traffic signal control model based on individual trajectories obtained in step S6 to optimize the traffic signal timing and phase sequence at the intersection. Each time, the traffic signal is optimized for the current cycle and several cycles thereafter to ensure that each individual traveler can leave the intersection within the optimized time range. The optimization results are updated in real time.

[0130] Figure 2 This is a schematic diagram of the dual-loop control structure of a traffic signal according to the present invention. The horizontal axis represents time, which describes the temporal relationship between the various phases. It can be seen from the figure that after the p1 phase ends, the p2 phase comes, and the p1 phase and the p5 phase are activated at the same time.

[0131] It should be noted that relational terms such as "first" and "second" are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus comprising a series of elements includes not only those elements, but also other elements not explicitly listed, or elements inherent to such process, method, article, or apparatus. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of additional identical elements in the process, method, article, or apparatus comprising the element.

[0132] Although the present application has been described above with reference to specific embodiments, various modifications may be made thereto and components may be substituted with equivalents without departing from the scope of the present application. In particular, as long as there are no structural conflicts, the various features of the embodiments disclosed herein may be combined with each other in any manner, and the omission of an exhaustive description of these combinations in this specification is solely for the sake of space and resource conservation. Therefore, the present application is not limited to the specific embodiments disclosed herein, but includes all technical solutions within the scope of the claims.

Claims

1. An adaptive traffic light control method based on individual-level data, characterized in that: The steps include: S1. Collect vehicle status information, slow-moving traffic status information, and traffic light status information; S2. Construct the optimization objective function to minimize the sum of delay times of vehicles and slow-moving traffic individuals; S3. Construct traffic signal structure constraints; S4. Construct mutual constraints between vehicles; S5. Construct the mutual constraints between individual travel trajectories and traffic signals; Step S5 constructs the mutual constraints between individual travel trajectories and traffic signals as follows: The pedestrian phase w is set to meet the minimum duration requirement, as shown in equations (12) and (13): in q,k -in p,k ≥(Γ w +R w )×Δ w,k (12) in q,k -in p,k ≤M×Δ w,k (13) Among them, Γ w is the minimum green light time for pedestrian phase w, R w is the green light interval of pedestrian phase w, Δ w,k A variable indicating whether the pedestrian phase w is not skipped in the kth cycle, Δ w,k A value of 0 means it is skipped, Δ w,k A value of 1 indicates that it is not skipped; q,k is the next phase start time of vehicle phase p, u p,k is the starting time of vehicle phase p in the kth cycle; Assume a pedestrian flow direction for a single crossing, pedestrian n leaves during the green light period of any cycle, and each pedestrian leaves the intersection in a certain cycle, as shown in equations (14) and (15): Among them, α k,n A variable indicating whether pedestrian n leaves the intersection within k cycles, α k,n A value of 0 means not leaving the intersection, α k,n A value of 1 indicates leaving the intersection; e n It is the time when the last traffic signal turns green for pedestrians to cross the street; Assuming that pedestrians cross the street twice, the first pedestrian crossing time is during the green light period, as shown in formulas (16) and (17): Among them, ρ n is the time it takes for the second pedestrian to leave the first pedestrian crossing section, ε k,n The variable indicating whether pedestrian n leaves the first pedestrian crossing in k cycles, ε k,n A value of 0 means not leaving the first pedestrian crossing, ε k,n A value of 1 indicates leaving the first pedestrian crossing; Assuming that pedestrians cross the street twice, the time for the second pedestrian crossing is greater than the sum of the time for leaving the first pedestrian crossing and the length of the first pedestrian crossing, as shown in formula (18): r n +T w ≤e n (18) Among them, T w is the duration of the first pedestrian crossing corresponding to the pedestrian n who crosses the street twice S6. Based on steps S2-S5, an adaptive traffic light control model based on individual trajectories is formed; S7. Solve the adaptive traffic signal control model based on individual trajectories obtained in step S6 to optimize the traffic signal timing and phase sequence at the intersection. Each time, optimize the traffic signal for the current cycle and several cycles thereafter to ensure that each individual traveler can leave the intersection within the optimized time range. Update the optimization results in real time.

2. The method for adaptive traffic light control based on individual-level data according to claim 1, characterized in that: The minimum sum of the delay times of vehicles and slow-moving traffic individuals constructed in step S2 is the expression of the optimization objective function: Among them, i is the number of the vehicle, n is the number of the pedestrian, b i is the time when the i-th car leaves the stop line, e n It is the time when the last traffic signal light turns green for pedestrians to cross the street.

3. The method for adaptive traffic light control based on individual-level data according to claim 2, characterized in that: Step S3 constructs the traffic signal structure constraint conditions as follows: The traffic signal adopts a double-loop control structure including 8 motor vehicle phases and 6 pedestrian phases, of which 4 pedestrian phases are pedestrian secondary crossing phases. The starting time of motor vehicle phase p in the kth cycle is u p,k , where k starts at 1 and the maximum value K of the cycle is determined according to the intersection range and the expected speed; The motor vehicle phase is set to meet the minimum duration requirement, as shown in formulas (2) and (3): in q,k -in p,k ≥(γ p +r p )×δ p,k (2) in q,k -in p,k ≤M×δ p,k (3) Among them, u q,k is the next phase start time of vehicle phase p, γ p is the minimum green light time of the vehicle in phase p, r p is the green light interval of the vehicle at phase p, δ p,k is a variable that determines whether the vehicle phase p is skipped in the kth cycle, δ p,k If the value is 0, skip it. p,k If the value is 1, it will not be skipped; When the traffic signal reaches the barrier, the phase time of each motor vehicle ends at the same time, as shown in formula (4): u q,k =u p,k ,(q,p)∈{(3,7),(1,5)} (4) 。 4. The method for adaptive traffic light control based on individual-level data according to claim 3, characterized in that: Step S4 constructs the mutual constraints between vehicles as follows: Assume that vehicles leave during the green light period of any cycle, and each vehicle leaves the intersection during a certain cycle, as shown in equations (5) and (6): Among them, β k,i The variable indicating whether vehicle i leaves the intersection within k cycles, β k,i If the value is 0, then do not leave the intersection. k,i If the value is 1, leave the intersection; When a vehicle passes through the widening section junction, for the lane upstream of the widening section junction, the traffic flow on the same lane leaves the widening section junction in sequence, and the departure time meets the saturated headway constraint, as shown in formula (7): Where j is the sequential number of the vehicle on lane l, τ j is the time when the jth vehicle in lane l leaves the junction of the widening section, is the saturated headway of lane l; The time it takes for a vehicle to leave the widening section junction is set to be greater than the time it takes to travel to the widening section junction without stopping at the current position, as shown in formula (8): Among them, d i is the distance from vehicle i to the stop line at the current moment, Z is the distance from the widening section to the stop line, and v is the expected speed of the vehicle; For the lanes downstream of the widening section junction, the traffic on the same lane leaves the stop line in sequence and the departure time meets the saturated headway constraint, as shown in formula (9). The departure time of the vehicle downstream of the widening section junction is greater than the time it takes to drive from the widening section junction to the stop line without stopping, as shown in formula (10). The departure time of the vehicle downstream of the widening section junction is greater than the time it takes to drive from the current position to the stop line without stopping, as shown in formula (11): （11）。 5. The method for adaptive traffic light control based on individual-level data according to claim 4, characterized in that: The input of the adaptive traffic light control model based on individual trajectories in step S6 includes the following parameters: Static parameters include travel speed, queue density, saturation flow rate, widening section length, and pedestrian or non-vehicle crossing time; Real-time vehicle detection information includes distance to the stop line, lane, and direction; Real-time pedestrian and non-vehicle detection information includes the direction of crossing; traffic signal related information includes phase sequence scheme, minimum phase duration, green light interval, and real-time operation status; Status information of vehicles and slow-moving traffic entities, and traffic light status information; The output of the adaptive traffic light control model based on individual-level data includes the phase sequence and duration plan of several signal cycles starting from the current cycle.

Images