Mixed intersection lane organization and signal control collaborative optimization method based on genetic algorithm and computer storage medium

Abstract

The invention discloses a hybrid intersection lane organization and signal control collaborative optimization method based on a genetic algorithm and a computer storage medium, and belongs to the technical field of traffic control, and the method comprises the following steps: 1, taking vehicle average delay as a target variable, and constructing a target function; 2, setting constraints based on a traffic flow theory, and constructing a mixed intersection lane organization and signal control collaborative optimization model; step 3, solving the objective function based on a genetic algorithm to obtain an optimal solution; initializing model parameters, generating an initial population, designing a signal timing scheme by adopting a Webster method, defining a fitness function, carrying out genetic manipulation on a sample, and continuously iterating to obtain a scheme with minimum vehicle average delay as an optimal solution; the method provided by the invention not only improves the service level of the intersection, but also enhances the toughness of the traffic system, and provides powerful theoretical support and practical guidance for wide application of the automatic driving technology in urban traffic.

Description

Technical Field

[0001] The invention belongs to the technical field of traffic control, and in particular relates to a mixed traffic intersection lane organization and signal control collaborative optimization method based on genetic algorithm and a computer storage medium. Background Art

[0002] At present, autonomous driving technology is regarded as an important trend in the future development of transportation. In the short term, it is difficult for autonomous vehicles to completely replace manually driven vehicles. Therefore, in a mixed traffic environment, how to accurately and effectively dispatch autonomous driving vehicles (CAV) and manually driven vehicles (HV) and maximize control benefits has become a problem that needs to be solved urgently.

[0003] In current research, the scheduling strategies for mixed traffic flows at intersections are mostly unified control methods, that is, autonomous driving vehicles and manually driven vehicles use the same intersection entrance lanes and signal phases, which will cause autonomous driving vehicles and manually driven vehicles to interfere with each other, greatly affecting the autonomous driving vehicles from exerting their own driving advantages.

[0004] In response to the above problems, the present invention proposes to introduce dedicated lanes and dedicated phases for autonomous driving vehicles at intersections, and establishes a collaborative optimization model for lane organization and signal control at intersections that consider mixed traffic flows. The autonomous driving vehicles are separated from manually driven vehicles in time and space, so that the autonomous driving vehicles can give full play to their driving characteristics, thereby effectively reducing the average vehicle delay at the intersection. Summary of the invention

[0005] The purpose of the present invention is to provide a method for collaborative optimization of lane organization and signal control at mixed intersections based on genetic algorithms and a computer storage medium, so as to solve the problems existing in the prior art of the current scheduling strategy for mixed traffic flows at intersections, such as unified control, cross-traffic, and the absence of dedicated lanes and phases for autonomous driving.

[0006] To achieve the above object, the present invention provides a method for collaborative optimization of lane organization and signal control at mixed traffic intersections based on genetic algorithm, comprising the following steps:

[0007] Step 1: Take the average vehicle delay as the target variable and construct the target function;

[0008] Step 2: Set constraints based on traffic flow theory and build a collaborative optimization model for lane organization and signal control at mixed traffic intersections; the constraints include lane layout constraints, flow distribution constraints, and signal timing constraints;

[0009] Step 3: Solve the objective function based on the genetic algorithm to obtain the optimal solution; initialize the model parameters, generate the initial population, use the Webster method to design the signal timing plan, define the fitness function, perform genetic operations on the samples, and continuously iterate to obtain the plan with the smallest average vehicle delay as the optimal solution.

[0010] Preferably, in step 1, the average vehicle delay is used as the target variable, and the target function is constructed as follows:

[0011] Z = mind;

[0012]

[0013] Where d is the average vehicle delay, Z is the vehicle type set, Z = {A, H}, where A and H represent autonomous driving vehicles and manually driven vehicles, respectively, and Q i,j is the traffic volume of the j-type functional lane in the entrance direction of intersection i, d i,j Indicates that all vehicles in the jth lane of the entrance lane in the i direction are delayed, Y i,j is the saturation of the j-type functional lane in the entrance direction of intersection i, T is the signal cycle length, β i,j is the green signal ratio of the j-type functional lane in the entrance direction of intersection i.

[0014] Preferably, the lane layout constraints are as follows:

[0015] The layout of the dedicated entrance road for autonomous driving follows the following formula:

[0016] M(sgn(f i,1 )-1)≤g i,1 ≤Msgn(f i,1 )

[0017] Where M is a sufficiently large positive number; sgn() is a sign function, which takes 1 when the parameter is positive and 0 otherwise; f i,1 is the number of lanes in the dedicated automatic driving lane at the entrance direction of intersection i; g i,1 The green light time of the dedicated lane for autonomous driving in the entrance direction of intersection i;

[0018] When the number of dedicated autopilot entrance lanes is not 0, the intersection dedicated autopilot phase is turned on. i,1 >0,sgn(f i,1 )=1; when no dedicated entrance lane for autonomous driving is set, the dedicated phase for autonomous driving at the intersection is closed. i,1 =0,sgn(f i,1 )=0;

[0019] For manual driving lanes, some types of lanes cannot exist at the same time in the same entrance direction, and their constraints follow the following formula:

[0020]

[0021] Among them, f i,2 ,f i,4 ,f i,5 ,f i,6 ,f i,7 ,f i,8 are the numbers of left-turn lanes, through lanes, left-straight combined lanes, straight-right combined lanes, left-right combined lanes, and left-straight-right combined lanes on the entrance direction of intersection i;

[0022] The number of lane groups is guaranteed to be a non-negative integer, constrained by the following formula:

[0023]

[0024] In the formula, f i,j Indicates the number of lanes of type j in the entrance direction of intersection i;

[0025] For each import direction, the number of dedicated autonomous driving lanes is equal to the number of dedicated autonomous driving lanes arranged in that direction, and the number of ordinary lanes is equal to the number of import lanes in that direction minus the number of dedicated autonomous driving lanes, where the number of lanes is defined by the following formula:

[0026]

[0027] in, are the number of automatic driving dedicated lanes and the number of manual driving lanes in the entrance direction of intersection i, respectively. Fi is the number of import lanes in the import direction of intersection i. i represents the direction of the import lane. In the cross intersection, i∈{1, 2, 3, 4} represents the north import lane, south import lane, west import lane and east import lane, respectively.

[0028] Preferably, the traffic distribution constraints include traffic constraints of dedicated autonomous driving lanes, traffic volume constraints of manual driving lanes, turning traffic balance constraints, multi-turn lane traffic balance constraints, and traffic distribution equilibrium constraints. The specific expressions are as follows:

[0029] When there is a dedicated lane for autonomous driving, all autonomous driving vehicles use this lane to pass, otherwise the flow is 0. The flow constraint Q i,1 as follows:

[0030]

[0031] Where k is the flow direction symbol, k∈{L, T, R}, representing left turn, straight ahead, and right turn, respectively; is the traffic volume of autonomous driving vehicles in direction k of the i-entrance road;

[0032] The traffic volume constraints for the manual driving lane are as follows:

[0033]

[0034] Among them, Q i,k is the traffic volume of the manual driving lane in the direction of k on the i-entrance road; is the traffic volume of manually driven vehicles in direction k of the i-entrance lane;

[0035] In order to ensure that all turning traffic flows on each entrance are allocated to the corresponding lanes, the following formula is used to realize the balance constraint of each turning flow:

[0036] Q i,2 f i,2 +Q i,5 f i,5 +Q i,7,L f i,7 +Q i,8,L f i,8 =Q i,L ;

[0037] Q i,3 f i,3 +Q i,6,R f i,6 +Q i,7,R f i,7 +Q i,8,R f i,8 =Q i,R ;

[0038] Q i,4 f i,4 +Q i,5,T f i,5 +Q i,6,T f i,6 +Q i,8,T f i,8 =Q i,T ;

[0039] Among them, Q i,j,k is the traffic flow of the jth lane group of the i-entrance road in the k-direction, Q i,k is the traffic volume of the manual driving lane in the direction of the i-th entrance lane, k∈{L,T,R}, Q i,j is the traffic volume of the j-type functional lane in the entrance direction of intersection i, i∈{1, 2, 3, 4}, representing the north entrance lane, south entrance lane, west entrance lane, and east entrance lane respectively; j represents the lane function, j∈{1, 2, ..., 6, 7, 8}, representing the automatic driving lane, left turn lane, right turn lane, straight lane, left-straight combined lane, straight-right combined lane, left-right combined lane, and left-straight-right combined lane respectively;

[0040] In order to ensure that various import lanes correctly match the corresponding turning traffic, the flow balance constraint of multiple turning lanes is realized by the following formula:

[0041] Q i,5,L +Q i,5,T =Q i,5 ;

[0042] Q i,6,R +Q i,6,T =Q i,6 ;

[0043] Q i,7,L +Q i,7,R =Q i,7 ;

[0044] Q i,8,T +Q i,8,L +Q i,8,R =Q i,8 ;

[0045] When there are multiple lane groups facing a certain flow rate at the i-th entrance, the flow rate in this direction is allocated among the lane groups according to the equal saturation principle, and the traffic flow allocation equilibrium constraint is realized by the following formula:

[0046]

[0047] M(2-sgn(f i,j1 )-sgn(f i,j2 ))≥Y i,j1 -Y i,j2 ≥-M(2-sgn(f i,j1 )-sgn(f i,j2 )),

[0048]

[0049] In the formula, ε is an infinitesimal quantity, which is used to ensure the computability of the model when the lane group does not exist; δ is the vehicle's startup loss time; C i,j is the traffic capacity of the j-type functional lane at the entrance direction of intersection i, g i,j Y represents the green light signal time of the j-type lane in the i-entry direction. i,j represents the saturation of the j-type lane in the i-entry direction, f i,j1 represents the number of j1-type lanes in the i-entry direction, f i,j2 represents the number of j2-type lanes in the direction of entry i, Y i,j1 represents the saturation of the j1-type lane in the direction of the i entrance, Y i,j2 Indicates the saturation of the j2-type lane in the i-entry direction.

[0050] Preferably, the signal timing constraints are as follows: the signal timing of the intersection takes into account the interlaced passage of autonomous driving vehicles. On the basis of the original signal phase, an additional phase dedicated to autonomous driving is added. The "double-loop-three-group" structure of the dedicated phase for autonomous driving is designed. The autonomous driving traffic flow in each entrance direction constitutes the third group of dedicated phases for autonomous driving. The specific constraints are as follows:

[0051] The green light duration in signal timing is constrained by the following formula:

[0052] g min ≤g i,j ≤g max ;

[0053] Among them, g i,j is the green light time of the j-type functional lane in the entrance direction of intersection i; g min and g max They are the minimum green light duration and the maximum green light duration of the signal phase respectively;

[0054] The signal group needs to be determined in advance, and the green light time of the signal flows in the signal group should be equal, which is defined by the following formula:

[0055]

[0056] Among them, g m is the green light time of the mth signal group; Ω m is the mth signal group; g i,j(i,j) It represents the green light signal time of lane j (i, j) in the direction of entry i; signal group refers to the combination of lane groups that can be used in the same period;

[0057] The intersection signal cycle time T is not greater than the maximum cycle time T max , not less than the minimum cycle length T min , the expression is as follows:

[0058] T min ≤T≤T max ;

[0059]

[0060] Where σ is the intersection clearing time.

[0061] Preferably, the fitness function f(X) in step 3 is as follows:

[0062]

[0063] Where d(X) represents the average vehicle delay.

[0064] The present invention also provides a computer storage medium on which computer-readable instructions are stored. When the instructions are executed by a computer, the above method is implemented.

[0065] Therefore, the present invention adopts the above-mentioned mixed-traffic intersection lane organization and signal control collaborative optimization method and computer storage medium based on genetic algorithm, and makes control decisions after information integration, feature analysis and key parameter optimization processing of the collected traffic data according to the preset algorithm framework, so as to improve the traffic efficiency of the intersection. By integrating the characteristics of autonomous driving vehicles and the dynamic behavior of manually driven vehicles, the problem of insufficient adaptability in existing traffic control strategies is solved. At the same time, compared with traditional signal control methods, the optimization speed is significantly improved, and a mixed-traffic intersection lane organization and signal control collaborative optimization model is constructed to obtain better traffic efficiency, overcoming the disadvantages of the existing technology in intersection traffic flow control that needs to overcome a single control strategy and lack of dynamic adaptability, which is crucial for intelligent transportation systems to predict traffic congestion and provide real-time scheduling, and also provides more decision-making time for traffic managers.

[0066] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0067] Figure 1 A flowchart of a method for collaboratively optimizing lane organization and signal control at a mixed traffic intersection based on a genetic algorithm according to the present invention;

[0068] Figure 2 It is a layout diagram of the intersection lane organization of an embodiment of the present invention;

[0069] Figure 3 is a graph showing changes in average intersection vehicle delay under different CAV penetration rates according to an embodiment of the present invention;

[0070] Figure 4 This is a graph showing the reduction in average delays for HV and CAV vehicles and average delay for intersection vehicles at different CAV penetration rates according to an embodiment of the present invention. DETAILED DESCRIPTION

[0071] The following detailed description of the embodiments of the present invention provided in the accompanying drawings is not intended to limit the scope of the invention claimed for protection, but merely represents selected embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0072] See also Figure 1-Figure 2 , a mixed traffic intersection lane organization and signal control collaborative optimization method based on genetic algorithm, comprising the following steps:

[0073] Step 1: Take the average vehicle delay as the target variable and construct the target function; the specific expression is as follows:

[0074] Z = mind;

[0075]

[0076] Where d is the average vehicle delay, Z is the vehicle type set, Z = {A, H}, where A and H represent autonomous driving vehicles and manually driven vehicles, respectively, and Q i,j is the traffic volume of the j-type functional lane in the entrance direction of intersection i, d i,j Indicates that all vehicles in the jth lane of the entrance lane in the i direction are delayed, Y i,j is the saturation of the j-type functional lane in the entrance direction of intersection i, T is the signal cycle length, β i,j is the green signal ratio of the j-type functional lane in the entrance direction of intersection i.

[0077] Step 2: Set constraints based on traffic flow theory and build a collaborative optimization model for lane organization and signal control at mixed traffic intersections; the constraints include lane layout constraints, flow distribution constraints, and signal timing constraints;

[0078] The lane layout constraints are as follows:

[0079] The layout of the dedicated entrance road for autonomous driving follows the following formula:

[0080] M(sgn(f i,1 )-1)≤g i,1 ≤Msgn(f i,1 )

[0081] Where M is a sufficiently large positive number; sgn() is a sign function, which takes 1 when the parameter is positive and 0 otherwise; f i,1 is the number of lanes in the dedicated automatic driving lane at the entrance direction of intersection i; g i,1 The green light time of the dedicated lane for autonomous driving in the entrance direction of intersection i;

[0082] When the number of dedicated autopilot entrance lanes is not 0, the intersection dedicated autopilot phase is turned on. i,1 >0,sgn(f i,1 )=1; when no dedicated entrance lane for autonomous driving is set, the dedicated phase for autonomous driving at the intersection is closed. i,1 =0,sgn(f i,1 )=0;

[0083] For manual driving lanes, some types of lanes cannot exist at the same time in the same entrance direction, and their constraints follow the following formula:

[0084]

[0085] Among them, f i,2 ,f i,4 ,f i,5 ,f i,6 ,f i,7 ,f i,8 are the numbers of left-turn lanes, through lanes, left-straight combined lanes, straight-right combined lanes, left-right combined lanes, and left-straight-right combined lanes on the entrance direction of intersection i;

[0086] The number of lane groups is guaranteed to be a non-negative integer, constrained by the following formula:

[0087]

[0088] In the formula, f i, j represents the number of lanes of type j in the entrance direction of intersection i;

[0089] For each import direction, the number of dedicated autonomous driving lanes is equal to the number of dedicated autonomous driving lanes arranged in that direction, and the number of ordinary lanes is equal to the number of import lanes in that direction minus the number of dedicated autonomous driving lanes, where the number of lanes is defined by the following formula:

[0090]

[0091] in, are the number of automatic driving dedicated lanes and the number of manual driving lanes in the entrance direction of intersection i, respectively. Fi is the number of import lanes in the import direction of intersection i. i represents the direction of the import lane. In the cross intersection, i∈{1, 2, 3, 4} represents the north import lane, south import lane, west import lane and east import lane, respectively.

[0092] The traffic distribution constraints include the traffic constraints of the dedicated autonomous driving lanes, the traffic volume constraints of the manual driving lanes, the turning traffic balance constraints, the multi-turn lane traffic balance constraints and the traffic distribution equilibrium constraints. The specific expressions are as follows:

[0093] When there is a dedicated lane for autonomous driving, all autonomous driving vehicles use this lane to pass, otherwise the flow is 0. The flow constraint Q i,1 as follows:

[0094]

[0095] Where k is the flow direction symbol, k∈{L, T, R}, representing left turn, straight ahead, and right turn, respectively; is the traffic volume of autonomous driving vehicles in direction k of the i-entrance road;

[0096] The traffic volume constraints for the manual driving lane are as follows:

[0097]

[0098] Among them, Q i,k is the traffic volume of the manual driving lane in the direction of k on the i-entrance road; is the traffic volume of manually driven vehicles in direction k of the i-entrance lane;

[0099] In order to ensure that all turning traffic flows on each entrance are allocated to the corresponding lanes, the following formula is used to realize the balance constraint of each turning flow:

[0100] Q i,2 f i,2 +Q i,5 f i,5 +Q i,7,L f i,7 +Q i,8,L f i,8 =Q i,L ;

[0101] Q i,3 f i,3 +Q i,6,R f i,6 +Q i,7,R f i,7 +Q i,8,R f i,8 =Q i,R ;

[0102] Q i,4 f i,4 +Q i,5,T f i,5 +Q i,6,T f i,6 +Q i,8,T f i,8 =Q i,T ;

[0103] Among them, Q i,j,k is the traffic flow of the jth lane group of the i-entrance road in the k-direction, Q i,k is the traffic volume of the manual driving lane in the direction of the i-th entrance lane, k∈{L,T,R}, Q i,j is the traffic volume of the j-type functional lane in the entrance direction of intersection i, i∈{1, 2, 3, 4}, representing the north entrance lane, south entrance lane, west entrance lane, and east entrance lane respectively; j represents the lane function, j∈{1, 2, ..., 6, 7, 8}, representing the automatic driving lane, left turn lane, right turn lane, straight lane, left-straight combined lane, straight-right combined lane, left-right combined lane, and left-straight-right combined lane respectively;

[0104] In order to ensure that various import lanes correctly match the corresponding turning traffic, the flow balance constraint of multiple turning lanes is realized by the following formula:

[0105] Qi,5,L +Q i,5,T =Q i,5 ;

[0106] Q i,6,R +Q i,6,T =Q i,6 ;

[0107] Q i,7,L +Q i,7,R =Q i,7 ;

[0108] Q i,8,T +Q i,8,L +Q i,8,R =Q i,8 ;

[0109] When there are multiple lane groups facing a certain flow rate on the i-th entrance, the flow rate in this direction is allocated among the lane groups according to the equal saturation principle, and the traffic flow allocation equilibrium constraint is realized by the following formula:

[0110]

[0111] M(2-sgn(f i,j1 )-sgn(f i,j2 ))≥Y i,j1 -Y i,j2 ≥-M(2-sgn(f i,j1 )-sgn(f i,j2 )),

[0112]

[0113] In the formula, ε is an infinitesimal quantity, which is used to ensure the computability of the model when the lane group does not exist; δ is the vehicle's startup loss time; C i,j is the traffic capacity of the j-type functional lane at the entrance direction of intersection i, g i,j Y represents the green light signal time of the j-type lane in the i-entry direction. i,j represents the saturation of the j-type lane in the i-entry direction, f i,j1 represents the number of j1-type lanes in the i-entry direction, f i,j2 represents the number of j2-type lanes in the direction of entry i, Y i,j1 represents the saturation of the j1-type lane in the direction of the i entrance, Y i,j2 Indicates the saturation of the j2-type lane in the i-entry direction.

[0114] The signal timing constraints are as follows: The signal timing of the intersection takes into account the interlaced passage of autonomous driving vehicles. On the basis of the original signal phase, an additional phase dedicated to autonomous driving is added. The design considers the "double-loop-three-group" structure of the dedicated phase for autonomous driving. The autonomous driving traffic flow in each entrance direction constitutes the third group of dedicated phases for autonomous driving. The specific constraints are as follows:

[0115] The green light duration in signal timing is constrained by the following formula:

[0116] g min ≤g i,j ≤g max ;

[0117] Among them, g i,j is the green light time of the j-type functional lane in the entrance direction of intersection i; g min and g max They are the minimum green light duration and the maximum green light duration of the signal phase respectively;

[0118] The signal group needs to be determined in advance, and the green light time of the signal flows in the signal group should be equal, which is defined by the following formula:

[0119]

[0120] Among them, g m is the green light time of the mth signal group; Ω m is the mth signal group; g i,j(i,j) It represents the green light signal time of lane j (i, j) in the direction of entry i; signal group refers to the combination of lane groups that can be used in the same period;

[0121] The intersection signal cycle time T is not greater than the maximum cycle time T max , not less than the minimum cycle length T min , the expression is as follows:

[0122] T min ≤T≤T max ;

[0123]

[0124] Where σ is the intersection clearing time.

[0125] Step 3: Solve the objective function based on the genetic algorithm to obtain the optimal solution; initialize the model parameters, generate the initial population, use the Webster method to design the signal timing plan, define the fitness function, perform genetic operations on the samples, and continuously iterate to obtain the plan with the minimum average vehicle delay as the optimal solution; the specific process is as follows:

[0126] S1. Initialization parameters:

[0127] Initialize the key parameters of the model, including lane combination type, traffic flow, autonomous vehicle penetration rate, lane group saturation rate, analysis time length, population size, crossover and mutation probability, and the maximum number of iterations of the algorithm. These parameters are set based on preliminary research and field data analysis to ensure that the model can achieve good results in practical applications.

[0128] S2. Generate the initial population:

[0129] According to the set population size, a series of possible solutions are randomly generated. These solutions include all possible combinations of different CAV penetration rates and different lane organization schemes, ensuring the diversity of the initial population and providing a wide gene pool for the operation of the genetic algorithm.

[0130] S3. Timing scheme design:

[0131] For each lane organization scheme generated in step S2, the Webster method is used to design the signal timing scheme. The Webster method is a classic signal timing design method that can effectively adjust the green light time of the signal according to the traffic flow demand and optimize the traffic flow efficiency.

[0132] S4.Fitness function setting:

[0133] The fitness function is defined to evaluate the effectiveness of each sample solution. The fitness function is mainly based on the average delay time of the vehicle, which is used to ensure that the algorithm gives priority to the solution that can minimize the delay. After the fitness calculation of each sample is completed, a corresponding selection probability is assigned to each sample according to their fitness value so that it can be selected in subsequent iterations. The fitness function is defined by the following formula:

[0134]

[0135] S5. Genetic operations and sample updates:

[0136] In this step, samples are selected to enter the next generation according to the sampling probability calculated in the previous step. After selection, genetic operations, including crossover and mutation, are performed on the selected samples to generate a new population.

[0137] S6. Iteration and Convergence

[0138] Repeat steps S3 and S5 until the preset number of iterations is reached or the quality of the solution is no longer significantly improved. At the end of the iteration process, the lane organization and signal control solution that performs best under different autonomous driving vehicle penetration rates in all rounds, that is, the solution with the smallest average vehicle delay, is the optimal solution under the autonomous driving vehicle penetration rate.

[0139] The present invention Figure 2The case analysis is carried out by taking the intersection lane organization shown in Figure 1 and the intersection traffic volume shown in Table 1 as examples to verify the effectiveness of the coordinated optimization model of intersection lane organization and signal control in mixed traffic environment. The values ​​of relevant parameters in the modeling process are shown in Table 2

[0140] Table 2 Initial traffic volume at intersection

[0141] flow straight Turn left Turn right East 811 268 132 West 968 339 155 South 1333 251 301 north 887 236 188

[0142] Table 3 Model parameter values

[0143]

[0144] Based on the above parameter settings, the model is solved using the designed genetic algorithm. At the beginning of the algorithm, 200 lane organization schemes are randomly generated as the initial population. In each generation of evolution, the fitness value of each individual is first calculated, that is, the inverse of the corresponding average vehicle delay, and then selection, crossover and mutation operations are performed according to a certain probability to generate a new generation of population. By running the algorithm independently multiple times, the optimal solution among the multiple running results is finally taken as the optimal lane organization and signal control scheme for the intersection.

[0145] This paper sets 6 typical CAV penetration rates, and the solution results under different penetration rates are shown in Tables 3 and 4. Table 3 shows the minimum average vehicle delay and the optimal number of CAV dedicated lanes under different penetration rates. The average vehicle delay of the classic model (intersection control model without dedicated entrance lanes and dedicated phases for autonomous driving) is 60.577s. When the CAV penetration rate is 0-42%, no CAV dedicated lanes are set, and the average intersection vehicle delay is equal to the average intersection vehicle delay of the classic model; when the CAV penetration rate is 42-73%, 1 CAV dedicated lane is set; when the CAV penetration rate increases to 73% and above, 2 CAV dedicated lanes are set.

[0146] Table 3 Minimum average vehicle delay under different CAV penetration rates

[0147]

[0148]

[0149] Table 4 shows the intersection signal timing scheme under different CAV penetration rates. When the CAV penetration rate is 0-42%, no CAV dedicated phase is set. At this time, the intersection signal timing scheme is the same as when the CAV penetration rate is 0; when the CAV penetration rate is higher than 42%, a CAV dedicated phase is set. As the CAV penetration rate increases, the signal cycle duration gradually decreases. When the CAV penetration rate reaches 80%, the signal cycle duration decreases significantly.

[0150] Table 4 Intersection signal timing schemes under different CAV penetration rates

[0151]

[0152] In order to verify the effectiveness of the optimization model proposed in this paper under different CAV penetration rates, this paper conducted a detailed analysis of the average vehicle delay at the intersection. The following are the main analysis results and findings:

[0153] (1) Impact of CAV penetration rate on average vehicle delay

[0154] This paper analyzes how the average delay at intersections changes with CAV penetration. Figure 3 The results show that: when the CAV penetration rate is 42%, the average vehicle delay calculated by setting up a CAV dedicated lane is the same as the classic model; when the CAV penetration rate is below 42%, the average vehicle delay calculated by setting up a CAV dedicated lane is greater than the classic model. Therefore, this intersection is not suitable for setting up a CAV dedicated phase and a dedicated entrance lane; as the CAV penetration rate increases, the advantages of the collaborative optimization model begin to emerge. When the CAV penetration rate is between 42% and 73%, the average vehicle delay calculated by setting up one CAV dedicated lane is less than that of the classic model and the case of setting up multiple CAV dedicated lanes. For example, when the CAV penetration rate is 50%, 60%, and 70%, At this time, setting a CAV-only phase and a CAV-only entrance lane, compared with the classic traffic organization and signal control schemes, the delay reduction rates are 7.3%, 19.1% and 34.7% respectively, which can effectively reduce the average vehicle delay and improve the intersection service level; when the CAV penetration rate is 73% and above, the average vehicle delay calculated by setting two CAV-only lanes is smaller than that of the classic model and the case of setting one CAV-only lane. Among them, when the CAV penetration rate is 80%, the average vehicle delay reduction rate is as high as 67%. This is because under high CAV penetration rates, the reasonable allocation of CAV and HV right of way is more effective in improving the intersection capacity.

[0155] (2) Comparison of delays between CAVs and HVs at different CAV penetration rates

[0156] This paper compares the average vehicle delay of CAV and HV under different CAV penetration rates, such as Figure 4 When the CAV penetration rate is lower than 42%, no CAV lanes are set up, and the average delay of CAV vehicles and HV vehicles is equal to the average delay of intersection vehicles; when the CAV penetration rate is higher than 42%, setting up CAV lanes and phases can reduce the average delay of intersection vehicles, and when the CAV penetration rate exceeds 70%, the average delay of HV vehicles decreases more with the increase of CAV penetration rate.

[0157] In summary, the collaborative optimization model proposed in this paper has a more significant effect on optimizing the traffic efficiency of mixed-traffic intersections under medium and high CAV penetration rates. As the CAV penetration rate increases, the optimal lane organization scheme changes accordingly, and the average vehicle delay gradually decreases. The model in this paper can effectively coordinate the lane organization and signal control of the intersection, thereby significantly improving the operation of mixed-traffic intersections.

[0158] The present invention also provides a computer storage medium on which computer-readable instructions are stored. When the instructions are executed by a computer, the above method is implemented.

[0159] Therefore, the present invention adopts the above-mentioned mixed-traffic intersection lane organization and signal control collaborative optimization method based on genetic algorithm and computer storage medium, and through fine analysis of intersection traffic flow, and combined with intelligent optimization genetic algorithm, the lane configuration, signal timing and vehicle passage sequence of the intersection are collaboratively optimized. By utilizing the vehicle's automatic driving capability and vehicle networking communication technology, the overall optimization of lane selection, passage timing and speed guidance is achieved, which effectively improves the traffic efficiency and operation stability of the intersection, and provides strong theoretical support and practical guidance for the widespread application of automatic driving technology in urban transportation.

[0160] Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that they can still modify or replace the technical solution of the present invention with equivalents, and these modifications or equivalent replacements cannot cause the modified technical solution to deviate from the spirit and scope of the technical solution of the present invention.

Claims

1. A method for collaborative optimization of lane organization and signal control at mixed traffic intersections based on genetic algorithm, characterized in that: The following steps are involved: Step 1: Take the average vehicle delay as the target variable and construct the target function; Step 2: Set constraints based on traffic flow theory and build a collaborative optimization model for lane organization and signal control at mixed traffic intersections; the constraints include lane layout constraints, flow distribution constraints, and signal timing constraints; Step 3: Solve the objective function based on the genetic algorithm to obtain the optimal solution; initialize the model parameters, generate the initial population, use the Webster method to design the signal timing plan, define the fitness function, perform genetic operations on the samples, and continuously iterate to obtain the plan with the smallest average vehicle delay as the optimal solution.

2. The method for collaborative optimization of lane organization and signal control at mixed traffic intersections based on genetic algorithm according to claim 1, characterized in that: In step 1, the average vehicle delay is used as the target variable, and the objective function is constructed as follows: Z = mind; Where d is the average vehicle delay, Z is the vehicle type set, Z = {A, H}, where A and H represent autonomous driving vehicles and manually driven vehicles, respectively, and Q i,j is the traffic volume of the j-type functional lane in the entrance direction of intersection i, d i,j Indicates that all vehicles in the jth lane of the entrance lane in the i direction are delayed, Y i,j is the saturation of the j-type functional lane in the entrance direction of intersection i, T is the signal cycle length, β i,j is the green signal ratio of the j-type functional lane in the entrance direction of intersection i.

3. The method for collaborative optimization of lane organization and signal control at mixed traffic intersections based on genetic algorithm according to claim 2, characterized in that: The lane layout constraints are as follows: The layout of the dedicated entrance road for autonomous driving follows the following formula: M(sgn(f i,1 )-1)≤g i,1 ≤Msgn(f i,1 ) Where M is a sufficiently large positive number; sgn() is a sign function, which takes 1 when the parameter is positive and 0 otherwise; f i,1 is the number of lanes in the dedicated automatic driving lane at the entrance direction of intersection i; g i,1 The green light time of the dedicated lane for autonomous driving in the entrance direction of intersection i; When the number of dedicated autopilot entrance lanes is not 0, the intersection dedicated autopilot phase is turned on. i,1 >0,sgn(f i,1 )=1; when no dedicated entrance lane for autonomous driving is set, the dedicated phase for autonomous driving at the intersection is closed. i,1 =0,sgn(f i,1 )=0; For the manual driving lane, in the same import direction, its constraints follow the following formula: Among them, f i,2 ,f i,4 ,f i,5 ,f i,6 ,f i,7 ,f i,8 are the numbers of left-turn lanes, through lanes, left-straight combined lanes, straight-right combined lanes, left-right combined lanes, and left-straight-right combined lanes on the entrance direction of intersection i; The number of lane groups is guaranteed to be a non-negative integer, constrained by the following formula: In the formula, f i,j It represents the number of lanes of type j in the entrance direction of intersection i; For each import direction, the number of dedicated autonomous driving lanes is equal to the number of dedicated autonomous driving lanes arranged in that direction, and the number of ordinary lanes is equal to the number of import lanes in that direction minus the number of dedicated autonomous driving lanes, where the number of lanes is defined by the following formula: f i A =f i,1 ; f i H =F i -f i A ; Among them, f i A ,f i H are the number of dedicated automatic driving lanes and the number of manual driving lanes at the entrance direction of intersection i, respectively. i is the number of entrance lanes in the entrance direction of intersection i; i represents the direction of the entrance lane. In the cross intersection, i∈{1, 2, 3, 4} represents the north entrance lane, south entrance lane, west entrance lane, and east entrance lane, respectively.

4. The method for collaborative optimization of lane organization and signal control at mixed traffic intersections based on genetic algorithm according to claim 3, characterized in that: The traffic distribution constraints include the traffic constraints of the dedicated autonomous driving lanes, the traffic volume constraints of the manual driving lanes, the turning traffic balance constraints, the multi-turn lane traffic balance constraints and the traffic distribution equilibrium constraints. The specific expressions are as follows: When there is a dedicated lane for autonomous driving, all autonomous driving vehicles use this lane to pass, otherwise the flow is 0. The flow constraint Q i,1 as follows: Where k is the flow direction symbol, k∈{L, T, R}, representing left turn, straight ahead, and right turn, respectively; Q A i,k is the traffic volume of autonomous driving vehicles in direction k of the i-entrance road; The traffic volume constraints for the manual driving lane are as follows: Q i,k =Q H i,k +Q A i,k (1-sgn(f i,1 )); Among them, Q i,k is the traffic volume of the manual driving lane in the direction of the i-entrance road k; Q H i,k is the traffic volume of manually driven vehicles in direction k of the i-entrance lane; In order to ensure that all turning traffic flows on each entrance are allocated to the corresponding lanes, the following formula is used to realize the balance constraint of each turning flow: Q i,2 f i,2 +Q i,5 f i,5 +Q i,7,L f i,7 +Q i,8,L f i,8 =Q i,L ; Q i,3 f i,3 +Q i,6,R f i,6 +Q i,7,R f i,7 +Q i,8,R f i,8 =Q i,R ; Q i,4 f i,4 +Q i,5,T f i,5 +Q i,6,T f i,6 +Q i,8,T f i,8 =Q i,T ; Among them, Q i,j,k is the traffic flow of the jth lane group of the i-entrance road in the k-direction, Q i,k is the traffic volume of the manual driving lane in the direction of the i-th entrance lane, k∈{L,T,R}, Q i,j is the traffic volume of the j-type functional lane in the entrance direction of intersection i, i∈{1, 2, 3, 4}, representing the north entrance lane, south entrance lane, west entrance lane, and east entrance lane respectively; j represents the lane function, j∈{1, 2, ..., 6, 7, 8}, representing the automatic driving lane, left turn lane, right turn lane, straight lane, left-straight combined lane, straight-right combined lane, left-right combined lane, and left-straight-right combined lane respectively; In order to ensure that various import lanes correctly match the corresponding turning traffic, the flow balance constraint of multiple turning lanes is realized by the following formula: Q i,5,L +Q i,5,T =Q i,5 ; Q i,6,R +Q i,6,T =Q i,6 ; Q i,7,L +Q i,7,R =Q i,7 ; Q i,8,T +Q i,8,L +Q i,8,R =Q i,8 ; When there are multiple lane groups facing a certain flow rate at the i-th entrance, the flow rate in this direction is allocated among the lane groups according to the equal saturation principle, and the traffic flow allocation equilibrium constraint is realized by the following formula: M(2-sgn(f i,j1 )-sgn(f i,j2 ))≥Y i,j1 -Y i,j2 ≥-M(2-sgn(f i,j1 )-sgn(f i,j2 )), In the formula, ε is an infinitesimal quantity; δ is the vehicle's starting loss time; C i,j is the traffic capacity of the j-type functional lane at the entrance direction of intersection i, g i,j Y represents the green light signal time of the j-type lane in the i-entry direction. i,j represents the saturation of the j-type lane in the i-entry direction, f i,j1 represents the number of j1-type lanes in the i-entry direction, f i,j2 represents the number of j2-type lanes in the direction of entry i, Y i,j1 represents the saturation of the j1-type lane in the direction of the i entrance, Y i,j2 Indicates the saturation of the j2-type lane in the i-entry direction.

5. The method for collaborative optimization of lane organization and signal control at mixed traffic intersections based on genetic algorithm according to claim 4, characterized in that: The signal timing constraints are as follows: The signal timing of the intersection takes into account the interlaced passage of autonomous driving vehicles. On the basis of the original signal phase, an additional phase dedicated to autonomous driving is added. The design considers the "double-loop-three-group" structure of the dedicated phase for autonomous driving. The autonomous driving traffic flow in each entrance direction constitutes the third group of dedicated phases for autonomous driving. The specific constraints are as follows: The green light duration in signal timing is constrained by the following formula: g min ≤g i,j ≤g max ; Among them, g i,j is the green light time of the j-type functional lane in the entrance direction of intersection i; g min and g max They are the minimum green light duration and the maximum green light duration of the signal phase respectively; The signal group needs to be determined in advance, and the green light time of the signal flows in the signal group should be equal, which is defined by the following formula: Among them, g m is the green light time of the mth signal group; Ω m is the mth signal group; g i,j(i,j) Indicates the green light signal time of lane j (i, j) in the direction of entry i; The intersection signal cycle time T is not greater than the maximum cycle time T max , not less than the minimum cycle length T min , the expression is as follows: T min ≤T≤T max ; Where σ is the intersection clearing time.

6. The method for collaborative optimization of lane organization and signal control at mixed traffic intersections based on genetic algorithm according to claim 5, characterized in that: The fitness function f(X) in step 3 is as follows: Where d(X) represents the average vehicle delay.

7. A computer storage medium, characterized in that: Computer-readable instructions are stored thereon, and when the instructions are executed by a computer, the method according to any one of claims 1 to 6 is implemented.

Images