Emergency lane management method and terminal device

Abstract

The application is suitable for the field of traffic control technology, and provides an emergency lane control method and a terminal device. The target emergency lane is divided into multiple spatial segments, and a switch state quantity is set. A transformation frequency constraint and a lane component constraint are constructed. A set of space-time control strategies is generated according to the constructed constraints. A strategy evaluation function is constructed according to the vehicle passing time and the vehicle collision exposure time of the spatial segment. The space-time control strategies are evaluated by using the strategy evaluation function, and the space-time control strategy with the highest evaluation score is taken as an initial control strategy. The set of space-time control strategies is crossed and mutated by using a genetic algorithm to obtain an intermediate control strategy. A final control strategy is determined from the initial control strategy and the intermediate control strategy, and the target emergency lane is controlled according to the final control strategy. The application can improve the control effect of the emergency lane control method.

Description

Technical Field

[0001] This application belongs to the field of traffic control technology, and in particular relates to an emergency lane control method and terminal equipment. Background Technology

[0002] Smart highways are a new type of highway development technology that can provide rapid and efficient travel guidance through real-time traffic prediction and control, effectively improving the traffic efficiency, system control capabilities, service levels, and reducing driving risks of highway networks.

[0003] Numerous preliminary studies have shown that timely opening of emergency lanes can effectively alleviate highway congestion and improve highway safety to some extent. During specific time periods, such as morning and evening rush hours, using emergency lanes or hard shoulders as additional lanes can increase traffic capacity by approximately 20% to 25%.

[0004] However, existing emergency lane control methods only target strategies that control open space under fixed opening hours or control opening hours under fixed open space. These are control methods based on a single control variable, which are insufficient to fully realize the traffic efficiency of emergency lanes as supplementary lanes on highways. They also lack a comprehensive interaction between efficiency and safety, resulting in poor control effectiveness. Summary of the Invention

[0005] This application provides an emergency lane control method and terminal device, which can solve the problem of poor control effect of current emergency lane control methods.

[0006] In a first aspect, embodiments of this application provide an emergency lane control method, including:

[0007] The target emergency lane is divided into multiple spatial segments, and each spatial segment is assigned a switch status variable; the switch status variables include open and closed.

[0008] Based on the switching state variables of each spatial segment and the pre-set state transition interval, construct the transition frequency constraint and lane component constraint.

[0009] Based on the transformation frequency constraint and lane component constraint, a set of spatiotemporal control strategies for the target emergency lane is randomly generated; the set of spatiotemporal control strategies includes multiple spatiotemporal control strategies, and any one of the multiple spatiotemporal control strategies includes the on / off state variables of all spatial segments of the target emergency lane.

[0010] A strategy evaluation function is constructed based on the vehicle passage time and the vehicle collision exposure time of each spatial segment; the vehicle collision exposure time represents the total time that a vehicle is in a critical situation during its journey.

[0011] Each spatiotemporal control strategy is evaluated using a strategy evaluation function, and the spatiotemporal control strategy with the highest evaluation score is used as the initial control strategy.

[0012] A genetic algorithm is used to perform crossover and mutation on the set of spatiotemporal control strategies to obtain intermediate control strategies.

[0013] The final control strategy is determined from the initial and intermediate control strategies, and the target emergency lane is controlled according to the final control strategy.

[0014] Optionally, the expression for the transform frequency constraint is as follows:

[0015]

[0016] Where i represents the i-th spatial segment, L represents the total number of spatial segments, t represents the t-th state transition interval, and E i (t) represents the switching state quantity of the i-th spatial segment within the t-th state transition interval, E i =[0,1], E i =0 indicates that the space segment is closed, E i =1 indicates that the space segment is in the open state, N time This represents the number of times the switch state variables of all spatial segments change within any given state transition interval.

[0017] Optionally, the expression for the lane component constraint is as follows:

[0018]

[0019] Among them, E cc The lane component represents a spatial segment where both the switch states are active (on) within a state transition interval. N distance This indicates the number of all lane components of the target emergency lane.

[0020] Optionally, the expression for the policy evaluation function is as follows:

[0021]

[0022] Where Y represents the evaluation score, TTS i (t,k) represents the vehicle travel time in the i-th spatial segment, where k represents the vehicle number, TET i (t,k) represents the vehicle collision exposure time in the i-th spatial segment, α tts and β tet All of these represent weighting coefficients.

[0023] Optionally, each spatiotemporal control strategy can be evaluated using a strategy evaluation function, including:

[0024] Perform the following steps for each of the multiple spatiotemporal control strategies:

[0025] The spatiotemporal control strategy is input into the SUMO simulation platform to obtain the index data of the spatiotemporal control strategy. The index data includes the vehicle passage time of each spatial segment and the vehicle collision exposure time of each spatial segment.

[0026] By using the strategy evaluation function and combining it with indicator data, the evaluation score of the spatiotemporal control strategy is obtained.

[0027] Optionally, a genetic algorithm can be used to perform crossover and mutation on the set of spatiotemporal control strategies to obtain intermediate control strategies, including:

[0028] Step 1: Based on the genetic algorithm, construct the parent generation control strategy population according to the set of spatiotemporal control strategies; wherein, the individuals in the parent generation control strategy population correspond one-to-one with the spatiotemporal control strategies in the set of spatiotemporal control strategies.

[0029] Step 2: Perform crossover mutation on the parent generation control strategy population to generate the intermediate generation control strategy population;

[0030] Step 3: If all individuals in the intermediate generation control strategy population satisfy the frequency conversion constraint and lane component constraint, then proceed to step 4; otherwise, use the intermediate generation control strategy population as the parent control strategy population in step 2 and return to step 2.

[0031] Step 4: If the intermediate generation control strategy population meets the preset accuracy requirements, then input the spatiotemporal control strategies corresponding to all individuals in the intermediate generation control strategy population into the SUMO simulation platform. Combined with the strategy evaluation function, obtain the evaluation score of the spatiotemporal control strategy corresponding to each individual in the population, and use the evaluation score as the fitness of that individual in the population; otherwise, use the spatiotemporal control strategies corresponding to all individuals in the intermediate generation control strategy population to train the Kriging surrogate model to obtain a new set of spatiotemporal control strategies. Input the new set of spatiotemporal control strategies into the SUMO simulation platform. Combined with the strategy evaluation function, obtain the fitness of each individual in the population.

[0032] Step 5: Based on the fitness of each individual in the population, and using the elite selection strategy, obtain a new intermediate generation control strategy population.

[0033] Step 6: If the new intermediate generation control strategy population meets the update termination condition, then the best population individual of the new intermediate generation control strategy population is used as the intermediate control strategy; otherwise, the new intermediate generation control strategy population is used as the parent generation control strategy population in step 2, and the process returns to step 2.

[0034] Optionally, before performing step 4, the emergency lane control method provided in this application also includes:

[0035] Count the number of times step 2 is executed, and use the number of executions as the update count;

[0036] Calculate the modulo result of the update count divided by integers. If the modulo result is zero, it is determined that the intermediate generation control strategy population meets the preset accuracy requirements; otherwise, it is determined that the intermediate generation control strategy population does not meet the preset accuracy requirements.

[0037] Optionally, before performing step 6, the emergency lane control method provided in this application also includes:

[0038] If the number of updates is greater than or equal to the preset maximum number of generations of the population, then the new intermediate generation control strategy population is determined to meet the update termination condition; otherwise, the new intermediate generation control strategy population is determined not to meet the update termination condition.

[0039] Optionally, the final control strategy may be determined from the initial control strategy and intermediate control strategies, including:

[0040] Based on the strategy evaluation function, calculate the evaluation score of the initial control strategy and the evaluation score of the intermediate control strategy respectively;

[0041] If the evaluation score of the initial control strategy is greater than or equal to the evaluation score of the intermediate control strategy, the initial control strategy will be used as the final control strategy; otherwise, the intermediate control strategy will be used as the final control strategy.

[0042] Secondly, embodiments of this application provide a terminal device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the above-described emergency lane control method.

[0043] Thirdly, embodiments of this application provide an emergency lane control system, including:

[0044] The spatial segmentation module is used to divide the target emergency lane into multiple spatial segments and set on / off status variables for each spatial segment; the on / off status variables include on and off.

[0045] The constraint construction module is used to construct the transformation frequency constraint and lane component constraint based on the switching state quantity of each spatial segment and the pre-set state transformation interval time.

[0046] The first control strategy module is used to randomly generate a set of spatiotemporal control strategies for the target emergency lane based on the conversion frequency constraint and the lane component constraint. The set of spatiotemporal control strategies includes multiple spatiotemporal control strategies, and any one of the multiple spatiotemporal control strategies includes the on / off state quantities of all spatial segments of the target emergency lane.

[0047] The evaluation module is used to construct a strategy evaluation function based on the vehicle passage time and the vehicle collision exposure time of each spatial segment; the vehicle collision exposure time represents the total time that a vehicle is in a critical situation during its journey.

[0048] The second control strategy module is used to evaluate each spatiotemporal control strategy using a strategy evaluation function, and to take the spatiotemporal control strategy with the highest evaluation score as the initial control strategy.

[0049] The third control strategy module is used to perform crossover and mutation on the spatiotemporal control strategy set using a genetic algorithm to obtain intermediate control strategies.

[0050] The control module is used to determine the final control strategy from the initial control strategy and intermediate control strategies, and to control the target emergency lane according to the final control strategy.

[0051] The above-mentioned solution in this application has the following beneficial effects:

[0052] In the embodiments of this application, the target emergency lane is divided into multiple spatial segments, and a switching state variable is set for each spatial segment. Then, based on the switching state variable of each spatial segment and the pre-set state transition interval, transition frequency constraints and lane component constraints are constructed. Then, based on the transition frequency constraints and lane component constraints, a set of spatiotemporal control strategies for the target emergency lane is generated. By combining time and space as two control variables, the control of the emergency lane can be made more reasonable, thereby improving the control effect of the emergency lane. By constructing a strategy evaluation function based on the vehicle passage time and vehicle collision exposure time of each spatial segment, the interaction between the efficiency and safety of the emergency lane control strategy is comprehensively considered, thereby improving the control effect.

[0053] Other beneficial effects of this application will be described in detail in the following detailed description section. Attached Figure Description

[0054] To more clearly illustrate the technical solutions in the embodiments of this application, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0055] Figure 1 A flowchart illustrating an emergency lane control method provided in an embodiment of this application;

[0056] Figure 2 A flowchart of a SUMO simulation provided in one embodiment of this application;

[0057] Figure 3 A schematic diagram illustrating the relationship between the steps of an emergency lane control method provided in an embodiment of this application;

[0058] Figure 4 This is a schematic diagram of the structure of a terminal device provided in an embodiment of this application;

[0059] Figure 5 This is a schematic diagram of the structure of an emergency lane control system provided in an embodiment of this application. Detailed Implementation

[0060] In the following description, specific details such as particular system architectures and techniques are set forth for illustrative purposes and not for limitation, in order to provide a thorough understanding of the embodiments of this application. However, those skilled in the art will understand that this application may also be implemented in other embodiments without these specific details. In other instances, detailed descriptions of well-known systems, apparatuses, circuits, and methods have been omitted so as not to obscure the description of this application with unnecessary detail.

[0061] It should be understood that, when used in this application specification and the appended claims, the term "comprising" indicates the presence of the described features, integrals, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components and / or a collection thereof.

[0062] It should also be understood that the term “and / or” as used in this application specification and the appended claims means any combination of one or more of the associated listed items and all possible combinations, and includes such combinations.

[0063] As used in this application specification and the appended claims, the term "if" may be interpreted, depending on the context, as "when," "once," "in response to determination," or "in response to detection." Similarly, the phrase "if determined" or "if detected [the described condition or event]" may be interpreted, depending on the context, as meaning "once determined," "in response to determination," "once detected [the described condition or event]," or "in response to detection [the described condition or event]."

[0064] Furthermore, in the description of this application and the appended claims, the terms "first," "second," "third," etc., are used only to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0065] References to "one embodiment" or "some embodiments" as described in this specification mean that one or more embodiments of this application include a specific feature, structure, or characteristic described in connection with that embodiment. Therefore, the phrases "in one embodiment," "in some embodiments," "in other embodiments," "in still other embodiments," etc., appearing in different parts of this specification do not necessarily refer to the same embodiment, but rather mean "one or more, but not all, embodiments," unless otherwise specifically emphasized. The terms "comprising," "including," "having," and variations thereof mean "including but not limited to," unless otherwise specifically emphasized.

[0066] To address the issue of unsatisfactory control effects of current emergency lane management methods, this application proposes an emergency lane management method and terminal device. The method divides the target emergency lane into multiple spatial segments and assigns an on / off state variable to each segment. Based on the on / off state variables of each segment and a pre-set state transition interval, transition frequency constraints and lane component constraints are constructed. Then, based on these constraints, a spatiotemporal control strategy set for the target emergency lane is generated. By combining time and space control variables, emergency lane management can be made more rational, thereby improving its effectiveness. Furthermore, by constructing a strategy evaluation function based on the vehicle passage time and collision exposure time of each spatial segment, the method comprehensively considers the interaction between efficiency and safety in emergency lane management strategies, thus enhancing the overall control effect.

[0067] like Figure 1 As shown, the emergency lane control method provided in this application includes the following steps:

[0068] Step 11: Divide the target emergency lane into multiple spatial segments and set a switch status for each spatial segment.

[0069] The aforementioned switch status variables include "on" and "off". Specifically, when the switch status variable is "on", it indicates that the emergency lane section corresponding to that spatial segment is open, and vehicles can travel on that emergency lane section; when the switch status variable is "off", it indicates that the emergency lane section corresponding to that spatial segment is closed, and vehicles cannot travel on that emergency lane section. In the embodiments of this application, by reasonably designing the switch status variables of each spatial segment, the emergency lane can be controlled, thereby effectively alleviating traffic pressure on highways.

[0070] For example, according to the preset length L i The target emergency lane is divided into spatial segments i of approximately equal length. In some embodiments of this application, L can be... iThe setting is between 300m and 400m. The corresponding on / off state variable for each spatial segment is E. i E i =[0,1]. E i =0 indicates that the switch state of spatial segment i is closed, E i =1 indicates that the switch state of spatial segment i is on.

[0071] Step 12: Based on the switching state variables of each spatial segment and the pre-set state transition interval, construct the transition frequency constraint and lane component constraint.

[0072] The aforementioned state transition interval can be set according to the road conditions of the highway. In some embodiments of this application, 15 minutes can be used as a state transition interval. It should be noted that within the same state transition interval, the switching state variables of each spatial segment remain unchanged.

[0073] Specifically, the expression for the transform frequency constraint constructed in step 12 is as follows:

[0074]

[0075] Where i represents the i-th spatial segment, L represents the total number of spatial segments, t represents the t-th state transition interval, and E i (t) represents the switching state quantity of the i-th spatial segment within the t-th state transition interval, E i =[0,1], E i =0 indicates that the space segment is closed, E i =1 indicates that the space segment is in the open state, N time This represents the number of times the switch state variables of all spatial segments change within any given state transition interval.

[0076] It is worth mentioning that the purpose of constructing the transformation frequency constraint is to limit the number of transitions (E) of the switching state variables in each spatial segment. i The process from 0 to 1 or from 1 to 0 is denoted as a single switch state transition. This transition should be controlled within a reasonable range to ensure driving safety.

[0077] The expression for the lane component constraint constructed in step 12 is as follows:

[0078]

[0079] Among them, E cc The lane component represents a spatial segment where both the switch states are active (on) within a state transition interval. N distance This indicates the number of all lane components of the target emergency lane.

[0080] It is worth mentioning that keeping the number of lane components within a reasonable range can also ensure driving safety.

[0081] Step 13: Based on the frequency conversion constraint and lane component constraint, randomly generate a set of spatiotemporal control strategies for the target emergency lane.

[0082] The aforementioned set of spatiotemporal control strategies includes multiple spatiotemporal control strategies, and any one of these strategies includes the on / off state of all spatial segments of the target emergency lane.

[0083] For example, statistical methods can be used to enumerate all combinations of spatial segment switching state variables that satisfy the frequency change constraint and lane component constraint. For ease of understanding, taking a target emergency lane divided into three spatial segments (i = 1, 2, 3) as an example, the combinations of all spatial segment switching state variables that satisfy the frequency change constraint and lane component constraint are: Spatiotemporal control strategy 1 = {E1 = 0, E2 = 0, E3 = 0}, Spatiotemporal control strategy 2 = {E1 = 1, E2 = 0, E3 = 0}, Spatiotemporal control strategy 3 = {E1 = 0, E2 = 1, E3 = 0}, Spatiotemporal control strategy 4 = {E1 = 0, E2 = 0, E3 = 1}, Spatiotemporal control strategy 5 = {E1 = 1, E2 = 1, E3 = 0}, Spatiotemporal control strategy 6 = {E1 = 1, E2 = 0, E3 = 1}, Spatiotemporal control strategy 7 = {E1 = 0, E2 = 1, E3 = 1}. The corresponding set of spatiotemporal control strategies is {spatiotemporal control strategy 1, spatiotemporal control strategy 2, spatiotemporal control strategy 3, spatiotemporal control strategy 5, spatiotemporal control strategy 6, spatiotemporal control strategy 7}.

[0084] Step 14: Construct a strategy evaluation function based on the vehicle passage time and vehicle collision exposure time of each spatial segment.

[0085] The aforementioned vehicle collision exposure time (Time Exposed Time-to-collision) represents the total time a vehicle spends in a critical situation (such as brake failure or rear-end collision) while driving. It is an indicator of safety between vehicles. The total time a vehicle spends in a critical situation while driving is usually represented by the total time below the collision time threshold.

[0086] Specifically, the expression for the constructed policy evaluation function is as follows:

[0087]

[0088] Where Y represents the evaluation score, TTS i (t,k) represents the vehicle travel time in the i-th spatial segment, where k represents the vehicle number, TET i(t,k) represents the vehicle collision exposure time in the i-th spatial segment, α tts and β tet All of these represent weighting coefficients.

[0089] It should be noted that the vehicle passage time and vehicle collision exposure time mentioned above can be obtained by inputting the spatiotemporal control strategy into the urban traffic simulation (SUMO, Simulation of Urban Mobility, an open-source, highly portable, microscopic and continuous traffic simulation software package designed to handle large networks) through the Python (a programming language) interface.

[0090] like Figure 2 As shown in the embodiments of this application, the processing procedure of the SUMO simulation platform is as follows:

[0091] In the first stage, the real road network is marked and drawn in SUMO software, and its size is set according to a larger scale.

[0092] In the second phase, the main lane width was 3.75m and the emergency lane width was 3.5m. Based on actual traffic flow data, the experimental data categorized vehicles into three types: small cars, medium cars, and large cars, with each type accounting for 0.75%, 0.125%, and 0.125% respectively. Considering the psychological and physiological characteristics of drivers, Widemann 99 (a car-following model describing the interaction between adjacent vehicles in a convoy traveling on a one-way street with overtaking restrictions) and the LC2013 model (SUMO lane-changing model) were selected as the car-following and lane-changing models.

[0093] In the third stage, traffic flow data collected every 15 minutes from highway gantry was used to set up vehicle flow data and to calibrate the simulation model.

[0094] In the fourth stage, simulations are conducted, and traffic flow data (including vehicle travel time and vehicle collision exposure time) is acquired in real time through the Python programming interface traci.

[0095] Step 15: Use the strategy evaluation function to evaluate each spatiotemporal control strategy, and take the spatiotemporal control strategy with the highest evaluation score as the initial control strategy.

[0096] In some embodiments of this application, strategy evaluation mainly includes the following stages:

[0097] In the first phase, real-time monitoring data obtained using SUMO simulation software was used to establish highway traffic efficiency evaluation indicators. Statistical analysis was conducted on real-time lane traffic flow, waiting time, and vehicle energy consumption to calculate efficiency index values.

[0098] The second phase involves constructing highway driving safety evaluation indicators, incorporating collision time, collision exposure time, number of accidents, and number of emergency stops into the system. Driving safety indicator values ​​are calculated based on real-time monitoring data from SUMO simulation software.

[0099] In the third stage, based on the traffic efficiency and driving safety index values ​​constructed in the first two stages, the evaluation results of the opening strategy are calculated.

[0100] In step 15 above, the spatiotemporal control strategy with the highest evaluation score is used as the initial control strategy. This is because it is considered that a better control strategy may be obtained by using a genetic algorithm later. The initial control strategy can be used as a criterion for judging a better control strategy.

[0101] Step 16: Use a genetic algorithm to perform crossover and mutation on the set of spatiotemporal control strategies to obtain intermediate control strategies.

[0102] Step 17: Determine the final control strategy from the initial control strategy and intermediate control strategies, and control the target emergency lane according to the final control strategy.

[0103] The following is an illustrative example of the specific process of evaluating each spatiotemporal control strategy using the strategy evaluation function in step 15 (evaluating each spatiotemporal control strategy using the strategy evaluation function and taking the spatiotemporal control strategy with the highest evaluation score as the initial control strategy).

[0104] Perform the following steps for each of the multiple spatiotemporal control strategies:

[0105] Step 15.1: Input the spatiotemporal control strategy into the SUMO simulation platform to obtain the index data of the spatiotemporal control strategy.

[0106] The aforementioned data includes vehicle passage time for each spatial segment under the spatiotemporal control strategy, as well as vehicle collision exposure time for each spatial segment.

[0107] Step 15.2: Using the strategy evaluation function and combining the indicator data, obtain the evaluation score of the spatiotemporal control strategy.

[0108] The following is an illustrative example of the specific process of step 16 (using a genetic algorithm to perform crossover and mutation on the set of spatiotemporal control strategies to obtain intermediate control strategies).

[0109] Step 16.1: Based on the genetic algorithm, construct the parent generation control strategy population according to the set of spatiotemporal control strategies.

[0110] Among them, the individuals in the parent generation control strategy population correspond one-to-one with the spatiotemporal control strategies in the spatiotemporal control strategy set.

[0111] For example, in step 16.1.1, the maximum population size is set to 50, the maximum number of generations is set to 1000, the crossover rate is 0.9, and the mutation probability is 0.1.

[0112] Step 16.1.2: Construct the parent generation control strategy population based on the spatiotemporal control strategy set.

[0113] Step 16.2: Perform crossover mutation on the parent generation control strategy population to generate the intermediate generation control strategy population.

[0114] Step 16.3: If all individuals in the intermediate generation control strategy population satisfy the frequency conversion constraint and lane component constraint, then proceed to step 16.4; otherwise, use the intermediate generation control strategy population as the parent generation control strategy population in step 16.2 and return to step 16.2.

[0115] Step 16.4: If the intermediate generation control strategy population meets the preset accuracy requirements, then input the spatiotemporal control strategies corresponding to all individuals in the intermediate generation control strategy population into the SUMO simulation platform. Combined with the strategy evaluation function, obtain the evaluation score of the spatiotemporal control strategy corresponding to each individual in the population, and use the evaluation score as the fitness of that individual in the population. Otherwise, use the spatiotemporal control strategies corresponding to all individuals in the intermediate generation control strategy population to train the Kriging surrogate model (a high-precision interpolation response surface model that uses stochastic processes to represent the functional relationship between design variables and response variables) to obtain a new set of spatiotemporal control strategies. Input the new set of spatiotemporal control strategies into the SUMO simulation platform. Combined with the strategy evaluation function, obtain the fitness of each individual in the population.

[0116] Before proceeding to step 16.4, the following steps must be performed:

[0117] Step a: Count the number of times step 16.2 is executed, and use the number of executions as the update count.

[0118] Step b: Calculate the modulo result of the update count divided by integers 10. If the modulo result is zero, it is determined that the intermediate generation control strategy population meets the preset accuracy requirements; otherwise, it is determined that the intermediate generation control strategy population does not meet the preset accuracy requirements.

[0119] It should be noted that performing the above steps (steps a and b) can avoid the situation where the genetic algorithm has insufficient update iterations, resulting in severe data dispersion.

[0120] Step 16.5: Based on the fitness of each individual in the population, a new intermediate generation control strategy population is obtained based on the elite selection strategy.

[0121] The elite selection strategy (maintain the best solution found over time before selection, directly copying the best individual found in the population so far during the evolutionary process (called the elite individual) directly to the next generation without pairing or crossover) avoids the loss and destruction of the solution by selection, crossover and mutation operations.

[0122] Step 16.6: If the new intermediate generation control strategy population meets the update termination condition, then the best population individual of the new intermediate generation control strategy population is used as the intermediate control strategy; otherwise, the new intermediate generation control strategy population is used as the parent generation control strategy population in step 16.2, and the process returns to step 16.2.

[0123] Before proceeding to step 16.6, the following steps must be performed:

[0124] If the number of updates is greater than or equal to the preset maximum number of generations of the population, then the new intermediate generation control strategy population is determined to meet the update termination condition; otherwise, the new intermediate generation control strategy population is determined not to meet the update termination condition.

[0125] The following is an illustrative description of the specific process of determining the final control strategy from the initial control strategy and intermediate control strategies in step 17 (determining the final control strategy from the initial control strategy and intermediate control strategies, and controlling the target emergency lane according to the final control strategy).

[0126] Step 17.1: Calculate the evaluation score of the initial control strategy and the evaluation score of the intermediate control strategy according to the strategy evaluation function.

[0127] Step 17.2: If the evaluation score of the initial control strategy is greater than or equal to the evaluation score of the intermediate control strategy, then the initial control strategy shall be adopted as the final control strategy; otherwise, the intermediate control strategy shall be adopted as the final control strategy.

[0128] The emergency lane control method provided in this application will be illustrated below with reference to specific embodiments.

[0129] like Figure 3 As shown, firstly, the control strategy is spatiotemporally discretized and modeled based on the characteristics of emergency lane control on highways, and spatiotemporal constraints are designed. Then, an optimization method with a genetic algorithm as the core of the solution search is constructed using the Kriging surrogate model, and a simulation platform is built using SUMO simulation software to find the optimal solution. In practical applications, the optimized strategy can be recorded, and the optimal opening strategy can be matched based on traffic flow data from the real-time highway traffic monitor. Then, the emergency lane section of the highway can be opened in a timely manner when traffic congestion needs to be alleviated.

[0130] As can be seen from the above steps, the emergency lane control method provided in this application divides the target emergency lane into multiple spatial segments and sets on / off state variables for each spatial segment. Then, based on the on / off state variables of each spatial segment and the pre-set state transition interval, it constructs transition frequency constraints and lane component constraints. Finally, based on the transition frequency constraints and lane component constraints, it generates a set of spatiotemporal control strategies for the target emergency lane. By combining time and space as control variables, it can make emergency lane control more reasonable, thereby improving the control effect of emergency lanes. By constructing a strategy evaluation function based on the vehicle passage time and vehicle collision exposure time of each spatial segment, it comprehensively considers the interaction between the efficiency and safety of the emergency lane control strategy, thereby improving the control effect.

[0131] like Figure 4 As shown, embodiments of this application provide a terminal device, such as... Figure 4 As shown, the terminal device D10 of this embodiment includes: at least one processor D100 ( Figure 4 The diagram shows only one processor, a memory D101, and a computer program D102 stored in the memory D101 and executable on the at least one processor D100, wherein the processor D100 executes the computer program D102 to implement the steps in any of the above method embodiments.

[0132] Specifically, when the processor D100 executes the computer program D102, it divides the target emergency lane into multiple spatial segments and sets on / off state variables for each spatial segment. Then, based on the on / off state variables of each spatial segment and the pre-set state transition interval, it constructs transition frequency constraints and lane component constraints. Then, based on the transition frequency constraints and lane component constraints, it randomly generates a set of spatiotemporal control strategies for the target emergency lane. Subsequently, based on the vehicle passage time and vehicle collision exposure time of each spatial segment, it constructs a strategy evaluation function. Then, it uses the strategy evaluation function to evaluate each spatiotemporal control strategy and uses the spatiotemporal control strategy with the highest evaluation score as the initial control strategy. Then, it uses a genetic algorithm to perform crossover mutation on the set of spatiotemporal control strategies to obtain intermediate control strategies. Finally, it determines the final control strategy from the initial control strategy and intermediate control strategies and controls the target emergency lane according to the final control strategy. Specifically, by dividing the target emergency lane into multiple spatial segments and assigning on / off state variables to each segment, and then constructing transition frequency constraints and lane component constraints based on the on / off state variables of each spatial segment and the pre-set state transition interval, a spatiotemporal control strategy set for the target emergency lane is generated. This combination of time and space control variables makes emergency lane control more rational, thereby improving the control effect. Furthermore, by constructing a strategy evaluation function based on the vehicle passage time and vehicle collision exposure time of each spatial segment, the interaction between the efficiency and safety of the emergency lane control strategy is comprehensively considered, thereby improving the control effect.

[0133] The processor D100 can be a central processing unit (CPU), or it can be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor can be a microprocessor or any conventional processor.

[0134] In some embodiments, the memory D101 may be an internal storage unit of the terminal device D10, such as a hard disk or memory of the terminal device D10. In other embodiments, the memory D101 may be an external storage device of the terminal device D10, such as a plug-in hard disk, smart media card (SMC), secure digital card (SD), flash card, etc., equipped on the terminal device D10. Furthermore, the memory D101 may include both internal and external storage units of the terminal device D10. The memory D101 is used to store the operating system, applications, bootloader, data, and other programs, such as the program code of the computer program. The memory D101 can also be used to temporarily store data that has been output or will be output.

[0135] The following is an exemplary description of an emergency lane control system provided in this application.

[0136] like Figure 5 As shown, the emergency lane control system 500 includes:

[0137] The spatial segmentation module 501 is used to divide the target emergency lane into multiple spatial segments and set a switch status variable for each spatial segment; the switch status variable includes on and off.

[0138] The constraint construction module 502 is used to construct the transformation frequency constraint and lane component constraint based on the switching state quantity of each spatial segment and the preset state transformation interval time.

[0139] The first control strategy module 503 is used to randomly generate a set of spatiotemporal control strategies for the target emergency lane based on the conversion frequency constraint and the lane component constraint. The set of spatiotemporal control strategies includes multiple spatiotemporal control strategies, and any one of the multiple spatiotemporal control strategies includes the on / off state quantities of all spatial segments of the target emergency lane.

[0140] Evaluation module 504 is used to construct a strategy evaluation function based on the vehicle passage time and the vehicle collision exposure time of each spatial segment; the vehicle collision exposure time represents the total time that a vehicle is in a critical situation during its journey.

[0141] The second control strategy module 505 is used to evaluate each spatiotemporal control strategy using a strategy evaluation function, and to take the spatiotemporal control strategy with the highest evaluation score as the initial control strategy.

[0142] The third control strategy module 506 is used to perform crossover mutation on the spatiotemporal control strategy set using a genetic algorithm to obtain an intermediate control strategy.

[0143] The control module 507 is used to determine the final control strategy from the initial control strategy and intermediate control strategies, and to control the target emergency lane according to the final control strategy.

[0144] It should be noted that the information interaction and execution process between the above modules / units are based on the same concept as the method embodiments of this application. For details on their specific functions and technical effects, please refer to the method embodiments section, and they will not be repeated here.

[0145] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional units and modules is merely an example. In practical applications, the above functions can be assigned to different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiments can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit. Furthermore, the specific names of the functional units and modules are only for easy differentiation and are not intended to limit the scope of protection of this application. The specific working process of the units and modules in the above system can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0146] The advantages of the emergency lane control method provided in this application are as follows: an emergency lane control strategy and strategy constraints are designed, optimization objectives based on both efficiency and safety are proposed, a SUMO simulation analysis platform is built, a strategy evaluation system is constructed, and finally, the genetic algorithm of the Kriging surrogate model is used to solve the optimization strategy. It can be effectively applied to the actual emergency lane control of highways and has certain engineering application value.

[0147] The above description is the preferred embodiment of this application. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principles described in this application, and these improvements and modifications should also be considered within the scope of protection of this application.

Claims

1. A method for controlling emergency lanes, characterized in that, include: The target emergency lane is divided into multiple spatial segments, and a switch status variable is set for each spatial segment; the switch status variable includes on and off. Based on the switching state variables of each spatial segment and the pre-set state transition interval, construct the transition frequency constraint and lane component constraint. Based on the transformation frequency constraint and the lane component constraint, a spatiotemporal control strategy set for the target emergency lane is randomly generated; the spatiotemporal control strategy set includes multiple spatiotemporal control strategies, and any one of the multiple spatiotemporal control strategies includes the on / off state quantities of all spatial segments of the target emergency lane. A strategy evaluation function is constructed based on the vehicle passage time and the vehicle collision exposure time of each spatial segment; the vehicle collision exposure time represents the total time that a vehicle is in a critical situation during its journey. The strategy evaluation function is used to evaluate each spatiotemporal control strategy, and the spatiotemporal control strategy with the highest evaluation score is used as the initial control strategy. The spatiotemporal control strategy set is crossover and mutation is performed using a genetic algorithm to obtain an intermediate control strategy. The final control strategy is determined from the initial control strategy and the intermediate control strategy, and the target emergency lane is controlled according to the final control strategy.

2. The method according to claim 1, characterized in that, The expression for the frequency transformation constraint is as follows: Where i represents the i-th spatial segment, L represents the total number of spatial segments, t represents the t-th state transition interval, and E i (t) represents the switching state quantity of the i-th spatial segment within the t-th state transition interval, E i =[0,1], E i =0 indicates that the space segment is closed, E i =1 indicates that the space segment is in the open state, N time This represents the number of times the switch state variables of all spatial segments change within any given state transition interval.

3. The method according to claim 2, characterized in that, The expression for the lane component constraint is as follows: Among them, E cc The term N represents a lane component, where the switching state is always "on" within a state transition interval. distance This indicates the number of all lane components of the target emergency lane.

4. The method according to claim 3, characterized in that, The expression for the strategy evaluation function is as follows: Where Y represents the evaluation score, TTS i (t,k) represents the vehicle travel time in the i-th spatial segment, where k represents the vehicle number, TET i (t,k) represents the vehicle collision exposure time in the i-th spatial segment, α tts and β tet All of these represent weighting coefficients.

5. The method according to claim 4, characterized in that, The evaluation of each spatiotemporal control strategy using the strategy evaluation function includes: For each of the multiple spatiotemporal control strategies, perform the following steps: The spatiotemporal control strategy is input into the SUMO simulation platform to obtain the index data of the spatiotemporal control strategy; the index data includes the vehicle passage time of each spatial segment of the spatiotemporal control strategy and the vehicle collision exposure time of each spatial segment. The evaluation score of the spatiotemporal control strategy is obtained by using the strategy evaluation function and combining it with the indicator data.

6. The method according to claim 5, characterized in that, The step of using a genetic algorithm to perform crossover and mutation on the set of spatiotemporal control strategies to obtain intermediate control strategies includes: Step 1: Based on the genetic algorithm, construct a parent generation control strategy population according to the set of spatiotemporal control strategies; wherein, the individuals in the parent generation control strategy population correspond one-to-one with the spatiotemporal control strategies in the set of spatiotemporal control strategies. Step 2: Perform crossover mutation on the parent generation control strategy population to generate the intermediate generation control strategy population; Step 3: If all individuals in the intermediate generation control strategy population satisfy the change frequency constraint and the lane component constraint, then proceed to step 4; otherwise, use the intermediate generation control strategy population as the parent generation control strategy population in step 2, and return to step 2. Step 4: If the intermediate generation control strategy population meets the preset accuracy requirements, then the spatiotemporal control strategies corresponding to all individuals in the intermediate generation control strategy population are input into the SUMO simulation platform. Combined with the strategy evaluation function, the evaluation score of the spatiotemporal control strategy corresponding to each individual is obtained, and the evaluation score is used as the fitness of that individual. Otherwise, the Kriging surrogate model is trained using the spatiotemporal control strategies corresponding to all individuals in the intermediate generation control strategy population to obtain a new set of spatiotemporal control strategies. The new set of spatiotemporal control strategies is then input into the SUMO simulation platform, and combined with the strategy evaluation function, the fitness of each individual is obtained. Step 5: Based on the fitness of each individual in the population, and using the elite selection strategy, obtain a new intermediate generation control strategy population. Step 6: If the new intermediate generation control strategy population meets the update termination condition, then the optimal population individual of the new intermediate generation control strategy population is taken as the intermediate control strategy; otherwise, the new intermediate generation control strategy population is taken as the parent generation control strategy population in step 2, and the process returns to step 2.

7. The method according to claim 6, characterized in that, Before performing step 4, the method further includes: The number of times step 2 is executed is counted, and the number of executions is used as the update count; Calculate the modulo result of the update count divided by integers. If the modulo result is zero, it is determined that the intermediate generation control strategy population meets the preset accuracy requirements; otherwise, it is determined that the intermediate generation control strategy population does not meet the preset accuracy requirements.

8. The method according to claim 7, characterized in that, Before performing step 6, the method further includes: If the number of updates is greater than or equal to the preset maximum number of generations of the population, then the new intermediate generation control strategy population is determined to meet the update termination condition; otherwise, the new intermediate generation control strategy population is determined not to meet the update termination condition.

9. The method according to claim 8, characterized in that, Determining the final control strategy from the initial control strategy and the intermediate control strategies includes: Based on the strategy evaluation function, calculate the evaluation score of the initial control strategy and the evaluation score of the intermediate control strategy respectively; If the evaluation score of the initial control strategy is greater than or equal to the evaluation score of the intermediate control strategy, then the initial control strategy is adopted as the final control strategy; otherwise, the intermediate control strategy is adopted as the final control strategy.

10. A terminal device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the emergency lane control method as described in any one of claims 1 to 9.

Images