A vehicle following control system based on the action of the leading vehicle in an intelligent network environment

Abstract

The present invention belongs to the field of road vehicle control, and relates to a vehicle following control system based on the action of a leading vehicle in an intelligent network environment, wherein the control system comprises an information detection module, a model building module, a parameter calibration module, and a vehicle control module; the information detection module is used to obtain the speed information and position information of the vehicle and the leading vehicle; the model building module is used to establish a following model by using the action of the leading vehicle on the trailing vehicle; the parameter calibration module is used to calibrate the coefficients in the following model by using actual road data and an improved bat algorithm; the vehicle control module is used to control the motion state of the trailing vehicle according to the speed information and position information of the leading vehicle and the vehicle detected by the information detection module, and the acceleration of the trailing vehicle at the next moment obtained based on the following model after parameter calibration. The system enables the trailing vehicle to quickly respond to the change in the motion state of the leading vehicle, predict the following speed of the trailing vehicle, and improve traffic safety and efficiency.

Description

Technical Field

[0001] The present invention belongs to the field of road vehicle control, and relates to a vehicle driving control system in an intelligent network environment, and specifically to a vehicle following control system based on the action of a leading vehicle in an intelligent network environment. Background Art

[0002] The car-following model is a model used to simulate and analyze vehicle behavior in traffic flow. It is mainly used to describe how a vehicle follows the vehicle in front and adjusts its speed and position. In order to explore the mechanism of vehicle operation under microscopic conditions and improve the stability of vehicle traffic, the study of the car-following model is of great significance.

[0003] Traditional car-following models mainly compare car-following behavior with historical car-following data to predict the operating status of the following vehicle. This method has the following disadvantages and shortcomings: (1) It ignores dynamic factors and cannot respond to sudden acceleration or deceleration of the leading vehicle in a timely manner; (2) It lacks real-time adaptability. When traffic conditions change, the model cannot be adjusted quickly, resulting in inaccurate predictions; (3) It cannot handle unexpected events and cannot respond promptly to unexpected events such as emergency braking or traffic accidents; (4) It is limited to known data. The model based on historical data cannot effectively respond to emerging driving patterns or changes in traffic regulations.

[0004] In an intelligent network environment, real-time information of surrounding vehicles can be quickly obtained, and the following vehicle can receive acceleration and deceleration information from the front and surrounding vehicles in real time, which not only improves the perception and decision-making capabilities, but also provides a basis for the vehicle's intelligent decision-making. Therefore, it is necessary to provide a control system that can perform vehicle following based on the real-time received data. Summary of the invention

[0005] In view of the above-mentioned technical problems and defects, the purpose of the present invention is to provide a vehicle following control system based on the action of the leading vehicle in an intelligent network environment. The control system can enable the following vehicle to respond quickly according to the changes in the motion state of the leading vehicle, predict the following speed of the following vehicle, improve traffic safety and efficiency, and provide technical support for the development of intelligent transportation systems.

[0006] To achieve the above object, the present invention adopts the following technical solution:

[0007] A vehicle following control system based on the action of a preceding vehicle in an intelligent network environment, comprising an information detection module, a model building module, a parameter calibration module, and a vehicle control module;

[0008] Wherein, the information detection module is used to obtain the speed information and position information of the rear vehicle and the front vehicle;

[0009] The model building module is used to establish a car-following model by using the effect of the leading vehicle on the following vehicle; the effect of the leading vehicle on the following vehicle is used to indicate that the following vehicle is affected by the speed of the leading vehicle and the distance between the leading and following vehicles during the driving process;

[0010] When the intelligent connected vehicle is driving, the following vehicle detects the speed and position information of the following vehicle and the leading vehicle. The following vehicle has an expected following distance during driving. At this time, the leading vehicle has the following effects on the following vehicle:

[0011] ;

[0012] ;

[0013] Where: is the effect of the front vehicle on the rear vehicle, is the current speed of the preceding vehicle, is the current speed of the following vehicle, is the weight coefficient of the distance term, is the current position of the preceding vehicle, is the current position of the following vehicle, is the expected following distance of the following vehicle, is the speed of the following vehicle, and is the coefficient, which is determined by fitting the position information of the front and rear vehicles and the speed information of the rear vehicle in a stable following car on the road, and t is the current time;

[0014] The following model is used to represent the reaction of the rear vehicle to the front vehicle, that is, the acceleration of the rear vehicle at the next moment. The expression of the following model is:

[0015] ;

[0016] ;

[0017] Where: is the acceleration of the following vehicle at the next moment, is the time coefficient, is the sensitivity coefficient, is the theoretical speed of the following vehicle at the next moment, is the coefficient to be determined, is the effect of the front vehicle on the rear vehicle, is the current speed of the following vehicle, is the acceleration of the following vehicle at the current moment;

[0018] The parameter calibration module is used to calibrate the parameters in the car-following model using actual road data and an improved bat algorithm. , , , The coefficients are calibrated;

[0019] The vehicle control module is used to control the motion state of the rear vehicle according to the speed information and position information of the front vehicle and the rear vehicle detected by the information detection module, and the acceleration of the rear vehicle at the next moment obtained based on the following model after parameter calibration.

[0020] As a preferred embodiment of the present invention, the control system further comprises a database, and the data collected in real time by the information detection module and the data calculated in real time by the car-following model are stored in the database.

[0021] As a preferred embodiment of the present invention, the information detection module includes a vehicle-mounted sensor and a networked device; wherein the vehicle-mounted sensor is used to obtain speed information of the rear vehicle and the front vehicle; the networked device is used to obtain position information of the rear vehicle and the front vehicle, including the position of the front vehicle, the position of the rear vehicle and the distance between the front and rear vehicles.

[0022] As a preferred embodiment of the present invention, the actual road data is obtained by on-site recording by a drone, and a data set is formed by collecting the status information of vehicles on the lane on the actual road, and the data set includes the front vehicle speed, the front vehicle acceleration, the rear vehicle speed, the rear vehicle acceleration, and the position information of the front and rear vehicles; the front and rear vehicles that are stably following are screened out from the data set to form sample vehicle data; then, parameter fitting is performed on the rear vehicle speed of the sample vehicle and the position information of the front and rear vehicles, so as to determine the expected distance of the rear vehicle Parameters k and b in ; where k=1.04 and b=2.61.

[0023] As a preferred embodiment of the present invention, the parameter calibration module uses sample vehicle data and utilizes an improved bat algorithm to calibrate the parameters in the car-following model. , , , The parameters are calibrated, the specific steps are as follows:

[0024] Initialization parameters: Determine the number of bats ; Set the dimension of the search space ; Set the minimum frequency and maximum frequency , sound loudness and pulse rate ;

[0025] Initialize the bat's position and speed: Randomly generate the initial position and speed of each bat;

[0026] The initial position is: ;

[0027] The initial velocity is: , ;

[0028] in, Indicates Bat The value of Indicates Bat The value of Indicates Bat The value of Indicates Bat The value of Indicates Bat The speed of change; Indicates Bat The speed of change; Shidi Bat The speed of change; Indicates Bat's The speed of change;

[0029] Evaluate fitness: Calculate the fitness value of each bat based on the mean square error;

[0030] ;

[0031] in, For fitness, is the actual acceleration of the following vehicle in the actual data set, To use i The predicted acceleration is calculated by calculating the parameters corresponding to the bats. is the number of sample vehicles in the actual road dataset;

[0032] The top 5% of individuals are selected as parents according to fitness, and the selected parents are crossovered; at the same time, all parent individuals are mutated with a probability of 1%; then the individuals with the worst fitness in the parent are replaced with the newly generated offspring individuals after crossover mutation, thus generating a new population;

[0033] For each bat in the new population, generate a new frequency , and then update the bat's position according to the frequency. The update rule is:

[0034] ;

[0035] ;

[0036] ;

[0037] in, is a random vector, is the number of iterations, is the global optimal solution in the current group, It is The number of bat iterations is The moving speed at It is The number of bat iterations is The moving speed at It is The number of bat iterations is The position at the time; It is The number of bat iterations is The position at the time;

[0038] Calculate the fitness of the new position and compare it with the previous fitness value; if the fitness value of the new solution is better, update the optimal solution location;

[0039] Generate a new local solution by any flight and generate a random number , yes A random number on ; if , then the expression of the generated local new solution is;

[0040] ;

[0041] in, is a random number; is the global optimal solution, It is a newly generated local new solution;

[0042] Generate a random number , yes A random number on ; if , then accept the generated local new solution and update the sound loudness and pulse rate. The update rule is:

[0043] ;

[0044] ;

[0045] in, and is a constant, Take 0.9, Take 0.6; Represents the number of iterations Loudness The value of Represents the number of iterations Loudness The value of Represents the number of iterations Pulse rate The value of

[0046] Repeat the above steps. When the maximum number of iterations is reached or the convergence condition is met, the global optimal solution and its fitness value are output.

[0047] As a preferred embodiment of the present invention, the specific steps of performing a crossover operation on the selected parent generation are: selecting two individuals in the parent generation, and the parent generation has a total of , , , Select one to three gene loci from four gene loci, exchange the values ​​of the gene loci of two parent individuals, and generate new offspring individuals.

[0048] As a preferred embodiment of the present invention, the specific steps of performing mutation operation on all parent individuals with a probability of 1% are: randomly selecting individuals and their gene loci in the population, randomly mutating the selected genes, changing their values, and thus generating new offspring individuals.

[0049] As a further preferred embodiment of the present invention, in the following car model The value is 0.05. The value is 1. The value is 0.22. The value is 0.16.

[0050] The advantages and beneficial effects of the present invention are:

[0051] (1) The present invention takes into account that in an intelligent network environment, a following vehicle can obtain information such as the speed, position and acceleration of the leading vehicle in real time, and proposes a vehicle following control system based on the action of the leading vehicle in an intelligent network environment. The control system is based on the speed information and position information of the leading vehicle, and combines it with the current speed and acceleration of the following vehicle to form a vehicle following model based on the action of the leading vehicle. The following model obtains the motion state of the leading vehicle in real time and adjusts the speed and acceleration of the vehicle itself according to the acquired information, thereby achieving more precise following control.

[0052] (2) The control system provided by the present invention can enable the following vehicle to respond quickly to the state changes of the leading vehicle, and predict the acceleration of the following vehicle at the next moment based on the self-designed following model. The following vehicle can be controlled through more accurate vehicle behavior prediction, thereby improving driving safety and facilitating the realization of a higher level of autonomous driving function.

[0053] (3) The control system provided by the present invention controls the following vehicle based on real-time data. This control method is highly adaptable and can adapt to different traffic conditions. It can also respond to unexpected events in a timely manner to avoid traffic accidents and ensure the safety of the vehicle and the stability of the road.

[0054] (4) The present invention uses an improved bat algorithm to calculate various parameters in the car-following model. The improved bat algorithm performs crossover and mutation operations after obtaining the parent individuals. The population diversity is increased through crossover and mutation, the search range is expanded while the exploration capability is improved, and high-quality solutions are retained, thereby increasing the convergence speed, obtaining the global optimal solution more quickly, and avoiding falling into the local optimum, so that the final car-following model can more accurately predict vehicle behavior. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] Figure 1 It is a structural block diagram of a vehicle following control system based on the action of a preceding vehicle in an intelligent network environment of the present invention;

[0056] Figure 2 It is a graph showing the relationship between the speed of the following vehicle and the expected distance. DETAILED DESCRIPTION

[0057] In order to enable those skilled in the art to better understand the technical solution and advantages of the present invention, the present application is described in detail below in conjunction with the accompanying drawings, but it is not intended to limit the protection scope of the present invention.

[0058] Figure 1 The present invention provides a logic block diagram of a vehicle following control system based on the action of the preceding vehicle in an intelligent network environment, such as Figure 1 As shown, a vehicle following control system based on the action of a preceding vehicle in an intelligent network environment provided by this embodiment includes: an information detection module, a model building module, a parameter calibration module and a vehicle control module;

[0059] Wherein, the information detection module is used to obtain the speed information and position information of the rear vehicle and the front vehicle;

[0060] The model building module is used to establish a car-following model by utilizing the effect of the leading vehicle on the following vehicle;

[0061] The effect of the leading vehicle on the following vehicle is used to indicate the influence of the following vehicle on the speed of the leading vehicle and the distance between the leading and following vehicles during the driving process;

[0062] When the intelligent connected vehicle is driving, the following vehicle detects the speed and position information of the following vehicle and the leading vehicle. The following vehicle has an expected following distance during driving. At this time, the leading vehicle has the following effects on the following vehicle:

[0063] ;

[0064] ;

[0065] Where: is the effect of the front vehicle on the rear vehicle, is the current speed of the preceding vehicle, is the current speed of the following vehicle, is the weight coefficient of the distance term, is the current position of the preceding vehicle, is the current position of the following vehicle, is the expected following distance of the following vehicle, is the speed of the following vehicle, and is the coefficient, which is determined by fitting the position information of the front and rear vehicles and the speed information of the rear vehicle in a stable following car on the road, and t is the current time;

[0066] The following model is used to represent the reaction of the rear vehicle to the front vehicle, that is, the acceleration of the rear vehicle at the next moment. The expression of the following model is:

[0067] ;

[0068] ;

[0069] Where: is the acceleration of the following vehicle at the next moment, is the time coefficient, is the sensitivity coefficient, is the theoretical speed of the following vehicle at the next moment, is the coefficient to be determined, is the effect of the front vehicle on the rear vehicle, is the current speed of the following vehicle, is the acceleration of the following vehicle at the current moment;

[0070] The parameter calibration module is used to calibrate the parameters in the car-following model using actual road data and an improved bat algorithm. , , , The coefficients are calibrated;

[0071] The vehicle control module is used to control the motion state of the rear vehicle according to the speed information and position information of the front vehicle and the rear vehicle detected by the information detection module, and the acceleration of the rear vehicle at the next moment obtained based on the following model after parameter calibration.

[0072] In this embodiment, the control system also includes a database, and the data collected in real time by the information detection module and the data calculated in real time by the following model are stored in the database. By updating the data in the database, the actual following data is continuously saved, thereby continuously increasing the following behavior under various traffic conditions. In this way, when encountering emergencies, a reasonable following method can be found from similar following scenarios in the database, which is conducive to dealing with emergencies and real-time changes in traffic conditions.

[0073] Furthermore, in this embodiment, the information detection module includes a vehicle-mounted sensor and a network-connected device; wherein the vehicle-mounted sensor is used to obtain speed information of the rear vehicle and the front vehicle; the network-connected device is used to obtain position information of the rear vehicle and the front vehicle, including the position of the front vehicle, the position of the rear vehicle, and the distance between the front and rear vehicles.

[0074] In this embodiment, actual road data and an improved bat algorithm are used to calibrate parameters of the following model; the actual road data is obtained by on-site recording by a drone, and a data set is formed by collecting status information of vehicles on lanes on actual roads, and the data set includes the front vehicle speed, the front vehicle acceleration, the rear vehicle speed, the rear vehicle acceleration, and the position information of the front and rear vehicles; the front and rear vehicles that are stably following are screened out from the data set, and data noise reduction processing is performed.

[0075] Specifically, the steps of data collection are as follows:

[0076] A drone is used to record videos on actual roads, and then the motion trajectories of the front and rear vehicles in the videos are extracted. All the extracted pairs of vehicles are used as the following data set. Among them, the front and rear vehicles that become samples of the following data set need to meet the following conditions:

[0077] The front and rear vehicles of the following car are both ordinary cars;

[0078] The following time shall not be less than 20 seconds, and the following distance shall not be greater than 100 meters;

[0079] Do not overtake, change lanes, etc. during following.

[0080] Data preprocessing is performed on all samples: Python software is used to perform noise reduction on all samples, and the following data of the samples are converted into the speed, position and acceleration information corresponding to the front and rear vehicles at the same time.

[0081] Perform parameter fitting on the speed of the following vehicle and the position information of the leading and trailing vehicles in the car-following dataset to determine the expected distance of the following vehicle The expression of Figure 2 The relationship between the speed of the following vehicle and the expected distance is shown in the figure, through which it can be determined that k=1.04 and b=2.61.

[0082] In this embodiment, sample vehicle data is used and the improved bat algorithm is used to analyze the following car model. , , , The parameters are calibrated, the specific steps are as follows:

[0083] Initialization parameters: Determine the number of bats (value 50); Set the dimension of the search space (value 4); set the minimum frequency (value 0) and maximum frequency (value 10), sound loudness (value 1) and pulse rate (value 0.5);

[0084] Initialize the bat's position and speed: Randomly generate the initial position and speed of each bat;

[0085] The initial position is: ;

[0086] The initial velocity is: , ;

[0087] in, Indicates Bat The value of Indicates Bat The value of Indicates Bat The value of Indicates Bat The value of Indicates Bat The speed of change; Indicates Bat The speed of change; Shidi Bat The speed of change; Indicates Bat's The speed of change;

[0088] Evaluate fitness: Calculate the fitness value of each bat based on the mean square error;

[0089] ;

[0090] in, For fitness, is the actual acceleration of the following vehicle in the actual data set, To use i The predicted acceleration is calculated by calculating the parameters corresponding to the bats. is the number of sample vehicles in the actual data set;

[0091] Crossover mutation: select the top 5% of individuals as parents according to fitness, and perform crossover operation on the selected parents; at the same time, perform mutation operation on all parent individuals with a probability of 1% to generate new offspring; then replace the individual with the worst fitness in the parent with the newly generated offspring after crossover mutation (if the parent has 100 individuals, 5 new offspring are generated through crossover operation, and 1 new offspring is generated through mutation operation, then only the 6 worst offspring in the parent need to be replaced), thus generating a new population;

[0092] Specifically, the specific steps of performing the crossover operation on the selected parent generation are: select two individuals in the parent generation, and there are a total of , , , Select one to three gene loci from four gene loci, exchange the values ​​of the gene loci of two parent individuals, and generate new offspring individuals.

[0093] The specific steps for performing mutation operations on all parent individuals with a probability of 1% are: randomly selecting individuals and their gene loci in the population, randomly mutating the selected genes, changing their values, and thus generating new offspring individuals.

[0094] Update the bat positions: For each bat in the new population, generate a new frequency , and then update the bat's position according to the frequency. The update rule is as follows:

[0095] ;

[0096] ;

[0097] ;

[0098] in, is a random vector, is the number of iterations, is the global optimal solution in the current group, It is The number of bat iterations is The moving speed at It is The number of bat iterations is The moving speed at It is The number of bat iterations is The position at the time; It is The number of bat iterations is The position at the time;

[0099] Calculate the fitness of the new position and compare it with the previous fitness; if the fitness of the new solution is better, update the optimal solution location;

[0100] Generate a new local solution by arbitrary flight: Generate a random number , yes A random number on ; if , then a local new solution is generated by the following formula;

[0101] ;

[0102] in, is a random number; is the global optimal solution (equal to the updated ), It is a newly generated local new solution;

[0103] Update the sound volume and pulse rate: Generate a random number again , yes A random number on ; if , then accept the new solution generated by the above formula and update the sound loudness and pulse rate. The update rules are as follows:

[0104] ;

[0105] ;

[0106] in, and is a constant, Take 0.9, Take 0.6; Represents the number of iterations Loudness The value of Represents the number of iterations Loudness The value of Represents the number of iterations Pulse rate The value of

[0107] Output result: Repeat the above steps. When the maximum number of iterations is reached (the maximum number of iterations is 300) or the convergence condition is met, the global optimal solution is output ( The value is 0.05. The value is 1. The value is 0.22. The value is 0.16) and its fitness value.

[0108] The control system provided by the present invention uses the optimal solution calculated by the improved bat algorithm as the parameter in the car-following model. , , , The value of is used to obtain the complete form of the following model. During the following process, the following vehicle obtains the speed and position information of the leading and following vehicles through the information detection module. By substituting the speed, acceleration and position information into the following model, the acceleration of the following vehicle at the next moment can be obtained. The operating state of the following vehicle can be controlled through more accurate vehicle behavior prediction, thereby ensuring the safety of the vehicle and the stability of the road.

[0109] The present invention also provides an electronic device, comprising: one or more processors and a memory; wherein the memory is used to store one or more programs, and when the one or more programs are executed by the one or more processors, the one or more processors implement the above-mentioned vehicle following control system based on the action of the leading vehicle in an intelligent network environment.

[0110] The present invention also provides a computer-readable medium having a computer program stored thereon, and when the computer program is executed by a processor, the vehicle following control system based on the action of a leading vehicle in an intelligent network environment as described above is implemented.

[0111] Those skilled in the art will appreciate that all or part of the functions of the various methods / modules in the above embodiments may be implemented by hardware or by computer programs. When all or part of the functions in the above embodiments are implemented by computer programs, the program may be stored in a computer-readable storage medium, which may include: a read-only memory, a random access memory, a disk, an optical disk, a hard disk, etc. The program is executed by a computer to implement the above functions. For example, the program is stored in the memory of the device, and when the program in the memory is executed by the processor, all or part of the above functions can be implemented.

[0112] In addition, when all or part of the functions in the above-mentioned embodiments are implemented by means of a computer program, the program can also be stored in a storage medium such as a server, another computer, a disk, an optical disk, a flash drive or a mobile hard disk, and saved to the memory of a local device by downloading or copying, or the system of the local device is updated. When the program in the memory is executed by the processor, all or part of the functions in the above-mentioned embodiments can be implemented.

[0113] The above specific examples are used to illustrate the present invention, which is only used to help understand the present invention and is not intended to limit the present invention. For those skilled in the art of the present invention, according to the idea of ​​the present invention, some simple deductions, deformations or substitutions can be made. Therefore, the protection scope of the present invention shall be based on the protection scope of the claims.

Claims

1. A vehicle following control system based on the action of the preceding vehicle in an intelligent network environment, characterized in that: It includes information detection module, model building module, parameter calibration module and vehicle control module; Wherein, the information detection module is used to obtain the speed information and position information of the rear vehicle and the front vehicle; The model building module is used to establish a car-following model by using the effect of the leading vehicle on the following vehicle; the effect of the leading vehicle on the following vehicle is used to indicate that the following vehicle is affected by the speed of the leading vehicle and the distance between the leading and following vehicles during the driving process; When the intelligent connected vehicle is driving, the following vehicle detects the speed and position information of the following vehicle and the leading vehicle. The following vehicle has an expected following distance during driving. At this time, the leading vehicle has the following effects on the following vehicle: ； ； Where: is the effect of the front vehicle on the rear vehicle, is the current speed of the preceding vehicle, is the current speed of the following vehicle, is the weight coefficient of the distance term, is the current position of the preceding vehicle, is the current position of the following vehicle, is the expected following distance of the following vehicle, is the speed of the following vehicle, and is the coefficient, which is determined by fitting the position information of the front and rear vehicles and the speed information of the rear vehicle in a stable following car on the road, and t is the current time; The following model is used to represent the reaction of the rear vehicle to the front vehicle, that is, the acceleration of the rear vehicle at the next moment. The expression of the following model is: ； ； Where: is the acceleration of the following vehicle at the next moment, is the time coefficient, is the sensitivity coefficient, is the theoretical speed of the following vehicle at the next moment, is the coefficient to be determined, is the effect of the front vehicle on the rear vehicle, is the current speed of the following vehicle, is the acceleration of the following vehicle at the current moment; the parameter calibration module is used to calibrate the following model using the actual road data and the improved bat algorithm. , , , The coefficients are calibrated; The vehicle control module is used to control the motion state of the rear vehicle according to the speed information and position information of the front vehicle and the rear vehicle detected by the information detection module, and the acceleration of the rear vehicle at the next moment obtained based on the following model after parameter calibration.

2. According to claim 1, a vehicle following control system based on the action of the preceding vehicle in an intelligent network environment is characterized in that: The control system also includes a database, and the data collected in real time by the information detection module and the data calculated in real time by the car-following model are stored in the database.

3. A vehicle following control system based on the action of the preceding vehicle in an intelligent network environment according to claim 1 or 2, characterized in that: The information detection module includes a vehicle-mounted sensor and a network-connected device; wherein the vehicle-mounted sensor is used to obtain speed information of the rear vehicle and the front vehicle; the network-connected device is used to obtain position information of the rear vehicle and the front vehicle, including the position of the front vehicle, the position of the rear vehicle, and the distance between the front and rear vehicles.

4. A vehicle following control system based on the action of the preceding vehicle in an intelligent network environment according to claim 1 or 2, characterized in that: The actual road data is obtained by on-site recording by a drone. A data set is formed by collecting the status information of vehicles on the lane on the actual road. The data set includes the front vehicle speed, the front vehicle acceleration, the rear vehicle speed, the rear vehicle acceleration, and the position information of the front and rear vehicles. The front and rear vehicles that are stably following each other are selected from the data set to form sample vehicle data. After that, parameter fitting is performed on the rear vehicle speed and the position information of the front and rear vehicles of the sample vehicle to determine the expected distance of the rear vehicle. Parameters k and b in ; where k=1.04 and b=2.

61.

5. The vehicle following control system based on the action of the preceding vehicle in an intelligent network environment according to claim 4, characterized in that: The parameter calibration module uses sample vehicle data and an improved bat algorithm to calibrate the parameters in the following car model. , , , The parameters are calibrated, the specific steps are as follows: Initialization parameters: Determine the number of bats ; Set the dimension of the search space ; Set the minimum frequency and maximum frequency , sound loudness and pulse rate ; Initialize the bat's position and speed: Randomly generate the initial position and speed of each bat; The initial position is: ; The initial velocity is: , ; in, Indicates Bat The value of Indicates Bat The value of Indicates Bat The value of Indicates Bat The value of Indicates Bat The speed of change; Indicates Bat The speed of change; Shidi Bat The speed of change; Indicates Bat's The speed of change; Evaluate fitness: Calculate the fitness value of each bat based on the mean square error; ； in, For fitness, is the actual acceleration of the following vehicle in the actual data set, To use i The predicted acceleration is calculated by calculating the parameters corresponding to the bats. is the number of sample vehicles in the actual road dataset; The top 5% of individuals are selected as parents according to fitness, and the selected parents are crossovered; at the same time, all parent individuals are mutated with a probability of 1%; then the individuals with the worst fitness in the parent are replaced with the newly generated offspring individuals after crossover mutation, thus generating a new population; For each bat in the new population, generate a new frequency , and then update the bat's position according to the frequency. The update rule is: ； ； ； in, is a random vector, is the number of iterations, is the global optimal solution in the current group, It is The number of bat iterations is The moving speed at It is The number of bat iterations is The moving speed at It is The number of bat iterations is The position at the time; It is The number of bat iterations is The position at the time; Calculate the fitness of the new position and compare it with the previous fitness value; if the fitness value of the new solution is better, update the optimal solution location; Generate a new local solution by any flight and generate a random number , yes A random number on ; if , then the expression of the generated local new solution is; ； in, is a random number; is the global optimal solution, It is a newly generated local new solution; Generate a random number , yes A random number on ; if , then accept the generated local new solution and update the sound loudness and pulse rate. The update rule is: ； ； in, and is a constant, Take 0.9, Take 0.6; Represents the number of iterations Loudness The value of Represents the number of iterations Loudness The value of Represents the number of iterations Pulse rate The value of .

6. The vehicle following control system based on the action of the preceding vehicle in an intelligent network environment according to claim 5, characterized in that: The specific steps of crossover operation on the selected parent generation are: select two individuals in the parent generation, and there are a total of , , , Select one to three gene loci from four gene loci, exchange the values ​​of the gene loci of two parent individuals, and generate new offspring individuals.

7. The vehicle following control system based on the action of the preceding vehicle in an intelligent network environment according to claim 6, characterized in that: The specific steps for performing mutation operations on all parent individuals with a probability of 1% are: randomly selecting individuals and their gene loci in the population, randomly mutating the selected genes, changing their values, and thus generating new offspring individuals.

8. The vehicle following control system based on the action of the preceding vehicle in an intelligent network environment according to claim 7, characterized in that: In the following model The value is 0.

05. The value is 1. The value is 0.

22. The value is 0.16.

Images