A method, system and storage medium for introducing a driving style of bunching lane changing

Abstract

The present application relates to the technical field of automatic driving vehicle gathering lane changing, and particularly relates to a gathering lane changing method and system introducing driving style, and a storage medium; the gathering lane changing method introducing driving style comprises the following steps: S1, constructing an improved gathering lane changing model introducing driving style; S2, acquiring simulation parameters of the improved gathering lane changing model; S3, inputting the simulation parameters acquired in step S2 into the improved gathering lane changing model constructed in step S1, simulating traffic flow under the mixed driving state of CAV vehicles and HV vehicles, and outputting gathering lane changing simulation results; the improved gathering lane changing model takes a KKW model as a basic model, introduces boundaries of adaptive speed and inter-vehicle synchronization distance, introduces vehicle driving style and a gathering lane changing model. The technical scheme of the present application is more obvious in improving traffic flow operation efficiency along with the increase of CAV vehicle penetration rate, and further improves road traffic efficiency by limiting CAV queue length to a certain extent.

Description

Technical Field

[0001] This invention relates to the field of lane-changing technology for autonomous vehicles, and specifically to a lane-changing method, system, and storage medium that incorporates driving style. Background Technology

[0002] With the continuous development and progress of technology, more and more Connected Autonomous Vehicles (CAVs) are being developed. In order to better leverage the advantages of CAVs, researchers have proposed a car-following strategy that takes into account the speed of the vehicle in front, as well as a lane-changing strategy to further optimize the car-following state. In addition, to improve the efficiency of traffic flow, the driving style of CAV drivers is taken into consideration.

[0003] However, existing technologies neglect the impact of driving style on the cluster lane-changing model. This leads to significant differences in how vehicles with different driving styles judge lane-changing attempts under safe conditions during the lane-changing process of the cluster lane-changing strategy, thus affecting the overall traffic flow.

[0004] Therefore, those skilled in the art urgently need to improve the existing cluster lane-changing model in order to overcome the problems existing in the prior art. Summary of the Invention

[0005] Therefore, the technical problem to be solved by the present invention is to overcome the defects existing in the prior art, thereby providing a cluster lane-changing method that introduces driving style.

[0006] A cluster lane-changing method incorporating driving style includes:

[0007] S1. Construct an improved cluster lane-changing model that incorporates driving style;

[0008] S2. Obtain the simulation parameters of the improved cluster lane-changing model;

[0009] S3. Input the simulation parameters obtained in step S2 into the improved clustering lane-changing model constructed in step S1, simulate the traffic flow under the mixed state of CAV vehicles and HV vehicles, and output the clustering lane-changing simulation results.

[0010] Among them, the improved lane-changing cluster model is based on the KKW model, introduces the boundaries of adaptive speed and synchronization distance between vehicles, introduces three different vehicle driving styles, and replaces the original lane-changing model in the KKW model with the lane-changing cluster model.

[0011] Preferably, the KKW model is used as the base model to introduce speed adaptation and inter-vehicle synchronization distance. The specific principle is as follows:

[0012] When the distance between vehicles is within a preset range, the traffic flow on the road enters a synchronized flow state. The vehicle adjusts its driving speed according to the speed difference with the vehicle in front. The specific adaptive speed expression used is:

[0013] ;

[0014] The initial speed of the vehicle is set as follows: ;

[0015] Meanwhile, to avoid vehicle collisions, a synchronization distance between vehicles is introduced, and the constraints for the synchronization boundary flow are set as follows: ;

[0016] In the formula, This indicates the vehicle's adaptive speed. Indicates the actual speed of the vehicle; Indicates vehicle acceleration; Code indicating time step; Indicates the vehicle code; Indicates the distance between your vehicle and the vehicle in front; Represents the constraints for synchronous boundary flows; Indicates the speed of the vehicle in front; Indicates the vehicle's maximum speed; This represents one of the boundary parameters of the synchronous flow; This represents another parameter indicating the boundary of the synchronous flow.

[0017] Preferably, the three different vehicle driving styles include:

[0018] The driver exhibits an aggressive driving style for HV vehicles, specifically characterized by: , , ;

[0019] The driver exhibits a conservative driving style for HV vehicles, specifically characterized by: , , ;

[0020] CAV vehicle driving style, specifically manifested as follows: , , ;

[0021] In the formula, Indicates the maximum speed of an aggressive driver; This indicates the maximum speed for a conservative driver. This indicates the maximum acceleration of the CAV vehicle; This indicates the acceleration of the vehicle. This indicates the maximum acceleration of a vehicle driven by an aggressive driver. This indicates the maximum acceleration of a conservative driver. This indicates the maximum acceleration of the CAV vehicle; This indicates the maximum deceleration of the vehicle; This indicates the maximum deceleration of an aggressive driver; This indicates the maximum deceleration under conservative conditions; This indicates the maximum deceleration of the CAV vehicle.

[0022] The preferred lane-switching strategy used in the cluster lane-switching model is as follows:

[0023] If and only if the vehicle forms a convoy with the vehicle in front, and the vehicle makes a judgment based on the situation of the vehicle in front:

[0024] When the vehicle in front is an HV vehicle, use the conventional lane-changing approach;

[0025] When the preceding vehicle is a CAV vehicle, the length of the CAV queue shared by the vehicle and the preceding vehicle is judged: if the length of the CAV queue exceeds the limit condition N, the vehicle cannot change lanes; if the length of the CAV queue does not exceed the limit condition N, the vehicle will ignore the restriction of the cluster lane-changing strategy and perform lane-changing operation according to the normal lane-changing approach.

[0026] Preferably, the lane-changing intent calculation expression used in the clustered lane-changing model is:

[0027] ;

[0028] In the formula, Indicates the distance between the vehicle and the vehicle in front; This indicates the vehicle's maximum speed.

[0029] Preferably, the standard expression for lane switching used in the cluster lane switching model is:

[0030] ;

[0031] In the formula, Indicates the length of the queue in which the vehicle is located. Represents a constant, indicating a fixed queue length. Indicates the type of vehicle in front in the adjacent lane, It indicates the distance between your vehicle and the vehicle in front in the adjacent lane.

[0032] A lane-changing system that incorporates driving style features includes:

[0033] Model building module: Constructs an improved cluster lane-changing model that incorporates driving style considerations;

[0034] Data acquisition module: Acquires simulation parameters of the improved cluster lane-switching model;

[0035] Simulation module: Inputs the simulation parameters obtained by the data acquisition module into the improved clustering lane-changing model constructed by the model construction module, simulates the traffic flow under the mixed state of CAV vehicles and HV vehicles, and outputs the clustering lane-changing simulation results;

[0036] Among them, the improved lane-changing cluster model is based on the KKW model, introduces the boundaries of adaptive speed and synchronization distance between vehicles, introduces three different vehicle driving styles, and replaces the original lane-changing model in the KKW model with the lane-changing cluster model.

[0037] A computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of a cluster lane-changing method that incorporates driving style.

[0038] The technical solution of this invention has the following advantages:

[0039] This invention combines and improves existing lane-changing strategies and driving styles to adapt them for CAV (Continuous Access Vehicle) applications. Furthermore, verification shows that the technical solution of this invention significantly improves traffic flow efficiency as the penetration rate of CAVs increases, and further enhances road traffic efficiency by limiting the length of CAV queues. Attached Figure Description

[0040] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0041] Figure 1 This is a schematic diagram of the overall method flow of the present invention;

[0042] Figure 2-7 This diagram illustrates the maximum capacity of a single lane for different lane-changing strategies. Detailed Implementation

[0043] The technical solution of the present invention will now be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0044] In the description of this invention, it should be noted that the terms "center," "upper," "lower," "left," "right," "vertical," "horizontal," "inner," and "outer," etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. They are used only for the convenience of describing the invention and for simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on the invention. Furthermore, the terms "first," "second," and "third" are used for descriptive purposes only and should not be construed as indicating or implying relative importance.

[0045] In the description of this invention, it should be noted that, unless otherwise explicitly specified and limited, the terms "installation," "connection," and "linking" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal connection of two components. Those skilled in the art can understand the specific meaning of the above terms in this invention based on the specific circumstances.

[0046] Furthermore, the technical features involved in the different embodiments of the present invention described below can be combined with each other as long as they do not conflict with each other.

[0047] Example 1

[0048] like Figure 1 This embodiment discloses a cluster lane-changing method that incorporates driving style, including:

[0049] S1. Construct an improved cluster lane-changing model that incorporates driving style;

[0050] S2. Obtain the simulation parameters of the improved cluster lane-changing model;

[0051] S3. Input the simulation parameters obtained in step S2 into the improved clustering lane-changing model constructed in step S1, simulate the traffic flow under the mixed state of CAV vehicles and HV vehicles, and output the clustering lane-changing simulation results.

[0052] Among them, the improved lane-changing cluster model is based on the KKW model, introduces the boundaries of adaptive speed and synchronization distance between vehicles, introduces three different vehicle driving styles, and replaces the original lane-changing model in the KKW model with the lane-changing cluster model.

[0053] Specifically:

[0054] First, this embodiment introduces the classic Gipps safety rules to reflect the safety-oriented driving style of CAV vehicles in real-world driving.

[0055] The Gipps security rule expression is as follows:

[0056] ;

[0057] ;

[0058] In the formula, This indicates the safe distance that a vehicle should maintain to avoid colliding with the vehicle in front. Indicates the position of the front of the vehicle in front; Indicates the position of the vehicle; Indicates the length of the vehicle in front; Indicates the actual speed of the vehicle. Indicates the speed of the vehicle in front; Indicates the driver's reaction time; and These represent the maximum deceleration of the vehicle and the vehicle in front, respectively.

[0059] In this embodiment, the KKW model is used as the base model to introduce speed adaptation and inter-vehicle synchronization distance. The specific principle is as follows:

[0060] When the distance between vehicles is within a preset range, the traffic flow on the road enters a synchronized flow state. The vehicle adjusts its driving speed according to the speed difference with the vehicle in front. The specific adaptive speed expression used is:

[0061] ;

[0062] The initial speed of the vehicle is set as follows: ;

[0063] It should be noted that, This refers to the sign function, when hour, ;when hour, ; If when hour, The speed adaptive expression indicates that when the distance between the vehicle's speed and the vehicle in front is greater than the constraint distance, the vehicle will increase its speed to improve the traffic flow efficiency of the method in this embodiment; when the distance between the vehicle and the vehicle in front is less than the constraint distance, the vehicle will gradually adjust its speed to reach the same speed as the vehicle in front. In this process, to avoid vehicle collisions, a synchronization distance between vehicles is introduced, and the constraint conditions for the synchronization boundary flow are set as follows: ;

[0064] In the formula, This indicates the vehicle's adaptive speed. Indicates vehicle acceleration; Code indicating time step; Indicates the vehicle code; Indicates the distance between your vehicle and the vehicle in front; Represents the constraints for synchronous boundary flows; Indicates the vehicle's maximum speed; This represents one of the boundary parameters of the synchronous flow; This represents another parameter indicating the boundary of the synchronous flow. The real number representing the sign function.

[0065] Furthermore, in this embodiment, based on data analysis obtained from the NGSIM database, HV vehicle drivers are categorized into aggressive and conservative types during the speed adaptation phase, while CAV vehicle parameters—vehicle speed, maximum acceleration, and maximum deceleration—remain consistent with the conservative type. This further yields three different vehicle driving styles:

[0066] The driver exhibits an aggressive driving style for HV vehicles, specifically characterized by: , , ;

[0067] The driver exhibits a conservative driving style for HV vehicles, specifically characterized by: , , ;

[0068] CAV vehicle driving style, specifically manifested as follows: , , ;

[0069] In the formula, Indicates the maximum speed of an aggressive driver; This indicates the maximum speed for a conservative driver. This indicates the maximum acceleration of the CAV vehicle; This indicates the acceleration of the vehicle. This indicates the maximum acceleration of a vehicle driven by an aggressive driver. This indicates the maximum acceleration of a conservative driver. This indicates the maximum acceleration of the CAV vehicle; This indicates the maximum deceleration of the vehicle; This indicates the maximum deceleration of an aggressive driver; This indicates the maximum deceleration under conservative conditions; This indicates the maximum deceleration of the CAV vehicle.

[0070] It should be noted that the specific methods for data analysis can be chosen according to actual needs. Specifically, in this embodiment, different driving styles are classified as follows: using Principal Component Analysis (PCA), drivers with large and frequent fluctuations in headway and speed from the NGSIM database are defined as aggressive drivers, while those with low speed fluctuations and who frequently adjust their speed to maintain a stable speed are defined as conservative drivers. Furthermore, this embodiment uses cluster analysis to determine that the maximum speed of aggressive-style vehicles is 20 m / s, while the maximum speed of conservative-style vehicles is 15 m / s, indicating that aggressive-style vehicles have a higher maximum speed than conservative-style vehicles. The acceleration of aggressive-style vehicles is set to... The deceleration is set to Conservative setting The deceleration is set to The acceleration and deceleration changes of vehicles with an aggressive driving style are greater than those of vehicles with a conservative driving style. Regarding the probability of random slowdown, the probability of random slowdown is higher for the aggressive driving style than for the conservative driving style. Therefore, in this embodiment, the probability is set to 0.4 for the aggressive driving style and 0.2 for the conservative style. In terms of safe distance, the safe distance is set to 1.75m for the aggressive driving style and 3.11m for the conservative style. The aggressive style maintains a closer following distance.

[0071] In this embodiment, the lane-switching strategy used by the cluster lane-switching model is as follows:

[0072] If and only if the vehicle forms a convoy with the vehicle in front, and the vehicle makes a judgment based on the situation of the vehicle in front:

[0073] When the vehicle in front is an HV vehicle, use the conventional lane-changing approach;

[0074] Conventional lane changing: When the driving conditions in the lane where the vehicle is currently located do not allow for a higher speed, and the adjacent lane meets the driving requirements, the vehicle changes lanes, provided that safety conditions are met. Safety conditions: The distance between the vehicle and the vehicle in front in the adjacent lane is greater than the vehicle's maximum speed, and the distance between the vehicle and the vehicle behind in the adjacent lane is greater than the maximum speed of the vehicle behind. It should be noted that conventional lane changing is a common practice in this field; therefore, the above description is for brief reference only.

[0075] When the preceding vehicle is a CAV vehicle, the length of the CAV queue shared by the vehicle and the preceding vehicle is judged: if the length of the CAV queue exceeds the limit condition N, the vehicle cannot change lanes; if the length of the CAV queue does not exceed the limit condition N, the vehicle will ignore the restriction of the cluster lane-changing strategy and perform lane-changing operation according to the normal lane-changing approach.

[0076] When the driving conditions in the current lane are restricted and the driving conditions in the adjacent lane are better, the vehicle will intend to change lanes.

[0077] Specifically, the lane-changing intention calculation expression used in the cluster lane-changing model is as follows:

[0078] ;

[0079] In the formula, Indicates the distance between the vehicle and the vehicle in front; This indicates the vehicle's maximum speed.

[0080] In addition, when changing lanes, it is also necessary to pay attention to the safety of vehicles behind in the adjacent lane. Therefore, the safety condition expression is: In the formula, This indicates the distance of the vehicle from the adjacent lane with better driving conditions. Indicates the speed of vehicles behind in the adjacent lane with better driving conditions. This indicates the acceleration of vehicles behind in the adjacent lane with better driving conditions.

[0081] Compared to HV vehicles, CAV vehicles, with their inherent advantages, can quickly and accurately identify surrounding vehicles and react efficiently. Using appropriate lane-changing strategies can enable CAV vehicles on the road to locally cluster, forming more CACC (Carrier-Assisted Collision-Assisted) queues, thus better leveraging the advantages of CAV vehicles. Therefore, the standard lane-changing expression used in the clustering lane-changing model is:

[0082] ;

[0083] In the formula, Indicates the length of the queue in which the vehicle is located. Represents a constant, indicating a fixed queue length. Indicates the type of vehicle in front in the adjacent lane, It indicates the distance between your vehicle and the vehicle in front in the adjacent lane.

[0084] Example 2

[0085] This embodiment discloses a lane-changing system that incorporates driving style, including:

[0086] Model building module: Constructs an improved cluster lane-changing model that incorporates driving style considerations;

[0087] Data acquisition module: Acquires simulation parameters of the improved cluster lane-switching model;

[0088] Simulation module: Inputs the simulation parameters obtained by the data acquisition module into the improved clustering lane-changing model constructed by the model construction module, simulates the traffic flow under the mixed state of CAV vehicles and HV vehicles, and outputs the clustering lane-changing simulation results;

[0089] Among them, the improved cluster lane-changing model is based on the KKW model, introduces the boundaries of adaptive speed and synchronization distance between vehicles, introduces three different vehicle driving styles, and replaces the original lane-changing model in the KKW model with the cluster lane-changing model, specifically adopting the CVA cluster lane-changing strategy.

[0090] Specifically:

[0091] Obtain simulation parameters for the improved cluster lane-switching model, specifically including:

[0092] S201. In this embodiment, the 7:50am-8:05am time period data from the US-101 dataset in the NGSIM database is used as a basis to extract vehicle driving styles. The NGSIM database is a high-resolution traffic trajectory database established by the Federal Highway Administration (NHTA) of the United States, storing a wealth of vehicle driving information such as speed, acceleration, lane-changing behavior, headway, and time headway for corresponding roads. This paper uses 80% of the data from the NGSIM database for the corresponding road time period to determine driving styles and calibrate parameters, and the remaining 20% ​​of the data for model validation.

[0093] S202. Use SPSS software to preprocess the extracted data to eliminate outliers and extreme values, and then use exponential smoothing to smooth the velocity and acceleration in the data to eliminate noise and outlier problems caused by the detection equipment.

[0094] S203. Process the driving speed v_Vel, speed change v_Acc, and time distance between vehicles Time_Hdwy in the preprocessed data to extract the average speed V_mean, maximum speed V_max, average acceleration A_mean, average deceleration D_mean, acceleration variance var_acc, deceleration variance var_dec, average headway T_mean, headway var_T, and lane change count lane_changes.

[0095] S204. Since step S203 involves many indicators with close correlations, principal component analysis is used in step S204 to reduce the dimensionality of the variables corresponding to each indicator in order to improve the efficiency and accuracy of the analysis. Specifically, SPSS software is used to perform principal component analysis on the indicators in Table 1. Table 3 shows the total variance interpretation when SPSS software outputs 9 components. It is found that the cumulative contribution rate of the first three indicators has reached more than 80%, so the first three indicators are selected as principal components, as shown in Table 2. It should be noted that the number of components is not limited in practical applications. The number of components in Tables 3 and 2 in this embodiment is only an example.

[0096] Table 1 Extraction of Driving Style Indicators

[0097]

[0098] Table 2 Component Matrix

[0099]

[0100] Table 3 Explanation of Total Variance

[0101]

[0102] S205. Based on the three principal components obtained by principal component dimensionality reduction, k-means clustering analysis was performed, which mainly divided them into two categories. The final cluster centers are shown in Table 4.

[0103] Table 4. Final Cluster Centers

[0104]

[0105] S206. Obtain the correlation matrix between the three principal components and the selected nine variables using the component matrix in Table 2: A 9x3 matrix; Table 4 provides the correlation matrices between the two cluster centers and the three principal components: A 3x2 matrix; through Multiplying the two matrices yields the relationship between the original nine coordinates corresponding to the two cluster centers:

[0106] ;

[0107] The signs of the values ​​in Table 5 indicate the direction of deviation of the corresponding values ​​of the cluster centers relative to the variable centers; specifically, the values ​​represent how many standard deviations they have deviated from the sample mean. Therefore, the corresponding values ​​of the original data for each cluster center are calculated as follows:

[0108] ;

[0109] in Indicate category Corresponding variable Raw data, Indicate category Corresponding variable Standardized data, Representing variables standard deviation Representing variables The mean of the values ​​was used. The results of the cluster analysis were substituted into the model as parameters. For CAV vehicles, since there was a lack of actual data, the parameters from the literature were selected as the model parameters.

[0110] Since autonomous vehicles are not yet widespread, this embodiment refers to relevant research literature in this field and, by analyzing the relationship with the model in this embodiment, obtains the corresponding simulation parameters of CAV vehicles and HV vehicles as shown in Table 5.

[0111] Table 5 Relevant Parameters

[0112]

[0113] Indicates the safe distance between your vehicle and the vehicle in front; This represents the probability of slowing down when the vehicle's speed is greater than 0.

[0114] In addition, this embodiment compares the basic traffic flow maps of different CAV penetration rates under different lane-changing strategies, analyzes the impact of different lane-changing strategies on road traffic flow, and compares the traffic flow under different CAV penetration rates under the same lane-changing strategy, thereby analyzing and determining the impact of the driver's driving style on the final result of the lane-changing strategy.

[0115] The proportions of aggressive drivers were set to 0, 0.2, 0.4, 0.6, 0.8, and 1, and the CAV vehicle penetration rates were set to 0, 0.2, 0.4, 0.6, 0.8, and 1, respectively. Simulation analysis was conducted under different road conditions with varying proportions of aggressive drivers and CAV vehicle penetration rates. The maximum capacity of a single lane under different clustering strategies (NOV, CVA, and CDA) was calculated as follows: Figure 2-7 As shown. From Figure 2-7 It can be seen that, with the same proportion of aggressive drivers, the maximum capacity increases with the increase of CAV penetration rate, further indicating that the high degree of interconnection and fast and efficient decision-making of CAV vehicles have a significant advantage in improving road traffic flow.

[0116] Example 3

[0117] A computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the cluster lane-changing method of Embodiment 1 that introduces driving style.

[0118] Obviously, the above embodiments are merely illustrative examples for clear explanation and are not intended to limit the implementation. Those skilled in the art will recognize that other variations or modifications can be made based on the above description. It is neither necessary nor possible to exhaustively list all possible implementations here. However, obvious variations or modifications derived therefrom are still within the scope of protection of this invention.

Claims

1. A cluster lane-changing method incorporating driving style, characterized in that, include: S1. Construct an improved cluster lane-changing model that incorporates driving style; S2. Obtain the simulation parameters of the improved cluster lane-changing model; S3. Input the simulation parameters obtained in step S2 into the improved clustering lane-changing model constructed in step S1, simulate the traffic flow under the mixed state of CAV vehicles and HV vehicles, and output the clustering lane-changing simulation results. Among them, the improved lane-changing cluster model is based on the KKW model, introduces the boundaries of adaptive speed and synchronization distance between vehicles, introduces three different vehicle driving styles, and replaces the original lane-changing model in the KKW model with the lane-changing cluster model. Among them, the KKW model is used as the basic model to introduce speed adaptation and inter-vehicle synchronization distance. The specific principle is as follows: When the distance between vehicles is within a preset range, the traffic flow on the road enters a synchronized flow state. The vehicle adjusts its driving speed according to the speed difference with the vehicle in front. The specific adaptive speed expression used is: ； The initial speed of the vehicle is set as follows: ; Meanwhile, to avoid vehicle collisions, a synchronization distance between vehicles is introduced, and the constraints for the synchronization boundary flow are set as follows: ; In the formula, This indicates the vehicle's adaptive speed. Indicates the actual speed of the vehicle; Indicates vehicle acceleration; Code indicating time step; Indicates the vehicle code; Indicates the distance between your vehicle and the vehicle in front; Represents the constraints for synchronous boundary flows; Indicates the speed of the vehicle in front; Indicates the vehicle's maximum speed; This represents one of the boundary parameters of the synchronous flow; Another parameter representing the synchronous flow boundary; Among them, the three different vehicle driving styles include: The driver exhibits an aggressive driving style for HV vehicles, specifically characterized by: , , ; The driver exhibits a conservative driving style for HV vehicles, specifically characterized by: , , ; CAV vehicle driving style, specifically manifested as follows: , , ; In the formula, Indicates the maximum speed of an aggressive driver; This indicates the maximum speed for a conservative driver. This indicates the maximum acceleration of the CAV vehicle; This indicates the acceleration of the vehicle. This indicates the maximum acceleration of a vehicle driven by an aggressive driver. This indicates the maximum acceleration of a conservative driver. This indicates the maximum deceleration of the vehicle; This indicates the maximum deceleration of an aggressive driver; This indicates the maximum deceleration under conservative conditions; This indicates the maximum deceleration of the CAV vehicle; The lane-switching strategy used in the cluster lane-switching model is as follows: If and only if the vehicle forms a convoy with the vehicle in front, and the vehicle makes a judgment based on the situation of the vehicle in front: When the vehicle in front is an HV vehicle, use the conventional lane-changing approach; When the preceding vehicle is a CAV vehicle, the length of the CAV queue shared by the vehicle and the preceding vehicle is judged: if the length of the CAV queue exceeds the limit N, the vehicle cannot change lanes; if the length of the CAV queue does not exceed the limit N, the vehicle will ignore the restriction of the cluster lane-changing strategy and perform lane-changing operation according to the normal lane-changing approach. The expression for calculating lane-changing intent used in the cluster lane-changing model is: ； In the formula, Indicates the distance between the vehicle and the vehicle in front; This indicates the vehicle's maximum speed.

2. The method for clustered lane changing that incorporates driving style according to claim 1, characterized in that, The standard expression for lane switching used in the cluster lane switching model is: ； In the formula, Indicates the length of the queue in which the vehicle is located. Represents a constant, indicating a fixed queue length. Indicates the type of vehicle in front in the adjacent lane, It indicates the distance between your vehicle and the vehicle in front in the adjacent lane.

3. A lane-changing system incorporating driving style, characterized in that, include: Model building module: Constructs an improved cluster lane-changing model that incorporates driving style considerations; Data acquisition module: Acquires simulation parameters of the improved cluster lane-switching model; Simulation module: Inputs the simulation parameters obtained by the data acquisition module into the improved clustering lane-changing model constructed by the model construction module, simulates the traffic flow under the mixed state of CAV vehicles and HV vehicles, and outputs the clustering lane-changing simulation results; Among them, the improved lane-changing cluster model is based on the KKW model, introduces the boundaries of adaptive speed and synchronization distance between vehicles, introduces three different vehicle driving styles, and replaces the original lane-changing model in the KKW model with the lane-changing cluster model. Among them, the KKW model is used as the basic model to introduce speed adaptation and inter-vehicle synchronization distance. The specific principle is as follows: When the distance between vehicles is within a preset range, the traffic flow on the road enters a synchronized flow state. The vehicle adjusts its driving speed according to the speed difference with the vehicle in front. The specific adaptive speed expression used is: ； The initial speed of the vehicle is set as follows: ; Meanwhile, to avoid vehicle collisions, a synchronization distance between vehicles is introduced, and the constraints for the synchronization boundary flow are set as follows: ; In the formula, This indicates the vehicle's adaptive speed. Indicates the actual speed of the vehicle; Indicates vehicle acceleration; Code indicating time step; Indicates the vehicle code; Indicates the distance between your vehicle and the vehicle in front; Represents the constraints for synchronous boundary flows; Indicates the speed of the vehicle in front; Indicates the vehicle's maximum speed; This represents one of the boundary parameters of the synchronous flow; Another parameter representing the synchronous flow boundary; Among them, the three different vehicle driving styles include: The driver exhibits an aggressive driving style for HV vehicles, specifically characterized by: , , ; The driver exhibits a conservative driving style for HV vehicles, specifically characterized by: , , ; CAV vehicle driving style, specifically manifested as follows: , , ; In the formula, Indicates the maximum speed of an aggressive driver; This indicates the maximum speed for a conservative driver. This indicates the maximum acceleration of the CAV vehicle; This indicates the acceleration of the vehicle. This indicates the maximum acceleration of a vehicle driven by an aggressive driver. This indicates the maximum acceleration of a conservative driver. This indicates the maximum deceleration of the vehicle; This indicates the maximum deceleration of an aggressive driver; This indicates the maximum deceleration under conservative conditions; This indicates the maximum deceleration of the CAV vehicle; The lane-switching strategy used in the cluster lane-switching model is as follows: If and only if the vehicle forms a convoy with the vehicle in front, and the vehicle makes a judgment based on the situation of the vehicle in front: When the vehicle in front is an HV vehicle, use the conventional lane-changing approach; When the preceding vehicle is a CAV vehicle, the length of the CAV queue shared by the vehicle and the preceding vehicle is judged: if the length of the CAV queue exceeds the limit N, the vehicle cannot change lanes; if the length of the CAV queue does not exceed the limit N, the vehicle will ignore the restriction of the cluster lane-changing strategy and perform lane-changing operation according to the normal lane-changing approach. The expression for calculating lane-changing intent used in the cluster lane-changing model is: ； In the formula, Indicates the distance between the vehicle and the vehicle in front; This indicates the vehicle's maximum speed.

4. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by the processor, it implements the steps of the cluster lane-changing method for introducing driving style as described in any one of claims 1 to 2.

Images