Traffic flow model correction method, device, electronic device and storage medium
By analyzing driving behavior in road network data, determining driving tendencies and correcting traffic flow model parameters, the problem of insufficient accuracy of existing models is solved, the authenticity and diversity of simulation results are improved, and the needs of autonomous driving testing are met.
Patent Information
- Application Number
- CN202311272105.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2023-09-27
- Publication Date
- 2024-12-06
- Estimated Expiration
- 2043-09-27
AI Technical Summary
The existing traffic flow model lacks accuracy in the testing of autonomous driving algorithms and cannot effectively reflect the actual driving behavior, resulting in untrue simulation results, affecting the testing efficiency and cost.
By obtaining driving behavior data in road network data, the driving tendencies of each vehicle are determined, and the traffic flow model parameters are corrected based on these tendencies, and free driving, follow-up and lane-changing behaviors are considered to improve the accuracy of the model.
It improves the authenticity, rationality and diversity of simulated traffic flow, enhances the parameter accuracy of the traffic flow model, and meets the needs of high-level autonomous driving testing.
Smart Images

Figure CN117523818B_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of vehicle simulation technology, and more specifically, to a correction method, device, electronic device and storage medium for a traffic flow model. Background Art
[0002] In the context of the booming development of artificial intelligence technology, vehicle engineering has ushered in new development opportunities, and autonomous driving systems have emerged. Autonomous driving algorithms have become a research hotspot in the field of vehicle engineering, but they are still in their infancy, related technologies are not yet mature, and industry development is relatively slow. Before autonomous driving technology is applied on a large scale, its safety and reliability must be verified through mileage testing.
[0003] Traffic flow simulation can simulate the operation rules of real road traffic flow and provide a real traffic environment for autonomous driving algorithm testing, thereby effectively improving test efficiency and reducing test costs. When using traffic flow simulation to test autonomous driving algorithms, the accuracy of the parameters of the traffic flow model will affect the authenticity of the simulated traffic flow, which will affect the testing of the autonomous driving algorithm. Summary of the invention
[0004] In view of the above problems, the present application proposes a method, device, electronic device and storage medium for correcting a traffic flow model.
[0005] In a first aspect, an embodiment of the present application provides a method for correcting a traffic flow model, the method comprising: obtaining driving behavior data corresponding to each vehicle in the road network data; determining a driving tendency corresponding to each vehicle in the road network data based on the driving behavior data; and correcting parameters of a traffic flow model of the vehicle corresponding to each driving tendency based on the driving behavior data of the vehicle corresponding to each driving tendency.
[0006] In an optional embodiment, determining the driving tendency corresponding to each vehicle in the road network data based on the driving behavior data includes: determining the free driving segments, following segments and number of lane changes corresponding to each vehicle in the road network data based on the driving behavior data; determining the driving tendency corresponding to each vehicle in the road network data based on the free driving segments, following segments and number of lane changes.
[0007] In an optional embodiment, the driving tendency corresponding to each vehicle in the road network data is determined based on the free driving segments, the following segments and the number of lane changes, including: determining the free driving speed corresponding to each vehicle according to the free driving segments corresponding to each vehicle; determining the minimum headway distance between each vehicle and the corresponding preceding vehicle according to the following segments as the minimum headway distance corresponding to each vehicle; determining the driving tendency corresponding to each vehicle in the road network data according to the free driving speed, the minimum headway distance and the number of lane changes corresponding to each vehicle.
[0008] In an optional embodiment, the driving tendency corresponding to each vehicle in the road network data is determined according to the free traveling speed, minimum headway and number of lane changes corresponding to each vehicle, including: clustering the free traveling speed, minimum headway and number of lane changes of each vehicle to obtain multiple cluster centers; determining the driving tendency corresponding to each cluster center according to the size of the free traveling speed in each cluster center; determining the driving tendency corresponding to each vehicle according to the cluster center to which each vehicle belongs.
[0009] In an optional embodiment, the parameters of the traffic flow model of the vehicle corresponding to each driving tendency are corrected according to the driving behavior data of the vehicle corresponding to each driving tendency, including: obtaining the leading vehicle trajectory and the leading vehicle size corresponding to the leading vehicle of each vehicle in each driving tendency; correcting the following model parameters of the traffic flow model corresponding to each driving tendency according to the leading vehicle trajectory and the leading vehicle size; calibrating the free driving speeds of multiple vehicles of each driving tendency to obtain the expected speed distribution corresponding to each driving tendency; and correcting the lane changing model parameters of the traffic flow model corresponding to each driving tendency according to the expected speed distribution and the corrected following model parameters.
[0010] In an optional embodiment, the method of correcting the parameters of the traffic flow model of the vehicle corresponding to each driving tendency according to the driving behavior data of the vehicle corresponding to each driving tendency also includes: obtaining the size of each vehicle in the road network data to determine the model of each vehicle; and correcting the parameters of the traffic flow model of the vehicle corresponding to each model of each driving tendency according to the driving behavior data of the vehicle corresponding to each model of each driving tendency.
[0011] In an optional embodiment, the method further includes: simulating the traffic flow of the target area corresponding to the road network data based on the corrected parameters of the traffic flow model of the vehicle corresponding to each driving tendency.
[0012] In a second aspect, an embodiment of the present application provides a correction device for a traffic flow model, the device comprising: a driving behavior data acquisition module, used to acquire driving behavior data corresponding to each vehicle in the road network data; a driving tendency determination module, used to determine the driving tendency corresponding to each vehicle in the road network data based on the driving behavior data; and a correction module, used to correct the parameters of the traffic flow model of the vehicle corresponding to each driving tendency based on the driving behavior data of the vehicle corresponding to each driving tendency.
[0013] In a third aspect, an embodiment of the present application provides an electronic device, comprising: one or more processors; a memory; one or more applications, wherein the one or more applications are stored in the memory and configured to be executed by the one or more processors, and the one or more programs are configured to execute the traffic flow model correction method provided in the first aspect above.
[0014] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, in which a program code is stored. The program code can be called by a processor to execute the method for correcting the traffic flow model provided in the first aspect.
[0015] The solution provided in the present application analyzes the driving behavior data in the road network data to obtain a variety of driving tendencies, and then corrects the parameters of the traffic flow model according to the driving tendencies. It not only takes into account the actual driving data, but also takes into account the different driving tendencies of the drivers during the driving process, thereby improving the accuracy of the parameters of the traffic flow model and effectively improving the authenticity, rationality and diversity of the driving behavior of simulated traffic flow vehicles. BRIEF DESCRIPTION OF THE DRAWINGS
[0016] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For those skilled in the art, other drawings can be obtained based on these drawings without creative work.
[0017] Figure 1 A schematic flow chart of a method for correcting a traffic flow model provided in an embodiment of the present application is shown.
[0018] Figure 2 A schematic flow chart of a method for correcting a traffic flow model provided in another embodiment of the present application is shown.
[0019] Figure 3 A detailed flow chart of step S230 in another embodiment of the present application is shown.
[0020] Figure 4A schematic flow chart of a method for correcting a traffic flow model provided in yet another embodiment of the present application is shown.
[0021] Figure 5 A flow chart of a method for correcting a traffic flow model provided in yet another embodiment of the present application is shown.
[0022] Figure 6 A structural block diagram of a traffic flow model correction device provided in an embodiment of the present application is shown.
[0023] Figure 7 A structural block diagram of an electronic device provided in an embodiment of the present application for executing a method for correcting a traffic flow model according to an embodiment of the present application is shown. DETAILED DESCRIPTION
[0024] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application.
[0025] Traffic flow is the most complex and changeable element in the dynamic layer, but existing virtual testing tools lack the ability to simulate high-fidelity traffic flow scenarios, and therefore cannot meet the needs of high-level autonomous driving testing. In the microscopic traffic flow model in the field of traffic engineering, traffic flow is regarded as a complex self-driving particle system composed of a large number of vehicles. Taking a single vehicle as the research object, the vehicle motion law and interaction model are established, mainly including the longitudinal following model and the lateral lane change model.
[0026] The car-following behavior describes the interaction between two adjacent vehicles in a convoy on a single lane with restricted overtaking. The car-following model studies the corresponding behavior of the following vehicle caused by the change of the motion state of the leading vehicle.
[0027] The lane changing model can be divided into forced lane changing and free lane changing. Forced lane changing refers to the lane changing behavior that the vehicle must take in order to complete its normal driving purpose, and free lane changing refers to the lane changing behavior that occurs in order to pursue a faster speed and more free driving space.
[0028] In related technologies, based on the aggregated detection data and with the goal of making the overall traffic flow state consistent, the traffic flow is treated as a black box for model correction, thereby uniformly adjusting the parameters of all traffic flow models in the traffic flow. However, this parameter correction method cannot reflect the actual traffic flow.
[0029] In view of the background technology and the technical problems raised above, the inventors proposed a method, device, electronic device and storage medium for correcting a traffic flow model. By analyzing the driving behavior data in the road network data, a variety of driving tendencies are obtained, and then the parameters of the traffic flow model are corrected according to the driving tendencies. Not only the actual driving data is taken into account, but also the different driving tendencies of the driver during the driving process, thereby improving the accuracy of the parameters of the traffic flow model and effectively improving the authenticity, rationality and diversity of the driving behavior of simulated traffic flow vehicles.
[0030] See also Figure 1 , Figure 1 FIG. 1 is a flow chart of a method for correcting a traffic flow model provided by an embodiment of the present application. In a specific embodiment, the method for correcting a traffic flow model is applied to Figure 6 The traffic flow model correction device 200 and the electronic device 100 equipped with the traffic flow model correction device 200 are shown.
[0031] The following will focus on Figure 1 The process shown is described in detail, and the correction method of the traffic flow model may specifically include the following steps:
[0032] Step S110: Obtain driving behavior data corresponding to each vehicle in the road network data.
[0033] Among them, road network data refers to the road data composed of various roads that are interconnected and interwoven into a network distribution within a specified area, vehicle data on the roads, pedestrian flow data within a specified area, and landmark or building data.
[0034] Driving behavior data refers to the various driving behaviors generated by a vehicle while driving on the road, including but not limited to following the vehicle in front with a very small distance, changing lanes from the current lane to other lanes, free driving at a certain speed, and other driving behaviors.
[0035] In some embodiments, the road network data can be obtained from a collection website, or the user can collect road data for a period of time in a specified area and vehicle data corresponding to the road data, pedestrian flow data in the specified area, and landmark or building data to form the final road network data. The acquisition of road network data is not specifically limited here. For example, a drone is used to take aerial photos of road network data in a specified area for 2-4 hours.
[0036] After obtaining the above road network data, the driving trajectory of each vehicle in the road network data can be extracted according to the obtained road network data to obtain a variety of driving behavior data corresponding to each vehicle.
[0037] Step S120: Determine the driving tendency corresponding to each vehicle in the road network data according to the driving behavior data.
[0038] Among them, the driving tendency can represent the degree of aggressiveness of the driver during driving. Driving tendency includes but is not limited to conservative tendency, normal tendency and aggressive tendency. Conservative tendency means that the driver tends to drive smoothly and at a lower speed, aggressive tendency means that the driver drives at a higher speed throughout the whole journey, and normal tendency is between conservative tendency and aggressive tendency, and the speed tends to be average.
[0039] In an embodiment of the present application, by analyzing the driving data corresponding to each vehicle in the road network data, the driving tendency corresponding to each vehicle can be obtained. The analysis method can be to calculate the mean of multiple driving behaviors of each vehicle, obtain the mean data of multiple driving behavior data of each vehicle, and determine the driving tendency of the vehicle according to the size of the mean and the mean threshold. It can also be to use a clustering algorithm to perform cluster analysis on the driving behavior data, so as to obtain the cluster center corresponding to each vehicle or the cluster center corresponding to each driving tendency, and determine the driving tendency of each vehicle according to the cluster center. The analysis method is not specifically limited here.
[0040] Step S130: Correcting the parameters of the traffic flow model of the vehicle corresponding to each driving tendency according to the driving behavior data of the vehicle corresponding to each driving tendency.
[0041] Traffic flow refers to the traffic flow formed by the continuous driving of cars on the road. The traffic flow model is based on various physical principles and uses mathematical tools such as differential equations and partial differential equations to describe the behaviors of vehicles on the road such as following and changing lanes.
[0042] In the embodiment of the present application, the driving behavior data of all vehicles in each driving tendency are analyzed to obtain analysis data, and then the parameters of the traffic flow model of the vehicles corresponding to each driving tendency are corrected according to the analysis data, so that the traffic model of the vehicles corresponding to each driving tendency is closer to the actual driving behavior. The analysis method can be a mean analysis method or a cluster analysis method, and the specific analysis method is not specifically limited here.
[0043] The solution provided in the embodiment of the present application analyzes the driving behavior data in the road network data to obtain a variety of driving tendencies, and then corrects the parameters of the traffic flow model according to the driving tendencies. It not only takes into account the actual driving data, but also takes into account the different driving tendencies of the driver during the driving process, thereby improving the accuracy of the parameters of the traffic flow model and effectively improving the authenticity, rationality and diversity of the driving behavior of simulated traffic flow vehicles.
[0044] See also Figure 2 , Figure 2A flow chart of a method for correcting a traffic flow model provided by another embodiment of the present application is shown below. Figure 2 The process shown is described in detail, and the correction method of the traffic flow model may specifically include the following steps:
[0045] Step S210: Obtain driving behavior data corresponding to each vehicle in the road network data.
[0046] For the detailed description of step S220, please refer to step S110, which will not be repeated here.
[0047] Step S220: Determine the free driving segments, the following segments and the number of lane changes corresponding to each vehicle in the road network data according to the driving behavior data.
[0048] The free driving segment refers to the driving segment in the driving behavior data that is driven at the maximum speed and maintains the preset duration. In the driving behavior data, a vehicle may have multiple driving segments with driving durations exceeding the preset duration. The driving segment corresponding to the maximum speed among the multiple driving segments is used as the free driving segment corresponding to the vehicle. The preset duration can be 10s, 15s or 30s, and the preset duration is not specifically limited here.
[0049] A following segment refers to a driving behavior data in which the distance between the vehicle and the vehicle in front of the vehicle in the same lane is less than the preset distance, and the driving time of maintaining the distance reaches the preset following time, and the difference in longitudinal speed between the vehicle and the vehicle in front is the preset difference. The distance between the vehicle and the vehicle in front of the vehicle in the same lane can be the distance between the front of the two vehicles, or the distance between the front of the vehicle and the parking space of the vehicle in front. The distance is not limited here. The preset distance can be 15m, 20m or other distances, which are set by the user. The preset following time can be 10s, 15s or 30s, and the preset following time is not specifically limited here.
[0050] The number of lane changes refers to the number of times the vehicle changes from the current lane to other lanes in the driving behavior data.
[0051] In an embodiment of the present application, the free driving segments, following segments and lane change times of each vehicle traveling within a specified range can be obtained from the driving behavior data, so as to determine the driving tendency corresponding to the vehicle based on these data related to the driver's driving tendency.
[0052] Step S230: Determine the driving tendency corresponding to each vehicle in the road network data based on the free driving segments, the following segments and the number of lane changes.
[0053] In the embodiment of the present application, after obtaining the free driving segments, the following segments and the number of lane changes corresponding to each vehicle, the driving tendency corresponding to each vehicle can be determined according to the free driving segments, the following segments and the number of lane changes. It can be understood that since the free driving segments can indicate the maximum speed of the driver's continuous driving, the following segments can indicate the driver's aggressive state obtained by using the distance between the driver and the vehicle in front during driving, and the number of lane changes can indicate the urgency of the driver's driving process, the driving tendency corresponding to each vehicle can be determined based on the free driving segments, the following segments and the number of lane changes corresponding to each vehicle.
[0054] In a possible implementation, the driving tendency corresponding to each vehicle can be determined based on whether there is a free driving segment, the number of following segments, and the number of lane changes. When the vehicle has a free driving segment, and the number of following segments exceeds the preset number of following segments, and the number of lane changes is less than the preset number of lane changes, the vehicle is judged to have a conservative tendency. When the vehicle has a free segment, and the number of following segments exceeds the preset number of following segments, and the number of lane changes exceeds the preset number of lane changes, the vehicle is judged to have a normal tendency. When the vehicle has a free segment, and the number of following segments is less than the preset number of following segments, and the number of lane changes exceeds the preset number of lane changes, the vehicle is judged to have an aggressive tendency. The specific method for determining the driving tendency corresponding to each vehicle based on the free driving segment, the following segment, and the number of lane changes is not specifically limited here.
[0055] In some embodiments, based on the free driving segments, the following segments, and the number of lane changes, determining the driving tendency corresponding to each vehicle in the road network data may include: determining the free driving speed corresponding to each vehicle according to the free driving segments corresponding to each vehicle. Determining the minimum headway between each vehicle and the corresponding preceding vehicle according to the following segments as the minimum headway corresponding to each vehicle. Determining the driving tendency corresponding to each vehicle in the road network data according to the free driving speed, the minimum headway, and the number of lane changes corresponding to each vehicle.
[0056] The free-running speed is the average vehicle speed during the free-running segment.
[0057] In a possible implementation, the driving tendency of the vehicle can be determined by analyzing the free speed, minimum headway and number of lane changes of the vehicle in the road network data. The analysis method can be a group analysis method, which divides the vehicles in the road network data into 3 groups according to the free speed, minimum headway and number of lane changes, and determines the driving tendency corresponding to the vehicle based on the multiple groups of analysis results. The analysis method can also be a cluster analysis, which clusters the free speed, minimum headway and number of lane changes in the road network data, obtains multiple cluster centers, and determines the driving tendency of each vehicle based on the cluster centers. The specific analysis method is determined by the user, and the analysis method is not specifically limited here.
[0058] Optionally, see Figure 3 , according to the free travel speed, minimum headway and lane change number corresponding to each vehicle, determining the driving tendency corresponding to each vehicle in the road network data includes steps S231 to S233, which are described in detail as follows:
[0059] Step S231: clustering the free travel speed, minimum headway and lane change times of each vehicle to obtain a plurality of cluster centers.
[0060] Step S232: Determine the driving tendency corresponding to each cluster center according to the magnitude of the free driving speed in each cluster center.
[0061] In this embodiment, the free speed, minimum headway and number of lane changes of each vehicle in the road network data can be clustered according to the clustering algorithm, and multiple cluster centers are obtained, and the driving tendency corresponding to each cluster center is determined according to the free speed corresponding to each cluster center. The clustering algorithm can be a fuzzy clustering algorithm, and a mean clustering algorithm is also used. The fuzzy clustering algorithm is a mathematical method that describes and classifies things according to certain requirements in a fuzzy mathematical language. The mean clustering algorithm is an iterative clustering analysis algorithm. In the embodiment of the present application, a fuzzy clustering algorithm is preferably used. The fuzzy clustering algorithm in the embodiment of the present application is a fuzzy clustering algorithm based on random forest weighting. For example, the free speed, minimum headway and number of lane changes of each vehicle in the road network data are clustered according to the fuzzy clustering algorithm to obtain three cluster centers. The cluster center with the smallest free speed among the three cluster centers is determined as a conservative tendency, the cluster center with the largest free speed is determined as a radical tendency, and the remaining cluster centers are determined as ordinary tendencies.
[0062] Step S233: Determine the driving tendency corresponding to each vehicle according to the cluster center to which each vehicle belongs.
[0063] In this embodiment, after the driving tendency corresponding to the cluster center is determined, the driving tendency of the vehicles in the cluster center is determined. Clustering is performed directly through multiple data corresponding to each vehicle to obtain multiple cluster centers. The driving tendency of the cluster center is determined to determine the driving tendency corresponding to each vehicle subordinate to the cluster center. The determination of the driving tendency of each vehicle is avoided, and the time for determining the driving tendency is saved.
[0064] Step S240: Obtain the preceding vehicle track and preceding vehicle size corresponding to the preceding vehicle of each vehicle in each driving tendency.
[0065] Step S250: Correcting the following model parameters of the traffic flow model corresponding to each driving tendency according to the preceding vehicle trajectory and the preceding vehicle size.
[0066] In the embodiment of the present application, considering the different sizes of the leading vehicle, the determined minimum headway is different. Therefore, the parameters of the following model can be further determined according to the size of the leading vehicle.
[0067] In some embodiments, the front vehicle trajectory can be input into the car-following model, and the rear vehicle trajectory can be calculated by the car-following model. The model parameters that minimize the error are calibrated by comparing the error between the minimum headway in the calculated value and the actual minimum headway. The error index can be a root mean square percentage, which is used to measure the degree of difference between the minimum headway in the calculated value and the actual minimum headway. The error calibration in the calculation process can be a genetic algorithm, which can perform a global search and optimize it to obtain the minimum error value.
[0068] Step S260: calibrate the free travel speeds of multiple vehicles for each driving tendency to obtain an expected speed distribution corresponding to each driving tendency.
[0069] In the embodiment of the present application, the free travel speeds of all vehicles in each driving tendency may be calibrated to obtain the expected speed distribution corresponding to the vehicles of each driving tendency. The calibration method may be to fit and calibrate the free travel speeds of all vehicles of each driving tendency by normal distribution fitting to obtain the expected speed distribution of the vehicles of each driving tendency.
[0070] Step S270: Correcting the lane-changing model parameters of the traffic flow model corresponding to each driving tendency according to the expected speed distribution and the corrected car-following model parameters.
[0071] In the embodiment of the present application, the high-precision map, road section flow, intersection diversion ratio, expected speed distribution after correction, and the parameters of the following model are input into the model simulation software, and the lane change model determines whether the vehicle in the model simulation software changes lanes. The model parameters that minimize the error are calibrated by calculating the error between the simulated value of the number of lane changes of the vehicle model and the actual number of lane changes. The error calibration algorithm and error index can be the same as the algorithm used to determine the following model parameters, or they can be different, and are not specifically limited here.
[0072] The solution provided in the embodiment of the present application obtains the driving tendency corresponding to each vehicle based on the free driving speed, minimum headway and number of lane changes of each vehicle in the road network data, and then corrects the parameters of the traffic flow model based on multiple driving tendencies, which can improve the accuracy of the parameters of the traffic flow model and make the traffic flow model more realistic.
[0073] See also Figure 4 , Figure 4 A flow chart of a method for correcting a traffic flow model provided by another embodiment of the present application is shown below. Figure 4 The process shown is described in detail, and the correction method of the traffic flow model may specifically include the following steps:
[0074] Step S310: Obtain driving behavior data corresponding to each vehicle in the road network data.
[0075] Step S320: Determine the driving tendency corresponding to each vehicle in the road network data according to the driving behavior data.
[0076] For detailed description of steps S310 to S320 , please refer to steps S110 to S120 , which will not be repeated here.
[0077] Step S330: Obtain the size of each vehicle in the road network data and determine the model of each vehicle.
[0078] In an embodiment of the present application, when calibrating the parameters of the traffic flow model corresponding to vehicles with different driving tendencies, the parameters of the traffic flow model corresponding to vehicles of different models can also be calibrated to further improve the accuracy of the parameters of the traffic flow model. Among them, the model of the vehicle can be determined according to the size of the vehicle. For example, a vehicle with a size smaller than a preset size is determined as a small car, and a vehicle with a size larger than a preset size is determined as a large car. The preset size can be 6m or 10m, and the preset size is not specifically limited here.
[0079] Step S340: Correcting the parameters of the traffic flow model of the vehicles corresponding to each vehicle type with each driving tendency according to the driving behavior data of the vehicles corresponding to each vehicle type with each driving tendency.
[0080] In the embodiment of the present application, after determining the model of each vehicle, the parameters of the traffic flow model of each vehicle corresponding to each model of each driving tendency can be corrected according to the driving behavior data corresponding to the vehicle after determining the driving tendency and the model. Not only the driving tendency is considered, but also the driving influence brought by the model of each model in the traffic process is considered, so that the parameters of the corrected traffic flow model are closer to the real traffic flow. Moreover, in the process of correcting the parameters of the following model, the trajectory and size of the preceding vehicle are also considered, and a refined calibration is realized, so as to achieve the purpose of simulating the diverse driving behaviors in the real traffic flow.
[0081] See also Figure 5 , Figure 5 A flow chart of a method for correcting a traffic flow model provided in another embodiment of the present application is shown. Figure 5 The process shown is described in detail, and the correction method of the traffic flow model may specifically include the following steps:
[0082] Step S410: Obtain driving behavior data corresponding to each vehicle in the road network data.
[0083] Step S420: Determine the driving tendency corresponding to each vehicle in the road network data according to the driving behavior data.
[0084] Step S430: Correcting the parameters of the traffic flow model of the vehicle corresponding to each driving tendency according to the driving behavior data of the vehicle corresponding to each driving tendency.
[0085] For detailed description of steps S410 to S430 , please refer to steps S110 to S130 , which will not be repeated here.
[0086] Step S440: Based on the corrected parameters of the traffic flow model of the vehicle corresponding to each driving tendency, simulate and obtain the traffic flow of the target area corresponding to the road network data.
[0087] The parameters of the corrected traffic flow model are input into the model simulation software, and the traffic flow model of each driving tendency in the model simulation software is corrected, so as to obtain the traffic flow of the target area corresponding to the road network data. Since the vehicle model and driving parameters of each vehicle are calibrated when simulating the road network data, after the corrected traffic flow model parameters are input into the simulation software, the corresponding vehicle model will be automatically matched, so as to correct the parameters of the vehicle model and obtain a simulated traffic flow that is closer to the real traffic flow. It should be noted that before generating the simulated traffic flow model, it is necessary to set the corresponding driving tendency and / or vehicle model label for each traffic flow model, so as to facilitate the automatic matching of the corresponding traffic flow model when inputting the model parameters corrected according to the driving tendency. The method of inputting the parameters of the corrected traffic flow model into the simulation software can be automatic input into the simulation software after correction, or manual input. When manually inputting, you can first manually select the traffic flow model that needs to be corrected or select the traffic flow model with the corresponding driving tendency label, and correct the parameters of the traffic flow model. When manually inputting, you can input the simulation software that obtains the correction parameters, or you can input the corrected parameters into other traffic flow simulation software to realize the data commonality of multiple simulation software. The input method is not specifically limited here.
[0088] See also Figure 6 , which shows a structural block diagram of a correction device 200 for a traffic flow model provided in an embodiment of the present application. The correction device 200 for a traffic flow model is applied to an electronic device 100, and the correction device 200 for a traffic flow model comprises: a driving behavior data acquisition module 210, which is used to acquire driving behavior data corresponding to each vehicle in the road network data; a driving tendency determination module 220, which is used to determine the driving tendency corresponding to each vehicle in the road network data according to the driving behavior data; and a correction module 230, which is used to correct the parameters of the traffic flow model of the vehicle corresponding to each driving tendency according to the driving behavior data of the vehicle corresponding to each driving tendency.
[0089] In some embodiments of the present application, the driving tendency determination module 220 includes: a driving behavior segment determination module, which is used to determine the free driving segment, following segment and number of lane changes corresponding to each vehicle in the road network data according to the driving behavior data; and a driving tendency determination module based on driving behavior segments, which is used to determine the driving tendency corresponding to each vehicle in the road network data based on the free driving segment, following segment and number of lane changes.
[0090] In some embodiments of the present application, the module for determining the driving tendency based on the driving behavior fragments includes: a free driving speed determination module, used to determine the free driving speed corresponding to each vehicle according to the free driving fragment corresponding to each vehicle; a minimum headway determination module, used to determine the minimum headway between each vehicle and the corresponding preceding vehicle according to the following fragment, as the minimum headway corresponding to each vehicle; a driving tendency determination module for each vehicle, used to determine the driving tendency corresponding to each vehicle in the road network data according to the free driving speed, minimum headway and number of lane changes corresponding to each vehicle.
[0091] In some embodiments of the present application, the driving tendency determination module for each vehicle includes: a clustering processing module, which is used to cluster the free driving speed, minimum headway and number of lane changes of each vehicle to obtain multiple cluster centers; a cluster center corresponding driving tendency determination module, which is used to determine the driving tendency corresponding to each cluster center according to the size of the free driving speed in each cluster center; a vehicle driving tendency determination module according to the cluster center, which is used to determine the driving tendency corresponding to each vehicle according to the cluster center to which each vehicle belongs.
[0092] In some embodiments of the present application, the correction module 230 includes: a leading vehicle information acquisition module, which is used to obtain the leading vehicle trajectory and the leading vehicle size corresponding to the leading vehicle of each vehicle in each driving tendency; a following model parameter correction module, which is used to correct the following model parameters of the traffic flow model corresponding to each driving tendency according to the leading vehicle trajectory and the leading vehicle size; an expected speed distribution acquisition module, which is used to calibrate the free driving speeds of multiple vehicles for each driving tendency to obtain the expected speed distribution corresponding to each driving tendency; a lane changing model parameter correction module, which is used to correct the lane changing model parameters of the traffic flow model corresponding to each driving tendency according to the expected speed distribution and the corrected following model parameters.
[0093] In some embodiments of the present application, the driving tendency determination module 220 includes: a vehicle type determination module, used to obtain the size of each vehicle in the road network data and determine the vehicle type of each vehicle; a vehicle type correction parameter module, used to correct the parameters of the traffic flow model of the vehicle corresponding to each vehicle type of each driving tendency according to the driving behavior data of the vehicle corresponding to each vehicle type of each driving tendency.
[0094] In some embodiments of the present application, the traffic flow model correction device 200 also includes: a corrected parameter simulation module, which is used to simulate the traffic flow of the target area corresponding to the road network data based on the corrected parameters of the traffic flow model of the vehicle corresponding to each driving tendency.
[0095] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described devices and modules can refer to the corresponding processes in the aforementioned method embodiments, and will not be repeated here.
[0096] In several embodiments provided in the present application, the coupling between modules may be electrical, mechanical or other forms of coupling.
[0097] In addition, each functional module in each embodiment of the present application can be integrated into a processing module, or each module can exist physically separately, or two or more modules can be integrated into one module. The above integrated modules can be implemented in the form of hardware or software functional modules.
[0098] Please refer to Figure 7 , which shows a structural block diagram of an electronic device provided in an embodiment of the present application. The electronic device 100 can be a switch, a computer, or a control unit with data transmission. The electronic device 100 in the present application may include one or more of the following components: a processor 110, a memory 120, and one or more application programs, wherein the one or more application programs may be stored in the memory 120 and configured to be executed by one or more processors 110, and the one or more programs are configured to execute the method described in the aforementioned method embodiment.
[0099] The processor 110 may include one or more processing cores. The processor 110 uses various interfaces and lines to connect various parts of the entire electronic device 100, and executes various functions and processes data of the electronic device 100 by running or executing instructions, programs, code sets or instruction sets stored in the memory 120, and calling data stored in the memory 120. Optionally, the processor 110 can be implemented in at least one hardware form of digital signal processing (DSP), field-programmable gate array (FPGA), and programmable logic array (PLA). The processor 110 can integrate one or a combination of a central processing unit (CPU), a graphics processing unit (GPU), and a modem. Among them, the CPU mainly processes the operating system, user interface, and application programs; the GPU is responsible for rendering and drawing display content; and the modem is used to process wireless communications. It can be understood that the above-mentioned modem may not be integrated into the processor 110, but may be implemented separately through a communication chip.
[0100] The memory 120 may include a random access memory (RAM) or a read-only memory (ROM). The memory 120 may be used to store instructions, programs, codes, code sets or instruction sets. The memory 120 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for implementing at least one function (such as a touch function, a sound playback function, an image playback function, etc.), instructions for implementing the following various method embodiments, etc. The data storage area may also store data (such as a phone book, audio and video data, chat record data) created by the electronic device 100 during use.
[0101] A computer-readable storage medium is also provided in an embodiment of the present application. A program code is stored in the computer-readable storage medium. The program code can be called by a processor to execute the method described in the above method embodiment.
[0102] The computer-readable storage medium may be an electronic memory such as a flash memory, an EEPROM (electrically erasable programmable read-only memory), an EPROM, a hard disk, or a ROM. Optionally, the computer-readable storage medium includes a non-transitory computer-readable storage medium. The computer-readable storage medium has storage space for program codes that execute any of the method steps in the above method. These program codes can be read from or written to one or more computer program products. The program code can be compressed, for example, in an appropriate form.
[0103] To summarize, the solution provided in the present application analyzes the driving behavior data in the road network data to obtain a variety of driving tendencies, and then corrects the parameters of the traffic flow model according to the driving tendencies. It not only takes into account the actual driving data, but also takes into account the different driving tendencies of the driver during the driving process, thereby improving the accuracy of the parameters of the traffic flow model and effectively improving the authenticity, rationality and diversity of the driving behavior of simulated traffic flow vehicles.
[0104] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present application.
Claims
1. A method for calibrating a traffic flow model, characterized in that: The method comprises: Obtain driving behavior data corresponding to each vehicle in the road network data; Determine, according to the driving behavior data, a free driving segment, a following segment, and a number of lane changes corresponding to each vehicle in the road network data; Determining a driving tendency corresponding to each vehicle in the road network data based on the free driving segments, the following segments, and the number of lane changes; Correcting the parameters of the traffic flow model of the vehicle corresponding to each driving tendency according to the driving behavior data of the vehicle corresponding to each driving tendency; The step of correcting the parameters of the traffic flow model of the vehicle corresponding to each driving tendency according to the driving behavior data of the vehicle corresponding to each driving tendency includes: Obtain the preceding vehicle trajectory and preceding vehicle size corresponding to each preceding vehicle in each driving tendency; Correcting the following model parameters of the traffic flow model corresponding to each driving tendency according to the preceding vehicle trajectory and the preceding vehicle size; Calibrate the free speeds of multiple vehicles for each driving tendency to obtain the expected speed distribution corresponding to each driving tendency; The lane-changing model parameters of the traffic flow model corresponding to each driving tendency are corrected according to the expected speed distribution and the corrected car-following model parameters.
2. The method according to claim 1, characterized in that The determining, based on the free driving segments, the following segments, and the number of lane changes, the driving tendency corresponding to each vehicle in the road network data includes: Determining a free travel speed corresponding to each vehicle according to the free travel segment corresponding to each vehicle; Determine, according to the following segment, a minimum headway distance between each vehicle and a corresponding preceding vehicle as the minimum headway distance corresponding to each vehicle; The driving tendency corresponding to each vehicle in the road network data is determined according to the free travel speed, the minimum headway and the number of lane changes corresponding to each vehicle.
3. The method according to claim 2, characterized in that Determining the driving tendency corresponding to each vehicle in the road network data according to the free travel speed, the minimum headway and the number of lane changes corresponding to each vehicle includes: Performing clustering processing on the free travel speed, minimum headway and lane change times of each vehicle to obtain a plurality of cluster centers; Determining the driving tendency corresponding to each cluster center according to the magnitude of the free driving speed in each cluster center; The driving tendency corresponding to each vehicle is determined according to the cluster center to which each vehicle belongs.
4. The method according to claim 1, characterized in that The method of correcting the parameters of the traffic flow model of the vehicle corresponding to each driving tendency according to the driving behavior data of the vehicle corresponding to each driving tendency further includes: Obtaining the size of each vehicle in the road network data, and determining the model of each vehicle; According to the driving behavior data of the vehicle corresponding to each vehicle type of each driving tendency, the parameters of the traffic flow model of the vehicle corresponding to each vehicle type of each driving tendency are corrected.
5. The method according to any one of claims 1 to 4, characterized in that: The method further comprises: Based on the corrected parameters of the traffic flow model of the vehicle corresponding to each driving tendency, the traffic flow of the target area corresponding to the road network data is simulated.
6. A traffic flow model correction device, characterized in that: include: A driving behavior data acquisition module is used to acquire driving behavior data corresponding to each vehicle in the road network data; A driving behavior segment determination module, used to determine the free driving segment, the following segment and the number of lane changes corresponding to each vehicle in the road network data according to the driving behavior data; A driving tendency determination module based on driving behavior segments, used to determine the driving tendency corresponding to each vehicle in the road network data based on the free driving segments, the following segments and the number of lane changes; A correction module, used for correcting the parameters of the traffic flow model of the vehicle corresponding to each driving tendency according to the driving behavior data of the vehicle corresponding to each driving tendency; The correction module includes a preceding vehicle information acquisition module, a following model parameter correction module, an expected speed distribution acquisition module and a lane change model parameter correction module. The preceding vehicle information acquisition module is used to obtain the preceding vehicle trajectory and preceding vehicle size corresponding to the preceding vehicle of each vehicle in each driving tendency; The car-following model parameter correction module is used to correct the car-following model parameters of the traffic flow model corresponding to each driving tendency according to the front vehicle trajectory and the front vehicle size; The expected speed distribution acquisition module is used to calibrate the free travel speeds of multiple vehicles for each driving tendency to obtain the expected speed distribution corresponding to each driving tendency; The lane-changing model parameter correction module is used to correct the lane-changing model parameters of the traffic flow model corresponding to each driving tendency according to the expected speed distribution and the corrected car-following model parameters.
7. An electronic device, characterized in that: include: one or more processors; Memory; One or more application programs, wherein the one or more application programs are stored in the memory and configured to be executed by the one or more processors, and the one or more programs are configured to execute the method according to any one of claims 1-5.
8. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores program codes, which can be called by a processor to execute the method according to any one of claims 1 to 5.
