CN114677837B - Traffic simulation method and device based on radar data and electronic equipment - Google Patents
Traffic simulation method and device based on radar data and electronic equipment Download PDFInfo
- Publication number
- CN114677837B CN114677837B CN202210262028.7A CN202210262028A CN114677837B CN 114677837 B CN114677837 B CN 114677837B CN 202210262028 A CN202210262028 A CN 202210262028A CN 114677837 B CN114677837 B CN 114677837B
- Authority
- CN
- China
- Prior art keywords
- vehicle
- data
- model parameters
- target
- file
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0125—Traffic data processing
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S13/00—Systems using the reflection or reradiation of radio waves, e.g. radar systems; Analogous systems using reflection or reradiation of waves whose nature or wavelength is irrelevant or unspecified
- G01S13/88—Radar or analogous systems specially adapted for specific applications
- G01S13/93—Radar or analogous systems specially adapted for specific applications for anti-collision purposes
- G01S13/931—Radar or analogous systems specially adapted for specific applications for anti-collision purposes of land vehicles
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0137—Measuring and analyzing of parameters relative to traffic conditions for specific applications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Electromagnetism (AREA)
- Computer Networks & Wireless Communication (AREA)
- Traffic Control Systems (AREA)
Abstract
The application provides a traffic simulation method and device based on radar data and electronic equipment. According to the application, the characteristics that the obtained thunder data is richer and higher in precision compared with the passing data information are utilized on the basis of the obtained thunder data in the real traffic scene, and the vehicle driving model file for describing the dynamic driving behavior of the vehicle in the simulation scene and the path file for describing the driving path information of the vehicle are obtained from the characteristics, so that the traffic simulation is carried out by matching with the obtained road network file, and the method has higher data precision and simulation reduction degree compared with the traditional traffic simulation mode of generating the vehicle path based on the vehicle flow or the passing data and describing the dynamic driving behavior of the vehicle by manually setting parameters.
Description
Technical Field
The present application relates to intelligent traffic technologies, and in particular, to a traffic simulation method and apparatus based on radar data, and an electronic device.
Background
Traffic simulation is a key technology for researching complex traffic problems, and is widely applied to the fields of various traffic algorithm verification, reinforcement learning signal control model training and the like. In the traffic simulation scene, one main factor influencing the simulation deduction effect is the reduction degree of the real traffic environment, namely, the higher the reduction degree of the simulation scene to the real scene is, the better the deduction research effect such as the optimization of the signal control algorithm is based on the reduction degree.
In practical applications, two common simulation loading methods are used: one is based on the vehicle flow loading simulation, namely through the road network edge road section flow and steering data loading simulation obtained, the defect is that the vehicle information of the road network internal road section is lacking and the distortion phenomenon exists; the other is based on vehicle path loading simulation, namely, the monitoring equipment deployed in the entrance way is used for collecting passing data as passing data when each vehicle passes, so that the simulation is loaded, and the defect is that the passing data contains less information and has certain limitation on simulation restoration.
Along with diversification of traffic application scenes, users have higher requirements on scene reduction degree of traffic simulation, and the two simulation loading modes have the problem of lower reduction degree in the current simulation scenes of a large-scale road network, so that the simulation deduction effect performed on the basis is poor.
Disclosure of Invention
The embodiment of the application provides a traffic simulation method, a traffic simulation device and electronic equipment based on thunder data, which are used for carrying out traffic simulation with higher reduction degree through the thunder data and improving the simulation deduction effect.
In a first aspect, an embodiment of the present application provides a traffic simulation method based on radar data, including:
Acquiring historical radar data, wherein the historical radar data comprises radar data of a plurality of road sections;
acquiring initial model parameters from the historical radar data, determining dynamic driving behavior parameters related to a vehicle based on the initial model parameters, and generating a vehicle driving model file based on the dynamic driving behavior parameters;
acquiring a path file according to the historical radar data; the path file comprises a plurality of pieces of vehicle running path information, wherein the vehicle running path information is used for expressing one or more road sections through which a vehicle passes;
and carrying out traffic simulation based on the path file, the vehicle driving model file and the acquired road network file.
In one possible implementation manner, the dynamic driving behavior parameters include at least one of a basic model parameter, a following model parameter and a lane change model parameter;
wherein the basic model parameters are determined based on the initial model parameters, and the basic model parameters are used for expressing basic driving conditions of the vehicle; the following model parameters are determined based on the basic model parameters, and the following model parameters are used for expressing the following time limit of the vehicle; the lane change model parameters are determined based on the initial model parameters, and the lane change model parameters are used for expressing lane change will of the vehicle.
In one possible implementation manner, the basic model parameters at least include a distance value, a speed value and a deceleration value of the vehicle, and the following model parameters include a driver expected time interval and a driver driving perfection;
the determining the following model parameter for expressing the following time interval of the vehicle based on the basic model parameter comprises the following steps:
screening vehicles affected by the front vehicle from the historical radar data to serve as target rear vehicles, and taking the front vehicle of the target rear vehicles as target front vehicles; wherein, the vehicle affected by the preceding vehicle is a vehicle with a distance value smaller than a preset distance from the preceding vehicle;
determining a driver expected time interval according to the distance value, the speed value and the deceleration value of the target front vehicle and the target rear vehicle; wherein, the expected time interval of the driver is used for restraining the running speed of the simulation vehicle;
and determining the following model parameters according to the expected time interval of the driver and the obtained driving perfection of the driver.
In one possible implementation manner, the initial model parameters at least include a lane-level vehicle flow in the road section and lane-level vehicle queuing data in the road section;
the determining the lane change model parameter for expressing the lane change willingness of the vehicle based on the initial model parameter comprises the following steps:
And determining the lane change model parameters by adopting a genetic algorithm based on the vehicle flow and the vehicle queuing data.
In a possible implementation manner, the historical radar data includes radar data under multiple scenes, multiple time periods and multiple vehicle types, the initial model parameters correspond to multiple vehicle types in a target scene under a target time period, and the vehicle driving model file is used for describing dynamic driving behaviors of vehicles of the multiple vehicle types under the target scene and the target time period respectively.
In one possible implementation manner, the obtaining the path file according to the historical radar data includes:
selecting the thunder data matched with the target road section from the historical thunder data as the thunder data to be restored;
acquiring the path file according to the to-be-restored radar data; the path file includes a plurality of pieces of vehicle travel path information, and the vehicle travel path information is used for expressing that the vehicle passes through one or more road sections in the target road sections.
In one possible implementation manner, the vehicle travel path information is obtained by:
analyzing the to-be-restored thunder data to obtain thunder passing data; the lightning passing data comprises a vehicle identifier of a target vehicle, a vehicle type and time for the target vehicle to pass through one or more intersections in the target road section;
And generating a vehicle travel path of the target vehicle based on the thunder passing data.
In a second aspect, an embodiment of the present application provides a traffic simulation device based on radar data, including:
a data acquisition unit configured to acquire historical radar data including radar data of a plurality of road segments;
a model determining unit, configured to obtain initial model parameters from the historical radar data, determine dynamic driving behavior parameters associated with the vehicle based on the initial model parameters, and generate a vehicle driving model file based on the dynamic driving behavior parameters;
a path determining unit for obtaining a path file according to the historical radar data; the path file comprises a plurality of pieces of vehicle running path information, wherein the vehicle running path information is used for expressing one or more road sections through which a vehicle passes;
and the traffic simulation unit is used for carrying out traffic simulation based on the path file, the vehicle driving model file and the acquired road network file.
In a third aspect, an embodiment of the present application further provides an electronic device, including: a processor and a machine-readable storage medium;
the machine-readable storage medium stores machine-executable instructions executable by the processor;
The processor is configured to execute machine-executable instructions to implement the steps of the methods disclosed above.
According to the technical scheme, the embodiment is based on the acquired thunder data in the real traffic scene, and the characteristics that the thunder data is richer and higher in precision compared with the traditional passing data information are utilized, and the vehicle driving model file for describing the dynamic driving behavior of the vehicle in the simulation scene and the path file for describing the driving path information of the vehicle are acquired from the thunder data, so that the acquired road network file is matched for traffic simulation, and the embodiment has higher data precision and simulation reduction degree compared with the traditional traffic simulation mode of generating the vehicle path based on the traffic flow data or the passing data and describing the dynamic driving behavior of the vehicle through the artificial setting parameters.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the disclosure and together with the description, serve to explain the principles of the disclosure.
FIG. 1 is a flow chart of a method according to an embodiment of the present application;
FIG. 2 is another flow chart provided by an embodiment of the present application;
FIG. 3 is a block diagram of a device according to an embodiment of the present application;
Fig. 4 is a block diagram of an electronic device according to an embodiment of the present application.
Detailed Description
Reference will now be made in detail to exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, the same numbers in different drawings refer to the same or similar elements, unless otherwise indicated. The implementations described in the following exemplary examples do not represent all implementations consistent with the application. Rather, they are merely examples of apparatus and methods consistent with aspects of the application as detailed in the accompanying claims.
The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. As used in this specification and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise.
In order to better understand the technical solution provided by the embodiments of the present application and make the above objects, features and advantages of the embodiments of the present application more obvious, the technical solution in the embodiments of the present application will be described in further detail below with reference to the accompanying drawings.
Referring to fig. 1, fig. 1 is a flowchart of a method provided in an embodiment of the present application. The flow can be applied to any electronic equipment with the traffic simulation program running capability, such as a personal computer, a server, a mobile terminal and the like; the traffic simulation program herein may be mainstream traffic simulation software in current practical applications, such as SUMO (Simulation of Urban Mobility, a microscopic traffic simulation software), VISSIM (a simulation modeling tool for running urban traffic and public traffic), or other traffic simulation software that is not mainstream or self-developed, and the embodiment is not particularly limited to the traffic simulation program or software applying the method. For easy understanding and description, the method disclosed in this embodiment is described below by taking SUMO with strong relative openness, good expansibility and high portability as an example; it should be clear that, there is a certain difference between the links of data calling and simulation loading, but those skilled in the art can apply the method disclosed in this embodiment to other traffic simulation programs such as VISSIMs without performing creative work.
As shown in fig. 1, the process may include the steps of:
Step 101, acquiring historical radar data, wherein the historical radar data comprises radar data of a plurality of road segments.
In this embodiment, the radar data mainly refers to traffic data in a real scene acquired by radar and/or video, and may be generally collected by a radar vehicle detector or other devices. For example, the radar vehicle detector may collect radar data of all objects (including vehicles, non-vehicles, pedestrians on roads, etc.) within a detection range every 100ms or other frequencies, for example, collect information of a plurality of vehicles on a road at a certain moment (including but not limited to vehicle position coordinates, license plate information, road section information, intersection information, collection time, etc.) and determine data required for implementing the method subsequently (including but not limited to position coordinates of each vehicle at the current moment, lanes, real-time intervals between vehicles, queuing lengths of each lane, lane changing conditions, etc.), and can obtain more abundant traffic data than devices such as electric alarms at intersections, bayonets, etc. which can collect information only when each vehicle passes through the detection point, thereby providing a basis for implementing the embodiment.
In this embodiment, the road section may also include an intersection at the junction between roads, that is, the intersection is regarded as a special position in the road section; the aforementioned radar vehicle detectors may be installed in various areas including intersections in a road section to acquire radar data under the corresponding areas.
Optionally, when traffic simulation is required, the radar data in all the areas can be acquired to comprehensively simulate; the method can also independently acquire the thunder data at the intersection or acquire the thunder data at other areas in the road section which does not contain the intersection, so that traffic simulation is respectively carried out on the intersection or the non-intersection, and the simulation effect on the specific road area is improved pertinently. Preferably, when the radar data of the vehicle in a certain road section is acquired, the radar data may further include a direction of arrival and departure of the vehicle when passing through the road section, a specific lane in which the vehicle is located, a lane change situation, and the like, which is not limited in this embodiment.
In order to facilitate distinguishing from the following to-be-restored radar data for the target road segment, the radar data including the information in the plurality of road segments acquired in step 101 is referred to as historical radar data, and is used as a data base for determining the vehicle driving model and the vehicle path subsequently.
Step 102, obtaining initial model parameters from the historical radar data, determining dynamic driving behavior parameters associated with the vehicle based on the initial model parameters, and generating a vehicle driving model file based on the dynamic driving behavior parameters.
In this embodiment, the traffic simulation needs to be performed based on a vehicle driving model file, a path file, and a road network file, where the vehicle driving model file is generated in the manner of step 102. Specifically, after the historical radar data is acquired, the historical radar data needs to be analyzed and extracted to be used as a basis for calculating relevant parameters of a vehicle driving model subsequently, for convenience of distinction, the data obtained through direct analysis and extraction of the historical radar data are called initial model parameters, such as real-time speed, front-rear vehicle distance, road section speed limit and the like of a specific vehicle in a road section, parameters which are determined based on the initial model parameters and are used for being subsequently applied to the vehicle driving model are called dynamic driving behavior parameters, such as speed variance, lane change willingness, expected following time interval and the like of the vehicle in the road section, and vehicle driving model files (named add.xml in SUMO) required by simulation are generated based on the dynamic driving behavior parameters.
The initial model parameters may be obtained by calculation at a corresponding device for performing data acquisition, for example, the thunder vision vehicle detector may determine the real-time speed of the vehicle according to the position coordinates of the same vehicle in two adjacent times of data acquisition, the time interval between two times of data acquisition, determine the distance between front and rear vehicles according to the position coordinates of two adjacent vehicles in the same lane, and so on; the corresponding equipment can also only be responsible for data acquisition, the acquired data such as vehicle position coordinates, license plate information, road section information, intersection information, acquisition time and the like are transmitted to the electronic equipment for executing the method, and the equipment acquires initial model parameters from the historical thunder data in the mode.
There are various alternative embodiments for determining the dynamic driving behavior parameters associated with the vehicle based on the initial model parameters described above, one or more of which will be given by way of example hereinafter and will not be described in detail.
Step 103, obtaining a path file according to the historical radar data; the path file contains a plurality of pieces of vehicle travel path information, and the vehicle travel path information is used for expressing one or more road sections through which the vehicle passes.
In this embodiment, the traffic simulation needs to be performed based on a vehicle driving model file, a path file, and a road network file, where the path file is generated in the manner of step 103. Specifically, after the historical radar data is acquired, path characteristic data of a vehicle passing road section needs to be extracted therefrom to generate a path file (which may be named rou. Xml in SUMO) for describing each road section through which the vehicle passes, which is used as a basis for vehicle path loading generation in a simulation scene. The path file is composed of a plurality of pieces of vehicle driving path information, and each piece of vehicle driving path information is used for expressing that a certain vehicle drives across one or more road sections. Alternatively, since the intersection at the intersection junction between two adjacent road sections is fixed, the vehicle travel path information may not include information related to the number of the intersection or the like.
As an optional embodiment, the radar data matched with the target road section may be selected from the historical radar data as the radar data to be restored, and the path file may be obtained according to the radar data to be restored.
That is, the thunder data for determining the driving model of the vehicle is distinguished from the thunder data for determining the path of the vehicle, for example, when it is necessary to perform traffic simulation for a specified target road section to perform signal control algorithm optimization, the thunder data, a part of which contains only the target road section-related information, is selected from the acquired historical thunder data containing arbitrary road section-related information, and is referred to as the thunder data to be restored. Further training a vehicle driving model according to the advantage of larger information quantity of the historical radar data so as to improve the reduction degree of the vehicle driving model to the driving condition in the real scene; and determining a path file aiming at the target road section according to the to-be-restored thunder data so as to accurately acquire the driving path information of the vehicle passing through the target road section and improve the data extraction efficiency. In the path file generated for the target road section, the driving path information of the vehicle driving through one or more road sections in the target road section is recorded, so that the simulated vehicle can be accurately generated in the target road section for driving in the subsequent traffic simulation, and the simulation deduction efficiency for the specific road section is improved.
As an alternative embodiment, further, the above-described vehicle travel path information may be acquired by: analyzing the to-be-restored thunder data to obtain thunder passing data; and generating a vehicle driving path of the target vehicle based on the thunder passing data. The lightning passing data may include a vehicle identifier of the target vehicle, a vehicle type, and a time when the target vehicle passes through one or more intersections in the target road section.
That is, when generating a path file for a target link, since different roads are connected through each intersection, it is mainly used as the thunder passing data for describing the condition of the vehicle passing through the link in the to-be-restored thunder passing data, and the driving path related data is generated for each vehicle according to the time of each vehicle passing through each intersection or link in the target link from the thunder passing data.
Alternatively, as a specific example, the vehicle travel path information for a certain vehicle in the path file may contain data as shown in table 1.
TABLE 1
Wherein, the depart represents the time when the vehicle appears in the road network, for example, depart= "0.00" represents that the vehicle appears in the simulation scene when the simulation starts running; id represents a unique identification of a vehicle, can be data obtained by removing a Chinese field from a license plate, can also be generated by other calculation rules, and can be used for only representing a specific vehicle in a path file; type represents a vehicle type and is used for calling when simulation deduction is carried out on different types of vehicles, such as distinguishing a household car from a truck, distinguishing a bus from a non-bus and the like; the examples in the segment numbering table where the edges represent the sequential passage of a vehicle represent that the vehicle has sequentially passed five segments numbered 129_2, 5076767597_2, 507647726_2, 507647723_3, 507647721_3. Alternatively, the corresponding intersection numbers may be set for the intersections in the road segments separately, and the intersection numbers through which the vehicle passes may not be included in the vehicle travel path information as in table 1 above, the vehicle paths may be described using the order in which the vehicles pass through the intersections, and the like, which is not limited in this embodiment. In addition, other parameters, such as information of a scene or a period when the vehicle passes through the road section, may be added to the vehicle driving path according to actual requirements, which is not limited in this embodiment.
And 104, carrying out traffic simulation based on the path file, the vehicle driving model file and the acquired road network file.
In this embodiment, the traffic simulation needs to be performed based on a vehicle driving model file, a path file, and a road network file, where the vehicle driving model file and the path file may be acquired in the manners described in step 102 and step 103, respectively, and the acquisition manner of the road network file is not limited in this embodiment, for example, the road network file may be converted into the road network file (named as net. Xml in SUMO) based on the existing map data file (for example, PBF or OSM format, etc.), or the road network file with relatively higher accuracy may be generated based on the analysis of the video image data about the target road section recorded in the thunder data, so as to further improve the simulation reduction degree, and so on.
By performing traffic simulation, deduction can be performed by using the generated simulation scene, for example, the function of verifying the effect of the signal control optimization algorithm is provided for the signal control algorithm: firstly, operating an original signal control scheme in a simulation scene to obtain a simulation analysis result; then, carrying out algorithm optimization on the information control scheme, and then loading the information control scheme into the same simulation scene to obtain a simulation analysis result aiming at the optimized information control algorithm, and comparing the front simulation analysis result with the rear simulation analysis result so as to verify whether the optimized information control scheme is effective; the higher the reduction degree of the simulation scene is, the more accurate the verification result is.
Similarly, as an optional embodiment, different scenes, time periods and vehicle types can be divided to generate more accurate and more targeted simulation scenes so as to correspond to more application scenes: the vehicle driving model file and/or the path file of each vehicle type under the target scene and the target time period can be obtained based on the historical thunder data containing various scenes, various time periods and various vehicle types, so that traffic simulation for distinguishing different vehicle types is carried out according to the target scene and the target time period, specific simulation deduction is carried out, and the optimization efficiency of a signal control algorithm is improved.
For example, the historical radar data includes radar data under multiple scenes, multiple time periods and multiple vehicle types, so that the obtained initial model parameters can be corresponding to the multiple vehicle types in the target scene under the target time period, and the generated vehicle driving model file is used for describing the dynamic driving behaviors of the vehicles of the multiple vehicle types under the target scene and the target time period respectively. Similarly, a driving model file of the target vehicle in a plurality of scenes in the target vehicle model and the target time period can be obtained in a similar manner, or a path file of the target vehicle in a plurality of scenes in the target vehicle model and the target time period can be obtained, and the description is omitted here.
Optionally, specific classification modes of scenes, time periods and vehicle types can be set according to actual requirements, for example, when the influence of different types of roads on traffic needs to be deduced, the scenes can be divided according to the modes of 'intersection area/road section area' or 'trunk road/branch road/expressway', and when the influence of different weather on traffic needs to be deduced, the scenes can be divided according to the modes of 'sunny/rainy/fog/snow/hail', and the like; the vehicle type can be divided into a bus/non-bus to simulate and analyze the influence of a special bus lane on traffic, or a small car (such as a household car)/a large car (such as a truck and a bus), and the like; similarly, the time period can be divided into "peak/flat peak", "early peak/late peak/other time period", etc. according to the requirements, and the specific classification basis of the scene, the time period and the vehicle type in the embodiment is not limited.
Thus, the flow shown in fig. 1 is completed.
As can be seen from the flow shown in fig. 1, the embodiment is based on the obtained radar data in the real traffic scene, and utilizes the characteristics that the radar data is richer in information and higher in accuracy compared with the traditional passing data, and the vehicle driving model file for describing the dynamic driving behavior of the vehicle in the simulation scene and the path file for describing the driving path information of the vehicle are obtained from the radar data, so that the embodiment is matched with the obtained road network file to perform traffic simulation, and has higher data accuracy and simulation reduction degree compared with the traditional traffic simulation mode of generating the vehicle path based on the vehicle flow or the passing data and describing the dynamic driving behavior of the vehicle by manually setting parameters.
Furthermore, there are a number of alternative embodiments for determining the dynamic driving behavior parameters associated with the vehicle based on the initial model parameters in step 102 above, several of which are given here by way of example:
as an optional embodiment, the dynamic driving behavior parameters may include at least one of a basic model parameter, a following model parameter and a lane changing model parameter, and may be calibrated by different methods according to characteristics of different parameters, so that calibration time can be saved to a certain extent. Wherein the basic model parameters are determined based on the initial model parameters, and the basic model parameters are used for expressing basic driving conditions of the vehicle; the following model parameters are determined based on the basic model parameters, and the following model parameters are used for expressing the following time limit of the vehicle; the lane change model parameters are determined based on the initial model parameters, and the lane change model parameters are used for expressing lane change will of the vehicle.
Optionally, the basic model parameters may include a distance value, a speed value, and a deceleration value of the vehicle, and the following model parameters for expressing a following time interval of the vehicle are determined based on the basic model parameters, specifically, the vehicle affected by the preceding vehicle is screened from the historical radar data to be a target following vehicle, and the preceding vehicle of the target following vehicle is taken as a target preceding vehicle; determining a driver expected time interval according to the distance value, the speed value and the deceleration value of the target front vehicle and the target rear vehicle; and determining the following model parameters according to the expected time interval of the driver and the obtained driving perfection of the driver.
Wherein, the vehicle affected by the preceding vehicle is a vehicle with a distance value smaller than a preset distance from the preceding vehicle; the expected time interval of the driver is used for restraining the running speed of the simulation vehicle; the driver perfection may be obtained in various ways, for example, the driver perfection received in advance, the driver perfection adjusted in real time according to the simulation effect, and the like, which is not limited in this embodiment.
Optionally, the initial model parameters may include a vehicle flow rate in a road segment and vehicle queuing data in the road segment, and the lane change model parameters for expressing a lane change intention of the vehicle are determined based on the initial model parameters, specifically, a genetic algorithm is adopted and the lane change model parameters are determined based on the vehicle flow rate and the vehicle queuing data.
Wherein, the vehicle flow and queuing data can be divided into different orders, such as crossing level, road section level, lane level, etc.; as a preferred embodiment, lane-level vehicle flow and queuing data may be used herein to accurately describe the vehicle flow and queuing conditions in each lane in the multi-lane road section, respectively, so as to improve simulation accuracy and restoration effect.
Alternatively, as a specific example, the base model parameters in the vehicle driving model file may contain data as shown in table 2.
TABLE 2
Wherein:
accel is an acceleration value describing the vehicle acceleration capability, v t For the real-time speed of the vehicle at the time t, the coordinate position change and sampling interval calculation of the same vehicle sampled twice in the thunder data can be utilized to determine, the data of all vehicles in the road network at each time are correspondingly calculated, and the maximum value is taken as acel from the values larger than 0;
the decel is a deceleration value and is used for describing the deceleration capacity of the vehicle, the calculation mode is similar to that of the acel, and after the absolute value is taken from the value smaller than 0, 99.9% quantile is used as the decel;
the emergencyDecel is a physical maximum deceleration value, is used for describing the extremely limited capability of the vehicle in an emergency, is similar to decel in calculation mode, takes an absolute value from a value smaller than 0, and takes the maximum value as the emergencyDecel;
length is a vehicle length value, namely the length of a vehicle body, and can be extracted from the thunder data;
the minGap is a vehicle distance value, namely the distance from the front vehicle tail to the rear vehicle head when the vehicle is parked, and the minimum value can be taken as the minGap after all the vehicle distance conditions are directly extracted from the thunder data;
the maximum speed is the maximum speed value, namely the maximum vehicle speed in the road network, and the maximum value can be taken as the maximum speed after all real-time vehicle speeds are directly extracted from the thunder data;
The speed factor is a speed factor for describing the driving speed willingness of the vehicle, the product of the speed limit value of the corresponding lane and the speed factor is the expected speed of the vehicle, v is the instantaneous speed of the vehicle, v lim The speed limit of the lane where the vehicle is located is set;
the speed dev is a speed variance value, the calculation mode is similar to that of a speed factor, and the quotient of the instantaneous speed and the speed limit of the vehicle is obtained by taking a standard deviation;
vClass is a vehicle type and can be extracted from the radar data.
The parameters accel, decel, emergencyDecel, minGap and the like in the basic model parameters can be used as the calculation basis of the following model parameters, so that the following model parameters can be calculated and calibrated through a formula.
Alternatively, as a specific example, the following model parameters in the vehicle driving model file may include data as shown in table 3, and the following model may be the SUMO default following model Krauss or may be adjusted to other following models.
TABLE 3 Table 3
Wherein:
tau is the (minimum) time interval expected by the driver, and the speed v of the front vehicle is utilized by screening vehicles affected by the front vehicle (i.e. front and rear vehicles with a distance between two vehicles smaller than a preset value, such as front and rear vehicles with a distance between vehicles smaller than 100 meters) l Speed v of rear vehicle f The distance gap between two vehicles (the distance from the front vehicle tail to the rear vehicle head) and the decel deceleration value are determined through calculation according to the corresponding formulas in the table 2, and the data of all vehicles in the road network are calculated and then 0.1% quantile is taken as tau in the following model parameter;
sigma is the driver driving perfection, and the larger the value is, the lower the driver driving perfection is, namely the more the driver driving perfection deviates from the optimal driving condition in the ideal.
In practical application, the maximum safe vehicle speed is calculated through the following model so as to restrict the vehicles in the simulation scene to run at a relatively proper speed, and avoid collision or overlarge distance between the front vehicle and the rear vehicle and deviate from the actual situation. Alternatively, when the driver driving perfection is not considered (i.e., assumed sigma is 0), the vehicle speed is v in the simulation scene l Is set to a maximum safe vehicle speed v of a rear vehicle which follows the vehicle and has a vehicle distance from the rear vehicle smaller than a preset vehicle distance safe Can be determined by the following equation 1:
L(v f )+v f τ<L(v l ) +gap (equation 1)
Wherein L (v) f ) For the braking distance of the rear vehicle, L (v l ) The tau is the braking distance of the front vehicle, namely tau obtained by the calibration; will v l Substituting τ and gap into the formula 1, and taking the equality of the left side and the right side of the formula 1, and obtaining the velocity v of the vehicle after the solution f Namely the maximum safe speed v of the rear vehicle under the corresponding condition safe I.e. the speed of the preceding vehicle is v l The speed of the rear vehicle is v safe And under the condition that the distance between the two vehicles is gap, the front vehicle and the rear vehicle brake simultaneously, and when the two vehicles stop, the front vehicle and the rear vehicle just contact and do not collide.
Therefore, in the simulation scene, the following vehicle v can be calculated by the following model and the formula 1 safe And restraining the running speed of the vehicle by the method, when the speed is lower than the valueAcceleration is performed when the value exceeds the value, and deceleration is performed when the value exceeds the value.
Alternatively, since there are other disturbance factors such as the reaction time of the driver, the driving style, etc. in the real scene, the vehicle does not travel at a constant speed, and thus can be driven by the driving force of the driver at v safe Random disturbance is carried out on the basis of the simulation to serve as the rear vehicle driving speed in the simulation so as to improve the simulation reduction degree.
There are various alternative embodiments for randomly perturbing the velocity, which are not limited in this example; for example, the following vehicle speed may be determined by the following equation 2:
wherein sigma is the driving perfection sigma of the driver; v safe The maximum safe vehicle speed of the rear vehicle when the assumed sigma is 0, which is determined for the calculation; the rand function takes random value in the corresponding interval to simulate the actual speed of the rear vehicle in the simulation and the maximum safe speed v under ideal condition safe A speed difference exists between the two; a is a preset speed threshold, i.e. when v safe After exceeding the speed threshold, the random disturbance range is defined by (0, σv safe ) Change to (0, σa) to avoid v safe When the speed of the rear vehicle is larger, the speed of the rear vehicle changes too fast and deviates from the actual situation.
Alternatively, as a specific example, the lane-changing model parameters in the vehicle driving model file may include data as shown in table 4, and the lane-changing model may be the SUMO default lane-changing model LC2013 or may be adjusted to other lane-changing models.
TABLE 4 Table 4
Wherein:
lcstratic is used to indicate the willingness to make strategic changes, the larger the lcstratic value, the earlier the change is relative;
lcSpeedGain is used to indicate a desire to change lanes to increase speed, with larger lcSpeedGain being relatively more frequent;
the lclothahead left is used to represent the factor used to configure the strategic look-ahead distance when a left lane change is required (relative to right look-ahead);
lcasserve is used to indicate how much lower back-and-forth clearance on the target lane is willing to be accepted.
The lane change model parameters can be obtained through calibration of a genetic algorithm according to the lane-level vehicle flow and lane-level vehicle queuing data in the initial model parameters so as to simulate the lane change will of the vehicles in each lane in a real scene, and the embodiment is not limited to the type or the use mode of the genetic algorithm which is specifically adopted.
Thus far, the description of several alternative embodiments of determining the dynamic driving behavior parameters corresponding to the vehicle driving model file based on the initial model parameters in step 102 is completed.
In order to enable those skilled in the art to better understand the technical solution provided by the embodiment of the present application, the embodiment of the present application further provides a flowchart shown in fig. 2, so as to implement the above method disclosed in the embodiment of the present application, where the flowchart may include the following steps:
step 201, historical radar data is extracted and parsed.
In this embodiment, the data extraction and analysis are performed on the obtained historical radar data to obtain the radar road network data required by the road network file to be determined later and the initial model parameters required by the vehicle driving model file to be determined. As an alternative embodiment, the initial model parameters may be subdivided into historical radar passing data, radar traffic parameters and radar track data, and specific meanings and contents thereof will be given in connection with specific steps, which are not described herein.
Step 202, analyzing the data of the radar road network;
step 203, simulating road network conversion.
As an alternative embodiment, after the sensing device, such as a radar vehicle detector, acquires the radar data, the radar road network data matched with the radar track data can be obtained, the road side line and the mark marking information are recorded in the form of multi-section lines and polygons in the radar road network data, the coordinates and the shape information of the center point of the intersection can be automatically identified and extracted according to the road side line information, and then a road network file (named as net. Xml in SUMO) containing elements such as points, lines, connectors and the like is generated in a semi-automatic mode combined with the script by manual marking.
Step 204, analyzing historical radar passing data and analyzing radar traffic parameters;
step 205, vehicle flow extraction;
and 206, queuing data extraction.
As an optional embodiment, historical radar passing data recording the lane-level driving-out flow under each period and radar traffic parameters recording the lane-level queuing length under each period and the like can be extracted from the historical radar data to serve as the basis for calibrating the subsequent lane-changing model parameters.
Step 207, analyzing the thunder track data;
and step 208, parameter sensitivity analysis.
As an optional embodiment, the radar track data representing the position coordinates of each vehicle in the acquisition range at each moment may be extracted from the historical radar track data, so as to determine the real-time speed, the vehicle distance, the lane where each vehicle is located, and so on, to calculate the basic model parameters and part of the initial model parameters required by the following model parameters, and the specific content may be referred to the related description of the step 102 and will not be repeated here.
As an alternative embodiment, the sensitivity of each parameter can be determined through analysis of variance, and the parameter with the greatest influence on the calibration target is selected as the parameter to be calibrated in the basic model and the following model, for example, each parameter exemplarily described in the foregoing table 2 and table 3 is the parameter with the great influence on the calibration target, which is screened through analysis of variance.
And step 209, calibrating parameters.
In this embodiment, the lane change model parameters for expressing the lane change will of the vehicle may be calibrated by a genetic algorithm based on the traffic of the lane level in the road section and the vehicle queuing data of the lane level in the road section obtained in steps 204-206, and the following model parameters for expressing the following time limit of the vehicle may be calculated and calibrated by a corresponding formula based on the initial model parameters obtained in steps 207 and 208, and the specific calibration method may be referred to in the foregoing step 102 and will not be repeated here.
Step 210, extracting and analyzing the to-be-restored radar data;
step 211, analyzing the data of the lightning passing vehicle to be restored;
and step 212, extracting path data.
As an alternative embodiment, the to-be-restored radar data may be obtained by selecting data matched with the target road section from the historical radar data, or may be obtained from the data acquisition device directly independent of the historical radar data, which is not limited in this embodiment. The path data extraction is performed based on the to-be-restored radar passing data to generate the path file required for the simulation, and the specific generation mode thereof can be referred to the related description of the step 103, which is not repeated here.
Step 213, simulate loading.
And loading the generated road network file, the vehicle driving model file and the path file to perform traffic simulation so as to obtain a simulation scene with higher reduction degree.
So far, the description of the flow example shown in fig. 2 is completed.
The method provided by the embodiment of the application is described above, and the device provided by the embodiment of the application is described below:
referring to fig. 3, fig. 3 is a block diagram of an apparatus according to an embodiment of the present application. As shown in fig. 3, the apparatus may include:
a data acquisition unit 301 for acquiring historical radar data, the historical radar data including radar data of a plurality of road segments;
a model determining unit 302, configured to obtain initial model parameters from the historical radar data, determine dynamic driving behavior parameters associated with the vehicle based on the initial model parameters, and generate a vehicle driving model file based on the dynamic driving behavior parameters;
a path determining unit 303 for acquiring a path file according to the above-mentioned historical radar data; the path file comprises a plurality of pieces of vehicle running path information, wherein the vehicle running path information is used for expressing one or more road sections through which a vehicle passes;
and a traffic simulation unit 304, configured to perform traffic simulation based on the path file, the vehicle driving model file, and the acquired road network file.
Optionally, the dynamic driving behavior parameters in the model determining unit 302 include at least one of a base model parameter, a following model parameter, and a lane change model parameter; the basic model parameters are determined based on the initial model parameters, and the basic model parameters are used for expressing the basic driving condition of the vehicle; the following model parameters are determined based on the basic model parameters, and the following model parameters are used for expressing the following time limit of the vehicle; the lane change model parameters are determined based on the initial model parameters, and the lane change model parameters are used for expressing lane change will of the vehicle.
Optionally, the basic model parameters at least comprise a distance value, a speed value and a deceleration value of the vehicle; the model determining unit 302 is specifically configured to determine a following model parameter for expressing a following time interval of the vehicle based on the basic model parameter: screening vehicles affected by the front vehicle from the historical radar data to serve as target rear vehicles, and taking the front vehicle of the target rear vehicles as target front vehicles; wherein, the vehicle affected by the preceding vehicle is a vehicle with a distance value smaller than a preset distance from the preceding vehicle; determining a driver expected time interval according to the distance value, the speed value and the deceleration value of the target front vehicle and the target rear vehicle; wherein, the expected time interval of the driver is used for restraining the running speed of the simulation vehicle; and determining the following model parameters according to the expected time interval of the driver and the obtained driving perfection of the driver.
Optionally, the initial model parameters at least comprise vehicle flow for expressing the level of lanes in the road section and vehicle queuing data for expressing the level of lanes in the road section; the model determining unit 302 is specifically configured to, when determining lane change model parameters for expressing a lane change intention of the vehicle based on the initial model parameters: and determining the lane change model parameters by adopting a genetic algorithm based on the vehicle flow and the vehicle queuing data.
Optionally, the historical radar data comprises radar data under various scenes, various time periods and various vehicle types; the initial model parameters in the model determining unit 302 correspond to multiple vehicle types in a target scene in a target period, and the vehicle driving model file is used for describing dynamic driving behaviors of vehicles of the multiple vehicle types in the target scene and the target period respectively.
Alternatively, the path determining unit 303 is specifically configured to, when acquiring a path file according to the historical radar data: selecting the thunder data matched with the target road section from the historical thunder data as the thunder data to be restored; acquiring the path file according to the to-be-restored radar data; the path file includes a plurality of pieces of vehicle travel path information, and the vehicle travel path information is used for expressing that the vehicle passes through one or more road sections in the target road sections.
Alternatively, the path determining unit 303 is specifically configured to, when acquiring the vehicle travel path information: analyzing the to-be-restored thunder data to obtain thunder passing data; the lightning passing data comprises a vehicle identifier of a target vehicle, a vehicle type and time for the target vehicle to pass through one or more intersections in the target road section; and generating a vehicle travel path of the target vehicle based on the thunder passing data.
The structural description of the apparatus shown in fig. 3 is thus completed.
The embodiment of the application also provides a hardware structure of the device shown in fig. 3. Referring to fig. 4, fig. 4 is a block diagram of an electronic device according to an embodiment of the present application. As shown in fig. 4, the hardware structure may include: a processor and a machine-readable storage medium storing machine-executable instructions executable by the processor; the processor is configured to execute machine-executable instructions to implement the methods disclosed in the above examples of the present application.
Based on the same application concept as the above method, the embodiment of the present application further provides a machine-readable storage medium, where a number of computer instructions are stored, where the computer instructions can implement the method disclosed in the above example of the present application when the computer instructions are executed by a processor.
By way of example, the machine-readable storage medium may be any electronic, magnetic, optical, or other physical storage device that can contain or store information, such as executable instructions, data, and the like. For example, a machine-readable storage medium may be: RAM (Radom Access Memory, random access memory), volatile memory, non-volatile memory, flash memory, a storage drive (e.g., hard drive), a solid state drive, any type of storage disk (e.g., optical disk, dvd, etc.), or a similar storage medium, or a combination thereof.
The system, apparatus, module or unit set forth in the above embodiments may be implemented in particular by a computer chip or entity, or by a product having a certain function. A typical implementation device is a computer, which may be in the form of a personal computer, laptop computer, cellular telephone, camera phone, smart phone, personal digital assistant, media player, navigation device, email device, game console, tablet computer, wearable device, or a combination of any of these devices.
For convenience of description, the above devices are described as being functionally divided into various units, respectively. Of course, the functions of each element may be implemented in the same piece or pieces of software and/or hardware when implementing the present application.
It will be appreciated by those skilled in the art that embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, embodiments of the application may take the form of a computer program product on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
Moreover, these computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
The foregoing is merely exemplary of the present application and is not intended to limit the present application. Various modifications and variations of the present application will be apparent to those skilled in the art. Any modification, equivalent replacement, improvement, etc. which come within the spirit and principles of the application are to be included in the scope of the claims of the present application.
Claims (7)
1. A traffic simulation method based on radar data, the method comprising:
acquiring historical radar data, wherein the historical radar data comprises radar data of a plurality of road sections;
acquiring initial model parameters from the historical radar data, determining dynamic driving behavior parameters associated with a vehicle based on the initial model parameters, and generating a vehicle driving model file based on the dynamic driving behavior parameters;
acquiring a path file according to the historical radar data; the path file comprises a plurality of pieces of vehicle driving path information, wherein the vehicle driving path information is used for expressing one or more road sections through which a vehicle passes;
carrying out traffic simulation based on the path file, the vehicle driving model file and the acquired road network file;
wherein the dynamic driving behavior parameters include at least one of a base model parameter, a following model parameter, and a lane change model parameter; the following model parameters are determined based on the basic model parameters, and the following model parameters are used for expressing the following time limit of the vehicle; the basic model parameters at least comprise a distance value, a speed value and a deceleration value of the vehicle; the determining the following model parameters for expressing the following time interval of the vehicle based on the basic model parameters comprises the following steps of: screening vehicles affected by the front vehicle from the historical thunder data to serve as target rear vehicles, and taking the front vehicle of the target rear vehicles as a target front vehicle; the vehicle affected by the front vehicle is a vehicle with a distance value smaller than a preset distance from the front vehicle; determining a driver expected time interval according to the distance value, the speed value and the deceleration value of the target front vehicle and the target rear vehicle; wherein the driver expected time interval is used for restraining the simulated vehicle running speed; determining the following model parameters according to the expected time interval of the driver and the obtained driving perfection of the driver;
Wherein the basic model parameters are determined based on the initial model parameters, and the basic model parameters are used for expressing basic driving conditions of the vehicle; the lane change model parameters are determined based on the initial model parameters, and the lane change model parameters are used for expressing lane change will of the vehicle; the initial model parameters at least comprise traffic flow of a lane level in a road section and vehicle queuing data of the lane level in the road section; the determining the lane change model parameter for expressing the lane change willingness of the vehicle based on the initial model parameter comprises the following steps: and determining the lane-changing model parameters by adopting a genetic algorithm and based on the vehicle flow and the vehicle queuing data.
2. The method according to claim 1, wherein the historical radar data comprises radar data of multiple scenes, multiple time periods and multiple vehicle types, the initial model parameters correspond to multiple vehicle types in a target scene of a target time period, and the vehicle driving model file is used for describing dynamic driving behaviors of vehicles of the multiple vehicle types in the target scene and the target time period respectively.
3. The method of claim 1, wherein the obtaining a path file from the historical radar data comprises:
Selecting the thunder data matched with the target road section from the historical thunder data as the thunder data to be restored;
acquiring the path file according to the to-be-restored radar data; the path file contains a plurality of pieces of vehicle driving path information, and the vehicle driving path information is used for expressing that a vehicle passes through one or more road sections in the target road sections.
4. A method according to claim 3, wherein the vehicle travel path information is obtained by:
analyzing the to-be-restored thunder data to obtain thunder passing data; the lightning passing data comprises a vehicle identifier of a target vehicle, a vehicle type and time for the target vehicle to pass through one or more intersections in the target road section;
a vehicle travel path of the target vehicle is generated based on the thunder passing data.
5. A traffic simulation device based on radar data, the device comprising:
a data acquisition unit for acquiring historical radar data, wherein the historical radar data comprises radar data of a plurality of road sections;
the model determining unit is used for acquiring initial model parameters from the historical radar data, determining dynamic driving behavior parameters related to the vehicle based on the initial model parameters, and generating a vehicle driving model file based on the dynamic driving behavior parameters;
A path determining unit, configured to obtain a path file according to the historical radar data; the path file comprises a plurality of pieces of vehicle driving path information, wherein the vehicle driving path information is used for expressing one or more road sections through which a vehicle passes;
the traffic simulation unit is used for carrying out traffic simulation based on the path file, the vehicle driving model file and the acquired road network file;
wherein the dynamic driving behavior parameters in the model determination unit include at least one of a base model parameter, a following model parameter, and a lane change model parameter; the following model parameters are determined based on the basic model parameters, and the following model parameters are used for expressing the following time limit of the vehicle; the basic model parameters at least comprise a distance value, a speed value and a deceleration value of the vehicle; the model determination unit is specifically configured to, when determining a following model parameter for expressing a following time interval of a vehicle based on the basic model parameter: screening vehicles affected by the front vehicle from the historical thunder data to serve as target rear vehicles, and taking the front vehicle of the target rear vehicles as a target front vehicle; the vehicle affected by the front vehicle is a vehicle with a distance value smaller than a preset distance from the front vehicle; determining a driver expected time interval according to the distance value, the speed value and the deceleration value of the target front vehicle and the target rear vehicle; wherein the driver expected time interval is used for restraining the simulated vehicle running speed; determining the following model parameters according to the expected time interval of the driver and the obtained driving perfection of the driver;
Wherein the basic model parameters are determined based on the initial model parameters, and the basic model parameters are used for expressing basic driving conditions of the vehicle; the lane change model parameters are determined based on the initial model parameters, and the lane change model parameters are used for expressing lane change will of the vehicle; the initial model parameters at least comprise traffic flow of a lane level in a road section and vehicle queuing data of the lane level in the road section; the model determining unit is specifically configured to, when determining lane change model parameters for expressing a lane change intention of the vehicle based on the initial model parameters: and determining the lane-changing model parameters by adopting a genetic algorithm and based on the vehicle flow and the vehicle queuing data.
6. The apparatus of claim 5, wherein the device comprises a plurality of sensors,
the historical radar data comprise radar data under various scenes, various time periods and various vehicle types; the initial model parameters in the model determining unit correspond to multiple vehicle types in a target scene in a target period, and the vehicle driving model file is used for describing dynamic driving behaviors of vehicles of the multiple vehicle types in the target scene and the target period respectively;
The path determining unit is specifically configured to, when acquiring a path file according to the historical radar data: selecting the thunder data matched with the target road section from the historical thunder data as the thunder data to be restored; acquiring the path file according to the to-be-restored radar data; the path file comprises a plurality of pieces of vehicle driving path information, wherein the vehicle driving path information is used for expressing that a vehicle passes through one or more road sections in the target road sections;
the route determining unit is specifically configured to, when acquiring the vehicle travel route information: analyzing the to-be-restored thunder data to obtain thunder passing data; the lightning passing data comprises a vehicle identifier of a target vehicle, a vehicle type and time for the target vehicle to pass through one or more intersections in the target road section; a vehicle travel path of the target vehicle is generated based on the thunder passing data.
7. An electronic device, comprising: a processor and a machine-readable storage medium;
the machine-readable storage medium stores machine-executable instructions executable by the processor;
the processor is configured to execute machine executable instructions to implement the method steps of any one of claims 1-4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210262028.7A CN114677837B (en) | 2022-03-16 | 2022-03-16 | Traffic simulation method and device based on radar data and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210262028.7A CN114677837B (en) | 2022-03-16 | 2022-03-16 | Traffic simulation method and device based on radar data and electronic equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114677837A CN114677837A (en) | 2022-06-28 |
| CN114677837B true CN114677837B (en) | 2023-08-25 |
Family
ID=82073525
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210262028.7A Active CN114677837B (en) | 2022-03-16 | 2022-03-16 | Traffic simulation method and device based on radar data and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114677837B (en) |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2010152497A (en) * | 2008-12-24 | 2010-07-08 | Toyota Motor Corp | Driving property acquisition device and traffic simulation system |
| CN103593535A (en) * | 2013-11-22 | 2014-02-19 | 南京洛普股份有限公司 | Urban traffic complex self-adaptive network parallel simulation system and method based on multi-scale integration |
| WO2014192615A1 (en) * | 2013-05-30 | 2014-12-04 | 三菱重工業株式会社 | Simulation device, simulation method, and program |
| CN109733415A (en) * | 2019-01-08 | 2019-05-10 | 同济大学 | A kind of automatic Pilot following-speed model that personalizes based on deeply study |
| CN109739218A (en) * | 2018-12-24 | 2019-05-10 | 江苏大学 | It is a kind of that outstanding driver's lane-change method for establishing model is imitated based on GRU network |
| CN109977571A (en) * | 2019-04-01 | 2019-07-05 | 清华大学 | The emulated computation method and device mixed based on data with model |
| CN110164128A (en) * | 2019-04-23 | 2019-08-23 | 银江股份有限公司 | A kind of City-level intelligent transportation analogue system |
| CN111680451A (en) * | 2020-05-26 | 2020-09-18 | 银江股份有限公司 | Microcosmic urban traffic online simulation system and method |
| CN112700647A (en) * | 2020-12-29 | 2021-04-23 | 杭州海康威视数字技术股份有限公司 | Method and device for monitoring vehicle driving information |
| CN112818497A (en) * | 2021-04-19 | 2021-05-18 | 腾讯科技（深圳）有限公司 | Traffic simulation method, traffic simulation device, computer equipment and storage medium |
-
2022
- 2022-03-16 CN CN202210262028.7A patent/CN114677837B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2010152497A (en) * | 2008-12-24 | 2010-07-08 | Toyota Motor Corp | Driving property acquisition device and traffic simulation system |
| WO2014192615A1 (en) * | 2013-05-30 | 2014-12-04 | 三菱重工業株式会社 | Simulation device, simulation method, and program |
| CN103593535A (en) * | 2013-11-22 | 2014-02-19 | 南京洛普股份有限公司 | Urban traffic complex self-adaptive network parallel simulation system and method based on multi-scale integration |
| CN109739218A (en) * | 2018-12-24 | 2019-05-10 | 江苏大学 | It is a kind of that outstanding driver's lane-change method for establishing model is imitated based on GRU network |
| CN109733415A (en) * | 2019-01-08 | 2019-05-10 | 同济大学 | A kind of automatic Pilot following-speed model that personalizes based on deeply study |
| CN109977571A (en) * | 2019-04-01 | 2019-07-05 | 清华大学 | The emulated computation method and device mixed based on data with model |
| CN110164128A (en) * | 2019-04-23 | 2019-08-23 | 银江股份有限公司 | A kind of City-level intelligent transportation analogue system |
| CN111680451A (en) * | 2020-05-26 | 2020-09-18 | 银江股份有限公司 | Microcosmic urban traffic online simulation system and method |
| CN112700647A (en) * | 2020-12-29 | 2021-04-23 | 杭州海康威视数字技术股份有限公司 | Method and device for monitoring vehicle driving information |
| CN112818497A (en) * | 2021-04-19 | 2021-05-18 | 腾讯科技（深圳）有限公司 | Traffic simulation method, traffic simulation device, computer equipment and storage medium |
Non-Patent Citations (1)
| Title |
|---|
| 王翀.车路协同环境下的高速公路匝道区域控制关键技术研究.《中国博士学位论文全文数据库 工程科技II辑》.2020,(第05期),第25-116页. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114677837A (en) | 2022-06-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111179585B (en) | Site testing method and device for automatic driving vehicle | |
| CN108986465B (en) | Method, system and terminal equipment for detecting traffic flow | |
| CN109543245B (en) | Unmanned vehicle response capability boundary information determining method and device and electronic equipment | |
| CN110188482B (en) | Test scene creating method and device based on intelligent driving | |
| CN113378305B (en) | Driverless trolley-based vehicle-road cooperative testing method and device | |
| CN107578624A (en) | Urban transportation management-control method, apparatus and system | |
| CN107590999B (en) | Traffic state discrimination method based on checkpoint data | |
| CN112837542B (en) | Method and device for counting traffic volume of highway section, storage medium and terminal | |
| CN113343461A (en) | Simulation method and device for automatic driving vehicle, electronic equipment and storage medium | |
| CN111811828B (en) | Unmanned vehicle driving test method, device, system and storage medium | |
| CN110851490B (en) | Vehicle travel common stay point mining method and device based on vehicle passing data | |
| Buck et al. | Calibrating VISSIM to analyze delay at signalized intersections | |
| CN110827537B (en) | Method, device and equipment for setting tidal lane | |
| CN114973659A (en) | Method, device and system for detecting indirect event of expressway | |
| CN113850237B (en) | Internet vehicle target detection and evaluation method and system based on video and track data | |
| CN115017742A (en) | Automatic driving test scene generation method, device, equipment and storage medium | |
| CN113312733B (en) | Method, device, equipment and storage medium for calibrating simulation model parameters of signal-controlled roundabout | |
| CN114677837B (en) | Traffic simulation method and device based on radar data and electronic equipment | |
| CN116311913B (en) | High-speed road section congestion analysis method and system based on AI video intelligent analysis | |
| CN114030473B (en) | Vehicle automatic driving behavior evaluation method, device, equipment and storage medium | |
| CN115394089A (en) | Vehicle information fusion display method, sensorless passing system and storage medium | |
| CN114707567A (en) | Trajectory classification method, trajectory classification model training method and computer program product | |
| CN113963550A (en) | Ambiguous path identification method and device and electronic equipment | |
| CN106997678B (en) | Optimization design method for vehicle-mounted road directing information at upstream of expressway exit ramp | |
| CN115114786B (en) | Assessment method, system and storage medium for traffic flow simulation model |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |