Intelligent network connection mixed traffic flow prediction method and device, and electronic equipment

Abstract

The invention provides an intelligent network connection mixed traffic flow prediction method and device and electronic equipment, and belongs to the technical field of traffic flow prediction. According to the invention, the speed and position of the man-driven vehicle and the intelligent network connection vehicle at each moment can be predicted through the mixed traffic flow model. For a manually-driven vehicle, an acceleration random item is set in the manually-driven vehicle following model, and the perception error of a driver is represented by normal distribution with the mean value being zero. Furthermore, the variance of the normal distribution of the perception error is changed in real time, is determined based on the speed of the vehicle at the current moment and / or the vehicle following distance, and is in positive correlation. That is, the larger the speed of the vehicle and / or the vehicle following distance is, the larger the variance of the normal distribution of the perception error is, and the larger the represented perception error of the driver is. In this way, the real-time updated manual driving car following model describes the driving behavior, and the actual situation of manual driving perception error change is better met. Based on the real-time updated manual driving car-following model, the predicted mixed traffic flow is more accurate.

Description

Technical Field

[0001] The present invention relates to the technical field of traffic flow prediction, and in particular to an intelligent networked hybrid traffic flow prediction method, device and electronic equipment. Background Art

[0002] Intelligent network mixed traffic flow is a traffic flow in which manually driven vehicles and intelligent networked vehicles are mixed. The research and development of intelligent network (autonomous driving, vehicle-road collaboration) technology is an important direction and hot area for the development of road traffic. Intelligent networked vehicles will go through a development process from nothing to something, from low penetration rate to high penetration rate. Intelligent networked vehicles and manually driven vehicles will coexist for a long time in the future. The prediction of intelligent networked mixed traffic flow is an important part of the modern intelligent transportation system, which can improve traffic efficiency and safety. The mixed vehicles affect each other. Based on the driving behavior of each vehicle, the intelligent networked mixed traffic flow can be predicted, for example, the speed and position of each vehicle at a certain moment in the future can be predicted. The following model, also called the following model, is used to characterize the driving behavior of the vehicle. This model reflects the driver's reaction behavior after obtaining information about the vehicle in front, including acceleration or deceleration.

[0003] The existing vehicle following model is usually a deterministic vehicle following model. For example, according to the current vehicle speed, the speed of the vehicle in front or the distance between vehicles, a certain acceleration value is obtained based on the preset model rules to characterize the driving behavior. However, for manually driven vehicles, the driver's acceleration and deceleration behavior depends on the driver's perception of the vehicle's speed, the speed difference Δv with the vehicle in front, and the distance s between vehicles through vision, hearing, etc., and the perceived information has certain inaccuracies and errors. Therefore, the existing vehicle following model cannot accurately describe the human driving behavior, resulting in a reduced accuracy of the prediction results of intelligent networked mixed traffic flow. Summary of the invention

[0004] The present invention provides a method, device and electronic device for predicting intelligent networked mixed traffic flow, so as to solve the problem that the prediction results of intelligent networked mixed traffic flow are of low accuracy due to the inaccuracy of the existing vehicle following model.

[0005] In a first aspect, the present invention provides a method for predicting intelligent networked mixed traffic flow, comprising: obtaining a pre-constructed mixed traffic flow model, wherein the mixed traffic flow model includes a manual driving following model and an intelligent driving following model. The manual driving following model includes an acceleration determination item and an acceleration random item, and the acceleration random item includes a normal distribution of perception errors with a mean of zero. The speed and position of each vehicle in the mixed traffic flow at the current moment are obtained, wherein the types of the vehicles include manual driving vehicles and intelligent networked vehicles. For any of the manual driving vehicles, based on the speed and / or following distance of the manual driving vehicle at the current moment, the variance of the normal distribution of the perception error of the manual driving vehicle is determined through a positive correlation relationship; based on the variance of the normal distribution of the perception error of the manual driving vehicle, the perception error normal distribution of the manual driving following model is updated to obtain the updated manual driving following model of the manual driving vehicle; based on the speed and position of each vehicle at the current moment, the updated manual driving following model, and the intelligent networked vehicle model in the pre-constructed mixed traffic flow model, the speed and position of each vehicle at the next moment are predicted.

[0006] In a possible implementation, based on the speed and position of each vehicle at the current moment, the updated manual driving following model, and the intelligent connected vehicle model in the pre-built mixed traffic flow model, predicting the speed and position of each vehicle at the next moment includes: for any of the manually driven vehicles, based on the current position of the manually driven vehicle and the position of the vehicle in front, obtaining the following distance of the manually driven vehicle; according to the speed of the manually driven vehicle, the following distance and the speed of the vehicle in front, obtaining the acceleration determination item of the manually driven vehicle at the current moment; within the normal distribution range of the perception error of the updated manual driving following model, generating a random number to obtain the acceleration random item of the manually driven vehicle at the current moment; based on the acceleration determination item and the acceleration random item, obtaining the acceleration of the manually driven vehicle at the current moment; based on the acceleration, speed and position of the manually driven vehicle at the current moment, obtaining the speed and position of the manually driven vehicle at the next moment; for any of the intelligent connected vehicles, based on the speed and position of the intelligent connected vehicle at the current moment, predicting the speed and position of the intelligent connected vehicle at the next moment through the intelligent driving following model.

[0007] In a possible implementation, the manual driving following model includes:

[0008] a HDV =Mid{a c +a r , a mim , a max}

[0009] a c =f(v, Δv, s, τ)

[0010] a r =N(0,g(s or v,-))+N(0,ε 2 )

[0011] Among them, a HDV Indicates the acceleration of a manually driven vehicle. c represents the acceleration determination term. a r represents the random term of acceleration. min Indicates the lower limit of acceleration. max represents the upper limit of acceleration. v represents the speed. Δv represents the speed difference between the current vehicle and the vehicle in front. s represents the following distance between the current vehicle and the vehicle in front. τ represents the reaction time. N(0,g(s or v,-)) represents the normal distribution of perception error. g(s or v,-) represents the variance of the normal distribution of perception error. N(0,ε 2 ) indicates the normal distribution of interference error, which is the error caused by external interference.

[0012] In a possible implementation, obtaining the speed and position of the manually driven vehicle at the next moment based on the acceleration, speed and position of the manually driven vehicle at the current moment includes: obtaining the speed of the manually driven vehicle at the next moment based on the acceleration and speed of the manually driven vehicle at the current moment and the time difference between the current moment and the next moment. Obtaining the position of the manually driven vehicle at the next moment based on the speed and position of the manually driven vehicle at the current moment and the speed at the next moment.

[0013] In a possible implementation, based on the speed and / or the following distance of the manually driven vehicle at the current moment, determining the variance of the normal distribution of the perception error of the manually driven vehicle through a positive correlation includes: determining the variance of the normal distribution of the perception error based on the following distance of the manually driven vehicle based on the following formula:

[0014] g(s)=α*s β

[0015] Wherein, g(s) represents the variance of the normal distribution of the perception error determined based on the following vehicle distance. s represents the following vehicle distance. α and β represent the constant coefficients of the calibrated formula. Alternatively, the variance of the normal distribution of the perception error is determined based on the following formula according to the speed of the manually driven vehicle:

[0016] g(v)=α*v β

[0017] Wherein, g(v) represents the variance of the normal distribution of the perception error determined based on the following vehicle distance. v represents the speed. α and β represent the constant coefficients of the calibrated formula. Alternatively, the variance of the normal distribution of the perception error is determined based on any of the following formulas according to the speed and following vehicle distance of the manually driven vehicle:

[0018] g(s,v)=α*s β *v γ

[0019] g(s,v))=αln(v*S)

[0020]

[0021] Where g(v) represents the variance of the normal distribution of the perception error determined based on the speed and the following distance. α, β, and γ represent the constant coefficients of the calibration formula.

[0022] In a possible implementation, after predicting the speed and position of each vehicle at the next moment, it also includes: taking the above-mentioned next moment as the current moment, looping to obtain the speed and position of each vehicle at the current moment, and predicting the speed and position at the next moment, to obtain the speed and position of each vehicle at each moment; based on the speed and position of each vehicle at each moment, obtaining the number of vehicles passing through the target section within the target time period; taking the number of vehicles passing through the target section within the target time period as the flow rate of the mixed traffic flow.

[0023] In a second aspect, the present invention provides an intelligent networked hybrid traffic flow prediction device, comprising: a first acquisition module, used to acquire a pre-constructed hybrid traffic flow model, wherein the hybrid traffic flow model includes a manually driven vehicle following model and an intelligent driving vehicle following model; the manually driven vehicle following model includes an acceleration determination item and an acceleration random item, and the acceleration random item includes a normal distribution of perception errors with a mean of zero; a second acquisition module, used to acquire the speed and position of each vehicle in the hybrid traffic flow at the current moment, wherein the types of the vehicles include manually driven vehicles and intelligent networked vehicles; a variance update module, used to update the speed and position of each vehicle in the hybrid traffic flow at the current moment for any of the human A manually driven vehicle is used to determine the variance of the normal distribution of the perception error of the manually driven vehicle based on the speed and / or the following distance of the manually driven vehicle at the current moment through a positive correlation; a model updating module is used to update the normal distribution of the perception error of the manually driven vehicle following model based on the variance of the normal distribution of the perception error of the manually driven vehicle to obtain the updated manually driven following model of the manually driven vehicle; a prediction module is used to predict the speed and position of each vehicle at the next moment based on the speed and position of each vehicle at the current moment, the updated manually driven following model, and the intelligent networked vehicle model in the pre-constructed mixed traffic flow model.

[0024] In one possible implementation, the prediction module is specifically used to: for any of the manually driven vehicles, obtain the following distance of the manually driven vehicle based on the current position of the manually driven vehicle and the position of the vehicle in front; obtain the acceleration determination item of the manually driven vehicle at the current moment according to the speed of the manually driven vehicle, the following distance and the speed of the vehicle in front; generate a random number within the normal distribution range of the perception error of the updated manually driven following model to obtain the acceleration random item of the manually driven vehicle at the current moment; obtain the acceleration of the manually driven vehicle at the current moment based on the acceleration determination item and the acceleration random item; obtain the speed and position of the manually driven vehicle at the next moment based on the acceleration, speed and position of the manually driven vehicle at the current moment; for any of the intelligent connected vehicles, based on the speed and position of the intelligent connected vehicle at the current moment, predict the speed and position of the intelligent connected vehicle at the next moment through the intelligent driving following model.

[0025] In a third aspect, the present invention provides an electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the processor implements the steps of the method described in the first aspect or any possible implementation manner of the first aspect.

[0026] In a fourth aspect, the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the method described in the first aspect or any possible implementation of the first aspect are implemented.

[0027] The present invention provides a method, device and electronic device for predicting intelligent networked mixed traffic flow. The present invention predicts the speed and position of manually driven vehicles and intelligent networked vehicles at each moment through a mixed traffic flow model. For manually driven vehicles, a random item of acceleration is set in the manually driven following model, and the driver's perception error is characterized by a normal distribution with a mean of zero. Furthermore, the variance of the normal distribution of the perception error changes in real time, and is determined based on the speed and / or following distance of the vehicle at the current moment, and is positively correlated. That is, the greater the speed and / or following distance of the vehicle, the greater the variance of the normal distribution of the perception error, and the greater the driver's perception error represented. In this way, the manual driving following model updated in real time describes the driving behavior, which is more in line with the actual situation of the change of manual driving perception error. Based on the manual driving following model updated in real time, the predicted mixed traffic flow is more accurate. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0029] Figure 1 This is an application scenario diagram of the intelligent networked hybrid traffic flow prediction method provided by an embodiment of the present invention;

[0030] Figure 2 is a flowchart of an implementation method of an intelligent networked hybrid traffic flow prediction method provided by an embodiment of the present invention;

[0031] Figure 3 It is a structural schematic diagram of an intelligent networked hybrid traffic flow prediction device provided by an embodiment of the present invention;

[0032] Figure 4 is a schematic diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0033] In the following description, specific details such as specific system structures, technologies, etc. are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present invention. However, it should be clear to those skilled in the art that the present invention may be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to prevent unnecessary details from obstructing the description of the present invention.

[0034] In order to make the purpose, technical solutions and advantages of the present invention more clear, specific embodiments will be described below in conjunction with the accompanying drawings.

[0035] Figure 1 This is an application scenario diagram of the intelligent networked hybrid traffic flow prediction method provided by the embodiment of the present invention. Figure 1 As shown in the figure, the vehicles in the intelligent networked mixed traffic flow include manually driven vehicles and intelligent networked vehicles. There are significant differences between the two vehicles in terms of information acquisition, perception ability, reaction time, interactive behavior, and control characteristics. Compared with the traffic flow of purely manually driven vehicles, the characteristics of the new mixed traffic flow composed of intelligent networked vehicles and manually driven vehicles will change to a certain extent. Therefore, it is necessary to analyze the operating characteristics and internal laws of the new mixed traffic flow composed of intelligent networked vehicles and manually driven vehicles. The mixed traffic flow prediction method is an effective research method.

[0036] The embodiment of the present invention models intelligent connected vehicles and manually driven vehicles separately, and then integrates the two models to form a mixed traffic flow model, and sets acceleration random terms in the model to solve the problem of low accuracy of prediction results of mixed traffic flow caused by inaccurate existing vehicle following models.

[0037] Figure 2 is a flowchart of the implementation of the intelligent networked hybrid traffic flow prediction method provided by the embodiment of the present invention, referring to Figure 2 , as detailed below:

[0038] In step 201, a pre-built hybrid traffic flow model is obtained, wherein the hybrid traffic flow model includes a manual driving following model and an intelligent driving following model. The manual driving following model includes an acceleration determination item and an acceleration random item, and the acceleration random item includes a normal distribution of perception errors with a mean of zero.

[0039] In some embodiments, the mixed traffic flow model is used to simulate traffic flow changes under mixed driving conditions. For example, traffic flow changes can be simulated based on the driving behavior of each vehicle under a given initial state. The initial state may include the number of vehicles, initial positions, or initial speeds.

[0040] The vehicle following model is a model used to characterize vehicle driving behavior. For example, the mixed traffic flow includes manually driven vehicles and intelligent networked vehicles. Accordingly, the vehicle following model includes a manually driven vehicle following model and an intelligently driven vehicle following model.

[0041] The embodiment of the present invention improves the manual driving and following vehicle model. The structure of the manual driving and following vehicle model is described in detail below. Specifically, the manual driving and following vehicle model is a model about vehicle acceleration.

[0042] In some embodiments, the manual driving vehicle following model includes an acceleration determination term and an acceleration random term. For example, the acceleration of the manual driving vehicle is the sum of the acceleration determination term and the acceleration random term.

[0043] Regarding the acceleration determination item, for example, it can be a function of the vehicle's speed, the speed difference with the vehicle in front, the distance between vehicles, and the reaction time. For example, its specific form can adopt a mature deterministic vehicle following model such as an IDM (Intelligent Driver Model) with delay.

[0044] Regarding the acceleration random term, it should be noted that the reason for setting the random term is that the acceleration determination term depends on the values ​​of the vehicle's speed, the speed difference with the vehicle in front, and the distance between vehicles, while the actual acceleration of the vehicle is determined by the driver's behavior of stepping on the accelerator pedal and the brake pedal. The driver's acceleration and deceleration behavior depends on the information such as the vehicle's speed, the speed difference with the vehicle in front, and the distance between vehicles perceived by the driver through vision, hearing, etc. However, the information perceived by the driver has certain inaccuracies and errors, so the present invention adds a random term to the manually driven vehicle model.

[0045] Exemplarily, the acceleration random term includes a normal distribution of the perception error with a mean of zero. That is, the perception error is represented by a normal distribution with a mean of zero.

[0046] In another exemplary embodiment, the acceleration random term may also include a normal distribution of interference errors. The normal distribution of interference errors is used to characterize the errors caused by unobservable external interference, with a mean of zero and a variance of ε 2 The variance ε 2 The value of can be appropriately set according to modeling needs or calibrated according to the actual trajectory data of manually driven vehicles.

[0047] An embodiment of a manual driving following vehicle model is provided below, and the model structure is explained in formula form.

[0048] In a possible implementation, the manual driving following model includes:

[0049] α HDV =Mid{a c +a r , a min , a max}

[0050] a c =f(v, Δv, s, τ)

[0051] a r =N(0,g(s or v,-))+N(0,ε 2 )

[0052] Among them, a HDV Indicates the acceleration of a manually driven vehicle. c represents the acceleration determination term. a r represents the random term of acceleration. min Indicates the lower limit of acceleration. maxrepresents the upper limit of acceleration. v represents the speed. Δv represents the speed difference between the current vehicle and the vehicle in front. s represents the following distance between the current vehicle and the vehicle in front. τ represents the reaction time. N(0,g(a or v, -)) represents the normal distribution of perception error. g(s or v, -) represents the variance of the normal distribution of perception error. N(0,ε 2 ) indicates the normal distribution of interference error, which is the error caused by external interference.

[0053] It should be noted that the acceleration determination item can be determined according to the current vehicle speed, the speed of the vehicle ahead, the distance between vehicles, etc. For example, the acceleration determination item a c The specific value of is a function of the vehicle's speed v, the speed difference Δv with the vehicle ahead, the vehicle spacing s, and the reaction time τ, i.e., f(v, Δv, s, τ). Mid{,,} can represent the middle value of the three data arranged from small to large. The purpose of this function is to limit the acceleration within a certain range and avoid acceleration values ​​that violate the actual situation.

[0054] Acceleration random term a r It includes two parts. Both random items obey a normal distribution with a mean of zero, but the variances of the two parts are different. The above describes the method for determining the variance of the normal distribution of the interference error, and the method for determining the variance of the normal distribution of the perception error is described in detail in step 203. The following embodiment first describes the intelligent driving following model.

[0055] In some embodiments, the acceleration expression of the intelligent driving following model is as follows:

[0056] a CAV =Mid{a′ c +a′ r , a min , a max}or u

[0057] a′ c =F(v, Δv, s, a l , τ′)

[0058] a′ r =N(0,∈ 2 )

[0059] Among them, a CAV Represents the acceleration of the intelligent connected vehicle. a′ c represents the determined term in the acceleration of the intelligent networked vehicle, which can be a function of the intelligent networked vehicle's speed v, the speed difference Δv with the vehicle ahead, and the vehicle spacing s, that is, F(v, Δv, s, a l,τ′), and its specific form can be based on the mature adaptive cruise control model (ACC) and the collaborative adaptive cruise control (CACC) model and add the time delay term τ′. a′ r It represents the random term in the acceleration of the intelligent connected vehicle, which is the error caused by the unobservable external interference, and its mean is zero and its variance is ∈ 2 The normal distribution with variance ∈ 2 The value of can be appropriately set according to modeling needs or calibrated according to actual data. u represents the acceleration of the intelligent connected vehicle when it is remotely controlled, which can be specifically designed according to control requirements.

[0060] In summary, according to the above embodiments, a mixed traffic flow model can be obtained based on the constructed manual driving vehicle model and intelligent networked vehicle model formula, which can effectively simulate the complex situation of mixed driving of intelligent networked vehicles and manual driving vehicles, and can realistically simulate random mixed traffic flow. In addition, it is also possible to analyze the comprehensive situation under different interference levels, different driver reaction times, and different intelligent networked vehicle communication delays.

[0061] The following example illustrates the steps of making predictions based on the constructed mixed traffic flow model.

[0062] In step 202, the speed and position of each vehicle in the mixed traffic flow at the current moment are obtained, wherein the types of vehicles include manually driven vehicles and intelligent networked vehicles.

[0063] In some embodiments, based on the speed and position of each vehicle, the following distance of each vehicle and the speed of the vehicle in front can be obtained, and then the speed difference with the vehicle in front can be obtained.

[0064] Furthermore, each vehicle can obtain the acceleration according to the current vehicle state through the vehicle following model, and then obtain the speed and position at the next moment.

[0065] Different types of vehicles have different driving behavior patterns and different following models, and the corresponding accelerations adopted will also be different. The following steps 203-204 illustrate the process of updating the following model in real time for a manually driven vehicle.

[0066] In step 203, for any manually driven vehicle, based on the speed and / or following distance of the manually driven vehicle at the current moment, the variance of the normal distribution of the perception error of the manually driven vehicle is determined through a positive correlation.

[0067] In some embodiments, the variance of the normal distribution of the perception error is determined based on the speed of the manually driven vehicle and / or the distance between vehicles following the vehicle, wherein the greater the speed of the manually driven vehicle and / or the distance between vehicles following the vehicle, the greater the variance; and the smaller the speed of the manually driven vehicle and / or the distance between vehicles following the vehicle, the smaller the variance.

[0068] In some embodiments, based on the speed and / or the following distance of the manually driven vehicle at the current moment, determining the variance of the normal distribution of the perception error of the manually driven vehicle through a positive correlation relationship includes:

[0069] According to the following distance of the manually driven vehicle, the variance of the normal distribution of the perception error is determined based on the following formula:

[0070] g(s)=α*s β

[0071] Where g(s) represents the variance of the normal distribution of the perception error determined based on the following vehicle distance. s represents the following vehicle distance. α and β represent the constant coefficients of the calibration formula.

[0072] Alternatively, the variance of the normal distribution of the perception error is determined based on the following formula, depending on the speed of the human-driven vehicle:

[0073] g(v)=α*v β

[0074] Where g(v) represents the variance of the normal distribution of the perception error determined based on the following vehicle distance. v represents the speed. α and β represent the constant coefficients of the calibration formula.

[0075] Alternatively, the variance of the normal distribution of the perception error is determined based on the speed and following distance of the human-driven vehicle according to any of the following formulas:

[0076] g(s,v)=α*s β *v γ

[0077] g(s,v)=aln(v*s)

[0078]

[0079] Where g(v) represents the variance of the normal distribution of the perception error determined based on the speed and the following distance. α, β, and γ represent the constant coefficients of the calibration formula.

[0080] It should be noted that the constant coefficients α, β, and γ in the above formula can be calibrated using the least squares method based on the actual trajectory data of the manually driven vehicle.

[0081] The variance g(s or v,-) of the normal distribution of the perception error is constructed as a function of the vehicle spacing and / or vehicle speed, i.e., g(s,v), g(s) or g(v). Its physical meaning is that when the vehicle spacing is larger and the driving speed is higher, the driver's perception error of the actual spacing and speed difference will become larger, and the variance is constructed as a positively correlated function of the vehicle spacing and / or speed.

[0082] In step 204, based on the variance of the normal distribution of the perception error of the manually driven vehicle, the normal distribution of the perception error of the manually driven vehicle is updated to obtain an updated manual driving following model of the manually driven vehicle.

[0083] In some embodiments, the variance re-determined in step 203 is used as the variance of the updated perception error normal distribution to obtain the updated perception error normal distribution, and then the random item of the manual driving following model is updated to obtain the updated manual driving following model.

[0084] It should be noted that steps 203-204 are for updating the following model of any manually driven vehicle. That is, by repeating steps 203-204 for each manually driven vehicle, the following model of each manually driven vehicle can be obtained. Because the following model of each manually driven vehicle is related to the current state of the vehicle, the following models of each manually driven vehicle are not necessarily the same.

[0085] In step 205, based on the speed and position of each vehicle at the current moment, the updated manual driving following model, and the intelligent connected vehicle model in the pre-built mixed traffic flow model, the speed and position of each vehicle at the next moment are predicted.

[0086] In some embodiments, the acceleration determination item and the acceleration random item are determined respectively to obtain the acceleration of the manually driven vehicle at the current moment, and then based on the speed and position at the current moment and the above acceleration, the speed and position of the manually driven vehicle at the next moment are obtained.

[0087] In some embodiments, the acceleration random term can be obtained by perceiving the normal distribution of the error. The variance of the normal distribution of the error is not fixed, but changes at all times. At each moment, the variance of the normal distribution of the error is positively correlated with the speed of the manually driven vehicle at the current moment, or is positively correlated with the distance between the manually driven vehicle and the vehicle at the current moment, or is positively correlated with the speed and distance between the manually driven vehicle and the vehicle at the current moment. That is, the greater the speed of the manually driven vehicle and the distance between the vehicles at the current moment, the greater the variance of the normal distribution of the error.

[0088] In some embodiments, for any manually driven vehicle, based on the speed and position of the manually driven vehicle at the current moment, the speed and position of the manually driven vehicle at the next moment are predicted by updating the manually driven vehicle following model.

[0089] In some embodiments, for any intelligent connected vehicle, based on the speed and position of the intelligent connected vehicle at the current moment, the speed and position of the intelligent connected vehicle at the next moment are predicted through an intelligent driving and following model.

[0090] The following examples illustrate the process of prediction for manually driven vehicles and intelligent connected vehicles.

[0091] In a possible implementation, based on the speed and position of each vehicle at the current moment, the updated manual driving and following model, and the intelligent connected vehicle model in the pre-built mixed traffic flow model, the speed and position of each vehicle at the next moment are predicted, including:

[0092] Step 2051, for any manually driven vehicle, based on the current position of the manually driven vehicle and the position of the vehicle in front, obtain the following distance of the manually driven vehicle.

[0093] Exemplarily, the following distance of the manually driven vehicle is obtained by subtracting the position of the current manually driven vehicle from the position of the vehicle ahead.

[0094] It should be noted that the vehicle in front of a manually driven vehicle may be an intelligent connected vehicle or another manually driven vehicle.

[0095] Step 2052, according to the speed of the manually driven vehicle, the following distance and the speed of the vehicle in front, obtain the acceleration determination item of the manually driven vehicle at the current moment.

[0096] Exemplarily, the above-mentioned IDM model with delay or the like may be used to obtain the acceleration determination item.

[0097] Step 2053, generating a random number within the normal distribution range of the perception error of the updated manual driving vehicle following model to obtain a random item of acceleration of the manual driving vehicle at the current moment;

[0098] In addition, it should be noted that if the acceleration random term also includes the interference error normal distribution, a random number can be generated within the interference error normal distribution range to form the acceleration random term together with the random number of the perception error normal distribution.

[0099] Step 2054, based on the acceleration determination item and the acceleration random item, obtain the acceleration of the manually driven vehicle at the current moment.

[0100] Exemplarily, the acceleration determination term and the acceleration random term are added to obtain the acceleration of the manually driven vehicle at the current moment.

[0101] Step 2055, based on the acceleration, speed and position of the manually driven vehicle at the current moment, obtain the speed and position of the manually driven vehicle at the next moment.

[0102] In some embodiments, based on the acceleration, speed and position of the manually driven vehicle at the current moment, obtaining the speed and position of the manually driven vehicle at the next moment includes:

[0103] Step ①, based on the acceleration and speed of the manually driven vehicle at the current moment, and the time difference between the current moment and the next moment, obtain the speed of the manually driven vehicle at the next moment.

[0104] Exemplarily, V(t+1)=V(t)+a(t)*Δt is used to obtain the speed of the manually driven vehicle at the next moment. Δt represents the time difference between the current moment and the next moment.

[0105] Step ②, based on the speed and position of the manually driven vehicle at the current moment and the speed at the next moment, obtain the position of the manually driven vehicle at the next moment.

[0106] Step 2056, for any intelligent connected vehicle, based on the speed and position of the intelligent connected vehicle at the current moment, the speed and position of the intelligent connected vehicle at the next moment are predicted through the intelligent driving and following model.

[0107] Exemplarily, the intelligent driving following model may adopt the acceleration expression mentioned above.

[0108] It should be noted that the vehicle in front of the intelligent connected vehicle may be a manually driven vehicle or another intelligent connected vehicle.

[0109] From then on, steps 2051-2056 predict the speed and position of each manually driven vehicle and intelligent connected vehicle at the next moment, that is, predict the mixed traffic flow situation.

[0110] The embodiment of the present invention predicts the speed and position of manually driven vehicles and intelligent networked vehicles at each moment through a mixed traffic flow model. For manually driven vehicles, a random acceleration term is set in the manually driven following model, and the driver's perception error is characterized by a normal distribution with a mean of zero. Furthermore, the variance of the normal distribution of the perception error changes in real time, and is determined based on the speed and / or following distance of the vehicle at the current moment, and is positively correlated. That is, the greater the speed and / or following distance of the vehicle, the greater the variance of the normal distribution of the perception error, and the greater the driver's perception error represented. In this way, the manual driving following model updated in real time describes driving behavior, which is more in line with the actual situation of changes in manual driving perception errors. Based on the manual driving following model updated in real time, the predicted mixed traffic flow is more accurate.

[0111] In a possible implementation, after predicting the speed and position of each vehicle at the next moment, it also includes: taking the above next moment as the current moment, looping to obtain the speed and position of each vehicle at the current moment, and predicting the speed and position at the next moment, to obtain the speed and position of each vehicle at each moment.

[0112] Exemplarily, by looping through steps 202 - 205 , the speed and position of each vehicle at each moment can be obtained.

[0113] In a possible implementation, after predicting the speed and position of each vehicle at the next moment, it also includes: taking the above-mentioned next moment as the current moment, looping to obtain the speed and position of each vehicle at the current moment, and predicting the speed and position at the next moment, to obtain the speed and position of each vehicle at each moment; based on the speed and position of each vehicle at each moment, obtaining the number of vehicles passing through the target section within the target time period; taking the number of vehicles passing through the target section within the target time period as the flow rate of the mixed traffic flow.

[0114] The following is an application example to illustrate the specific application of the mixed traffic flow prediction method of the present invention. For example, taking the simulation analysis of traffic operation characteristics under different penetration rates of intelligent networked vehicles as an example, the specific application steps are as follows:

[0115] (1) Initialize the parameters of the constructed mixed traffic flow model formula. Set the length of the circular single lane to 1000 meters, the penetration rate of intelligent connected vehicles to p, and the M vehicles on the single lane at the initial moment to be evenly distributed on the circular lane. Generate M random numbers R between (0,1) i (i ranges from 1 to M), if R i If p is less than or equal to p, the vehicle is defined as an intelligent connected vehicle, otherwise the vehicle is a manually driven vehicle.

[0116] (2) The acceleration of the intelligent networked vehicle and the acceleration of the manually driven vehicle are updated according to the embodiment of the present invention. Based on the acceleration update, V(t+1)=V(t)+a(t)*Δt is used to update the vehicle speed, and then the vehicle position is updated, and then the average speed, speed variance, flow rate and other information of a certain section can be counted.

[0117] (3) By changing the intelligent connected vehicle penetration rate p and the total number of vehicles M, we can further obtain the operation rules of mixed traffic flows under different traffic densities and different intelligent connected vehicle penetration rates.

[0118] It should be understood that the order of execution of the steps in the above embodiment does not necessarily mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiment of the present invention.

[0119] The following is an embodiment of the device of the present invention. For details not described in detail therein, reference may be made to the corresponding method embodiment described above.

[0120] Figure 3 : is a schematic diagram of the structure of an intelligent networked hybrid traffic flow prediction device provided by an embodiment of the present invention. For the sake of convenience, only the parts related to the embodiment of the present invention are shown, which are described in detail as follows:

[0121] Reference Figure 3, the intelligent networked hybrid traffic flow prediction device 3 includes:

[0122] The first acquisition module 31 is used to acquire a pre-built mixed traffic flow model, wherein the mixed traffic flow model includes a manual driving following model and an intelligent driving following model. The manual driving following model includes an acceleration determination item and an acceleration random item, and the acceleration random item includes a normal distribution of perception errors with a mean of zero.

[0123] The second acquisition module 32 is used to obtain the speed and position of each vehicle in the mixed traffic flow at the current moment, wherein the types of vehicles include manually driven vehicles and intelligent networked vehicles.

[0124] The variance updating module 33 is used to determine the variance of the normal distribution of the perception error of any manually driven vehicle based on the speed and / or the following distance of the manually driven vehicle at the current moment through a positive correlation relationship;

[0125] A model updating module 34 is used to update the normal distribution of the perception error of the manually driven vehicle following model based on the variance of the normal distribution of the perception error of the manually driven vehicle, so as to obtain the updated manual driving following model of the manually driven vehicle;

[0126] The prediction module 35 is used to predict the speed and position of each vehicle at the next moment based on the speed and position of each vehicle at the current moment, the updated manual driving following model, and the intelligent connected vehicle model in the pre-built mixed traffic flow model.

[0127] The embodiment of the present invention predicts the speed and position of manually driven vehicles and intelligent networked vehicles at each moment through a mixed traffic flow model. For manually driven vehicles, a random acceleration term is set in the manually driven following model, and the driver's perception error is characterized by a normal distribution with a mean of zero. Furthermore, the variance of the normal distribution of the perception error changes in real time, and is determined based on the speed and / or following distance of the vehicle at the current moment, and is positively correlated. That is, the greater the speed and / or following distance of the vehicle, the greater the variance of the normal distribution of the perception error, and the greater the driver's perception error represented. In this way, the manual driving following model updated in real time describes driving behavior, which is more in line with the actual situation of changes in manual driving perception errors. Based on the manual driving following model updated in real time, the predicted mixed traffic flow is more accurate.

[0128] In one possible implementation, the first prediction module is specifically used to: for any manually driven vehicle, obtain the following distance of the manually driven vehicle based on the current position of the manually driven vehicle and the position of the vehicle in front; obtain the acceleration determination item of the manually driven vehicle at the current moment according to the speed of the manually driven vehicle, the following distance and the speed of the vehicle in front; generate a random number within the normal distribution range of the perception error of the updated manually driven following model to obtain the acceleration random item of the manually driven vehicle at the current moment; obtain the acceleration of the manually driven vehicle at the current moment based on the acceleration determination item and the acceleration random item; obtain the speed and position of the manually driven vehicle at the next moment based on the acceleration, speed and position of the manually driven vehicle at the current moment; for any intelligent connected vehicle, based on the speed and position of the intelligent connected vehicle at the current moment, predict the speed and position of the intelligent connected vehicle at the next moment through the intelligent driving following model.

[0129] In a possible implementation, the manual driving following model includes:

[0130] a HDV =Mid{a c +a r , a min , a max}

[0131] a c =f(v,Δv,s,τ)

[0132] a r =N(0,g(s or v,-))+N(0,ε 2 )

[0133] Among them, a HDV Indicates the acceleration of a manually driven vehicle. c represents the acceleration determination term. a r represents the random term of acceleration. min Indicates the lower limit of acceleration. max represents the upper limit of acceleration. v represents the speed. Δv represents the speed difference between the current vehicle and the vehicle in front. s represents the following distance between the current vehicle and the vehicle in front. τ represents the reaction time. N(0,g(s or v,-)) represents the normal distribution of perception error. g(s or v,-) represents the variance of the normal distribution of perception error. N(0,ε 2 ) indicates the normal distribution of interference error, which is the error caused by external interference.

[0134] In a possible implementation, based on the acceleration, speed and position of the manually driven vehicle at the current moment, obtaining the speed and position of the manually driven vehicle at the next moment includes: obtaining the speed of the manually driven vehicle at the next moment based on the acceleration and speed of the manually driven vehicle at the current moment and the time difference between the current moment and the next moment. Obtaining the position of the manually driven vehicle at the next moment based on the speed and position of the manually driven vehicle at the current moment and the speed at the next moment.

[0135] In a possible implementation, based on the speed and / or the following distance of the manually driven vehicle at the current moment, determining the variance of the normal distribution of the perception error of the manually driven vehicle through a positive correlation includes: determining the variance of the normal distribution of the perception error based on the following distance of the manually driven vehicle based on the following formula:

[0136] g(s)=α*s β

[0137] Where g(s) represents the variance of the normal distribution of the perception error determined based on the following vehicle distance. s represents the following vehicle distance. α and β represent the constant coefficients of the calibration formula. Alternatively, the variance of the normal distribution of the perception error is determined based on the following formula according to the speed of the manually driven vehicle:

[0138] g(v)=α*v β

[0139] Where g(v) represents the variance of the normal distribution of the perception error determined based on the following vehicle distance. v represents the speed. α and β represent the constant coefficients of the calibration formula. Alternatively, the variance of the normal distribution of the perception error is determined based on any of the following formulas according to the speed and following vehicle distance of the manually driven vehicle:

[0140] g(s,v)=α*s β *v γ

[0141] g(s,v)=αln(v*s)

[0142]

[0143] Where g(v) represents the variance of the normal distribution of the perception error determined based on the speed and the following distance. α, β, and γ represent the constant coefficients of the calibration formula.

[0144] In a possible implementation, after predicting the speed and position of each vehicle at the next moment, it also includes: taking the above-mentioned next moment as the current moment, looping to obtain the speed and position of each vehicle at the current moment, and predicting the speed and position at the next moment, to obtain the speed and position of each vehicle at each moment; based on the speed and position of each vehicle at each moment, obtaining the number of vehicles passing through the target section within the target time period; taking the number of vehicles passing through the target section within the target time period as the flow rate of the mixed traffic flow.

[0145] Figure 4 Schematic diagram of an electronic device provided by an embodiment of the present invention. Figure 4 As shown, the electronic device 4 of this embodiment includes: a processor 40, a memory 41, and a computer program 42 stored in the memory 41 and executable on the processor 40. When the processor 40 executes the computer program 42, the steps in the above-mentioned embodiments of the intelligent networked hybrid traffic flow prediction method are implemented, such as Figure 2 Alternatively, when the processor 40 executes the computer program 42, the functions of each module / unit in the above-mentioned device embodiments are realized, for example, Figure 3 The functions of the modules 31 to 35 are shown.

[0146] Exemplarily, the computer program 42 may be divided into one or more modules / units, which are stored in the memory 41 and executed by the processor 40 to implement the present invention. The one or more modules / units may be a series of computer program instruction segments capable of implementing specific functions, which are used to describe the execution process of the computer program 42 in the electronic device 4. For example, the computer program 42 may be divided into Figure 3 Modules 31 to 35 are shown.

[0147] The electronic device 4 may be a computing device such as a desktop computer, a notebook, a PDA, or a cloud server. The electronic device 4 may include, but is not limited to, a processor 40 and a memory 41. Those skilled in the art will appreciate that Figure 4 It is only an example of the electronic device 4 and does not constitute a limitation of the electronic device 4. It may include more or fewer components than shown in the figure, or a combination of certain components, or different components. For example, the electronic device may also include input and output devices, network access devices, buses, etc.

[0148] The processor 40 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc.

[0149] The memory 41 may be an internal storage unit of the electronic device 4, such as a hard disk or memory of the electronic device 4. The memory 41 may also be an external storage device of the electronic device 4, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the electronic device 4. Further, the memory 41 may also include both an internal storage unit and an external storage device of the electronic device 4. The memory 41 is used to store the computer program and other programs and data required by the electronic device. The memory 41 may also be used to temporarily store data that has been output or is to be output.

[0150] The technicians in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In practical applications, the above-mentioned function allocation can be completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated in a processing unit, or each unit can exist physically separately, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, which will not be repeated here.

[0151] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0152] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0153] In the embodiments provided by the present invention, it should be understood that the disclosed devices / electronic devices and methods can be implemented in other ways. For example, the device / electronic device embodiments described above are only schematic. For example, the division of the modules or units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0154] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0155] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0156] If the integrated module / unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present invention implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by the processor, the steps of the above-mentioned embodiments of the intelligent networked mixed traffic flow prediction method can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or device that can carry the computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal and software distribution medium.

[0157] The embodiments described above are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be included in the protection scope of the present invention.

Claims

1. A method for predicting intelligent networked hybrid traffic flow, characterized in that: include: Obtaining a pre-built hybrid traffic flow model, wherein the hybrid traffic flow model includes a manual driving following model and an intelligent driving following model; the manual driving following model includes an acceleration determination item and an acceleration random item, and the acceleration random item includes a perception error normal distribution with a mean of zero; Obtaining the speed and position of each vehicle in the mixed traffic flow at the current moment, wherein the types of the vehicles include manually driven vehicles and intelligent networked vehicles; For any of the manually driven vehicles, based on the speed and / or the following vehicle distance of the manually driven vehicle at the current moment, the variance of the normal distribution of the perception error of the manually driven vehicle is determined through a positive correlation; based on the variance of the normal distribution of the perception error of the manually driven vehicle, the normal distribution of the perception error of the manually driven vehicle following model is updated to obtain the updated manual driving following model of the manually driven vehicle; Based on the speed and position of each vehicle at the current moment, the updated manual driving following model, and the intelligent connected vehicle model in the pre-built mixed traffic flow model, the speed and position of each vehicle at the next moment are predicted.

2. The intelligent networked hybrid traffic flow prediction method according to claim 1 is characterized in that: Based on the speed and position of each vehicle at the current moment, the updated manual driving and following vehicle model, and the intelligent connected vehicle model in the pre-built mixed traffic flow model, the speed and position of each vehicle at the next moment are predicted, including: For any of the manually driven vehicles, based on the current position of the manually driven vehicle and the position of the vehicle ahead, obtaining the following vehicle distance of the manually driven vehicle; Obtaining an acceleration determination item of the manually driven vehicle at a current moment according to the speed of the manually driven vehicle, the following vehicle distance and the speed of the vehicle in front; Generate a random number within the normal distribution range of the perception error of the updated manual driving vehicle following model to obtain a random item of acceleration of the manual driving vehicle at the current moment; Based on the acceleration determination item and the acceleration random item, obtaining the acceleration of the manually driven vehicle at the current moment; Based on the acceleration, speed and position of the manually driven vehicle at the current moment, obtaining the speed and position of the manually driven vehicle at the next moment; For any of the intelligent connected vehicles, based on the speed and position of the intelligent connected vehicle at the current moment, the speed and position of the intelligent connected vehicle at the next moment are predicted through the intelligent driving and following model.

3. The intelligent networked hybrid traffic flow prediction method according to claim 2 is characterized in that: The obtaining of the speed and position of the manually driven vehicle at the next moment based on the acceleration, speed and position of the manually driven vehicle at the current moment comprises: Based on the acceleration and speed of the manually driven vehicle at the current moment and the time difference between the current moment and the next moment, obtaining the speed of the manually driven vehicle at the next moment; Based on the speed and position of the manually driven vehicle at the current moment and the speed at the next moment, the position of the manually driven vehicle at the next moment is obtained.

4. The intelligent networked hybrid traffic flow prediction method according to claim 1, characterized in that: The manual driving and following vehicle model comprises: a HDV =Mid{a c +a r ,a min ,a max } a c =f(v,Δv,s,τ) a r =N(0,g(s or v,-))+N(0,ε 2 ) Among them, a HDV Represents the acceleration of a manually driven vehicle; a c represents the acceleration determination term; a r represents the random term of acceleration; a min Indicates the lower limit of acceleration; a max represents the upper limit of acceleration; v represents the speed; Δv represents the speed difference between the current vehicle and the vehicle in front; s represents the following distance between the current vehicle and the vehicle in front; τ represents the reaction time; N(0,g(s or v,-)) represents the normal distribution of perception error; g(sorv,-) represents the variance of the normal distribution of perception error; N(0,ε 2 ) indicates the normal distribution of interference error, which is the error caused by external interference.

5. The intelligent networked hybrid traffic flow prediction method according to claim 1, characterized in that: Based on the speed and / or the following distance of the manually driven vehicle at the current moment, the variance of the normal distribution of the perception error of the manually driven vehicle is determined through a positive correlation, including: According to the following distance of the manually driven vehicle, the variance of the normal distribution of the perception error is determined based on the following formula: g(s)=α*s β Wherein, g(s) represents the variance of the normal distribution of the perception error determined based on the following vehicle distance; s represents the following vehicle distance; α and β represent the constant coefficients of the calibration formula; Alternatively, the variance of the normal distribution of the perception error is determined based on the following formula according to the speed of the manually driven vehicle: g(v)=α*v β Wherein, g(v) represents the variance of the normal distribution of the perception error determined based on the following vehicle distance; v represents the speed; α and β represent the constant coefficients of the calibration formula; Alternatively, the variance of the normal distribution of the perception error is determined based on any one of the following formulas according to the speed and the following distance of the manually driven vehicle: g(s,v)=α*s β *v γ g(s,v)=αln(v*s) Among them, g(v) represents the variance of the normal distribution of perception error determined based on speed and following distance; α, β, and γ represent the constant coefficients of the calibration formula.

6. The intelligent networked hybrid traffic flow prediction method according to claim 1, characterized in that: After predicting the speed and position of each vehicle at the next moment, it also includes: Taking the next moment as the current moment, cyclically executing the process of obtaining the speed and position of each vehicle at the current moment, and predicting the speed and position at the next moment, to obtain the speed and position of each vehicle at each moment; Based on the speed and position of each vehicle at each time, the number of vehicles passing through the target section within the target time period is obtained; The number of vehicles passing through the target section within the target time period is taken as the flow rate of the mixed traffic flow.

7. An intelligent networked hybrid traffic flow prediction device, characterized in that: include: A first acquisition module is used to acquire a pre-constructed hybrid traffic flow model, wherein the hybrid traffic flow model includes a manual driving following model and an intelligent driving following model; the manual driving following model includes an acceleration determination item and an acceleration random item, and the acceleration random item includes a perception error normal distribution with a mean of zero; A second acquisition module is used to acquire the speed and position of each vehicle in the mixed traffic flow at the current moment, wherein the types of the vehicles include manually driven vehicles and intelligent networked vehicles; A variance updating module, for determining, for any of the manually driven vehicles, a variance of a normal distribution of a perception error of the manually driven vehicle based on a current speed and / or a following distance of the manually driven vehicle through a positive correlation relationship; A model updating module, configured to update the normal distribution of the perception error of the manually driven vehicle following model based on the variance of the normal distribution of the perception error of the manually driven vehicle, and obtain an updated manual driving vehicle following model of the manually driven vehicle; The prediction module is used to predict the speed and position of each vehicle at the next moment based on the speed and position of each vehicle at the current moment, the updated manual driving following model, and the intelligent connected vehicle model in the pre-built mixed traffic flow model.

8. The intelligent networked hybrid traffic flow prediction device according to claim 7, characterized in that: The prediction module is specifically used for: For any of the manually driven vehicles, based on the current position of the manually driven vehicle and the position of the vehicle ahead, obtaining the following vehicle distance of the manually driven vehicle; Obtaining an acceleration determination item of the manually driven vehicle at a current moment according to the speed of the manually driven vehicle, the following vehicle distance and the speed of the vehicle in front; Generate a random number within the normal distribution range of the perception error of the updated manual driving vehicle following model to obtain a random item of acceleration of the manual driving vehicle at the current moment; Based on the acceleration determination item and the acceleration random item, obtaining the acceleration of the manually driven vehicle at the current moment; Based on the acceleration, speed and position of the manually driven vehicle at the current moment, obtaining the speed and position of the manually driven vehicle at the next moment; For any of the intelligent connected vehicles, based on the speed and position of the intelligent connected vehicle at the current moment, the speed and position of the intelligent connected vehicle at the next moment are predicted through the intelligent driving and following model.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the intelligent connected hybrid traffic flow prediction method as described in any one of claims 1 to 6 above are implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the intelligent networked hybrid traffic flow prediction method as described in any one of claims 1 to 6 above are implemented.

Images