Vehicle speed optimization method and device based on mixed traffic flow, equipment and medium

Abstract

The invention discloses a vehicle speed optimization method and device based on mixed traffic flow, equipment and a medium, and relates to the technical field of vehicle simulation control, and the method comprises the steps: obtaining vehicle driving information under a spiral road, carrying out the analysis of the vehicle driving information through a preset spiral road mixed traffic flow simulation model, and obtaining a traffic flow simulation result, and obtaining an optimized speed based on the traffic flow simulation result according to the vehicle driving information, and performing adjustment based on the optimized speed. According to the invention, the V2X technology is utilized to obtain the vehicle driving information of the spiral road, and the vehicle speed is analyzed and optimized through the mixed traffic flow simulation model, so that the traffic flow stability and safety are improved, and the traffic jam is relieved.

Description

Technical Field

[0001] The present invention relates to the technical field of vehicle simulation control, and in particular to a vehicle speed optimization method, device, equipment and medium based on mixed vehicle flow. Background Art

[0002] With the acceleration of urbanization and the surge in the number of motor vehicles, traffic congestion has become a prominent problem in urban development. Especially in the spiral road environment with a unique three-dimensional spiral structure, drivers may face greater psychological pressure during driving, which not only affects the continuity of traffic flow, but also poses a challenge to the stability of traffic flow. The complex environmental characteristics of spiral roads increase the difficulty of traffic management and control, and put forward higher requirements for the stability of traffic flow.

[0003] At present, traffic flow models mainly include vehicle following models, cellular automaton models, fluid dynamics models, etc. These models play an important role in describing the process of traffic flow changing from free flow to congested flow. However, most existing traffic flow models mainly focus on non-connected passenger cars, and rarely consider the characteristics of mixed traffic flow (i.e., different types of vehicles, such as connected and non-connected commercial vehicles and passenger cars) and their impact on traffic flow. Traditional fluid dynamics models focus more on the macroscopic performance of vehicle density and speed, while ignoring the impact of microscopic factors such as road curves and slopes on driver behavior. When dealing with traffic flow on complex terrain such as spiral roads, the instability of mixed traffic flow is easily amplified, resulting in reduced efficiency and safety of traffic flow.

[0004] In some cases, most models fail to fully consider the different behavioral characteristics of different types of vehicles (such as connected vehicles and non-connected vehicles) in mixed traffic flows, which leads to insufficient accuracy in predicting actual traffic flow behaviors and inability to reflect changes in traffic conditions in real time, affecting the practicality and adaptability of the models. A vehicle control method for mixed vehicles is urgently needed to handle mixed traffic flows in complex road environments. Summary of the invention

[0005] The main purpose of the present application is to provide a vehicle speed optimization method, device, equipment and medium based on mixed traffic flow, aiming to solve the technical problem of how to control the speed of mixed traffic flow under complex road conditions.

[0006] To achieve the above objectives, the present application proposes a vehicle speed optimization method based on mixed traffic flow, the method comprising:

[0007] Obtain vehicle driving information on spiral roads;

[0008] The vehicle driving information is analyzed by using a preset spiral road mixed traffic simulation model to obtain a traffic simulation result;

[0009] Obtaining an optimized speed based on the vehicle travel information based on the traffic flow simulation result;

[0010] Adjustments are made based on the optimized speed.

[0011] In one embodiment, before the step of analyzing the vehicle driving information by using a preset spiral road mixed traffic simulation model to obtain a traffic simulation result, the step includes:

[0012] Obtain vehicle driving sample information and establish an initial spiral road mixed traffic simulation model;

[0013] The initial spiral road mixed traffic flow simulation model is trained according to the vehicle driving sample information to obtain a preset spiral road mixed traffic flow simulation model.

[0014] In one embodiment, the step of training the initial spiral road mixed traffic flow simulation model according to the vehicle driving information to obtain a preset spiral road mixed traffic flow simulation model includes:

[0015] Initialize model parameters;

[0016] Inputting the vehicle driving sample information into the initial spiral road mixed traffic flow simulation model for calculation to obtain predicted traffic data;

[0017] Calculating according to the loss function, obtaining an error value between the predicted traffic data and the actual traffic data;

[0018] By calculating through the back propagation algorithm, the gradient of the model parameters is obtained;

[0019] The model parameters are iteratively updated through an optimization algorithm according to the gradient until a maximum number of iterations is reached or an error value calculated by a loss function converges to a preset threshold, thereby obtaining a preset spiral road mixed traffic simulation model.

[0020] In one embodiment, before the step of inputting the vehicle driving sample information into the initial spiral road mixed traffic flow simulation model for calculation to obtain predicted traffic data, the step includes:

[0021] Establishing a mixed traffic grid following model, wherein the mixed traffic grid following model is an information exchange model between the vehicle and the outside world;

[0022] Performing linear processing on the mixed traffic grid following model to obtain a density equation;

[0023] A small quantity is introduced into the density equation and deduced to obtain a nonlinear partial differential equation;

[0024] The nonlinear partial differential equation is discretized to determine an initial spiral road mixed traffic simulation model.

[0025] In one embodiment, the step of obtaining an optimized speed based on the vehicle driving information based on the traffic flow simulation result includes:

[0026] Combining the traffic flow simulation result with the vehicle driving information calculation, a preset speed of the vehicle in the current grid is obtained;

[0027] The preset speed is used as the optimized speed.

[0028] In one embodiment, the step of adjusting based on the optimized speed includes:

[0029] According to the vehicle driving information, the distance between vehicles is obtained;

[0030] Determining the distance between the vehicles and obtaining a determination result;

[0031] Based on the judgment result, adjustment is made according to the optimized speed according to the vehicle driving information.

[0032] In one embodiment, the step of adjusting the speed according to the optimized speed based on the vehicle driving information based on the judgment result includes:

[0033] When the distance between the vehicles exceeds a preset safety threshold, the speed of the vehicle is optimized and the vehicle speed is adjusted to a preset speed for driving;

[0034] When the distance between the vehicles does not exceed a preset safety threshold or the vehicle speed reaches a preset speed, the vehicle maintains its current speed for driving.

[0035] In addition, to achieve the above-mentioned purpose, the present application also proposes a vehicle speed optimization device based on mixed traffic flow, the vehicle speed optimization device based on mixed traffic flow comprising:

[0036] An acquisition module is used to acquire vehicle driving information on the spiral road;

[0037] The simulation module is further used to analyze the vehicle driving information through a preset spiral road mixed traffic simulation model to obtain a traffic simulation result;

[0038] A calculation module, used for obtaining an optimized speed according to the vehicle driving information based on the traffic flow simulation result;

[0039] An adjustment module is used to make adjustments based on the optimized speed.

[0040] In addition, to achieve the above objectives, the present application also proposes a medium, which is a computer-readable medium, on which a computer program is stored, and when the computer program is executed by a processor, the steps of the vehicle speed optimization method based on mixed traffic flow as described above are implemented.

[0041] In addition, to achieve the above-mentioned purpose, the present application also provides a computer program product, which includes a computer program. When the computer program is executed by a processor, the steps of the vehicle speed optimization method based on mixed traffic flow as described above are implemented.

[0042] This application obtains vehicle driving information on a spiral road, analyzes the vehicle driving information through a preset spiral road mixed traffic simulation model, obtains traffic simulation results, obtains optimized speeds based on the traffic simulation results and vehicle driving information, and makes adjustments based on the optimized speeds. By using V2X technology to obtain vehicle driving information on spiral roads, and using a mixed traffic simulation model to analyze and optimize vehicle speeds, traffic flow stability and safety can be improved, and traffic congestion can be alleviated. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0044] Figure 1 This is a flow chart of a first embodiment of a vehicle speed optimization method based on mixed traffic flow of the present application;

[0045] Figure 2 A density-sensitivity phase diagram of K changes of the first embodiment of the vehicle speed optimization method based on mixed traffic flow of the present application;

[0046] Figure 3 A density-sensitivity phase diagram of φ change of the first embodiment of the vehicle speed optimization method based on mixed traffic flow of the present application;

[0047] Figure 4 A schematic diagram of a spiral road and vehicle optimal speed optimization according to a first embodiment of the vehicle speed optimization method based on mixed traffic flow of the present application;

[0048] Figure 5 This is a flow chart of a second embodiment of the vehicle speed optimization method based on mixed traffic flow of the present application;

[0049] Figure 6 This is a flow chart of a third embodiment of the vehicle speed optimization method based on mixed traffic flow of the present application;

[0050] Figure 7 This is an optimal speed optimization flow chart of the third embodiment of the vehicle speed optimization method based on mixed traffic flow of the present application;

[0051] Figure 8 This is a schematic diagram of the module structure of a vehicle speed optimization device based on mixed traffic flow according to an embodiment of the present application;

[0052] Fig. 9 Schematic diagram of the device structure of the hardware operating environment involved in the vehicle speed optimization method based on mixed traffic flow in the embodiment of the present application.

[0053] The purpose, features and advantages of this application will be further described in conjunction with the embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0054] It should be understood that the specific embodiments described herein are only used to explain the technical solutions of the present application and are not used to limit the present application.

[0055] In order to better understand the technical solution of the present application, a detailed description will be given below in conjunction with the accompanying drawings and specific implementation methods.

[0056] The main solution of the embodiment of the present application is: to obtain vehicle driving information on the spiral road, analyze the vehicle driving information through a preset spiral road mixed traffic simulation model, obtain traffic simulation results, obtain the optimized speed based on the traffic simulation results and the vehicle driving information, and make adjustments based on the optimized speed.

[0057] Based on this, the embodiment of the present application provides a vehicle speed optimization method based on mixed traffic flow, referring to Figure 1 , Figure 1 This is a flow chart of a first embodiment of the vehicle speed optimization method based on mixed traffic flow of the present application.

[0058] In this embodiment, the vehicle speed optimization method based on mixed traffic flow includes steps S10 to S40:

[0059] Step S10, obtaining vehicle driving information on the spiral road.

[0060] It should be noted that the vehicle-to-everything (V2X) technology collects dynamic data such as the position, speed, acceleration, etc. of all vehicles on the spiral road in real time, as well as geometric information of the road, such as slope, curve radius, and road friction coefficient. The acquisition of this information helps to fully understand the current traffic conditions. In order to efficiently obtain vehicle driving information, a variety of sensors and communication devices can be used. For example, on-board sensors can monitor dynamic parameters such as vehicle speed, acceleration, and direction in real time; roadside units (RSUs) can collect road environment information such as slope, curve radius, etc. In addition, V2X technology allows real-time communication between vehicles and between vehicles and infrastructure, extracts useful information such as vehicle spacing, relative speed, etc. through algorithms, and combines road geometry characteristics and driver behavior characteristics to build a preset spiral road mixed traffic simulation model.

[0061] Step S20, analyzing the vehicle driving information by using a preset spiral road mixed traffic simulation model to obtain a traffic simulation result.

[0062] It should be noted that before constructing the above-mentioned preset spiral road mixed traffic simulation model, a mixed traffic grid following model was constructed. This model divides the road into multiple grids, each grid containing one or more vehicles, and introduces a variety of key parameters, such as road slope, turning radius, road friction coefficient, etc., while taking into account different types of vehicles (connected commercial vehicles, non-connected commercial vehicles, connected passenger cars, non-connected passenger cars) and their penetration rates, as well as the driver's desire for smooth driving, so as to more accurately reflect the actual driving behavior.

[0063] Furthermore, a mixed traffic grid following model is established, which is an information exchange model between the vehicle and the outside world. Specifically, a mixed traffic grid following system in a V2X environment is first established, taking into account the geometric characteristics of spiral roads. Factors such as slope, turning radius, and road friction coefficient are introduced into the basic optimization speed function. At the same time, the flow difference effect and the driver's desire for stable driving are introduced into the control equation of the networked commercial vehicle. The specific formula constructed is as follows:

[0064]

[0065] This formula represents the conservation equation of traffic flow at the macro level, where ρ j and v j They represent the density and velocity of the jth position on the one-dimensional lattice at time t, respectively, a represents the driver sensitivity, and ρ0 represents the average density.

[0066]

[0067] This formula represents the control of traffic flow at the macro level. In the improved traffic flow grid model, the following four types of vehicles are introduced: Connected Commercial Vehicles (CCV), non-connected passenger vehicles (CPV), CPV represents connected passenger vehicles, non-connected commercial vehicles (NCCV). c,c represents the penetration rate of connected passenger vehicles, ρ c,h represents the penetration rate of connected commercial vehicles, ρ n,c represents the penetration rate of non-connected passenger cars, ρ n,h represents the penetration rate of non-connected commercial vehicles. Obviously, the sum of the penetration rates of the four types of vehicles is 1, that is: ρ c,c +ρ c,h +ρ n,c +ρ n,h =1, considering the relationship between vehicle model penetration rates, it is clear that the penetration rate of non-connected commercial vehicles is ρ n,h =(ρ n,h +ρ c,h )(ρ n,c +ρ n,h ), penetration rate of connected commercial vehicles ρ c,h =(ρ n,h +ρ c,h )(ρ c,c +ρ c,h ), non-network-connected ride-hailing network car penetration rate ρ n,c =(ρ n,c +ρ c,c )(ρ n,c +ρ n,h ), penetration rate of connected passenger vehicles ρ c,c =(ρ n,c +ρ c,c )(ρ c,c +ρ c,h ).

[0068] Furthermore, in order to enhance the applicability of the model, it is necessary to accurately characterize the density state and stable state of the traffic flow grid in the improved traffic flow model. The density λ (0≤λ≤1) is introduced in the formula to represent the reaction coefficient of the density dispersion. When the density dispersion term decreases, the optimization speed increases, indicating that the local traffic flow in front is stable and the vehicle driving safety level is high, and the vehicle can accelerate; conversely, when the density dispersion term increases, the optimization speed decreases, indicating that the local vehicle flow in front is unstable and the vehicle driving safety level is low, and the vehicle should slow down, which is in line with the actual traffic situation. When λ=0 and the spiral road factor is not considered, the model can be degenerated into the Nagatani model. The mixed traffic grid following model is linearly processed to obtain the density equation. Specifically, the density equation formula is:

[0069]

[0070] In order to study the resistance of the mixed traffic grid following model to small disturbances, the density equation is used to obtain the stability condition of the grid model through linear analysis. The influence of the driver's desire for stable driving and the slope of the spiral section on the stability of the grid model are discussed, so as to preliminarily understand the resistance of the grid model to small disturbances and provide critical stability conditions for nonlinear analysis. The specific steps are as follows: First, the state solution is set to: ρ j (t) = ρ0, v j (t)=V(ρ0), and then add a small disturbance, then: ρ j (t) = ρ0 + y j (t), after introducing the density equation into the state solution and small perturbation, it can be linearized to obtain:

[0071]

[0072] in, By expanding y j (t) = exp(ijk + zt), we get the equation about z:

[0073]

[0074] Expand z=ikz1+(ik) 2 z2+…, substituting into:

[0075]

[0076] Further simplification yields:

[0077]

[0078] Further solving gives:

[0079]

[0080] According to the stability theory, if z2<0, the initially uniform traffic flow will show instability in the long wave mode; if z2>0, the original stable state will be maintained. Therefore, z2=0 corresponds to the critical stability condition of the mixed traffic grid following model:

[0081]

[0082] The corresponding stability condition is:

[0083]

[0084] Obviously, when the penetration rate of connected commercial vehicles, non-connected commercial vehicles, and connected passenger vehicles are all 0, and the slope θ is not considered j and the smooth driving desire reaction coefficient K, the stability condition is consistent with the lattice fluid dynamics model that describes traditional traffic, and the expression is:

[0085]

[0086] Furthermore, a small quantity is introduced into the density equation and deduced to obtain a nonlinear partial differential equation. Specifically, a small quantity 0<ε≤1 is introduced, and at the critical point (p c ,a c ) consider slow variables X and Y, defined as follows:

[0087] X=ε(j+bt),Y=ε 3 t

[0088] Among them, b is a parameter to be determined, let the density of j grids be:

[0089] ρ j (t) = ρ c +εG(X,Y)

[0090] After introducing the density equation into the slow variable and the density of the grid point j, the nonlinear partial differential equation can be obtained:

[0091]

[0092] in Pick get:

[0093]

[0094] The coefficients are:

[0095]

[0096]

[0097]

[0098]

[0099]

[0100] By transformation and derivation, the kink-antikink wave solution of the mKdv equation with high-order small quantities is obtained as follows:

[0101]

[0102] Furthermore, the amplitude of the density wave is:

[0103]

[0104] The density wave solution reflects the existence of a coexistence phase of traffic. The coexistence curve can be expressed as p = p c ±A is used to express it. Figure 2 , 3 Different states of the driver's steady driving desire reaction coefficient K and the spiral section slope φ in the density-sensitivity coefficient (p, a) phase space are given: stable is a stable state, unstable is an unstable state, and metastable is a metastable state. Figure 2 is the density-sensitivity phase diagram of K variation, Figure 3 is the density-sensitivity phase diagram of φ variation, where p c,c =p n,c =p c,h =p n,h =0.25, f cv =0.8, f t =0.86, R2=10, μ=0.25, g=9.8, λ=0.2, m=2, θ=60°. Depend on Figure 2 It can be seen that the increase in the driver's desire for smooth driving reaction coefficient K will cause the critical point in the phase diagram to decrease, and the area of ​​the traffic flow in the stable state will expand, which means that the improvement of the driver's desire for smooth driving will enhance the stability of the mixed traffic flow on the spiral road. Figure 3 It can be seen that the stable area of ​​traffic flow expands when going uphill, and the unstable area expands when going downhill. This shows that the uphill of the spiral road is conducive to the stability of mixed traffic flow, while the downhill of the spiral road is not conducive to the stability of mixed traffic flow. This is because the vehicles are affected by the acceleration of gravity. When going uphill, the slowing down of the traffic flow is conducive to the traffic flow entering a stable state, while when going downhill, the speed of the traffic flow increases, which is not conducive to the stability of the traffic flow. Figure 2 , 3The coexistence curves and nonlinear analysis results in Figure 2 show that near the critical point, the traffic congestion characteristics are represented by the kink-antikink density wave of the mKdV equation, and the density amplitude decreases with the increase of K value. The nonlinear partial differential equation is discretized to determine the initial spiral road mixed traffic simulation model.

[0105] Step S30, obtaining an optimized speed based on the traffic flow simulation result and vehicle driving information.

[0106] It should be understood that the complex geometric characteristics of the spiral road require the integration of the characteristics of the curve and the slope. Considering that when a vehicle is driving on a spiral road, the vehicle is subject to two forces, one is gravity and the other is centripetal force. Further factors such as slope, vehicle mass, and lateral friction coefficient are introduced, and the optimized speed function is proposed as follows:

[0107]

[0108] Among them, Figure 4 The spiral road and vehicle optimal speed optimization diagram shown in the figure, gravity can be decomposed into horizontal force qgsinφ and vertical force qgsinφ, φ represents the slope, gravity acceleration is g, vehicle mass is q, and lateral friction coefficient of the road section is μ. Assuming the maximum speed v on the spiral road max =f cv f t R1ω max , maximum angular velocity ω max =qgcosφ / R2, where R1 represents the curvature radius of the spiral road, and R2 represents the bending radius of the spiral road when it is linearly mapped to the plane. The relationship between the two is R1=R2 / cosφ. According to the centripetal force formula, we can get: Therefore, the maximum angular velocity can be obtained as Maximum speed change value v g,max =mgsinφ / μ1, where qg / μ1=1, μ1 represents the longitudinal friction coefficient, so the optimal speed function is expressed as:

[0109]

[0110] Among them, φ>0 means uphill, φ<0 means downhill, f t represents the turning correction factor, f cv Represents the vehicle model correction factor. According to the test, f tTaking the value of 0.86, it is found that 86.12% of the networked commercial vehicles have a speed between 60 and 200 km / h, while the maximum speed of networked commercial vehicles on highways generally cannot exceed 90 km / h. Therefore, the maximum value of 90 km / h and 86.12% are multiplied to obtain the expected maximum speed of networked commercial vehicles of 77.51 km / h. The average speed of cars on highways is 97 km / h. According to the proportion, cv Take 0.8.

[0111] Furthermore, V2X equipment is used to collect information such as the position, speed, acceleration, etc. of all vehicles on the spiral road, as well as geometric information of the road, such as slope, curve radius, road friction coefficient, etc. Based on the collected information, the optimal speed function of the established mixed traffic grid following model is used to calculate the optimal speed of each vehicle in the current grid. The optimal speed function takes into account the vehicle's current speed, the distance to the vehicle in front, the road conditions (such as slope, curve), and the driver's desire for smooth driving. In order to effectively quantify road safety risks, it is usually measured by designing reasonable safety indicators. In practical applications, time-based safety indicators are the most widely used, mainly used to calculate the severity of collisions. The collision time TTC is used to quantify the driving risk of vehicles in spiral road traffic flow, which is expressed as follows:

[0112]

[0113] Among them, x i (t) is the position information of vehicle i at time t, v i (t) is the speed of vehicle i at time t. Combining the traffic flow simulation results and vehicle driving information calculation, the preset speed of the vehicle in the current grid is obtained, and the preset speed is used as the optimized speed. Specifically, Figure 4 As shown in the figure, at t = 0, on the spiral road, there is a front vehicle NCPV and a rear vehicle CPV, and the grids where the NCPV and CPV are located are j and jm, and the optimal target speeds of the front vehicle NCPV and the rear vehicle CPV at t = 0 are:

[0114]

[0115]

[0116] Assume that the speeds of the front vehicle NCPV and the rear vehicle CPV at t = 0 are v NCPV (0), v NCPV (0), and v NCPV (0) = V(ρ j ,φ),v CPV (0) <V(ρ j,φ). At this time, the front vehicle NCPV does not need control optimization, it has reached the optimal target speed, and can just keep driving at a constant speed; while the rear vehicle CPV has not reached the target speed, it needs to be optimized for optimal speed, and the speed is accelerated to V(ρ,φ). At this time, the rear vehicle CPV and the front vehicle NCPV have a safe following distance, and the optimal speed optimization is performed at this time to adjust the speed of the rear vehicle CPV to the optimal speed. During the speed adjustment, the TTC status of CPV and the front vehicle is always monitored. When TTC is reduced to TTC SR (safe) CPV-NCPV When the vehicle stops adjusting speed, it maintains the current speed for stable driving.

[0117] Step S40, making adjustments based on the optimized speed.

[0118] It should be noted that after analyzing the vehicle driving information through the preset mixed traffic grid following system and calculating the optimal speed of each vehicle in the current grid, the next step is to send these optimized speed instructions to each vehicle in real time through V2X technology to guide the vehicle to adjust its speed. During the adjustment process, the safe distance between vehicles is an important consideration. Based on the improved spiral road environment collision time (TTC-SR) safety threshold, the model calculates the minimum safe distance between the vehicle and the vehicle in front. If the current distance between the vehicle and the vehicle in front is greater than this threshold, the vehicle can be adjusted according to the optimized speed; if the distance is less than the threshold, the vehicle maintains the current speed or decelerates appropriately to ensure safety. In addition, when the current speed of the vehicle is equal to or close to the optimized speed, no additional speed adjustment is made to maintain a uniform speed and avoid unnecessary acceleration and deceleration operations, thereby improving the stability and safety of traffic flow.

[0119] This embodiment provides a vehicle speed optimization method based on mixed traffic flow, which obtains vehicle driving information on a spiral road, analyzes the vehicle driving information through a preset spiral road mixed traffic flow simulation model, obtains a traffic flow simulation result, obtains an optimized speed based on the traffic flow simulation result and the vehicle driving information, and makes adjustments based on the optimized speed. By using V2X technology to obtain vehicle driving information on a spiral road, and using a mixed traffic flow simulation model to analyze and optimize vehicle speeds, traffic flow stability and safety are improved, and traffic congestion is alleviated.

[0120] Based on the first embodiment of the present application, in the second embodiment of the present application, the same or similar contents as those in the above-mentioned embodiment 1 can refer to the above introduction, and will not be repeated later. Figure 5 The vehicle speed optimization method based on mixed traffic flow further includes steps S201 to S202 before step S20:

[0121] Step S201, obtaining vehicle driving sample information and establishing an initial spiral road mixed traffic simulation model.

[0122] Step S202: training the initial spiral road mixed traffic flow simulation model according to the vehicle driving sample information to obtain a preset spiral road mixed traffic flow simulation model.

[0123] It should be noted that, to train the initial spiral road mixed traffic simulation model, first initialize the model parameters, obtain input data, and then normalize the input data to obtain processed input data, and then input the processed input data into the initial spiral road mixed traffic simulation model to obtain predicted traffic data, and then calculate according to the loss function to obtain the error value between the predicted traffic data and the actual traffic data, calculate through the back propagation algorithm to obtain the gradient of the model parameters, and finally update the model parameters iteratively through the optimization algorithm according to the gradient until the maximum number of iterations is reached or the error value calculated by the loss function converges to the preset threshold, and the preset spiral road mixed traffic simulation model is obtained. Specifically, first, collect vehicle driving data, clean and normalize it, eliminate noise and outliers, and form a high-quality training data set. The specific normalization is according to the formula:

[0124]

[0125] Normalize the input data to between 0 and 1 to facilitate neural network processing.

[0126] The data set is divided into training set, validation set and test set in a certain proportion, generally with a ratio of 70%, 15%, and 15%, to ensure that the training, tuning and generalization ability evaluation of the model are scientific and reasonable. Then, these data sets are used to train the initial model. The model adopts a multi-layer perceptron structure, including a carefully designed input layer, two hidden layers and an output layer. During the training process, the model predicts the output through forward propagation calculation, and the input data of the input layer is calculated through linear change to obtain the input data of the hidden layer. Specifically, the input data of the first hidden layer is obtained by the following formula:

[0127] Z (1) =W (1) x+b (1)

[0128] Where Z (1) is the input value of the first hidden layer, W (1) is the weight matrix of the first hidden layer, which indicates the connection strength between the input layer and the hidden layer. x is the input data of the input layer, and b (1) It is a bias vector used to adjust the activation value of the hidden layer. The superscript represents the data of the hidden layer. Each hidden layer has a different weight matrix and bias vector.

[0129] The input data of the hidden layer is calculated through the nonlinear ReLU activation function to obtain the output data of the first hidden layer. Specifically, it is obtained by the following formula:

[0130] A (1) =ReLU(z (1) )

[0131] Among them, A (1) The output data of the first hidden layer. This means that for the input data, the output of the ReLU function is a larger value between 0 and 1. If the input data is greater than 0, the output is 1; if the input data is less than or equal to 0, the output is 0. According to the above two formulas, the output data of the hidden layer is first calculated by linear change and then by nonlinear ReLU activation function until the output data Z of the last hidden layer is obtained. (2) and A (2) , the output data of the last hidden layer is used as the input data of the output layer, and is calculated according to the nonlinear Sigmoid activation function. Thus, the predicted output data is obtained. Specifically, it is obtained according to the following formula:

[0132] Z (3) =W (3) A (2) +b (3)

[0133] Y=Sigmoid(Z (3) )

[0134] Among them, Z (3) is the input value of the output layer, W (3) is the weight matrix of the output layer, which represents the connection strength between the output layer and the second hidden layer. (2) is the input data of the second hidden layer, b (3) is the bias vector, and Y is the output value of the output layer.

[0135] In this embodiment, the error value between the predicted result and the actual result is obtained by using the mean square error MSE as the loss function, specifically:

[0136]

[0137] Among them, Y i is the real data, Y iis the predicted data, and m is the number of samples. Then, the stochastic gradient descent optimization strategy is adopted to obtain the gradient a and gradually adjust the model parameters until the loss function converges or reaches the predetermined number of iterations. This process is repeated to gradually approach the global optimal solution. During the entire training phase, it is also necessary to pay close attention to the overfitting problem of the model and use regularization, dropout and other technologies to alleviate it when appropriate. The model hyperparameters, such as the learning rate and the number of hidden layer nodes, are continuously adjusted through cross-validation and other means to optimize the model performance.

[0138] This embodiment obtains vehicle driving sample data and establishes an initial spiral road mixed traffic simulation model, and trains the initial spiral road mixed traffic simulation model according to the vehicle driving sample data to obtain a preset spiral road mixed traffic simulation model. By establishing the spiral road mixed traffic simulation model, the vehicle simulation result is accurately judged, so as to adjust the vehicle speed.

[0139] Based on the first embodiment of the present application, in the third embodiment of the present application, the same or similar contents as those in the first embodiment can be referred to the above description, and will not be described in detail later. Figure 6 The vehicle speed optimization method based on mixed traffic flow step S40 further includes steps S401 to S403:

[0140] Step S401, obtaining the distance between vehicles according to the vehicle driving information.

[0141] It should be noted that V2X technology collects dynamic data such as the position, speed, acceleration, etc. of all vehicles on the spiral road in real time, as well as geometric information of the road, such as slope, curve radius, road friction coefficient, etc. These data are processed and analyzed in real time to calculate the distance between each vehicle and other vehicles, especially the distance between the front and rear vehicles. Specifically, the position coordinates of each vehicle in the road grid can be calculated through the vehicle's position information, and then the distance between adjacent vehicles can be calculated.

[0142] Step S402, judging the distance between vehicles and obtaining a judgment result.

[0143] It should be noted that the calculated vehicle spacing is judged to determine whether it meets the preset safety distance threshold. The preset safety distance threshold can be defined by the improved time to collision in spiral road environment (TTC-SR) model. Specifically, the TTC-SR model takes into account factors such as the driver's desire for smooth driving and road geometry, and calculates a dynamically adjusted collision time threshold. If the distance between the current vehicle and the vehicle in front is greater than this threshold, the system determines that the safety distance is sufficient, and the vehicle can be adjusted according to the optimized speed; if the distance is less than the threshold, the system determines that the safety distance is insufficient, and the vehicle needs to maintain the current speed or slow down appropriately to ensure safety.

[0144] Step S403: adjusting the speed according to the optimized speed based on the judgment result and the vehicle driving information.

[0145] It should be noted that the optimized speed instructions are generated based on the judgment results and sent to each vehicle in real time through V2X technology. After receiving the instructions, the vehicle adjusts its speed through the on-board control system to achieve the optimized speed.

[0146] Furthermore, when the distance between vehicles exceeds a preset safety threshold, the vehicle speed is optimized and the vehicle speed is adjusted to the preset speed for driving. Specifically, if the distance between the current vehicle and the vehicle in front is greater than the preset TTC-SR threshold, the vehicle can be adjusted according to the optimized speed. The TTC-SR threshold is calculated in real time based on the vehicle's position, speed, acceleration and other data as well as the geometric information of the road. The optimized speed is calculated based on the vehicle's current position, speed, road conditions (such as slope, curve) and the driver's desire for smooth driving.

[0147] Furthermore, when the distance between vehicles does not exceed the preset safety threshold or the vehicle speed reaches the preset speed, the vehicle maintains the current speed. Specifically, if the distance between the current vehicle and the vehicle in front is less than the preset TTC-SR threshold or the current speed of the vehicle is equal to or close to the optimized speed, the vehicle needs to maintain the current speed or decelerate appropriately to ensure safety.

[0148] Furthermore, if Figure 7 The optimal speed optimization flowchart shown in the figure starts with the V2X device continuously acquiring the spiral road traffic flow information, which includes the vehicle's position, speed, acceleration, and the geometric characteristics of the road, such as slope and curve radius. Then, the optimal speed of the vehicle is calculated using the improved spiral road traffic flow grid model optimal speed function, which takes into account factors such as vehicle density, road angle, road curvature radius, gravity acceleration, friction coefficient, etc. At the same time, an improved spiral road environment dynamic adjustment collision time model TTC-SR is introduced. This model dynamically calculates the collision time between vehicles by adjusting relevant parameters to adapt to the special environment of spiral roads. During the optimization process, the system checks whether the current vehicle speed has reached the optimal speed. If not, it will continue to optimize the speed. Before trying to optimize the speed, the system will also check whether the current TTC value meets the safety threshold to ensure driving safety during the optimization process. If the TTC value is lower than the safety threshold, the system will not allow speed optimization. Only when the vehicle speed is not optimal and the TTC value meets the safety requirements, the system will start speed optimization, which may gradually reach the optimal speed by adjusting the vehicle's acceleration.

[0149] In this embodiment, the distance between vehicles is obtained according to the vehicle driving information, the distance between vehicles is judged, a judgment result is obtained, and the speed is adjusted according to the optimized speed according to the vehicle driving information based on the judgment result. The adjustment is made based on the vehicle driving information and the optimized speed to improve the stability and safety of the traffic flow on the spiral road.

[0150] This application also provides a vehicle speed optimization device based on mixed traffic flow, please refer to Figure 8 , the device comprises:

[0151] The acquisition module 10 is used to acquire the vehicle driving information on the spiral road.

[0152] The simulation module 20 is also used to analyze vehicle driving information through a spiral road mixed traffic simulation model to obtain traffic simulation results.

[0153] The calculation module 30 is used to obtain the optimized speed based on the traffic flow simulation result and the vehicle driving information.

[0154] The adjustment module 40 is used to make adjustments based on the optimized speed.

[0155] The vehicle speed optimization device based on mixed traffic provided by the present application adopts the vehicle speed optimization method based on mixed traffic in the above embodiment, and can solve the technical problem of how to control the speed of mixed traffic under complex road conditions. Compared with the prior art, the beneficial effects of the vehicle speed optimization device based on mixed traffic provided by the present application are the same as the beneficial effects of the vehicle speed optimization method based on mixed traffic provided by the above embodiment, and the other technical features of the vehicle speed optimization device based on mixed traffic are the same as the features disclosed in the above embodiment method, which will not be repeated here.

[0156] In one embodiment, the simulation module 20 is also used to obtain vehicle driving sample information and establish an initial spiral road mixed traffic simulation model; the initial spiral road mixed traffic simulation model is trained according to the vehicle driving sample information to obtain a preset spiral road mixed traffic simulation model.

[0157] In one embodiment, the simulation module 20 is also used to initialize model parameters; input vehicle driving sample information into the initial spiral road mixed traffic simulation model for calculation to obtain predicted traffic data; calculate according to the loss function to obtain the error value between the predicted traffic data and the actual traffic data; calculate through the back propagation algorithm to obtain the gradient of the model parameters; iteratively update the model parameters through the optimization algorithm according to the gradient until the maximum number of iterations is reached or the error value calculated by the loss function converges to a preset threshold, thereby obtaining a preset spiral road mixed traffic simulation model.

[0158] In one embodiment, the simulation module 20 is also used to establish a mixed traffic grid following model, which is an information exchange model between the vehicle and the outside world; linearly process the mixed traffic grid following model to obtain a density equation; introduce a small quantity into the density equation and derive it to obtain a nonlinear partial differential equation; discretize the nonlinear partial differential equation to determine the initial spiral road mixed traffic simulation model.

[0159] In one embodiment, the calculation module 30 is further used to calculate the preset speed of the vehicle in the current grid by combining the traffic flow simulation result and the vehicle driving information; and the preset speed is used as the optimized speed.

[0160] In one embodiment, the adjustment module 40 is further used to obtain the distance between vehicles based on the vehicle driving information; judge the distance between vehicles to obtain a judgment result; and adjust the speed according to the optimized speed based on the vehicle driving information based on the judgment result.

[0161] In one embodiment, the adjustment module 40 is also used to optimize the speed of the vehicle and adjust the vehicle speed to a preset speed for driving when the distance between the vehicles exceeds a preset safety threshold; when the distance between the vehicles does not exceed the preset safety threshold or the vehicle speed reaches the preset speed, maintain the current speed of the vehicle for driving.

[0162] The present application provides a vehicle speed optimization device based on mixed traffic flow, and the vehicle speed optimization device based on mixed traffic flow includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the vehicle speed optimization method based on mixed traffic flow in the above-mentioned embodiment one.

[0163] Reference below Fig. 9 , which shows a schematic diagram of the structure of a vehicle speed optimization device based on mixed traffic flow suitable for implementing the embodiment of the present application. The vehicle speed optimization device based on mixed traffic flow in the embodiment of the present application may include but is not limited to mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions), PMPs (Portable Media Players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Fig. 9 The vehicle speed optimization device based on mixed traffic flow shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0164] like Fig. 9 As shown, the vehicle speed optimization device based on mixed traffic flow may include a processing device 1001 (e.g., a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM: Read Only Memory) 1002 or a program loaded from a storage device 1003 to a random access memory (RAM: Random Access Memory) 1004. Various programs and data required for the operation of the vehicle speed optimization device based on mixed traffic flow are also stored in the RAM 1004. The processing device 1001, the ROM 1002, and the RAM 1004 are connected to each other via a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems may be connected to the I / O interface 1006: input devices 1007 including, for example, a touch screen, a touchpad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; output devices 1008 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; storage devices 1003 including, for example, a magnetic tape, a hard disk, etc.; and communication devices 1009. The communication device 1009 may allow the vehicle speed optimization device based on mixed traffic to communicate wirelessly or wired with other devices to exchange data. Although the figure shows a vehicle speed optimization device based on mixed traffic with various systems, it should be understood that it is not required to implement or have all the systems shown. More or fewer systems may be implemented or have instead.

[0165] In particular, according to the embodiments disclosed in the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present application include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication device, or installed from a storage device 1003, or installed from a ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiment disclosed in the present application are executed.

[0166] The vehicle speed optimization device based on mixed traffic provided by the present application adopts the vehicle speed optimization method based on mixed traffic in the above embodiment, which can solve the technical problem of how to control the speed of mixed traffic under complex road conditions. Compared with the prior art, the beneficial effects of the vehicle speed optimization device based on mixed traffic provided by the present application are the same as the beneficial effects of the vehicle speed optimization method based on mixed traffic provided by the above embodiment, and the other technical features of the vehicle speed optimization device based on mixed traffic are the same as the features disclosed in the method of the previous embodiment, which will not be repeated here.

[0167] It should be understood that the various parts disclosed in this application can be implemented by hardware, software, firmware or a combination thereof. In the description of the above embodiments, specific features, structures, materials or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0168] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0169] The present application provides a computer-readable medium having computer-readable program instructions (ie, computer programs) stored thereon, and the computer-readable program instructions are used to execute the vehicle speed optimization method based on mixed traffic flow in the above-mentioned embodiment.

[0170] The computer-readable medium provided in the present application may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, systems or devices, or any combination of the above. More specific examples of computer-readable media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this embodiment, the computer-readable medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, system or device. The program code contained on the computer-readable medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination of the above.

[0171] The computer-readable medium may be included in the vehicle speed optimization device based on mixed traffic flow; or may exist independently without being assembled into the vehicle speed optimization device based on mixed traffic flow.

[0172] The computer-readable medium carries one or more programs. When the one or more programs are executed by the vehicle speed optimization device based on mixed traffic flow, the vehicle speed optimization device based on mixed traffic flow can be written in one or more programming languages ​​or a combination thereof to write computer program codes for performing the operations of the present application. The programming languages ​​include object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" language or similar programming languages. The program code can be executed completely on the user's computer, partially on the user's computer, as an independent software package, partially on the user's computer and partially on a remote computer, or completely on a remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computer (for example, using an Internet service provider to connect through the Internet).

[0173] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present application. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0174] The modules involved in the embodiments described in this application may be implemented by software or hardware, wherein the name of the module does not constitute a limitation on the unit itself in some cases.

[0175] The readable medium provided by the present application is a computer-readable medium, which stores computer-readable program instructions (i.e., computer programs) for executing the above-mentioned vehicle speed optimization method based on mixed traffic flow, and can solve the technical problem of how to control the speed of mixed traffic flow under complex road conditions. Compared with the prior art, the beneficial effects of the computer-readable medium provided by the present application are the same as the beneficial effects of the vehicle speed optimization method based on mixed traffic flow provided by the above-mentioned embodiment, and will not be repeated here.

[0176] The present application also provides a computer program product, comprising a computer program, wherein when the computer program is executed by a processor, the steps of the vehicle speed optimization method based on mixed traffic flow as described above are implemented.

[0177] The computer program product provided by the present application can solve the technical problem of how to control the speed of mixed traffic flow under complex road conditions. Compared with the prior art, the beneficial effects of the computer program product provided by the present application are the same as the beneficial effects of the vehicle speed optimization method based on mixed traffic flow provided by the above embodiment, which will not be repeated here.

[0178] The above descriptions are only some embodiments of the present application, and are not intended to limit the patent scope of the present application. All equivalent structural changes made using the contents of the present application specification and drawings under the technical concept of the present application, or direct / indirect applications in other related technical fields are included in the patent protection scope of the present application.

Claims

1. A vehicle speed optimization method based on mixed traffic flow, characterized in that: The method comprises: Obtain vehicle driving information on spiral roads; The vehicle driving information is analyzed by using a preset spiral road mixed traffic simulation model to obtain a traffic simulation result; Obtaining an optimized speed based on the vehicle travel information based on the traffic flow simulation result; Adjustments are made based on the optimized speed.

2. The method according to claim 1, characterized in that Before the step of analyzing the vehicle driving information by using a preset spiral road mixed traffic simulation model to obtain a traffic simulation result, the method includes: Obtain vehicle driving sample information and establish an initial spiral road mixed traffic simulation model; The initial spiral road mixed traffic flow simulation model is trained according to the vehicle driving sample information to obtain a preset spiral road mixed traffic flow simulation model.

3. The method according to claim 2, characterized in that The step of training the initial spiral road mixed traffic flow simulation model according to the vehicle driving information to obtain a preset spiral road mixed traffic flow simulation model comprises: Initialize model parameters; Inputting the vehicle driving sample information into the initial spiral road mixed traffic flow simulation model for calculation to obtain predicted traffic data; Calculating according to the loss function, obtaining an error value between the predicted traffic data and the actual traffic data; By calculating through the back propagation algorithm, the gradient of the model parameters is obtained; The model parameters are iteratively updated through an optimization algorithm according to the gradient until a maximum number of iterations is reached or an error value calculated by a loss function converges to a preset threshold, thereby obtaining a preset spiral road mixed traffic simulation model.

4. The method according to claim 3, characterized in that Before the step of inputting the vehicle driving sample information into the initial spiral road mixed traffic flow simulation model for calculation to obtain predicted traffic data, the method includes: Establishing a mixed traffic grid following model, wherein the mixed traffic grid following model is an information exchange model between the vehicle and the outside world; Performing linear processing on the mixed traffic grid following model to obtain a density equation; A small quantity is introduced into the density equation and deduced to obtain a nonlinear partial differential equation; The nonlinear partial differential equation is discretized to determine an initial spiral road mixed traffic simulation model.

5. The method according to claim 1, characterized in that The step of obtaining an optimized speed based on the vehicle flow simulation result and the vehicle driving information comprises: Combining the traffic flow simulation result with the vehicle driving information calculation, a preset speed of the vehicle in the current grid is obtained; The preset speed is used as the optimized speed.

6. The method according to claim 1, characterized in that The step of adjusting based on the optimized speed includes: According to the vehicle driving information, the distance between vehicles is obtained; Determining the distance between the vehicles and obtaining a determination result; Based on the judgment result, adjustment is made according to the optimized speed according to the vehicle driving information.

7. The method according to claim 6, characterized in that The step of adjusting the speed according to the optimized speed based on the judgment result and the vehicle driving information comprises: When the distance between the vehicles exceeds a preset safety threshold, the speed of the vehicle is optimized and the vehicle speed is adjusted to a preset speed for driving; When the distance between the vehicles does not exceed a preset safety threshold or the vehicle speed reaches a preset speed, the vehicle maintains its current speed for driving.

8. A vehicle speed optimization device based on mixed traffic flow, characterized in that: The device comprises: An acquisition module is used to acquire vehicle driving information on the spiral road; The simulation module is further used to analyze the vehicle driving information through a preset spiral road mixed traffic simulation model to obtain a traffic simulation result; A calculation module, used for obtaining an optimized speed according to the vehicle driving information based on the traffic flow simulation result; An adjustment module is used to make adjustments based on the optimized speed.

9. A vehicle speed optimization device based on mixed traffic flow, characterized in that: The device comprises: a memory, a processor, and a vehicle speed optimization program based on mixed traffic flow stored in the memory and executable on the processor, wherein the vehicle speed optimization program based on mixed traffic flow is configured to implement the steps of the vehicle speed optimization method based on mixed traffic flow as described in any one of claims 1 to 7.

10. A medium, characterized in that The medium stores a vehicle speed optimization program based on mixed traffic flow, and when the vehicle speed optimization program based on mixed traffic flow is executed by a processor, the steps of the vehicle speed optimization method based on mixed traffic flow as described in any one of claims 1 to 7 are implemented.

Images