A mixed traffic flow capacity calculation method, device, equipment and medium

Abstract

This invention relates to the field of intelligent connected vehicle (HDV) and traffic flow cooperative control technology, and discloses a method, apparatus, equipment, and medium for calculating the capacity of mixed traffic flow. This invention uses prospect theory to characterize the driving cooperation intentions of human drivers during car-following, and simultaneously predicts the congestion situation of the mixed traffic flow to be measured using a pre-set Markov chain model. Furthermore, by combining the predicted congestion state, the capacity of the mixed traffic flow to be measured can be calculated. Therefore, by implementing this invention, which fully combines prospect theory and Markov chain model, not only are the car-following behavior preferences of HDV drivers considered, but the temporal distribution characteristics of traffic congestion states are also described, ensuring the reliability and usability of the calculation results.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent networking and traffic flow coordinated control, and specifically to a mixed traffic flow capacity calculation method, device, equipment and medium. Background Art

[0002] With the rapid development of autonomous driving technology, it has become a reality that traditional human-driven vehicles (HDV) and connected and autonomous vehicles (CAV) travel together on the road, forming a new type of mixed traffic flow. In this mixed traffic flow, the interaction between CAV and HDV and its impact on traffic flow characteristics have become a new focus of traffic research. In particular, the cooperation willingness of human drivers is different under different traffic conditions, and the traffic capacity of the traffic flow may change significantly.

[0003] Traditional capacity measurement methods are mainly based on macro traffic flow theory, considering the overall characteristics of traffic flow, such as flow, density and speed, rather than the behavior of a single vehicle. The main models include basic flow model, speed-flow relationship and flow-density relationship, which are mostly based on field observation data and statistical analysis to describe the basic characteristics and behavior of traffic flow. However, these measurement methods do not fully consider the mixed driving environment of CAV and HDV, so they may no longer be applicable in new mixed traffic flow scenarios. CAV has a higher reaction speed and more accurate decision-making ability, and the way it interacts with HDV is also different from traditional traffic flow. Therefore, a new measurement method is needed to consider the interaction between CAV and HDV.

[0004] Existing measurement methods have obvious limitations in characterizing the cooperation willingness and micro-behavior of human drivers. These methods often fail to accurately capture the complexity and diversity of driver behavior, especially when considering the cooperation willingness of different drivers while driving. This leads to the lack of accuracy and reliability of the measurement results of existing methods in mixed traffic flow environments.

[0005] In addition, when measuring traffic capacity, only calculating the capacity of a certain scene or time is not practical and referenceable. Even if the measurement result is relatively accurate, it cannot provide information for traffic control. At the same time, when measuring traffic capacity under ideal road conditions, the value obtained is not the actual operating capacity of the road and has no practical guiding significance. Summary of the invention

[0006] In view of this, the present invention provides a mixed traffic flow capacity calculation method, device, equipment and medium to solve the problem that the existing calculation methods have obvious limitations in characterizing the cooperation willingness and micro-behavior of human drivers.

[0007] In a first aspect, the present invention provides a method for calculating the capacity of mixed traffic flow, the method comprising:

[0008] Obtain an HDV target traffic flow dataset and a CAV target traffic flow dataset corresponding to the mixed traffic flow to be measured; based on the HDV target traffic flow dataset, after processing using the preset vehicle following cooperation principle and prospect theory, determine the driver cooperation level utility value function; use a preset Markov chain model to predict the congestion situation of the mixed traffic flow to be measured, and obtain the predicted congestion state of the mixed traffic flow to be measured; based on the HDV target traffic flow dataset, the CAV target traffic flow dataset and the predicted congestion state, after processing using the driver cooperation level utility value function, calculate the capacity of the mixed traffic flow to be measured, and obtain the capacity calculation result of the mixed traffic flow to be measured.

[0009] The mixed traffic flow capacity calculation method provided by the present invention can characterize the driving cooperation willingness relationship of human drivers in the following process through prospect theory, and at the same time, predict the congestion situation of the mixed traffic flow to be measured through a preset Markov chain model. Furthermore, the capacity of the mixed traffic flow to be measured can be calculated in combination with the predicted congestion state. Therefore, by implementing the present invention, the prospect theory and the Markov chain model are fully combined, not only the following behavior preference of the HDV driver is considered, but also the time distribution characteristics of the traffic congestion state are described, ensuring the credibility and availability of the measurement results.

[0010] In an optional implementation, obtaining an HDV target traffic flow dataset and a CAV target traffic flow dataset corresponding to the mixed traffic flow to be measured includes:

[0011] An HDV initial traffic flow dataset and a CAV initial traffic flow dataset corresponding to the mixed traffic flow to be measured are obtained; the HDV initial traffic flow dataset and the CAV initial traffic flow dataset are processed respectively to obtain an HDV target traffic flow dataset and a CAV target traffic flow dataset.

[0012] The present invention can improve the data quality of the HDV target traffic flow data set and the CAV target traffic flow data set through data processing.

[0013] In an optional implementation, based on the HDV target traffic flow data set, after processing by the preset vehicle following cooperation principle and prospect theory, the utility value function of the driver cooperation level is determined, including:

[0014] Based on the HDV target traffic flow data set, the cooperation willingness urgency function is determined after processing with the preset vehicle following cooperation principle; based on the HDV target traffic flow data set, the weight function is determined after processing with prospect theory and cooperation willingness urgency function; based on the cooperation willingness urgency function and the weight function, the utility value function of the driver's cooperation level is determined.

[0015] The present invention uses prospect theory and combines the vehicle following cooperation principle to characterize the driving cooperation willingness relationship of human drivers in the following process and determine the corresponding driver cooperation level utility value function.

[0016] In an optional implementation, based on the HDV target traffic flow data set, after being processed by prospect theory and the urgency function of cooperation willingness, a weight function is determined, including:

[0017] Based on the HDV target traffic flow dataset, the probability function is determined after being processed by the cooperation willingness urgency function. Based on the probability function, the weight function is determined after being processed by prospect theory.

[0018] In an optional embodiment, the method further includes:

[0019] The HDV historical traffic flow dataset, the CAV historical traffic flow dataset and the mixed traffic flow historical traffic index are obtained. The mixed traffic flow historical traffic index is used to reflect the historical congestion status of the mixed traffic flow. The HDV historical traffic flow dataset and the CAV historical traffic flow dataset are used as input data, and the mixed traffic flow historical traffic index is used as output data for model training to obtain a preset Markov chain model.

[0020] The present invention obtains a preset Markov chain model through training of HDV historical traffic flow data set, CAV historical traffic flow data set and mixed traffic flow historical traffic index, which can provide support for the prediction of subsequent mixed traffic flow congestion.

[0021] In an optional implementation, based on the HDV target traffic flow data set, the CAV target traffic flow data set and the predicted congestion state, after being processed by the driver cooperation level utility value function, the capacity of the mixed traffic flow to be measured is measured, and the capacity measurement result of the mixed traffic flow to be measured is obtained, including:

[0022] Based on the HDV target traffic flow dataset and the predicted congestion status, the HDV headway is obtained after being processed by the driver's cooperative level utility value function; based on the HDV headway and CAV target traffic flow dataset, the capacity of the mixed traffic flow to be measured is calculated, and the capacity calculation result of the mixed traffic flow to be measured is obtained.

[0023] In an optional implementation, based on the HDV target traffic flow data set and the predicted congestion state, after being processed by the driver cooperation level utility value function, the HDV headway is obtained, including:

[0024] Based on the HDV target traffic flow dataset, the driver cooperation level utility value is obtained after being processed by the driver cooperation level utility value function; based on the HDV target traffic flow dataset, the predicted congestion status and the driver cooperation level utility value, the HDV headway is determined.

[0025] In a second aspect, the present invention provides a mixed traffic flow capacity calculation device, the device comprising:

[0026] The first acquisition module is used to obtain the HDV target traffic flow data set and the CAV target traffic flow data set corresponding to the mixed traffic flow to be measured; the processing and determination module is used to determine the driver's cooperation level utility value function based on the HDV target traffic flow data set after processing according to the preset vehicle following cooperation principle and prospect theory; the prediction module is used to predict the congestion situation of the mixed traffic flow to be measured by using the preset Markov chain model to obtain the predicted congestion state of the mixed traffic flow to be measured; the processing and measurement module is used to measure the capacity of the mixed traffic flow to be measured based on the HDV target traffic flow data set, the CAV target traffic flow data set and the predicted congestion state after processing according to the driver's cooperation level utility value function to obtain the capacity measurement result of the mixed traffic flow to be measured.

[0027] In a third aspect, the present invention provides a computer device, comprising: a memory and a processor, the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the mixed traffic flow capacity calculation method of the first aspect or any corresponding embodiment thereof by executing the computer instructions.

[0028] In a fourth aspect, the present invention provides a computer-readable storage medium having computer instructions stored thereon, the computer instructions being used to enable a computer to execute the mixed traffic flow capacity estimation method of the first aspect or any corresponding embodiment thereof. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] In order to more clearly illustrate the specific implementation methods of the present invention or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0030] Figure 1is a flow chart of a mixed traffic flow capacity estimation method according to an embodiment of the present invention;

[0031] Figure 2 is a schematic diagram of the cooperation relationship in the car-following process according to an embodiment of the present invention;

[0032] Figure 3 is a flow chart of another mixed traffic flow capacity estimation method according to an embodiment of the present invention;

[0033] Figure 4 is a schematic diagram of the urgency function of cooperation willingness according to an embodiment of the present invention;

[0034] Figure 5 is a flow chart of another mixed traffic flow capacity estimation method according to an embodiment of the present invention;

[0035] Figure 6 is a flow chart of a method for calculating the capacity of mixed traffic based on Markov chain and prospect theory according to an embodiment of the present invention;

[0036] Figure 7 is a structural block diagram of a device for calculating mixed traffic flow capacity according to an embodiment of the present invention;

[0037] Figure 8 It is a schematic diagram of the hardware structure of a computer device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0038] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0039] Existing traffic capacity estimation methods have significant limitations when dealing with mixed traffic flows, especially in mixed driving environments of HDVs and CAVs. Most of these methods are based on macroscopic traffic flow theory and focus on the overall characteristics of traffic flow, such as flow, density, and speed, but fail to fully consider the microscopic behavior and interactions of vehicles, especially in the characterization of the willingness of human drivers to cooperate. In mixed traffic, CAVs can maintain a relatively fixed following mode with their autonomous driving capabilities, while different drivers have different willingness to cooperate when driving, and the expected following time distances vary greatly.

[0040] Regarding the problem of modeling the cooperative willingness relationship of human drivers, existing methods mainly focus on trying to characterize the randomness of their behavior by subjectively classifying human drivers. This method ignores the diversity and complexity of driver behavior. The decision-making and behavior patterns of human drivers are affected by many factors, including but not limited to personal driving habits, psychological state, external environment, etc. These factors lead to a high degree of uncertainty and variability in driver behavior. Existing methods are usually unable to accurately capture this complex randomness, which affects the accuracy and reliability of the measurement results.

[0041] In order to calculate the traffic capacity, most studies use the traditional traffic flow calculation formula or make modifications based on it, as shown in the following equation (1):

[0042]

[0043] Where: N max It represents the theoretically achievable traffic capacity of a motor vehicle road section; v represents the uniform speed of motor vehicles (km / h); t0 represents the minimum headway between vehicles (s); l0 represents the minimum headway between vehicles (m).

[0044] The result obtained through the above calculation method is the traffic volume that can pass through a road under the most ideal conditions, which is almost impossible to achieve under actual road conditions. Such calculations cannot reflect the actual traffic capacity of the road and cannot provide information for traffic guidance.

[0045] It is mainly aimed at short-term traffic flow prediction for traffic control. Since short-term traffic flow prediction is greatly affected by random factors, the uncertainty of traffic flow measurement is high and the measurement accuracy is low. In addition, short-term traffic flow prediction requires a large amount of high-quality historical traffic flow data for continuous time periods, which requires a large amount of calculation, and the calculation procedure is complex and time-consuming, so the practicality and universality of the measurement method are low.

[0046] Currently, in calculating the traffic capacity of mixed HDVs and CAVs, there is a lack of objective characterization of human drivers' willingness to cooperate and a traffic capacity measurement method that reflects the actual operation of the road.

[0047] According to an embodiment of the present invention, an embodiment of a method for calculating the capacity of mixed traffic flow is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0048] In this embodiment, a mixed traffic flow capacity calculation method is provided. Figure 1is a flow chart of a mixed traffic flow capacity calculation method according to an embodiment of the present invention. Figure 1 As shown, the process includes the following steps:

[0049] Step S101, obtaining an HDV target traffic flow dataset and a CAV target traffic flow dataset corresponding to the mixed traffic flow to be measured.

[0050] Among them, the HDV target traffic flow dataset can include information such as vehicle type, vehicle speed and vehicle acceleration at each acquisition time step, and position; the CAV target traffic flow dataset can include CAV penetration rate, CAV headway time, etc.

[0051] Specifically, the HDV target traffic flow dataset can be obtained through video data extraction and GPS positioning.

[0052] When using the video acquisition method, it is necessary to select a road section that satisfies the traffic conditions, road conditions, and video shooting height and angle, etc. When using the GPS positioning method, the positioning module needs to be installed at the same position on the vehicle.

[0053] Specifically, for video data extraction, through key steps such as coordinate system establishment and conversion, vehicle detection and positioning, vehicle type classification, target tracking and trajectory information extraction, lane number, horizontal and vertical position, headway, front and rear vehicle number, etc. can be obtained. For GPS positioning method, the vehicle's position information, speed and acceleration information can be obtained through the positioning module and acceleration module built into the module.

[0054] Furthermore, the CAV headway H CAV It can be obtained through the IDM car-following model control, as shown in the following equation (2):

[0055]

[0056] Where: S represents the minimum headway of CAVs at rest; v1 represents the average vehicle speed of the target road section; and T represents the expected safety time interval.

[0057] Step S102, based on the HDV target traffic flow data set, after processing according to the preset vehicle following cooperation principle and prospect theory, a utility value function of the driver cooperation level is determined.

[0058] Among them, the preset vehicle following cooperation principle means that in the following state, the front and rear vehicles will continue to cooperate to complete a series of operations, thereby maintaining a stable following state. The cooperation between following vehicles is reflected in many aspects. When the rear vehicle follows the front vehicle, the movement states of the front and rear vehicles will restrict each other. When the distance between the front of the vehicle increases, the acceleration of the rear vehicle will increase, and when the distance between the front of the vehicle decreases, the acceleration of the rear vehicle will decrease or decelerate. This time lag also reflects the cooperative relationship between the front and rear vehicles during the following process, such as Figure 2 shown.

[0059] Further, prospect theory is also known as "expectation theory" and "prospect theory", and is used to deal with risky or uncertain probabilistic choice events. In prospect theory, decision makers associate their perceived utility with each available choice and choose the choice with the maximum perceived utility value as the final decision.

[0060] For example, when using prospect theory to model the commuter's choice behavior, choosing bus stops A and B represents a prospect respectively. At this time, the utility value function of prospect theory can be constructed using the waiting time and probability of the bus at each bus stop. Ultimately, the commuter will choose the bus stop with the largest utility value to take the bus.

[0061] Specifically, by combining the preset vehicle following cooperation principle and prospect theory, the utility value function of the driver's cooperation level can be determined.

[0062] Step S103 , predicting the congestion situation of the mixed traffic flow to be measured by using a preset Markov chain model to obtain a predicted congestion state of the mixed traffic flow to be measured.

[0063] The Markov chain refers to a stochastic process in probability theory and mathematical statistics that has the Markov property and exists in a discrete index set and state space.

[0064] Specifically, the Markov chain is a set of random variables with Markov properties. n , n=0,1,2,...}, where X1, X2,... represent the past states, and the future state X n+1 Depends only on the current state X n , and is completely independent of the past state, then the random process {X n ,n=0,1,2,...} has no aftereffect and is also called Markov process.

[0065] Specifically, the state transition of the vehicle can be described by presetting the Markov chain model, and then the congestion situation of the mixed traffic flow can be predicted.

[0066] Step S104, based on the HDV target traffic flow data set, the CAV target traffic flow data set and the predicted congestion status, the capacity of the mixed traffic flow to be measured is calculated after being processed by the driver's cooperative level utility value function to obtain the capacity calculation result of the mixed traffic flow to be measured.

[0067] Among them, capacity refers to the maximum hourly flow rate of vehicles that can be reasonably expected to pass through a lane or road at a point or uniform section under a certain period of time and normal road, traffic and control conditions, as well as specified service quality requirements.

[0068] Specifically, by combining the HDV target traffic flow dataset, the CAV target traffic flow dataset and the predicted congestion status and processing them through the driver cooperation level utility value function, the capacity of the mixed traffic flow to be measured can be calculated, and the measured capacity of the mixed traffic flow to be measured can be obtained.

[0069] The mixed traffic flow capacity calculation method provided in this embodiment can characterize the driving cooperation willingness relationship of human drivers in the following process through prospect theory, and at the same time, predict the congestion situation of the mixed traffic flow to be measured through a preset Markov chain model. Furthermore, the capacity of the mixed traffic flow to be measured can be calculated in combination with the predicted congestion state. Therefore, by implementing the present invention, the prospect theory and the Markov chain model are fully combined, not only the following behavior preference of the HDV driver is considered, but also the time distribution characteristics of the traffic congestion state are described, ensuring the credibility and availability of the measurement results.

[0070] In this embodiment, a mixed traffic flow capacity calculation method is provided. Figure 3 is a flow chart of a mixed traffic flow capacity calculation method according to an embodiment of the present invention. Figure 3 As shown, the process includes the following steps:

[0071] Step S301, obtaining an HDV target traffic flow dataset and a CAV target traffic flow dataset corresponding to the mixed traffic flow to be measured.

[0072] Specifically, the above step S301 includes:

[0073] Step S3011, obtaining an HDV initial traffic flow dataset and a CAV initial traffic flow dataset corresponding to the mixed traffic flow to be measured.

[0074] Specifically, the description of the HDV initial traffic flow dataset and the CAV initial traffic flow dataset refers to the description of the HDV target traffic flow dataset and the CAV target traffic flow dataset in step S101, which will not be repeated here.

[0075] Step S3012: Process the HDV initial traffic flow dataset and the CAV initial traffic flow dataset respectively to obtain the HDV target traffic flow dataset and the CAV target traffic flow dataset.

[0076] Specifically, quality problems are inevitable in the data collection process. Therefore, the acquired HDV initial traffic flow dataset and CAV initial traffic flow dataset are processed, such as outlier correction, to obtain the processed HDV target traffic flow dataset and CAV target traffic flow dataset.

[0077] Among them, for the processing of data outliers, the data needs to be reconstructed before application to reduce the impact of errors, and the interpolation method and filtering method are used to process the abnormal data, thereby reducing the noise of the vehicle trajectory data. First, through the physical performance of the vehicle and the limit of human tolerance, combined with the actual speed data of the experimental vehicle recorded in the experiment, the speed extremes, negative speed values ​​and second-class outliers that produce system errors are identified, and the Lagrange interpolation method is used to re-estimate the outliers; secondly, for the random errors in the video trajectory extraction process, that is, the noise data, the Kalman filter technology can be used for noise reduction.

[0078] Step S302: Based on the HDV target traffic flow data set, after processing using the preset vehicle following cooperation principle and prospect theory, determine the driver cooperation level utility value function.

[0079] Specifically, the above step S302 includes:

[0080] Step S3021, based on the HDV target traffic flow data set, after being processed according to the preset vehicle following cooperation principle, a cooperation willingness urgency function is determined.

[0081] Among them, the cooperation willingness urgency function is used to calculate the cooperation willingness of the following vehicle driver when the current vehicle state changes.

[0082] Specifically, according to the description of the preset vehicle following cooperation principle in step S102, for the driver, the urgency value of the cooperation willingness in the following process is inversely proportional to the headway distance in the current state, such as Figure 4 shown.

[0083] Therefore, the smaller the distance between the front and rear vehicles in the following state, the higher the urgency of the cooperation willingness of the rear vehicle, and vice versa. That is, the urgency function of the cooperation willingness V(S) is shown in the following relationship (3):

[0084]

[0085] Where: h represents the observed headway in the current following state, which can be calculated based on the HDV target traffic flow dataset; a and b represent the parameters to be calibrated.

[0086] Further, from Figure 4 It can be seen that when the observed headway is very small or very large, the change in the urgency value of the willingness to cooperate is relatively gentle. This phenomenon is consistent with the curve shape of the median function in prospect theory. When decision makers face too much loss and too much gain, their sensitivity decreases.

[0087] Step S3022: Based on the HDV target traffic flow data set, a weight function is determined after being processed by prospect theory and the cooperation willingness urgency function.

[0088] The weight function is used to calculate the following vehicle driver's intuitive perception of the current level of cooperation.

[0089] In some optional implementations, the above step S3022 includes:

[0090] Step a1, based on the HDV target traffic flow data set, after being processed by the cooperation willingness urgency function, a probability function is determined.

[0091] Step a2, based on the probability function and processed by prospect theory, a weight function is determined.

[0092] Specifically, the probability function is shown in the following equation (4):

[0093]

[0094] Where: h max and h min They represent the headway distances with respect to the driver of the following vehicle when the urgency function of cooperation willingness is close to 0 and 1 respectively;

[0095] Furthermore, the weights are mainly used to capture the driver's subjective attitude towards observing the headway.

[0096] Therefore, the construction of the weight function should also conform to the characteristics of probability weighting in prospect theory, that is, low-probability events are often overestimated, while high-probability events are often underestimated, as shown in the following relationship (5):

[0097]

[0098] Where: W(P) represents the weight function; γ represents the control parameter.

[0099] Furthermore, a, b and γ corresponding to the above equations (4) and (5) can be calibrated and solved based on measured data using a genetic algorithm.

[0100] Specifically, calibration is essentially an optimization problem, which is to find the optimal set of parameter values. In addition, in order to improve the computational efficiency of the algorithm, referring to existing research, the upper and lower limits of each parameter value are first defined, as shown in Table 1 below:

[0101] Table 1. Parameter upper and lower limits

[0102] parameter definition Upper and lower limits a Function parameters of the urgency of the cooperation willingness of the following vehicle [0.1，0.5] b Function parameters of the urgency of the cooperation willingness of the following vehicle [1，10] γ Weight function parameters of the following vehicle cooperation level [0.1，1]

[0103] Furthermore, based on the processed HDV target traffic flow dataset, 20 pairs of trajectory data of following groups were selected. It should be noted that, among every 10 pairs of following groups, the trajectory data of 9 pairs of following groups were used for parameter calibration, and the trajectory data of the remaining 1 pair of following groups were used for parameter verification.

[0104] Furthermore, the error of the parameter calibration results is shown in Table 2 below:

[0105] Table 2. Parameter calibration results (taking one of the following groups as an example)

[0106]

[0107]

[0108] Step S3023: Determine the driver's cooperation level utility value function based on the cooperation willingness urgency function and the weight function.

[0109] Specifically, the utility value function U of the driver's cooperation level is expressed as follows:

[0110] U=V(S)*W(P) (6)

[0111] Step S303: Use the preset Markov chain model to predict the congestion of the mixed traffic flow to be measured, and obtain the predicted congestion state of the mixed traffic flow to be measured. Figure 1 Step S103 of the illustrated embodiment will not be described in detail here.

[0112] Step S304: Based on the HDV target traffic flow data set, the CAV target traffic flow data set and the predicted congestion status, the capacity of the mixed traffic flow to be measured is calculated after being processed by the driver cooperation level utility value function to obtain the capacity calculation result of the mixed traffic flow to be measured. Figure 1 Step S104 of the illustrated embodiment will not be described in detail here.

[0113] The mixed traffic flow capacity calculation method provided in this embodiment uses prospect theory to analyze the urgency of human drivers' willingness to cooperate, and establishes different weight functions to satisfy the probability weighted characteristics in prospect theory to obtain a cooperative level utility value function, objectively describing the human driver's willingness to cooperate and avoiding subjective classification of drivers. At the same time, the congestion situation of the mixed traffic flow to be measured is predicted by a preset Markov chain model. Furthermore, the capacity of the mixed traffic flow to be measured can be calculated in combination with the predicted congestion state. Therefore, by implementing the present invention, the prospect theory and the Markov chain model are fully combined, not only the HDV driver's preference for following behavior is considered, but also the time distribution characteristics of the traffic congestion state are described, ensuring the credibility and availability of the measurement results.

[0114] In this embodiment, a mixed traffic flow capacity calculation method is provided. Figure 5 is a flow chart of a mixed traffic flow capacity calculation method according to an embodiment of the present invention. Figure 5 As shown, the process includes the following steps:

[0115] Step S501, obtain the HDV target traffic flow dataset and CAV target traffic flow dataset corresponding to the mixed traffic flow to be measured. Figure 3 Step S301 of the illustrated embodiment will not be described in detail here.

[0116] Step S502: Based on the HDV target traffic flow data set, the driver cooperation level utility value function is determined after processing by the preset vehicle following cooperation principle and prospect theory. Figure 3 Step S302 of the illustrated embodiment will not be described in detail here.

[0117] Step S503, obtaining the HDV historical traffic flow dataset, the CAV historical traffic flow dataset and the mixed traffic flow historical traffic index.

[0118] Among them, the mixed traffic flow historical traffic index is used to reflect the historical congestion status of the mixed traffic flow.

[0119] Specifically, the traffic index can range from 0 to 10, and is divided into five levels in two units (namely "smooth", "basically smooth", "mild congestion", "moderate congestion", and "severe congestion"). The higher the value, the more serious the traffic congestion.

[0120] Step S504 , using the HDV historical traffic flow dataset and the CAV historical traffic flow dataset as input data and the mixed traffic flow historical traffic index as output data to perform model training, and obtain a preset Markov chain model.

[0121] Specifically, the HDV historical traffic flow dataset and the CAV historical traffic flow dataset are used as the input data of the model, and the mixed traffic flow historical traffic index is used as the output data of the model. The corresponding preset Markov chain model can be obtained through training.

[0122] Step S505: Use the preset Markov chain model to predict the congestion of the mixed traffic flow to be measured, and obtain the predicted congestion state of the mixed traffic flow to be measured. Figure 1 Step S103 of the illustrated embodiment will not be described in detail here.

[0123] Step S506, based on the HDV target traffic flow data set, the CAV target traffic flow data set and the predicted congestion status, the capacity of the mixed traffic flow to be measured is calculated after being processed by the driver's cooperative level utility value function to obtain the capacity calculation result of the mixed traffic flow to be measured.

[0124] Specifically, the above step S506 includes:

[0125] Step S5061, based on the HDV target traffic flow data set and the predicted congestion state, the HDV headway is obtained through processing by the driver cooperation level utility value function.

[0126] Specifically, the obtained HDV target traffic flow data set and the predicted congestion status are combined and processed by the driver cooperation level utility value function to calculate the corresponding HDV headway.

[0127] In some optional implementations, the above step S5061 includes:

[0128] Step b1, based on the HDV target traffic flow data set, the driver cooperation level utility value is obtained by processing the driver cooperation level utility value function.

[0129] Step b2, determining the HDV headway based on the HDV target traffic flow data set, the predicted congestion status and the utility value of the driver's cooperation level.

[0130] First, calculate the time proportion of the corresponding predicted congestion state in the corresponding time period. For example, calculate the time proportion of different traffic congestion states ("smooth", "basically smooth", "mild congestion", "moderate congestion", "severe congestion") in the day (time period), and the calculation result is 6:2:1:1:0.

[0131] Secondly, using the driver cooperation level utility value function shown in the above relationship (6), the driver cooperation level utility value corresponding to the current HDV target traffic flow data set can be calculated, and then the corresponding driver cooperation level utility range can be determined. For example, the driver cooperation level utility range is [0: 0.12].

[0132] Then, the utility value of the driver's cooperation level is divided according to the calculated time proportion, and the utility value interval is divided according to the size of the time occupied. For example, the utility value of the driver's cooperation level is divided into 4 parts according to the ratio of 6:2:1:1:0. Then, the average headway time corresponding to different utility value intervals is taken.

[0133] Finally, the average values ​​of different headway times are multiplied by the corresponding ratios and then summed to obtain the HDV headway time H in that period of time. HDV .

[0134] Step S5062, based on the HDV headway time and the CAV target traffic flow data set, the capacity of the mixed traffic flow to be measured is calculated to obtain the calculation result of the capacity of the mixed traffic flow to be measured.

[0135] Specifically, because CAVs rely on advanced sensors, algorithms, and control systems to precisely control the speed and position of the vehicle, this means they can more accurately maintain the distance to the vehicle ahead, with the headway being consistently maintained at H. CAV .

[0136] Furthermore, in the road scenario with a CAV penetration rate of , the traffic capacity C is expressed as follows:

[0137]

[0138] The mixed traffic flow capacity calculation method provided in this embodiment predicts the traffic congestion state within a certain period of time through the Markov chain model, which can more comprehensively describe the operation state of the mixed traffic flow. Furthermore, the influence of different drivers' following behaviors and traffic flow states on the capacity calculation under different traffic congestion states and CAV penetration scenarios is fully considered, which significantly improves the practicality and universality of the calculation.

[0139] In one example, a mixed traffic capacity estimation method based on Markov chain and prospect theory is provided. Figure 6 shown.

[0140] First, mixed traffic flow data, including vehicle type, speed, location, etc., are collected through facilities such as traffic cameras and on-board sensors. After preprocessing and annotation, these data are used for subsequent analysis. Then, prospect theory is used to analyze the HDV driver's car-following preference. Through experimental data collection and model parameter estimation, a model describing the driver's car-following behavior can be obtained. At the same time, the decision-making algorithm of CAV and its interaction mode with HDV are analyzed to ensure the accuracy of the model. Secondly, the Markov chain model is used to describe the state transition of the vehicle. By defining different states, such as vehicle speed, headway, etc., and calculating the state transition probability, the dynamic behavior of mixed traffic flow can be simulated. Finally, the capacity is calculated by combining CAV penetration, driver preference and state transition. Through model verification and sensitivity analysis, the road capacity under different CAV penetration rates is obtained.

[0141] This example provides a mixed traffic flow capacity estimation method based on Markov chain and prospect theory. By comprehensively using prospect theory and Markov chain, it can not only consider the interaction between HDV and CAV, but also dynamically analyze the change in capacity under different CAV penetration rates. Furthermore, by introducing prospect theory, it is possible to more accurately simulate the decision-making behavior of HDV drivers in mixed traffic flow when facing uncertainty and risk. At the same time, the Markov chain is used to dynamically model the transition of road traffic status, thereby more accurately describing the dynamic changes of mixed traffic flow.

[0142] Therefore, the mixed traffic flow capacity estimation method based on Markov chain and prospect theory provided in this example can provide a more accurate and practical decision support tool for urban traffic planning and management. It is not only applicable to the current traffic environment, but also can effectively cope with the changes in traffic patterns brought about by the development of autonomous driving technology in the future. Through the present invention, traffic engineers and decision makers will be able to better understand and cope with the complexity of mixed traffic flows, and contribute to the realization of a more efficient, safe and sustainable urban transportation system.

[0143] In this embodiment, a mixed traffic flow capacity calculation device is also provided, which is used to implement the above-mentioned embodiments and preferred implementation modes, and the descriptions that have been made will not be repeated. As used below, the term "module" can be a combination of software and / or hardware that implements a predetermined function. Although the device described in the following embodiments is preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceivable.

[0144] This embodiment provides a mixed traffic flow capacity calculation device, such as Figure 7 As shown, including:

[0145] The first acquisition module 701 is used to acquire a HDV target traffic flow data set and a CAV target traffic flow data set corresponding to the mixed traffic flow to be measured.

[0146] The processing and determination module 702 is used to determine the driver cooperation level utility value function based on the HDV target traffic flow data set after processing according to the preset vehicle following cooperation principle and prospect theory.

[0147] The prediction module 703 is used to predict the congestion situation of the mixed traffic flow to be measured by using a preset Markov chain model to obtain the predicted congestion state of the mixed traffic flow to be measured.

[0148] The processing and calculation module 704 is used to calculate the capacity of the mixed traffic flow to be measured based on the HDV target traffic flow data set, the CAV target traffic flow data set and the predicted congestion status, after being processed by the driver's cooperative level utility value function, to obtain the capacity calculation result of the mixed traffic flow to be measured.

[0149] In some optional implementations, the first acquisition module 701 includes:

[0150] The acquisition submodule is used to acquire the HDV initial traffic flow data set and the CAV initial traffic flow data set corresponding to the mixed traffic flow to be measured.

[0151] The first processing submodule is used to process the HDV initial traffic flow dataset and the CAV initial traffic flow dataset respectively to obtain the HDV target traffic flow dataset and the CAV target traffic flow dataset.

[0152] In some optional implementations, the processing and determining module 702 includes:

[0153] The first processing and determination submodule is used to determine the urgency function of cooperation willingness based on the HDV target traffic flow data set and processed by a preset vehicle following cooperation principle.

[0154] The second processing and determination submodule is used to determine the weight function based on the HDV target traffic flow data set after being processed by prospect theory and the urgency function of cooperation willingness.

[0155] The determination submodule is used to determine the utility value function of the driver's cooperation level based on the cooperation willingness urgency function and the weight function.

[0156] In some optional implementations, the second processing and determining submodule includes:

[0157] The first processing and determining unit is used to determine the probability function based on the HDV target traffic flow data set after being processed by the cooperation willingness urgency function.

[0158] The second processing and determining unit is used to determine the weight function based on the probability function after being processed by prospect theory.

[0159] In some optional embodiments, the device further comprises:

[0160] The second acquisition module is used to acquire the HDV historical traffic flow data set, the CAV historical traffic flow data set and the mixed traffic flow historical traffic index, and the mixed traffic flow historical traffic index is used to reflect the historical congestion status of the mixed traffic flow.

[0161] The training module is used to perform model training using the HDV historical traffic flow dataset and the CAV historical traffic flow dataset as input data and the mixed traffic flow historical traffic index as output data to obtain a preset Markov chain model.

[0162] In some optional implementations, the processing and measuring module 704 includes:

[0163] The second processing submodule is used to obtain the HDV headway based on the HDV target traffic flow data set and the predicted congestion state through processing by the driver cooperation level utility value function.

[0164] The calculation submodule is used to calculate the capacity of the mixed traffic flow to be measured based on the HDV headway and the CAV target traffic flow data set, and obtain the calculation result of the capacity of the mixed traffic flow to be measured.

[0165] In some optional implementations, the second processing submodule includes:

[0166] The processing unit is used to obtain the driver cooperation level utility value based on the HDV target traffic flow data set through the driver cooperation level utility value function.

[0167] The determination unit is used to determine the HDV headway based on the HDV target traffic flow data set, the predicted congestion state and the driver cooperation level utility value.

[0168] The further functional description of each of the above modules and units is the same as that of the above corresponding embodiments and will not be repeated here.

[0169] The mixed traffic flow capacity calculation device in this embodiment is presented in the form of a functional unit, where the unit refers to an ASIC (Application Specific Integrated Circuit) circuit, a processor and memory that executes one or more software or fixed programs, and / or other devices that can provide the above functions.

[0170] The embodiment of the present invention also provides a computer device having the above Figure 7The mixed traffic flow capacity calculation device shown.

[0171] See also Figure 8 , Figure 8 is a schematic diagram of the structure of a computer device provided by an optional embodiment of the present invention, such as Figure 8 As shown, the computer device includes: one or more processors 10, a memory 20, and interfaces for connecting various components, including high-speed interfaces and low-speed interfaces. Various components are connected to each other using different buses for communication, and can be installed on a common mainboard or installed in other ways as needed. The processor can process the instructions executed in the computer device, including instructions stored in or on the memory to display the graphical information of the GUI on an external input / output device (such as, a display device coupled to the interface). In some optional embodiments, if necessary, multiple processors and / or multiple buses can be used together with multiple memories and multiple memories. Similarly, multiple computer devices can be connected, and each device provides some necessary operations (for example, as a server array, a group of blade servers, or a multi-processor system). Figure 8 A processor 10 is taken as an example.

[0172] The processor 10 may be a central processing unit, a network processor or a combination thereof. The processor 10 may further include a hardware chip. The hardware chip may be a dedicated integrated circuit, a programmable logic device or a combination thereof. The programmable logic device may be a complex programmable logic device, a field programmable gate array, a general purpose array logic or any combination thereof.

[0173] The memory 20 stores instructions executable by at least one processor 10, so that at least one processor 10 executes the method shown in the above embodiment.

[0174] The memory 20 may include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function; the data storage area may store data created according to the use of the computer device, etc. In addition, the memory 20 may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some optional embodiments, the memory 20 may optionally include a memory remotely arranged relative to the processor 10, and these remote memories may be connected to the computer device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0175] The memory 20 may include a volatile memory, such as a random access memory; the memory may also include a non-volatile memory, such as a flash memory, a hard disk or a solid state drive; the memory 20 may also include a combination of the above types of memory.

[0176] The computer device further comprises a communication interface 30 for the computer device to communicate with other devices or a communication network.

[0177] The embodiment of the present invention also provides a computer-readable storage medium. The method according to the embodiment of the present invention can be implemented in hardware, firmware, or can be implemented as a computer code that can be recorded in a storage medium, or can be implemented as a computer code that is originally stored in a remote storage medium or a non-temporary machine-readable storage medium and will be stored in a local storage medium through a network download, so that the method described herein can be stored in such software processing on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. Among them, the storage medium can be a magnetic disk, an optical disk, a read-only storage memory, a random access memory, a flash memory, a hard disk or a solid-state hard disk, etc.; further, the storage medium can also include a combination of the above types of memories. It can be understood that a computer, a processor, a microprocessor controller, or programmable hardware includes a storage component that can store or receive software or computer code. When the software or computer code is accessed and executed by a computer, a processor, or hardware, the method shown in the above embodiment is implemented.

[0178] Although the embodiments of the present invention have been described in conjunction with the accompanying drawings, those skilled in the art may make various modifications and variations without departing from the spirit and scope of the present invention, and such modifications and variations are all within the scope defined by the appended claims.

Claims

1. A mixed traffic flow capacity calculation method, characterized in that: The method comprises: Obtaining a HDV target traffic flow data set and a CAV target traffic flow data set corresponding to the mixed traffic flow to be measured; Based on the HDV target traffic flow data set, after processing with the preset vehicle following cooperation principle and prospect theory, a utility value function of the driver cooperation level is determined; Predicting the congestion of the mixed traffic flow to be measured by using a preset Markov chain model to obtain a predicted congestion state of the mixed traffic flow to be measured; Based on the HDV target traffic flow data set, the CAV target traffic flow data set and the predicted congestion state, the capacity of the mixed traffic flow to be measured is measured after being processed by the driver cooperation level utility value function to obtain a capacity measurement result of the mixed traffic flow to be measured; Wherein, based on the HDV target traffic flow data set, after processing by the preset vehicle following cooperation principle and prospect theory, the utility value function of the driver cooperation level is determined, including: Based on the HDV target traffic flow data set, after processing according to the preset vehicle following cooperation principle, a cooperation willingness urgency function is determined; based on the HDV target traffic flow data set, after processing according to the prospect theory and the cooperation willingness urgency function, a weight function is determined; based on the cooperation willingness urgency function and the weight function, a driver cooperation level utility value function is determined; Wherein, based on the HDV target traffic flow data set, after being processed by the prospect theory and the collaboration willingness urgency function, a weight function is determined, including: Based on the HDV target traffic flow data set, after being processed by the cooperation willingness urgency function, a probability function is determined; based on the probability function, after being processed by the prospect theory, a weight function is determined; The collaboration willingness urgency function is expressed as the following relational expression: Where: V(S) represents the urgency function of cooperation willingness; h represents the observed headway in the current following state, which is calculated based on the HDV target traffic flow data set; a and b represent the parameters to be calibrated; The probability function is expressed as the following relation: Where: P represents the probability function; h max and h min They represent the headway distances with respect to the driver of the following vehicle when the urgency function of cooperation willingness is close to 0 and 1 respectively; The weight function is expressed as the following relation: Where: W(P) represents the weight function; γ represents the control parameter; The driver cooperation level utility value function is expressed as the following relational expression: U=V(S)*W(P) Where: U represents the utility value function of the driver's cooperation level.

2. The method according to claim 1, characterized in that: Obtain the HDV target traffic flow dataset and CAV target traffic flow dataset corresponding to the mixed traffic flow to be measured, including: Acquire an HDV initial traffic flow data set and a CAV initial traffic flow data set corresponding to the mixed traffic flow to be measured; The HDV initial traffic flow dataset and the CAV initial traffic flow dataset are processed respectively to obtain the HDV target traffic flow dataset and the CAV target traffic flow dataset.

3. The method according to claim 1, characterized in that The method further comprises: Acquire an HDV historical traffic flow dataset, a CAV historical traffic flow dataset, and a mixed traffic flow historical traffic index, wherein the mixed traffic flow historical traffic index is used to reflect the historical congestion state of the mixed traffic flow; The HDV historical traffic flow dataset and the CAV historical traffic flow dataset are used as input data, and the mixed traffic flow historical traffic index is used as output data for model training to obtain the preset Markov chain model.

4. The method according to claim 1, characterized in that Based on the HDV target traffic flow data set, the CAV target traffic flow data set and the predicted congestion state, the capacity of the mixed traffic flow to be measured is measured after being processed by the driver cooperation level utility value function, and the capacity measurement result of the mixed traffic flow to be measured is obtained, including: Based on the HDV target traffic flow data set and the predicted congestion state, the HDV headway is obtained after being processed by the driver cooperation level utility value function; Based on the HDV headway time and the CAV target traffic flow data set, the capacity of the mixed traffic flow to be measured is calculated to obtain the capacity calculation result of the mixed traffic flow to be measured.

5. The method according to claim 4, characterized in that Based on the HDV target traffic flow data set and the predicted congestion state, after being processed by the driver cooperation level utility value function, the HDV headway is obtained, including: Based on the HDV target traffic flow data set, after being processed by the driver cooperation level utility value function, a driver cooperation level utility value is obtained; The HDV headway is determined based on the HDV target traffic flow data set, the predicted congestion state, and the driver cooperation level utility value.

6. A mixed traffic flow capacity calculation device, characterized in that: Used to execute the mixed traffic flow capacity calculation method according to any one of claims 1 to 5; the device comprises: The first acquisition module is used to acquire the HDV target traffic flow data set and the CAV target traffic flow data set corresponding to the mixed traffic flow to be measured; A processing and determination module, configured to determine the utility value function of the driver cooperation level based on the HDV target traffic flow data set after processing according to a preset vehicle following cooperation principle and prospect theory; A prediction module, used for predicting the congestion situation of the mixed traffic flow to be measured by using a preset Markov chain model to obtain a predicted congestion state of the mixed traffic flow to be measured; A processing and calculation module is used to calculate the capacity of the mixed traffic flow to be measured based on the HDV target traffic flow data set, the CAV target traffic flow data set and the predicted congestion status, after being processed by the driver's cooperative level utility value function, to obtain the capacity calculation result of the mixed traffic flow to be measured.

7. A computer device, characterized in that: include: A memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the mixed traffic flow capacity estimation method according to any one of claims 1 to 5 by executing the computer instructions.

8. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a computer to execute the mixed traffic flow capacity estimation method according to any one of claims 1 to 5.

Images