A merging area vehicle cooperative control method

Abstract

The application provides a kind of split-flow area vehicle cooperative control method, by deploying roadside equipment in split-flow key area, installing grating array sensing equipment on trunk line, fusing grating data with vehicle-road cloud data, compared with large-scale deployment equipment, not only cost is lower, deployment point is more flexible, but also can inform vehicle of ramp, split-flow area traffic situation in advance, carries out corresponding acceleration and deceleration operation, achieves the effect of energy saving and emission reduction. By evaluating the influence of lane speed and vehicle density on traffic capacity, based on fusion algorithm and speed limit control mechanism, the vehicle is divided into controllable grouping unit, and the cooperative vehicle formation is constructed, the formation is completed through the deceleration strategy of the front vehicle, and the optimal speed limit speed is broadcasted to the formation vehicle through the roadside unit to guide the lead vehicle to adjust the speed, so that the efficient passing of the formation vehicle is realized.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of intelligent transportation, more particularly, to a vehicle cooperative control method for a diverging or merging area. BACKGROUND

[0002] With the acceleration of urbanization and the continuous growth of population, the transportation industry is facing unprecedented challenges. As an important support for the development of national economy, the demand for transportation is increasing rapidly, especially on the trunk line such as highway, the traffic density is increasing, and the traffic efficiency is decreasing, which has become a prominent problem to be solved.

[0003] In the highway network, the traffic conditions at the continuous diverging or merging bottlenecks such as hub interchanges and ramps are particularly complex. These areas are prone to reduce the efficiency of the trunk line due to frequent interweaving, merging and exiting of vehicles, and further have a chain reaction on the entire road network, increasing the risk of traffic accidents. For example, during the morning and evening peak hours or holiday travel peaks, the diverging or merging areas of the highway often appear vehicle congestion, causing the rear vehicles to queue for several kilometers, seriously affecting the normal traffic of the road.

[0004] In view of the above traffic problems, the existing technology mainly adopts two strategies. One is to deploy a large number of roadside sensors and communication devices, trying to monitor and manage traffic flow comprehensively and in real time. However, this method has many drawbacks. On the one hand, large-scale deployment of devices requires a huge amount of investment, including device purchase costs, device installation and maintenance, and subsequent upgrade costs, which is a heavy economic burden for many transportation management departments. On the other hand, due to the limitations of infrastructure conditions in some areas, such as remote mountainous areas or old roads, it is difficult to meet the requirements of large-scale deployment of devices, which greatly limits the practical application of this method.

[0005] The other strategy is to deploy devices only in key areas such as ramps and diverging or merging areas. Although this way reduces the cost to some extent, it also brings new problems. Since vehicles can only receive traffic information and control information when they approach these key areas, there is a significant "lag" in information transmission. For example, when a vehicle approaches a diverging or merging area, it learns about the congestion ahead, and by then it is often too late to take action, making it difficult to effectively avoid congestion and fundamentally solve the problem of vehicle congestion. In addition, in the continuous ramps and diverging or merging areas, only a single area is controlled, and the traffic efficiency that can be improved is limited. Because the traffic conditions between the areas are interrelated when vehicles travel in continuous diverging or merging areas, the control of a single area cannot optimize the overall traffic flow, making it difficult to meet the growing demand for transportation. SUMMARY

[0006] The present application aims at the technical problems existing in the prior art, and provides a vehicle cooperative control method for a split-flow area, which solves the problems of high cost and control delay of the existing control method.

[0007] The present application provides a vehicle cooperative control method for a split-flow area, comprising:

[0008] obtaining grating array data parameters and car-road cloud data parameters, establishing a vector parameter, wherein the grating array data parameters include a first lane average speed of a specific detection area perceived by a grating array in a current t period and a first vehicle average density , the car-road cloud data parameters include a second lane average speed of the specific detection area perceived by a roadside device in the current t period and a second vehicle average density , the specific detection area refers to a fixed length lane area before the split-flow area, and the vector parameter is expressed as: ;

[0009] inputting the vector parameter into a data cross-domain fusion model to obtain cross-domain fusion data, wherein the cross-domain fusion data includes a fusion lane speed and a fusion vehicle density ;

[0010] when the fusion vehicle density is greater than a bottleneck density, obtaining an optimal speed limit value through a variable speed limit control model according to the fusion lane speed and the fusion vehicle density ;

[0011] establishing a cooperative vehicle formation, and sending the optimal speed limit value to each vehicle in the cooperative vehicle formation, so that each vehicle travels according to the optimal speed limit value.

[0012] The vehicle cooperative control method for a split-flow area provided by the present application realizes that the grating array and the car-road cloud data are used as bottom layer data, and based on a cooperative control algorithm and a variable speed limit control architecture, a mode of cooperative vehicle formation is used to solve the lane level trajectory and speed induction linkage control problem of multiple split-flow bottleneck areas, improve the dynamic equilibrium regulation and control effect and vehicle passing efficiency of trunk traffic in multiple split-flow areas, and reduce the accident rate. BRIEF DESCRIPTION OF DRAWINGS

[0013] Figure 1 A vehicle cooperative control method flowchart for a split-flow area is provided for an embodiment of the present application;

[0014] Figure 2 A schematic diagram for solving the optimal speed limit value of the embodiment of the present application is provided;

[0015] Figure 3 A speed v-time t curve diagram for the "front vehicle deceleration" strategy of the embodiment of the present application. DETAILED DESCRIPTION

[0016] In order to make the objects, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are some but not all of the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by a person of ordinary skill in the art without creative work fall within the protection scope of the present application. In addition, the technical features in each embodiment or in a single embodiment provided by the present application can be combined with each other at will to form a feasible technical solution, and such combination is not restricted by the sequence of steps and / or structure composition mode, but should be based on the fact that a person of ordinary skill in the art can realize it. When the combination of technical solutions appears contradictory or unfeasible, it should be considered that such combination of technical solutions does not exist and is not within the protection scope of the present application.

[0017] The merging and diverging area refers to an area where vehicles perform merging and diverging operations, and the traffic condition thereof is complex and prone to cause congestion.

[0018] In view of the problems of high cost, information lag and limited traffic efficiency improvement in single area control in the prior art, the present application makes a series of innovative improvements, aiming to realize efficient passing of vehicles on the expressway trunk in the continuous merging and diverging area and reduce the accident rate.

[0019] The grating array is composed of a plurality of grating sensors arranged in an array, which can be installed on road sections such as high-speed merging and diverging areas, and is used to accurately monitor various physical characteristic data of vehicles when passing, such as length, speed, etc., to provide basic information for traffic flow analysis.

[0020] The vehicle-road cloud integrates the intelligent traffic system of the vehicle end, the roadside infrastructure and the cloud data processing. The vehicle collects its own state information through the vehicle-mounted equipment, the roadside unit collects surrounding traffic data, and both of them transmit the data to the cloud for integration and analysis through the network, so as to realize comprehensive perception and intelligent decision of traffic information.

[0021] The application adopts a combination of a grating array and vehicle-road cloud data as a bottom layer data source. The grating array sensing device has the characteristics of relatively low cost and flexible deployment, and is suitable for being widely installed on traffic trunks. However, the detection accuracy of the grating array will be affected in bad weather conditions, such as rainy and snowy weather. The vehicle-road cloud system can obtain more comprehensive and accurate traffic information through various sensors, and is less affected by weather. The fusion of the data of the two can not only exert the cost and deployment advantages of the grating array, but also make up for the low detection accuracy of the grating array in special weather, forming a cost-effective and stable and reliable data acquisition method.

[0022] Based on the fusion of the grating array and the vehicle-road cloud data, the application generates a data fusion mechanism and a variable speed limit control model, and constructs a collaborative vehicle platoon. The dynamic balanced regulation and control of the trunk traffic in multiple split and merge areas is realized, the vehicle passing efficiency is effectively improved, and the accident rate is reduced.

[0023] Specifically, in the continuous split and merge area, the traffic conditions of the ramp and the split and merge area are informed to the vehicle in advance by deploying the roadside device in the key area, and the vehicle performs corresponding acceleration and deceleration operation according to the received information. Before the split and merge area, the roadside device generates lane-level trajectory and speed induction linkage control information according to the cooperative control algorithm, and transmits the information to the platoon vehicle. The vehicle adjusts the speed reasonably according to the information, combines the insertable gap, avoids congestion in the split and merge area, realizes the dynamic balanced regulation and control of the trunk traffic in multiple split and merge areas, effectively improves the vehicle passing efficiency, and reduces the accident rate.

[0024] Reference Figure 1 A flow chart of a split and merge area vehicle cooperative control method provided by the application, the method comprising the following steps:

[0025] Step 1, acquiring grating array data parameters and vehicle-road cloud data parameters, establishing a vector parameter, the grating array data parameters comprising a first lane average speed and a first vehicle average density in a specific detection area perceived by the grating array in a current t period, the vehicle-road cloud data parameters comprising a second lane average speed and a second vehicle average density in a specific detection area perceived by the roadside device in a current t period, the specific detection area referring to a fixed length lane area before the split and merge area, and the vector parameter being represented as: .

[0026] It can be understood that in the embodiments of the present application, the grating array is arranged on the trunk of the road due to its low cost, and the roadside equipment is arranged in the split-flow area and a detection area before the split-flow area (hereinafter referred to as a specific detection area) due to its relatively high cost. In the specific detection area, the lane average speed and the vehicle average density of the specific detection area are sensed by the grating array and the roadside equipment at the same time.

[0027] The grating array data acquisition includes:

[0028] The grating array senses the average time difference of multiple vehicles passing through the two ends of the specific detection area in the current t period (second);

[0029] According to the average time difference and the fixed length of the specific detection area (km), the first lane average speed (km / h) is calculated, and the calculation formula is ;

[0030] The number of vehicles passing through the lane range with a fixed length (km) covered by the grating array in the current t period is counted , and the first vehicle average density is calculated, and the calculation formula is .

[0031] The vehicle-road cloud data parameter acquisition includes:

[0032] The second lane average speed of the specific detection area is calculated by the driving speed of multiple vehicles detected by the roadside equipment of the traffic monitoring point in the specific detection area in the current t period ;

[0033] The total number of vehicles in the specific detection area is counted by collecting data uploaded from the roadside equipment of the traffic monitoring point in the specific detection area in the current t period and the total length of the lane of the specific detection area , and the second vehicle average density is calculated, and the calculation formula is .

[0034] Based on the first lane average speed, the first vehicle average density of the specific detection area perceived by the grating array, and the second lane average speed and the second vehicle average density of the specific detection area perceived by the roadside equipment, a vector parameter is formed .

[0035] Step 2, input the vector parameter into the data cross-domain fusion model to obtain cross-domain fusion data, and the cross-domain fusion data includes fusion lane speed and fusion vehicle density .

[0036] The vector parameter input data is input into the cross-domain fusion model to obtain cross-domain fusion data, which mainly includes fusion lane speed and fusion vehicle density.

[0037] Specifically, the working process of the cross-domain fusion model is as follows:

[0038] determining weight coefficients of the first lane average speed and the second lane average speed , and , and determining weight coefficients of the first vehicle average density and the second vehicle average density , and , wherein + =1, + =1.

[0039] According to the first lane average speed and the second lane average speed and the corresponding weight coefficients and , the fusion lane speed is calculated, and the calculation formula is: .

[0040] According to the first vehicle average density and the second vehicle average density and the corresponding weight coefficients and , the fusion vehicle density is calculated, and the calculation formula is: .

[0041] wherein the weight coefficients of the first lane average speed and the second lane average speed are determined as follows: and , including:

[0042] obtaining the first lane average speed of a specific detection area detected by the grating array in a similar scenario (such as the same time period, the same weather condition, and the similar traffic flow pattern) in a historical period, the second lane average speed of the specific detection area detected by the roadside device, and the third lane average speed of the center point of the specific detection area detected by the speed radar.

[0043] calculating a first error sum of squares between the first lane average speed detected by the grating array and the third lane average speed detected by the speed radar in n historical time periods, and a second error sum of squares between the second lane average speed detected by the road side equipment and the third lane average speed detected by the speed radar;

[0044] calculating a weight coefficient according to the first error sum of squares and the second error sum of squares and .

[0045] wherein the calculation formula of the first error sum of squares is:

[0046] ;

[0047] ;

[0048] wherein, denotes the first error sum of squares, is the first lane average speed detected by the grating array in the i-th historical time period, is the third lane average speed detected by the speed radar in the i-th historical time period, denotes the error square of the first lane average speed detected by the grating array and the third lane average speed detected by the speed radar in the i-th historical time period;

[0049] the calculation formula of the second error sum of squares is:

[0050] ;

[0051] ;

[0052] wherein, denotes the second error sum of squares, is the second lane average speed detected by the road side equipment in the i-th historical time period, denotes the error square of the second lane average speed detected by the road side equipment and the third lane average speed detected by the speed radar in the i-th historical time period, and n is the number of historical sample time periods;

[0053] calculating a weight coefficient according to the first error sum of squares and the second error sum of squares and , comprising:

[0054] ;

[0055] .

[0056] Similarly, the first vehicle average density and the second vehicle average density Weighting coefficients and ,include:

[0057] Obtain the first average vehicle density in a specific detection area detected by the grating array under similar scenarios in historical time periods to the current time period t. The second average vehicle density in a specific detection area detected by roadside equipment The average density of third vehicles at the center point of a specific detection area detected by microwave radar;

[0058] Calculate the third sum of squared errors between the first average vehicle density detected by the grating array and the third average vehicle density detected by the microwave radar over m historical time periods, and the fourth sum of squared errors between the second average vehicle density detected by the roadside equipment and the third average vehicle density detected by the microwave radar.

[0059] Calculate the weighting coefficients based on the third and fourth sums of squared errors. and .

[0060] The formula for calculating the third sum of squared errors is as follows:

[0061] ;

[0062] ;

[0063] in, This represents the sum of squares of the third error. The average density of the first vehicle detected by the grating array in the j-th historical time period. The average density of the third vehicle detected by microwave radar in the j-th historical time period. Let m represent the squared error between the average density of the first vehicle detected by the grating array and the average density of the third lane detected by the microwave radar in the j-th historical time period, where m is the number of historical sample time periods.

[0064] The formula for calculating the fourth sum of squared errors is:

[0065] ;

[0066] ;

[0067] in, This represents the fourth sum of squared errors. The second average vehicle density detected by the roadside equipment during the j-th historical time period. This represents the squared error between the average density of the second vehicle detected by the roadside equipment and the average density of the third lane detected by the microwave radar during the j-th historical period.

[0068] According to the third error square sum and the fourth error square sum, a weight coefficient is calculated And , comprising:

[0069] ;

[0070] .

[0071] Step 3, when the fusion vehicle density is greater than the bottleneck density, an optimal speed limit value is obtained through a variable speed limit control model according to the fusion lane speed and the fusion vehicle density .

[0072] It can be understood that after the fusion lane speed and the fusion vehicle density of the fixed length of the specific detection area before the split and merge area are calculated through step 2, the optimal speed limit value of the vehicle on the fixed length of the lane before the split and merge area is obtained based on the variable speed limit control model.

[0073] Specifically, referring to Figure 2 , when the fusion vehicle density is greater than the bottleneck density, the variable speed limit control model is triggered to re-plan the optimal speed limit value of the vehicle.

[0074] Firstly, the constraint range of the vehicle speed is determined, i.e. the safe speed range of the vehicle driving in the specific detection area: the speed limit cannot be lower than the minimum safe speed required by the road. This ensures that the vehicle has enough power and safety distance when driving on the road, avoiding rear-end accidents caused by too low speed. The speed limit cannot be higher than the maximum speed designed by the road. Taking the expressway as an example, the value range is: 60km / h-120km / h.

[0075] The traffic flow is calculated by using the Greenish model , wherein, is the lane fusion speed, is the vehicle fusion density, is the jam density (calculated according to historical data).

[0076] The deviation between the lane fusion speed of the current period t and the average speed of the lane in the past preset period is calculated to represent the speed stability, .

[0077] The accident risk , is calculated by using the historical accident data fitting coefficient.

[0078] The traffic flow , vehicle speed stability and accident risk , traffic flow , vehicle speed stability and accident risk are unified into the same dimension.

[0079] The principle of normalization is to calculate the maximum / minimum of the current traffic flow , vehicle speed stability and accident risk , so that they are within the range of [0, 1].

[0080] Among them, for traffic flow , by collecting historical traffic data, analyzing the traffic flow of the section in different time periods and different conditions, the maximum and minimum values of the traffic flow are found. Then normalize the traffic flow, the normalization formula is:

[0081] , wherein represents the minimum value of the traffic flow of all historical similar time periods, represents the maximum value of the traffic flow of all historical similar time periods.

[0082] For vehicle speed stability S, the normalization formula is:

[0083] , , wherein is the current period lane fusion speed, is the maximum value of the of the historical multiple similar scene time periods.

[0084] For accident risk R, the normalization formula is: , wherein represents the maximum value of the accident risk index under similar conditions. It can be obtained by historical data.

[0085] The objective function is constructed , vehicle speed stability and accident risk as factors, set the weight , , and , then .

[0086] According to the constructed objective function, the optimal speed limit value is solved. Specifically, taking the speed limit of 60km / h to 120km / h with a step of 10km / h as an example, =5km / h.

[0087] In the safety speed range, taking the lane fusion speed as the starting point, each speed limit speed candidate value is obtained in a stepwise decreasing manner;

[0088] Based on each speed limit speed candidate value and the vehicle fusion density , the corresponding , and are calculated, and the objective function is substituted to obtain value, wherein, when solving the optimal speed limit speed value, a plurality of speed limit speed candidate values are obtained in a stepwise decreasing manner, and the vehicle fusion density in the specific area is unchanged, that is, the optimal speed limit speed value is solved under the condition that the vehicle fusion density is the same.

[0089] Compare all values, find the speed limit speed candidate value that makes the maximum as the optimal speed limit value : .

[0090] Step 4, establishing a cooperative vehicle platoon, sending the optimal speed limit value to each vehicle in the cooperative vehicle platoon, so that each vehicle travels according to the optimal speed limit value.

[0091] It can be understood that the cooperative vehicle platoon: vehicles maintain a specific distance and speed through information interaction and cooperative control, and travel in a platoon form. This helps to improve road capacity, reduce energy consumption, and optimize traffic flow in complex road sections such as merging and diverging areas, and reduce traffic congestion.

[0092] When the merging and diverging area is congested, the vehicles on the lane of the specific detection area before the merging and diverging area are platooned to smoothly pass through the merging and diverging area.

[0093] Establishing a cooperative vehicle platoon, specifically, determining a lead vehicle according to the OBU installed on each vehicle on the lane in the specific detection area, and determining the number of vehicles in the vehicle platoon according to the communication distance range of the OBU of the lead vehicle.

[0094] It should be noted that the determination of the lead vehicle according to the OBU installed on each vehicle on the lane in the specific detection area is realized by using an existing relatively mature algorithm, and will not be described in detail here.

[0095] In the process of establishing the vehicle platoon, the front vehicle is decelerated, the speed of the following vehicle is unchanged, and the lead vehicle is appropriately lowered to form a small inter-vehicle distance with the following vehicle ​The vehicle fleet is reduced to reduce the influence of wind resistance, and a certain delay is caused due to the reduction of the speed of the leading vehicle.

[0096] It should be noted that the data of the leading vehicle and the vehicle to be added to the vehicle fleet are determined, and the process of establishing the vehicle fleet is that initially, only the leading vehicle is in the vehicle fleet, then the second vehicle applies to join the vehicle fleet, and then the third vehicle applies to join the vehicle fleet, and so on, and the vehicle to be added to the vehicle fleet is added to the vehicle fleet by one vehicle at a time.

[0097] In the process of adding each vehicle to the vehicle fleet, the speed of the leading vehicle is reduced, and the speed of the following vehicle remains unchanged, Figure 3 A curve of the speed v-time t of the deceleration strategy of the leading vehicle in the process of the vehicle fleet is shown. Specifically, the leading vehicle is initially added to the vehicle fleet, and in the process of adding the vehicle behind the current vehicle fleet to the vehicle fleet, the leading vehicle is free to decelerate at 0- - - The leading vehicle is decelerated to at - The leading vehicle starts to accelerate to the original speed , and the distance between the leading vehicle and the following vehicle is greater than or equal to the safe distance , and the following vehicle is added to the vehicle fleet, wherein the following vehicle maintains the original speed at 0- - After the period of , the leading vehicle and the following vehicle jointly maintain a constant speed.

[0098] The subsequent vehicles are sequentially added to the vehicle fleet by the same method;

[0099] In the process of adding the vehicle to the vehicle fleet, the leading vehicle refers to all the vehicles in the current vehicle fleet, and the following vehicle refers to the vehicle to be added to the vehicle fleet. For example, after the second vehicle is added to the vehicle fleet, the leading vehicle and the second vehicle behind it in the current vehicle fleet are regarded as a whole. When the third vehicle applies to join the vehicle fleet, the leading vehicle and the second vehicle are regarded as a whole as the leading vehicle to perform the same operation, and the third vehicle is the following vehicle.

[0100] After the vehicle fleet is completed, the optimal speed limit value is sent to each vehicle in the vehicle fleet. The calculated optimal speed limit value is first sent to the leading vehicle, and then the leading vehicle broadcasts the optimal speed limit value to other vehicles in the vehicle fleet, so that all vehicles in the vehicle fleet travel according to the optimal speed limit value to the merging and diverging area.

[0101] When the on-board unit (OBU) of the vehicle receives the optimal speed limit value information, on one hand, it is displayed on the on-board display screen to remind the driver to drive according to the new speed limit; on the other hand, for vehicles equipped with an automatic driving system, the automatic driving system automatically adjusts the vehicle speed according to the received speed limit information, so that the vehicle drives according to the optimal speed limit value.

[0102] At the same time, the vehicles in the platoon transmit and share the optimal speed limit value within the platoon through V2V communication, ensuring that all vehicles in the platoon can obtain and comply with the speed limit in a timely manner. The traffic management center can monitor the execution of the optimal speed limit value by the vehicles in real time, and adjust and optimize it according to the actual traffic conditions, further improving traffic efficiency and safety. For example, if it is found that some vehicles do not drive according to the optimal speed limit, the traffic management center can send reminder information to these vehicles through RSU, or re-evaluate and adjust the optimal speed limit value.

[0103] The vehicle cooperative control method provided by the application has the following advantages:

[0104] (1) From the cost point of view, the combination of grating array and CAV cloud data greatly reduces the cost compared with large-scale deployment of roadside sensors and communication equipment. The grating array sensing device has relatively low cost, and the deployment point is flexible, which can be arranged on the trunk line according to the actual demand, reducing unnecessary equipment investment. At the same time, the data collected by the existing sensors of the CAV cloud system are used to realize data complementation, avoiding large-scale repeated construction, so that the whole system can effectively control the cost under the premise of ensuring the data quality, saving a lot of money for the traffic management department and improving the resource utilization efficiency.

[0105] (2) In terms of traffic efficiency improvement, the application realizes speed induction linkage control. Through the data fusion mechanism and cooperative control algorithm, the vehicles are reasonably grouped, and the speed of the vehicles is adjusted according to the cooperative vehicle platoon to make the vehicles pass through the continuous split and merge area in an orderly manner. For example, in the case of heavy traffic, the signal generated by the cooperative control model is accurately transmitted to the leading vehicle through the roadside equipment, and the leading vehicle adjusts the speed according to the signal to guide the entire platoon of vehicles to pass through the split and merge area smoothly, avoiding congestion and disorderly interlacing of vehicles in this area. This effectively improves the dynamic balanced regulation effect of trunk traffic in multiple split and merge areas, greatly improving the vehicle passing efficiency.

[0106] (3) In terms of safety performance, the application effectively reduces the accident rate. On the one hand, by informing the vehicle of the traffic situation of the diverging and merging area in advance, the vehicle can perform acceleration and deceleration operation in advance, avoiding accidents such as rear-end collision and collision caused by sudden braking or acceleration in the diverging and merging area. On the other hand, the cooperative vehicle platoon mode enhances the coordination between vehicles and makes the driving more orderly, reducing the conflict and interference between vehicles. For example, in the continuous diverging and merging area, the vehicles drive in platoon according to the cooperative control algorithm, maintain appropriate distance and speed, and reduce the risk of accidents caused by too small distance or too large speed difference between vehicles.

[0107] It should be noted that in the above embodiments, the description of each embodiment has its own emphasis, and the parts not described in detail in a certain embodiment can be referred to the related description of other embodiments.

[0108] Those skilled in the art should understand that the embodiments of the present application can be provided as a method, a system, or a computer program product. Therefore, the present application can take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can take the form of a computer program product implemented on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0109] The present application is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present application. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, as well as combinations of flows and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded computer, or other programmable data processing devices to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing devices produce a device that implements the flow Figure 1 one or more flows and / or blocks Figure 1 an apparatus that performs the functions specified in one or more blocks or flows.

[0110] These computer program instructions can also be stored in a computer-readable memory that can direct the computer or other programmable data processing devices to work in a specific manner, so that the instructions stored in the computer-readable memory produce a manufactured product including instruction devices that implement the flow Figure 1 one or more flows and / or blocks Figure 1 an apparatus that performs the functions specified in one or more blocks or flows.

[0111] These computer program instructions can also be loaded into a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart block or blocks. Figure 1 one or more flowcharts and / or blocks Figure 1 one or more flowcharts and / or blocks

[0112] Although preferred embodiments of the application have been described herein, substitutions and modifications of these preferred embodiments made by those skilled in the art who are familiar with the state of the art, to which the application pertains, are considered to be within the scope of the application. Accordingly, the attached claims are intended to embrace all such substitutions and modifications.

[0113] Obviously, numerous modifications and variations of the present application are possible in light of the above teachings. It is therefore to be understood that within the scope of the appended claims and their equivalents, the application can be practiced otherwise than as specifically described.

Claims

1. A method for cooperative control of a merging area vehicle, characterized by, Comprise: Obtaining grating array data parameters and car-road cloud data parameters, establishing a vector parameter, the grating array data parameters including a first lane average speed of a specific detection area perceived by a grating array in a current t period and a first vehicle average density , the car-road cloud data parameters including a second lane average speed of a specific detection area perceived by a roadside device in a current t period and a second vehicle average density , the specific detection area refers to a fixed length lane area before a split and merge area, and the vector parameter is expressed as: ; input the vector parameter input data into the cross-domain fusion model to obtain cross-domain fusion data, the cross-domain fusion data including fused lane speed and fused vehicle density ; when the fusion vehicle density is greater than the bottleneck density, through a variable speed limit control model, according to the fusion lane speed and the fusion vehicle density , an optimal speed limit value is obtained; Establish a cooperative vehicle formation, send the optimal speed limit value to each vehicle in the cooperative vehicle formation, so that each vehicle travels according to the optimal speed limit value; According to the fused lane speed and the fused vehicle density , obtaining an optimal speed limit value, comprising: According to the road design standard, determine the safe speed range of the lane; Greenhill model is used to calculate traffic flow wherein, is the fused lane speed, is the fused vehicle density, is the jam density; a deviation measure of the lane fusion speed of the current time period and the lane average speed of the past preset time period to represent the speed stability, ; Computing an accident risk , , coefficient fitted from historical accident data; The traffic flow , the speed stability and the accident risk are normalized respectively; Constructing the objective function , with normalized traffic flow , speed stability , and accident risk as factors, set the weights , , and , then ; In the safe speed range, each speed limit speed candidate value is obtained in a step-down manner from the fusion lane speed as the starting point, with a step size of ​ based on each speed limit speed candidate value and the fusion vehicle density , a corresponding , and is calculated, and the target function is obtained value; Compare all values, find the maximum speed limit candidate value as the optimal speed limit value value .

2. The split stream region vehicle cooperative control method according to claim 1, characterized by, The acquisition of the grating array data parameters and the car-road cloud data parameters comprises: a grating array senses the average time difference between a plurality of vehicles passing through a particular detection zone at a current time period t ; According to the average time difference and the fixed length of the specific detection area , the first lane average speed is calculated, and the calculation formula is ; Counting the number of vehicles in the fixed length of the lane range covered by the grating array at the current time period t , and calculating the first vehicle average density according to the formula ;​ The second lane average speed of the specific detection area is calculated by the multiple vehicle traveling speeds detected by the road side device of the traffic monitoring point in the specific detection area at the current t period ; By collecting the data uploaded by the roadside equipment from the traffic monitoring point in the specific detection area at the current time period t, the total number of vehicles in the specific detection area is counted and the total length of the lanes of the specific detection area , the second vehicle average density is calculated, and the calculation formula is .

3. The split stream region vehicle cooperative control method according to claim 1, characterized by, The vector parameter input data is fused across domains to obtain cross-domain fusion data, and the cross-domain fusion data includes fused lane speed and fused vehicle density , comprising: determining a weight coefficient of the first lane average speed and the second lane average speed and and determining a weight coefficient of the first vehicle average density and the second vehicle average density and wherein, + = 1, + = 1;​​ According to the first lane average speed and the second lane average speed and the corresponding weight coefficient and , the fusion lane speed is calculated, and the calculation formula is: ; According to the first vehicle average density and the second vehicle average density and the corresponding weight coefficient and , the fusion vehicle density is calculated, and the calculation formula is: .

4. The split stream region vehicle cooperative control method according to claim 3, characterized by, determining a weight coefficient of the first lane average speed and the second lane average speed and and comprising: a first lane average speed of a specific detection area detected by the grating array in a similar scenario as the current period t in a historical period a second lane average speed of the specific detection area detected by the roadside device and a third lane average speed of a center point of the specific detection area detected by the speed measurement radar Calculate the first error sum of squares between the first lane average speed detected by the grating array and the third lane average speed detected by the speed measuring radar, and the second error sum of squares between the second lane average speed detected by the roadside equipment and the third lane average speed detected by the speed measuring radar in n historical periods; calculating a weight coefficient based on the first sum of squares of errors and the second sum of squares of errors and .

5. The split stream region vehicle cooperative control method according to claim 4, characterized by, The calculation formula of the first error sum of squares is: ； ； wherein, represents a first error sum of squares, is the first lane average speed detected by the grating array in the i-th historical period, is the third lane average speed detected by the speed radar in the i-th historical period, represents the error square of the first lane average speed detected by the grating array and the third lane average speed detected by the speed radar in the i-th historical period. The calculation formula of the second error sum of squares is: ； ； wherein, represents a second error square sum, is the second lane average speed detected by the roadside device in the i-th historical period, represents the error square of the second lane average speed detected by the roadside device and the third lane average speed detected by the speed radar in the i-th historical period, and n is the number of historical sample time periods. calculating a weight coefficient based on the first error sum of squares and the second error sum of squares and comprising: ； 。 6. The split stream region vehicle cooperative control method according to claim 3, characterized by determining a weight coefficient of the first vehicle average density and the second vehicle average density and comprising:​ a first vehicle average density of a specific detection area detected by the grating array in a similar scenario as the current time period t in a historical time period a second vehicle average density of the specific detection area detected by the roadside device and a third vehicle average density of a center point of the specific detection area detected by the microwave radar Calculate the third error sum of squares between the first vehicle average density detected by the grating array and the third vehicle average density detected by the microwave radar, and the fourth error sum of squares between the second vehicle average density detected by the roadside equipment and the third vehicle average density detected by the microwave radar in m historical periods; calculating a weight coefficient based on the third error sum of squares and the fourth error sum of squares and .

7. The split stream region vehicle cooperative control method according to claim 6, characterized by, The calculation formula of the third error sum of squares is: ； ； wherein, represents a third error sum of squares, is a first vehicle average density detected by the grating array in the jth historical period, is a third vehicle average density detected by the microwave radar in the jth historical period, represents an error square of the first vehicle average density detected by the grating array and the third vehicle average density detected by the microwave radar in the jth historical period, and m is the number of historical sample time periods; The calculation formula of the fourth error sum of squares is: ； ； wherein, represents a fourth error sum of squares, is a second vehicle average density detected by the roadside device for the jth historical period, represents an error square of the second vehicle average density detected by the roadside device and the third lane average detected by the microwave radar for the jth historical period. calculating a weight coefficient based on the third error sum of squares and the fourth error sum of squares and comprising: ； 。 8. The split stream region vehicle cooperative control method according to claim 1, characterized by, The establishment of the cooperative vehicle formation comprises: Determine the lead vehicle according to the OBU installed on each vehicle on the lane in a specific detection area, and determine the number of vehicles in the vehicle formation according to the communication distance range of the OBU of the lead vehicle; The lead vehicle is added to the vehicle platoon initially, and during the process of adding a following vehicle to the current vehicle platoon, at time 0- , the leading vehicle freely decelerates, reducing the following distance from the following vehicle, at time - , the leading vehicle decelerates to , maintains a constant speed, at time - , the leading vehicle starts to accelerate to the original speed , and the distance from the following vehicle is greater than or equal to the safe distance , completing the platoon of the following vehicle, wherein, at time 0- , the following vehicle maintains the original speed , and travels at a constant speed, , after time , the leading vehicle and the following vehicle jointly travel at a constant speed. In turn, the same method is used to add subsequent vehicles to the vehicle formation one by one; Wherein, in the process of adding vehicles to the vehicle formation, the front vehicle refers to all vehicles in the current vehicle formation, and the rear vehicle refers to the vehicle about to join the vehicle formation.

9. The split stream region vehicle cooperative control method according to claim 1, characterized by, Send the optimal speed limit value to the vehicles in the cooperative vehicle formation, so that the vehicles travel according to the optimal speed limit value, comprising: Send the optimal speed limit value to the lead vehicle in the vehicle formation, and the lead vehicle broadcasts the optimal speed limit value to other vehicles in the vehicle formation, so that all vehicles in the vehicle formation travel at a uniform speed according to the optimal speed limit value to the merging and splitting area.

Images