Road driving risk early warning method for dynamic traffic bottlenecks in intelligent connected environment

Abstract

This invention discloses a road driving risk warning method for dynamic traffic bottlenecks in an intelligent connected environment. The steps include: 1. Establishing a road plane rectangular coordinate system; 2. Obtaining current dynamic traffic bottleneck and vehicle-related information; 3. Predicting next-time dynamic traffic bottleneck and target vehicle-related information; 4. Predicting the road boundary risk field value, superimposed dynamic traffic bottleneck risk field value, and superimposed vehicle risk field value of the target vehicle at the next time; 6. Predicting the total risk field value of the target vehicle at the next time; 7. Determining whether to issue a risk warning signal to the target vehicle. This invention can prevent traffic accidents and improve road traffic safety by obtaining current road, dynamic traffic bottleneck, and vehicle-related information in an intelligent connected environment, predicting the dynamic risk value of the target vehicle during its journey at the next time, and determining whether to issue a risk warning signal to the target vehicle.

Description

Technical Field

[0001] This invention relates to the field of road driving risk research in intelligent connected environments, specifically a road driving risk early warning method for dynamic traffic bottlenecks in intelligent connected environments. Background Technology

[0002] As cities expand, traffic conditions become increasingly complex. Traffic bottlenecks often lead to traffic accidents, and dynamic traffic bottlenecks, such as those caused by obstructed vehicles or slow-moving vehicles, frequently occur on roads. These dynamic bottlenecks not only easily induce traffic accidents but also reduce road traffic efficiency. Currently, there is limited theoretical research on the risks associated with dynamic traffic bottlenecks, and research on early warning methods for road driving risks under dynamic traffic bottlenecks is even more lacking.

[0003] Currently, research on driving risks under dynamic traffic bottlenecks is limited, and the quantitative models of various driving influencing factors on driving risks under dynamic traffic bottlenecks are still unclear, making it difficult to predict driving risks on roads under dynamic traffic bottlenecks. With the continuous development of 5G and vehicle-road cooperative technologies, new ideas and methods have been provided for road driving risk early warning methods. The detection accuracy is higher and the information transmission speed is faster in the intelligent connected environment. However, how to use new intelligent connected technologies to propose a method for early warning of road driving risks under dynamic traffic bottlenecks will be a challenge. Summary of the Invention

[0004] To overcome the shortcomings of existing technologies, this invention proposes a road driving risk warning method for dynamic traffic bottlenecks in an intelligent connected environment. The aim is to predict short-term road driving risks based on real-time road and vehicle information when dynamic traffic bottlenecks occur on the road, and determine whether to issue a risk warning signal, thereby improving the level of road traffic safety.

[0005] To achieve the above-mentioned objectives, the present invention adopts the following technical solution:

[0006] The present invention provides a road driving risk warning method for dynamic traffic bottlenecks in an intelligent connected environment, characterized in that the vehicles in the intelligent connected environment are all connected autonomous vehicles traveling on a one-way three-lane road; the dynamic traffic bottleneck in the intelligent connected environment is non-stationary; and the driving risk warning method includes the following steps:

[0007] Step 1: Establish a rectangular coordinate system for the road by taking the starting point of the road boundary line of the innermost lane as the origin, the road boundary line of the innermost lane as the Y-axis, and the perpendicular line between the road boundary lines of the innermost lane and the road boundary lines of the outermost lane as the X-axis. The positive direction of the Y-axis in the rectangular coordinate system is the direction of vehicle travel, and the positive direction of the X-axis is the direction from the innermost lane to the outermost lane.

[0008] Step 2: Obtain relevant information about target vehicle j at time t:

[0009] Obtain the coordinates of the target vehicle j at time t.

[0010] Obtain the speed of target vehicle j in the X-axis direction at time t. acceleration

[0011] Obtain the speed of target vehicle j in the Y-axis direction at time t. acceleration

[0012] Step 3: Let Δt be the time interval, predict the relevant information of the target vehicle j at time t+Δt:

[0013] The coordinates of the target vehicle j at time t+Δt are calculated using equation (1).

[0014]

[0015] The velocity of the target vehicle j in the X-axis direction at time t+Δt is calculated using equation (2). and the speed of movement in the Y-axis direction

[0016]

[0017] The acceleration of the target vehicle j in the X-axis direction at time t+Δt is calculated using equation (3). and acceleration in the Y-axis direction

[0018]

[0019] Step 4: Predict the road boundary risk field value of vehicle j at time t+Δt:

[0020] Using equation (4), calculate the road boundary risk field values ​​of the innermost and outermost lanes at time t+Δt for vehicle j.

[0021]

[0022] In equation (4), α is the coefficient of the road boundary risk field; x s,k Represents the x-coordinate of any point on the k-th boundary; The x-coordinate of vehicle j at time t+Δt is represented.

[0023] Step 5: Determine the dynamic traffic bottlenecks and their total number on the information collection section at time t:

[0024] Step 5.1: The x-axis range is [0, 3w], and the y-axis range is... The road segment is designated as the information collection segment at time t; where w represents the width of a lane on the road and L represents the length of the information collection segment; the vehicles and their total number N on the information collection segment are identified using intelligent roadside detectors, and the vehicles are numbered sequentially, with any one vehicle numbered as h, h = 1, ..., N;

[0025] Step 5.2: Let h = 1;

[0026] Step 5.3: Define o as the number of the dynamic traffic bottleneck on the information collection section, and initialize o = 1;

[0027] Step 5.4: Obtain the speed of the h-th vehicle on the road segment at time t. judge If the condition is met, then the h-th vehicle is designated as the o-th dynamic traffic bottleneck, o+1 is assigned to o, h+1 is assigned to h, and step 5.5 is executed; otherwise, h+1 is assigned to h, and step 5.5 is executed; where v move The speed at which dynamic traffic bottlenecks are defined;

[0028] Step 5.5: Determine if h > N is true. If it is true, it means that the total number of dynamic traffic bottlenecks is O, and proceed to step 6; otherwise, return to step 5.4 and execute sequentially.

[0029] Step 6: Predict the superimposed dynamic traffic bottleneck risk field value of target vehicle j at time t+Δt:

[0030] Step 6.1, Initialize o = 1; Define This represents the superimposed dynamic traffic bottleneck risk field value experienced by target vehicle j at time t+Δt; and initializes...

[0031] Step 6.2: Obtain the information set of the o-th dynamic traffic bottleneck at time t. in, Represents the coordinates of the 0th dynamic traffic bottleneck at time t; These represent the moving speeds of the o-th dynamic traffic bottleneck at time t along the X and Y axes, respectively. Let X and Y represent the accelerations of the o-th dynamic traffic bottleneck at time t in the X and Y directions, respectively.

[0032] Step 6.3: Predict the information set of the o-th dynamic traffic bottleneck at time t+Δt.

[0033]

[0034] The coordinates of the o-th dynamic traffic bottleneck at time t+Δt are calculated using equation (5).

[0035]

[0036] The moving speed of the o-th dynamic traffic bottleneck in the X and Y axes at time t+Δt is calculated using equation (6).

[0037]

[0038] The speed of the o-th dynamic traffic bottleneck at time t+Δt is calculated using equation (7).

[0039]

[0040] Using equation (8), calculate the clockwise angle formed by the line connecting the centroid of the target vehicle j at time t+Δt and the centroid of the o-th dynamic traffic bottleneck, and the direction of motion of the o-th dynamic traffic bottleneck.

[0041]

[0042] The acceleration of the o-th dynamic traffic bottleneck at time t+Δt is calculated using equation (9).

[0043]

[0044] Step 6.4, if judge If the condition is met, then the risk field value of the target vehicle j at time t+Δt due to the o-th dynamic traffic bottleneck is determined. Otherwise, use equation (10) to calculate the risk field value of the target vehicle j at time t+Δt due to the o-th dynamic traffic bottleneck.

[0045]

[0046] In Equation (10), λ1 represents the coefficient of the dynamic traffic bottleneck risk field; β2 represents the undetermined coefficient value related to acceleration; τ represents the critical threshold of the safety distance; μ represents the undetermined coefficient related to speed; m o represents the mass of the o-th dynamic traffic bottleneck;

[0047] If judge is established, if so, the risk field value of the target vehicle j at time t + Δt affected by the o-th dynamic traffic bottleneck Otherwise, use Equation (10) to calculate the risk field value of the target vehicle j at time t + Δt affected by the o-th dynamic traffic bottleneck

[0048] Step 6.5, judge is established, if so, then assign to and execute Step 6.6; otherwise, directly execute Step 6.6; where, E od represents the dynamic traffic bottleneck risk threshold that can cause driving impact;

[0049] Step 6.6, judge whether o < O is established, if so, assign o + 1 to o, and return to Step 6.2 to execute sequentially; otherwise, execute Step 7;

[0050] Step 7, predict the superimposed vehicle risk field value of the target vehicle j at time t + Δt:

[0051] Step 7.1, define i to represent the number of the surrounding vehicles of the target vehicle j, and initialize i = 1;

[0052] Define to represent the superimposed vehicle risk field value of the target vehicle j at time t + Δt; and initialize

[0053] Step 7.2, obtain the information set of the i-th surrounding vehicle of the target vehicle j at time t where represents the coordinates of the i-th surrounding vehicle at time t; respectively represent the moving speeds of the i-th surrounding vehicle in the X-axis and Y-axis directions at time t; respectively represent the accelerations of the i-th surrounding vehicle in the X-axis and Y-axis directions at time t;

[0054] Step 7.3, predict the information set of the i-th surrounding vehicle at time t + Δt

[0055] Use Equation (11) to calculate the coordinates of the i-th surrounding vehicle at time t + Δt

[0056]

[0057] Calculate the moving speeds of the $i$-th surrounding vehicle in the $X$-axis and $Y$-axis directions at time $t + \Delta t$ using Equation (12).

[0058]

[0059] Calculate the speed of the $i$-th surrounding vehicle at time $t + \Delta t$ using Equation (13).

[0060]

[0061] Calculate the clockwise included angle formed by the line connecting the centroid of the target vehicle $j$ and the centroid of the $i$-th surrounding vehicle at time $t + \Delta t$ and the moving direction of the $i$-th surrounding vehicle using Equation (14).

[0062]

[0063] The acceleration of the $i$-th surrounding vehicle at time $t + \Delta t$ is calculated using Equation (15).

[0064]

[0065]

[0066]

[0067]

[0068] In Equation (16), $\lambda_2$ represents the coefficient of the vehicle risk field; $\beta_2$ represents the undetermined coefficient value related to the acceleration; $\tau$ represents the critical threshold of the safe distance; $\mu$ represents the undetermined coefficient related to the speed; $m$ i represents the mass of the $i$-th surrounding vehicle;

[0068] Step 7.4. Calculate the vehicle risk field value generated by the $i$-th surrounding vehicle on the target vehicle $j$ at time $t + \Delta t$ using Equation (16). Judge whether is established. If it is established, assign to vd and execute Step 7.6; otherwise, directly execute Step 7.6; where $E$

[0069] Step 7.6. Judge whether $i < n$ is established. If it is established, assign $i + 1$ to $i$ and return to Step 7.2 to execute sequentially; otherwise, execute Step 8; where $n$ represents the total number of surrounding vehicles of the target vehicle $j$.

[0070] Step 8: Calculate the total risk field value of target vehicle j at time t+Δt using equation (17).

[0071]

[0072] In equation (17), γ s This indicates the proportion of the risk field strength at the road boundary; γ o This indicates the proportion of the field strength in the dynamic traffic bottleneck risk field; γ v This indicates the proportion of the risk field strength of the vehicle.

[0073] Step 9, if Then, at time t, a risk warning signal is issued to the target vehicle j, and step 10 is executed;

[0074] like Then proceed directly to step 10; where E safe This indicates the risk threshold for ensuring safe vehicle operation;

[0075] Step 10: Assign t+Δt to t, then return to step 2 and execute sequentially.

[0076] The present invention provides an electronic device, including a memory and a processor, wherein the memory is used to store a program that supports the processor in executing the road driving risk warning method, and the processor is configured to execute the program stored in the memory.

[0077] The present invention discloses a computer-readable storage medium on which a computer program is stored, wherein the computer program, when executed by a processor, performs the steps of the road driving risk warning method.

[0078] Compared with existing technologies, the beneficial technical effects of this invention are reflected in:

[0079] 1. In a fully connected environment where all vehicles on the road are connected and autonomous, this invention provides a road driving risk warning method for dynamic traffic bottlenecks in an intelligent environment by utilizing new intelligent connected and vehicle-road cooperative technologies. It can predict the road driving risk of a target vehicle under dynamic traffic bottlenecks in the next short time based on the current road and vehicle information, and determine whether to issue a risk warning signal to the target vehicle to reduce the occurrence of traffic accidents and thus improve the level of road traffic safety.

[0080] 2. Compared with the prior art, the present invention proposes a method for collecting road and vehicle information using a sliding spatiotemporal window. The information collection window is updated in real time as the target vehicle moves, dynamically updating the road and vehicle information, thereby avoiding risk prediction errors caused by inaccurate dynamic information collection.

[0081] 3. Compared with existing technologies, this invention utilizes the advantage of real-time sharing of road information and connected autonomous vehicle information in an intelligent connected environment. Based on the acquired real-time road and vehicle-related information, the risk field value of the target vehicle is calculated, and the risk level of the target vehicle is determined based on the risk field value, thereby improving the calculation efficiency and accuracy of the driving risk prediction model.

[0082] 4. Compared with the prior art, the present invention takes into account the real-time movement of dynamic traffic bottlenecks on the road. When constructing the dynamic traffic bottleneck risk field, different models are used according to the moving speed of the target vehicle and the dynamic traffic bottleneck. This model is more in line with the actual situation, thereby improving the accuracy of risk prediction and improving the safety of road driving. Attached Figure Description

[0083] Figure 1 This is the overall flowchart of the present invention;

[0084] Figure 2 This is a flowchart of the superimposed dynamic traffic bottleneck risk field decision-making method of the present invention;

[0085] Figure 3 This is a flowchart of the superimposed vehicle risk field decision-making method of the present invention;

[0086] Figure 4 This is a schematic diagram of a scenario for the present invention;

[0087] Figure 5 This is a schematic diagram of the sliding time window information collection road segment update according to the present invention. Detailed Implementation

[0088] In this embodiment, as Figure 4 As shown, in a road driving risk warning method for dynamic traffic bottlenecks in an intelligent connected environment, all vehicles in the intelligent connected environment are connected autonomous vehicles traveling on a one-way three-lane road; the dynamic traffic bottleneck in this intelligent connected environment is non-stationary, such as... Figure 1 The following steps are shown for issuing a road driving risk warning:

[0089] Step 1: Establish a rectangular coordinate system by taking the starting point of the road boundary line of the innermost lane as the origin, the road boundary line of the innermost lane as the Y-axis, and the perpendicular line between the road boundary lines of the innermost and outermost lanes as the X-axis. In this rectangular coordinate system, the positive direction of the Y-axis represents the vehicle's travel direction, and the positive direction of the X-axis represents the direction from the innermost lane to the outermost lane. Figure 4 As shown;

[0090] Step 2: In the specific embodiments, the vehicles are all connected autonomous vehicles, capable of information interaction between the vehicles and intelligent roadside detectors, thereby also obtaining relevant information about the target vehicle j at time t.

[0091] Obtain the coordinates of the target vehicle j at time t.

[0092] Obtain the speed of target vehicle j in the X-axis direction at time t. acceleration

[0093] Obtain the speed of target vehicle j in the Y-axis direction at time t. acceleration

[0094] Step 3: Let Δt be the time interval, generally within 1 second, and predict the relevant information of the target vehicle j at time t+Δt:

[0095] Within a short time interval, the vehicle's motion is either uniformly accelerated or uniformly decelerated. Therefore, the coordinates of the target vehicle j at time t+Δt can be calculated using equation (1).

[0096]

[0097] The velocity of the target vehicle j in the X-axis direction at time t+Δt is calculated using equation (2). and the speed of movement in the Y-axis direction

[0098]

[0099] The acceleration of the target vehicle j in the X-axis direction at time t+Δt is calculated using equation (3). and acceleration in the Y-axis direction

[0100]

[0101] Step 4, as follows Figure 2 As shown, the decision-making method for predicting the road boundary risk field value of vehicle j at time t+Δt is as follows:

[0102] Using equation (4), calculate the road boundary risk field values ​​of the innermost and outermost lanes at time t+Δt for vehicle j.

[0103]

[0104] In equation (4), α is the coefficient of the road boundary risk field; x s,kRepresents the x-coordinate of any point on the k-th boundary; The x-coordinate of vehicle j at time t+Δt is represented.

[0105] Step 5: Determine the dynamic traffic bottlenecks and their total number on the information collection section at time t:

[0106] Step 5.1: The x-axis range is [0, 3w], and the y-axis range is... The road segment is designated as the information collection segment at time t; where w represents the width of a lane on the road and L represents the length of the information collection segment; the vehicles and their total number N on the information collection segment are identified using intelligent roadside detectors, and the vehicles are numbered sequentially, with any one vehicle numbered as h, h = 1, ..., N;

[0107] Step 5.2: Let h = 1;

[0108] Step 5.3: Define o as the number of the dynamic traffic bottleneck on the information collection section, and initialize o = 1;

[0109] Define O as the total number of dynamic traffic bottlenecks on the information collection section, and initialize O = 0;

[0110] Step 5.4: Obtain the speed h of vehicles on the road segment at time t. judge If the condition is met, define vehicle h as a dynamic traffic bottleneck and assign it the number o. Assign o+1 to o, o+1 to o, and h+1 to h, and proceed to step 5.5. Otherwise, assign h+1 to h and proceed to step 5.5. move This indicates the defining speed at which a vehicle is defined as a dynamic traffic bottleneck;

[0111] Step 5.5: Determine if h > N is true. If true, proceed to step 6; otherwise, return to step 5.4 and execute sequentially.

[0112] Step 6: Predict the superimposed dynamic traffic bottleneck risk field value of target vehicle j at time t+Δt:

[0113] Step 6.1, Initialize o = 1; Define This represents the superimposed dynamic traffic bottleneck risk field value experienced by target vehicle j at time t+Δt; and initializes...

[0114] Step 6.2: Obtain the information set of the dynamic traffic bottleneck o at time t. in, The coordinates of the dynamic traffic bottleneck o at time t; Let X and Y represent the moving speeds of the dynamic traffic bottleneck o at time t in the X and Y directions, respectively. Let X and Y represent the accelerations of the dynamic traffic bottleneck o at time t in the X and Y directions, respectively.

[0115] Step 6.3: Predict the information set of the dynamic traffic bottleneck o at time t+Δt.

[0116] The coordinates of the dynamic traffic bottleneck o at time t+Δt are calculated using equation (5).

[0117]

[0118] The moving speed of the dynamic traffic bottleneck o in the X and Y axes at time t+Δt is calculated using equation (6).

[0119]

[0120] The speed of the dynamic traffic bottleneck o at time t+Δt is calculated using equation (7).

[0121]

[0122] Using equation (8), calculate the clockwise angle formed by the line connecting the centroid of the target vehicle j and the centroid of the dynamic traffic bottleneck o at time t+Δt and the direction of motion of the dynamic traffic bottleneck o.

[0123]

[0124] The acceleration of the dynamic traffic bottleneck o at time t+Δt is calculated using equation (9).

[0125]

[0126] Step 6.4: When the target vehicle is behind the dynamic traffic bottleneck, if the target vehicle's speed in the Y-axis direction is lower than the dynamic traffic bottleneck's speed in the Y-axis direction, the dynamic traffic bottleneck cannot affect the target vehicle's movement. judge If true, then the risk field value of the target vehicle j to the dynamic traffic bottleneck o at time t+Δt. Otherwise, use equation (10) to calculate the risk field value of the target vehicle j under the dynamic traffic bottleneck o at time t+Δt.

[0127]

[0128] In Equation (10), λ1 represents the coefficient of the dynamic traffic bottleneck risk field; β2 represents the undetermined coefficient value related to acceleration; τ represents the critical threshold of the safety distance; μ represents the undetermined coefficient related to speed; m o represents the mass of the dynamic traffic bottleneck;

[0129] When the target vehicle is in front of the dynamic traffic bottleneck, if the moving speed of the target vehicle in the Y-axis direction is higher than the moving speed of the dynamic traffic bottleneck in the Y-axis direction, the boundary line of the dynamic traffic bottleneck cannot have an impact on the driving of the target vehicle, that is, if Judge holds. If it holds, then the risk field value of the target vehicle j affected by the dynamic traffic bottleneck o at time t + Δt Otherwise, use Equation (10) to calculate the risk field value of the target vehicle j affected by the dynamic traffic bottleneck o at time t + Δt

[0130] Step 6.5. Judge holds. If it holds, then assign to and execute Step 6.6; otherwise, directly execute Step 6.6; where E od represents the dynamic traffic bottleneck risk threshold that can cause driving impact; the impact of the dynamic traffic bottleneck on the target vehicle changes with the change of the position of the dynamic traffic bottleneck. However, when the target vehicle is far from the dynamic traffic bottleneck, the dynamic traffic bottleneck cannot have an impact on the driving of the target vehicle, and at this time, the risk field value of the dynamic traffic bottleneck on the target vehicle is ignored;

[0131] Step 6.6. Judge whether o < O holds. If it holds, then assign o + 1 to o and return to Step 6.2 to execute sequentially; otherwise, execute Step 7;

[0132] Step 7. As Figure 3 shown, the decision method for predicting the superimposed vehicle risk field value of the target vehicle j at time t + Δt in the present invention is as follows:

[0133] Step 7.1. Define i to represent the surrounding vehicle of the target vehicle j and initialize i = 1;

[0134] Define to represent the superimposed vehicle risk field value of the target vehicle j at time t + Δt; and initialize

[0135] Step 7.2. Obtain the information set of the surrounding vehicle i of the target vehicle j at time t Among them, represents the coordinate of the surrounding vehicle i at time t; Let X and Y represent the speeds of the surrounding vehicle i in the X and Y axes at time t, respectively. Let X and Y represent the accelerations of the surrounding vehicle i in the X and Y directions at time t, respectively.

[0136] Step 7.3: Predict the information set of surrounding vehicle i at time t+Δt.

[0137] The coordinates of the surrounding vehicle i at time t+Δt are calculated using equation (11).

[0138]

[0139] The speeds of the surrounding vehicle i in the X and Y axes at time t+Δt are calculated using equation (12).

[0140]

[0141] The velocity v of the surrounding vehicle i at time t+Δt is calculated using equation (13). i t+Δt ;

[0142]

[0143] Using equation (14), calculate the clockwise angle formed by the line connecting the centroid of the target vehicle j and the centroid of the surrounding vehicle i at time t+Δt with the direction of motion of the surrounding vehicle i.

[0144]

[0145] The acceleration of the surrounding vehicle i at time t+Δt is calculated using equation (15).

[0146]

[0147] Step 7.4: Calculate the vehicle risk field value generated by surrounding vehicles i on target vehicle j at time t+Δt using equation (16).

[0148] In equation (16), λ² represents the coefficient of the vehicle risk field; β² represents the undetermined coefficient value related to acceleration; τ represents the critical threshold of the safe distance; μ represents the undetermined coefficient related to speed; m i Indicates the mass of the surrounding vehicle i;

[0149] Step 7.5, Judgment Whether it is true or not, if true, then... Assign to and execute step 7.6; otherwise, directly execute step 7.6; where E vd represents the vehicle risk threshold that can cause traffic impact;

[0150] Step 7.6, determine whether i < n holds. If it holds, assign i + 1 to i and return to step 7.2 to execute sequentially; otherwise, execute step 8; where n represents the total number of surrounding vehicles of the target vehicle j;

[0151] Step 8, calculate the total risk field value of the target vehicle j at time t + Δt using Equation (17)

[0152]

[0153] In Equation (17), γ s represents the proportion of the field strength of the road boundary risk field; γ o represents the proportion of the field strength of the dynamic traffic bottleneck risk field; γ v represents the proportion of the field strength of the vehicle risk field;

[0154] Step 9, if then it means that the road traffic risk of the target vehicle j at time t + Δt will be higher than the safety risk threshold, and a risk warning signal will be sent to the target vehicle j at time t, and step 10 will be executed;

[0155] If then it means that the road traffic risk of the target vehicle j at time t + Δt will not be higher than the safety risk threshold, and directly execute step 10; where E safe represents the risk threshold to ensure the safe driving of the vehicle;

[0156] Step 10, as Figure 5 shown, the length of the information collection section is L. The information collection section is updated by using the method of a sliding space-time window. The sliding time step is Δt, and the sliding section length is v j,y Δt. The intelligent roadside detector re-obtains the relevant information of the dynamic traffic bottleneck and the target vehicle, and at the same time assigns t + Δt to t, and returns to step 2 to execute sequentially.

[0157] In this embodiment, an electronic device includes a memory and a processor. The memory is used to store a program that supports the processor to execute the above method, and the processor is configured to execute the program stored in the memory.

[0158] In this embodiment, a computer-readable storage medium stores a computer program on the computer-readable storage medium. When the computer program is run by a processor, it executes the steps of the above method.

Claims

1. A method for early warning of road driving risks in a smart connected environment facing dynamic traffic bottlenecks, characterized in that, The vehicles in the intelligent connected environment are all connected autonomous vehicles and are driving on a one-way three-lane road; the dynamic traffic bottleneck in the intelligent connected environment is in a non-static state; the driving risk warning method includes the following steps: Step 1: Take the starting point of the road boundary line of the innermost lane of the road as the origin, take the road boundary line of the innermost lane as the Y-axis, and take the perpendicular line between the road boundary line of the innermost lane and the road boundary line of the outermost lane as the X-axis, so as to establish a road rectangular coordinate system; the positive direction of the Y-axis in the rectangular coordinate system is the driving direction of the vehicle, and the positive direction of the X-axis is the direction from the innermost lane to the outermost lane; Step 2: Obtain the relevant information of the target vehicle j at time t: Obtain the coordinates of the target vehicle j at time t. Obtain the speed of target vehicle j in the X-axis direction at time t. acceleration Obtain the speed of target vehicle j in the Y-axis direction at time t. acceleration Step 3: Let Δt be the time interval, and predict the relevant information of the target vehicle j at time t+Δt: The coordinates of the target vehicle j at time t+Δt are calculated using equation (1). The velocity of the target vehicle j in the X-axis direction at time t+Δt is calculated using equation (2). and the speed of movement in the Y-axis direction The acceleration of the target vehicle j in the X-axis direction at time t+Δt is calculated using equation (3). and acceleration in the Y-axis direction Step 4: Predict the road boundary risk field value received by the vehicle j at time t+Δt: Using equation (4), calculate the road boundary risk field values ​​of the innermost and outermost lanes at time t+Δt for vehicle j. In equation (4), α is the coefficient of the road boundary risk field; x s,k Represents the x-coordinate of any point on the k-th boundary; The x-coordinate of vehicle j at time t+Δt is represented. Step 5: Determine the dynamic traffic bottleneck and the total number on the information collection section at time t: Step 5.1: The x-axis range is [0, 3w], and the y-axis range is... The road segment is designated as the information collection segment at time t; where w represents the width of a lane on the road and L represents the length of the information collection segment; the vehicles and their total number N on the information collection segment are identified using intelligent roadside detectors, and the vehicles are numbered sequentially, with any one vehicle numbered as h, h = 1, ..., N; Step 5.2: Let h = 1; Step 5.3: Define o to represent the number of the dynamic traffic bottleneck on the information collection section, and initialize o = 1; Step 5.4: Obtain the speed of the h-th vehicle on the road segment at time t. judge If the condition is met, then the h-th vehicle is designated as the o-th dynamic traffic bottleneck, o+1 is assigned to o, h+1 is assigned to h, and step 5.5 is executed; otherwise, h+1 is assigned to h, and step 5.5 is executed; where v move The speed at which dynamic traffic bottlenecks are defined; Step 5.5: Judge whether h > N holds. If it holds, it means that the total number O of the dynamic traffic bottleneck is obtained, and execute Step 6; otherwise, return to Step 5.4 and execute sequentially; Step 6: Predict the superimposed dynamic traffic bottleneck risk field value received by the target vehicle j at time t+Δt: Step 6.1, Initialize o = 1; Define This represents the superimposed dynamic traffic bottleneck risk field value experienced by target vehicle j at time t+Δt; and initializes... Step 6.2: Obtain the information set of the o-th dynamic traffic bottleneck at time t. in, Represents the coordinates of the 0th dynamic traffic bottleneck at time t; These represent the moving speeds of the o-th dynamic traffic bottleneck at time t along the X and Y axes, respectively. Let X and Y represent the accelerations of the o-th dynamic traffic bottleneck at time t in the X and Y directions, respectively. Step 6.3: Predict the information set of the o-th dynamic traffic bottleneck at time t+Δt. The coordinates of the o-th dynamic traffic bottleneck at time t+Δt are calculated using equation (5). The moving speed of the o-th dynamic traffic bottleneck in the X and Y axes at time t+Δt is calculated using equation (6). The speed of the o-th dynamic traffic bottleneck at time t+Δt is calculated using equation (7). Using equation (8), calculate the clockwise angle formed by the line connecting the centroid of the target vehicle j at time t+Δt and the centroid of the o-th dynamic traffic bottleneck, and the direction of motion of the o-th dynamic traffic bottleneck. The acceleration of the o-th dynamic traffic bottleneck at time t+Δt is calculated using equation (9). Step 6.4, if judge If the condition is met, then the risk field value of the target vehicle j at time t+Δt due to the o-th dynamic traffic bottleneck is determined. Otherwise, use equation (10) to calculate the risk field value of the target vehicle j at time t+Δt due to the o-th dynamic traffic bottleneck. In equation (10), λ1 represents the coefficient of the dynamic traffic bottleneck risk field; β2 represents the undetermined coefficient value related to acceleration; τ represents the critical threshold of the safe distance; μ represents the undetermined coefficient related to speed; m o This represents the quality of the o-th dynamic traffic bottleneck; like judge If the condition is met, then the risk field value of the target vehicle j at time t+Δt due to the o-th dynamic traffic bottleneck is determined. Otherwise, use equation (10) to calculate the risk field value of the target vehicle j at time t+Δt due to the o-th dynamic traffic bottleneck. Step 6.5, Judgment Whether it is true or not, if true, then... Assign to And proceed to step 6.6; otherwise, proceed directly to step 6.6; where E od This represents the dynamic traffic bottleneck risk threshold that can cause traffic disruptions. Step 6.6: Judge whether o < O holds. If it holds, assign o + 1 to o, and return to Step 6.2 and execute sequentially; otherwise, execute Step 7; Step 7: Predict the superimposed vehicle risk field value received by the target vehicle j at time t+Δt: definition This represents the superimposed vehicle risk field value experienced by target vehicle j at time t+Δt; and initializes... Step 7.2: Obtain the information set of the i-th surrounding vehicles of target vehicle j at time t. in, Let represent the coordinates of the i-th surrounding vehicle at time t; Let X and Y represent the speeds of the i-th surrounding vehicle at time t in the X and Y directions, respectively. Let X and Y represent the accelerations of the i-th surrounding vehicle at time t in the X and Y directions, respectively. Step 7.3: Predict the information set of the i-th surrounding vehicle at time t+Δt. The coordinates of the i-th surrounding vehicle at time t+Δt are calculated using equation (11). The speeds of the i-th surrounding vehicle in the X and Y axes at time t+Δt are calculated using equation (12). The velocity of the i-th surrounding vehicle at time t+Δt is calculated using equation (13). Using equation (14), calculate the clockwise angle formed by the line connecting the centroid of the target vehicle j at time t+Δt and the centroid of the i-th surrounding vehicle, and the direction of motion of the i-th surrounding vehicle. The acceleration of the i-th surrounding vehicle at time t+Δt is calculated using equation (15). Step 7.4: Calculate the vehicle risk field value generated by the i-th surrounding vehicle on the target vehicle j at time t+Δt using equation (16). In equation (16), λ² represents the coefficient of the vehicle risk field; β² represents the undetermined coefficient value related to acceleration; τ represents the critical threshold of the safe distance; μ represents the undetermined coefficient related to speed; m i Indicates the mass of the i-th surrounding vehicle; Step 7.5, Judgment Whether it is true or not, if true, then... Assign to And proceed to step 7.6; otherwise, proceed directly to step 7.6; where E vd This indicates the vehicle risk threshold that can cause driving disruptions; Step 7.1: Define i to represent the number of the surrounding vehicles of the target vehicle j, and initialize i = 1; Step 8: Calculate the total risk field value of target vehicle j at time t+Δt using equation (17). In equation (17), γ s This indicates the proportion of the risk field strength at the road boundary; γ o This indicates the proportion of the field strength in the dynamic traffic bottleneck risk field; γ v This indicates the proportion of the risk field strength of the vehicle. Step 9, if Then, at time t, a risk warning signal is issued to the target vehicle j, and step 10 is executed; like Then proceed directly to step 10; where E safe This indicates the risk threshold for ensuring safe vehicle operation; Step 7.6: Judge whether i < n holds. If it holds, assign i + 1 to i, and return to Step 7.2 and execute sequentially; otherwise, execute Step 8; where n represents the total number of the surrounding vehicles of the target vehicle j; 2. An electronic device, comprising a memory and a processor, characterized in that, Step 10: Assign t+Δt to t, and return to Step 2 and execute sequentially.

3. A computer-readable storage medium storing a computer program, characterized in that, The memory is used to store a program for supporting the processor to execute the road driving risk warning method described in claim 1, and the processor is configured to execute the program stored in the memory. When the computer program is run by the processor, it executes the steps of the road driving risk warning method described in claim 1.

Images