Intersection pedestrian-left turning vehicle conflict risk factor quantification method based on causal machine learning

Abstract

The invention discloses an intersection pedestrian-left-turn vehicle conflict risk factor quantification method based on causal machine learning. The method specifically comprises the following steps: 1, extracting pedestrian-left-turn vehicle conflict data; 2, matching the pedestrian-left turning vehicle conflict data with a signal control type Ttype and a safety influence factor; 3, constructing a directed acyclic graph; 4, on the basis of a directed acyclic graph, using a dual robust learning algorithm to construct causal inference models under different signal control types, and mining factors related to pedestrian-left turn vehicle conflicts from safety influence factors as conflict risk factors; and the heterogeneity causal effect of different signal control types on the pedestrian-left turn vehicle conflict risk is estimated. According to the method, confusion factors can be effectively identified and processed, and the robustness and generalization ability of the model facing real world data are improved.

Description

Technical Field

[0001] The present invention belongs to the field of traffic technology, and in particular relates to a method for quantifying risk factors of conflicts between pedestrians and left-turning vehicles at intersections based on causal machine learning. Background Art

[0002] Intersections are key nodes where pedestrians and vehicles meet in urban traffic networks, and they have also become areas where traffic accidents frequently occur. Conflicts between pedestrians and vehicles often arise from time overlap, unreasonable spatial design, blind spots, and lack of signal mechanisms designed specifically for pedestrians or turning vehicles. In order to alleviate these conflicts, urban planners have adopted strategies including optimizing signal phases, setting up independent turning signals, improving infrastructure visibility, and strengthening traffic safety education to improve the overall safety level of intersections. At signal-controlled intersections, frequent collisions or near-collisions between pedestrians and left-turning vehicles can result in reduced traffic efficiency and health risks. Therefore, it is crucial to infer the impact of left-turn control modes on pedestrian-vehicle safety and understand the potential patterns of other related safety factors. It is urgent to establish a method for mining risk factors for pedestrian-left-turning vehicle conflicts at intersections. Summary of the invention

[0003] Purpose of the invention: In order to solve the problems existing in the above-mentioned prior art, the present invention provides a method for quantifying the risk factors of pedestrian-left-turning vehicle conflicts at intersections based on causal machine learning.

[0004] Technical solution: The present invention discloses a method for quantifying the risk factors of pedestrian-left-turning vehicle conflicts at intersections based on causal machine learning, which is characterized by:

[0005] Step 1: Extract pedestrian-left-turn vehicle conflict data during the observation period;

[0006] Step 2: Pedestrian-left-turning vehicle conflict data and signal control type T type and matching of safety influencing factors;

[0007] Step 3: Set the signal control type to T type as treatment variables, safety influencing factors as confounding variables, and pedestrian-left-turning vehicle conflict frequency Y as output variable to construct a directed acyclic graph;

[0008] Step 4: Based on the directed acyclic graph, a dual robust learning algorithm is used to construct a causal inference model under different signal control types, and factors related to pedestrian-left-turn vehicle conflicts are mined from safety influencing factors as conflict risk factors, and the heterogeneous causal effects of different signal control types on pedestrian-left-turn vehicle conflict risks are estimated.

[0009] Furthermore, the step 1 is specifically as follows: setting a post-intrusion time threshold, and defining a conflict in the video stream in which the post-intrusion time is less than the post-intrusion time threshold as a pedestrian-left-turning vehicle conflict.

[0010] Furthermore, the signal control type T in step 2 type Includes protected left-turn phase, permitted left-turn phase, and protected-permitted left-turn phase;

[0011] Safety influencing factors include traffic volume attribute X vol , road geometry attributes X road , signal timing attribute X signal And the basic attribute X basic ; The traffic volume attribute X vol Including left-turn traffic volume Vol_Veh, pedestrian traffic volume Vol_Ped, and the opposite straight-moving vehicle traffic volume Vol_Opp of left-turn vehicles; road geometric attributes X road Including: number of left-turn lanes LT, number of import lanes EntL, number of exit lanes ExitL, number of lanes for opposite traffic Thr_Opp, speed limit for left turn Slim and speed limit for opposite traffic Slim_Opp; signal timing attribute X signal Including the minimum green light duration GM, the average left turn green light duration AG, the maximum cycle MaxC of signal control, the minimum cycle MinC, the pedestrian walking time ExiW and the red light flashing time ExiFDW; basic attributes X basic Includes: weekdays, weekends, off-peak hours, and morning and evening peak hours.

[0012] Furthermore, in step 3, when constructing the directed acyclic graph, the variable T type Any indirect path to the output variable Y is regarded as a backdoor path, that is, link T type ←X c →Y is the backdoor path, X c A safety factor.

[0013] Furthermore, a dual robust learning algorithm is used to estimate the heterogeneous causal effects of different signal control types.

[0014]

[0015]

[0016] in, represents the expected value, X c is the safety influencing factor, K(X c ) represents the similarity metric, θ t represents the treatment effect, θ t (Xc ) is:

[0017]

[0018] Among them, Y(T type =t) represents the frequency of pedestrian-left-turn vehicle conflicts of signal control type;

[0019] The expression is as follows:

[0020]

[0021] Among them, Y i is the frequency of pedestrian-left-turning vehicle conflicts actually observed, and the observation interval is obtained by dividing the observation time period. g t (X c ), For p t (X c ), t = 0, 1, 2; when t = 0, it means that the signal control type is the protection type left turn phase; when t = 1, it means that the signal control type is the permission type left turn phase; when t = 2, it means that the signal control type is the protection-permission left turn phase; g t (X c ) and p t (X c ) is as follows:

[0022] g t (X c )+ε t =Y(T type =t)

[0023] p t (X c )+δ=Pr(T type =t|X c )

[0024] Among them, ε t and δ are unobservable noises, Pr(T type =t|X c ) refers to the given X c Under the condition of , the probability of signal control type is predicted; based on the directed acyclic graph, the regression model is used to estimate g t (X c ), using the classification model to estimate p t (X c ).

[0025] Furthermore, the method also includes a preliminary screening of safety influencing factors after step 2, specifically using the Pearson correlation coefficient to quantify the linear relationship between safety-related factors and removing multicollinearity features. Then, the BorutaSHAP method is used to eliminate safety-related factors with low contribution to conflict risk prediction.

[0026] Beneficial effects:

[0027] 1. The present invention introduces causal graphs and dual robust learning algorithms, which can effectively identify and process confounding factors, thereby avoiding the problem of selection bias and improving the robustness and generalization ability of the model when facing real-world data.

[0028] 2. Different from previous studies that can only partially explain the impact of signal control types on conflict risk, the present invention more accurately quantifies the heterogeneous causal effects of different signal control types on pedestrian-left-turn vehicle conflicts, providing a scientific basis for optimizing signal control strategies.

[0029] 3. The present invention takes into account physical factors such as traffic volume, road geometry, and signal timing attributes, and can comprehensively evaluate various factors that affect conflict risks, thereby enhancing the comprehensiveness and practicality of the factor mining model.

[0030] 4. By using the Pearson correlation coefficient and the BorutaSHAP method to select important features, screen out key confounding variables, and construct a causal diagram, collinearity characteristics are effectively eliminated, thereby improving the accuracy of the factor mining of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] Figure 1 The present invention is a flow chart of the method.

[0032] Figure 2 This is a framework diagram of the method of the present invention.

[0033] Figure 3 Schematic diagram of Pearson correlation coefficient analysis.

[0034] Figure 4 is a directed acyclic graph.

[0035] Figure 5 This is a graph showing the results of heterogeneous causal effect estimation. DETAILED DESCRIPTION

[0036] The accompanying drawings, which constitute a part of the present invention, are used to provide a further understanding of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute improper limitations on the present invention.

[0037] like Figure 1 , as shown in 2, the present invention specifically includes the following steps:

[0038] S1: The post-encroachment time (PET) is used to define the pedestrian-left-turning vehicle conflict threshold, and the pedestrian-left-turning vehicle conflict data is extracted through video processing technology.

[0039] S2: Data aggregation. Match pedestrian-left-turn vehicle conflict data with signal control types and safety influencing factors.

[0040] S3: Confounding feature screening. Pearson correlation coefficient and BorutaSHAP method were used to eliminate collinearity and confounding factors with low contribution to model prediction from various safety influencing factors.

[0041] S4: Construct a causal relationship diagram to identify safety influencing factors and characteristics for pedestrian-left-turning vehicle conflict modeling.

[0042] S5: A causal inference model under a specific signal control type was constructed using the double robust learning (DRL) algorithm to explore the risk factors of pedestrian-left-turning vehicle conflicts and estimate the heterogeneous causal effects (HTE) of different signal control types on the risk of pedestrian-left-turning vehicle conflicts.

[0043] Specifically, S1 is: using the Post-Encroachment Time (PET) to define the intersection pedestrian-left-turning vehicle conflict. PET represents the time interval from the moment (t1) when the first road user (vehicle or pedestrian) leaves the potential conflict area to the moment (t2) when the second road user (vehicle or pedestrian) enters the area. The calculation of PET is shown in formula (1):

[0044] PET=t2-t1 (1)

[0045] The threshold range for recording PET is 10 seconds. Through video acquisition technology, conflicts with PET<5 in the video stream are identified as pedestrian-left-turning vehicle conflicts. As shown in formula (2), 1 means that the PET is recorded as a conflict, and 0 means that the PET is not recorded as a conflict.

[0046]

[0047] The total number of pedestrian-left-turning vehicle conflicts occurring during the period is counted every 60 minutes.

[0048] The S2 is specifically: matching pedestrian-left-turn vehicle conflict data with signal control types and multi-dimensional features (i.e., confusion factors and features). Determining safety influencing factors in heterogeneous causal reasoning, represented by high-dimensional confounding variables (X). Aggregating the collected confounding variables (X) at 60-minute intervals. The confounding variables considered in the present invention include:

[0049] Traffic volume attribute X vol Traffic volume attributes include the flow information of different types of traffic participants in a specific time period. Left-turn traffic volume Vol_Veh (veh / h), pedestrian traffic volume Vol_Ped (Ped / h). These two attributes are directly related to the occurrence of pedestrian-left-turn vehicle conflicts. The opposite straight-moving vehicle traffic volume of left-turn vehicles Vol_Opp (veh / h).

[0050] Road geometry attributes X road . Road geometry attributes describe the design layout of the intersection. Intersection geometry plays a key role in traffic signal design, especially when evaluating left-turn phases. In cases where left-turn traffic volume is large, especially in combination with protected control, it is usually necessary to set up a dedicated left-turn lane. In the present invention, the following variables are considered: the number of left-turn lanes LT, the number of entrance lanes EntL and the number of exit lanes ExitL, the number of lanes for opposing traffic Thr_Opp, the speed limit Slim for left turns and the speed limit Slim_Opp for opposing traffic.

[0051] Signal timing attribute X signal . The signal timing attributes involve the configuration of traffic lights. Specific signal timing attributes should be considered, including: maximum cycle MaxC and minimum cycle MinC. The signal control parameters for left-turn vehicles passing through the intersection include: minimum green light duration GM and average left-turn green light duration AG. Two typical pedestrian signal timing parameters include: pedestrian walking time ExiW and red light flashing time ExiFDW.

[0052] Basic AttributesX basic The basic attributes cover the time characteristics of the conflict. The day of the week when the conflict occurs DAY and the time of day when the conflict occurs PERIOD. These variables help mitigate the impact of potential factors such as lighting and holidays. Among them, DAY is divided into weekdays (marked as 0) and weekends (marked as 1). PERIOD is divided into off-peak hours (marked as 0) and morning and evening peak hours (marked as 1).

[0053] Specifically, S3 uses the Pearson correlation coefficient to quantify the linear relationship between safety-related factors X and removes multicollinearity. This deterministic interdependence, known as collinearity, complicates data analysis and exacerbates bias as collinearity increases. The Pearson correlation coefficient heat map is shown in Figure 1. Figure 3 Then, the BorutaSHAP method was used to eliminate the confounding variables with low contribution to conflict risk prediction.

[0054] Specifically, S4 is as follows: The present invention estimates the heterogeneous treatment effects (HTE) of different signal control types based on the Rubin Causal Model (RCM) framework. The HTE is the effect of the signal control type T under the influence of the high-dimensional confounding variable X. type The influence of the frequency Y of pedestrian-left-turning vehicle conflicts is quantified. Since the conflict between left-turning vehicles and pedestrians is mainly related to the signal control type, it is assumed that there are potential safety-related factors such as road alignment and traffic condition attributes (step S2) that may affect the selection of signal control type, and the frequency of pedestrian-left-turning vehicle conflicts is affected by the signal control type. type =t) indicates signal control type T type =Y corresponding to t. The present invention considers three typical signal control types (ie, protection-type left turn phase, permission-type left turn phase and protection-permission left turn phase). The present invention defines T type ∈{0,1,2} is the left turn signal control type: T type =0 is the protection type left turn phase; T type =1 is the permissive left turn phase, T type =2 is the protection-permit left turn phase. The extracted traffic conflicts are matched with the signal control type when the conflicts occur at 60-minute intervals. Then, the safety influencing factor X screened in step S3 is introduced; the estimated conditional average treatment effect (CATE) is calculated:

[0055]

[0056] The present invention uses a directed acyclic graph (DAG) to represent the potential causal relationship between high-dimensional observation data, such as Figure 4 As shown. type is defined as the treatment variable in the causal graph (i.e., directed acyclic graph), and the safety influencing factors screened in step S3 are defined as X c , X c=X road ∪X signal ∪X vol ∪X basic , the output variable Y is the frequency of pedestrian-left-turning vehicle conflicts (times / hour). type ←X c →Y is the backdoor path, which is from the disposal variable T type Any indirect paths to the output variable Y that pass through the confounding variable X c Pass, it can reflect X c By identifying these backdoor paths and blocking them, the confounding variable X can be eliminated. c , thereby more accurately estimating causal effects.

[0057] S5 is specifically: estimating the heterogeneous causal effect (HTE) of the signal control type. A double robust learning (DRL) algorithm is proposed to estimate HTE. First, assume that:

[0058] Y(T type =t) = g t (X c )+ε t (4)

[0059] Pr(T type =t|X c )=p t (X c )+δ (5)

[0060] In the formula, g t T type = the predicted value of the signal control class at time t, Pr is the predicted value of X c Under the influence of T type = the probability of t∈{0,1,2}, and ε t and δ is and The unobservable noise, represents the expected value, g t (X c ) is the function g t For X c The output of c The expected result of processing type t under the conditions. t (X c ) is the function p t For X c The output of c The predicted value of the probability that an individual will accept treatment t under the condition of type=t related CATE θ t (X c ) is calculated as follows:

[0061]

[0062] In the formula, g0(X c ) means that at a given X c Under the condition of type =0 is the predicted value of the signal control class.

[0063] Secondly, the DRL algorithm is used to estimate CATE θ t (X c ). The method models pedestrian-left-turning vehicle conflicts in a two-stage framework. In the first stage, two machine learning (ML) models are applied to estimate g based on the directed acyclic graph in step S4-2. t (X c ) and p t (X c ). Using regression model to estimate g t (X c ), and obtain the estimated result Using the classification model to estimate p t (X c ), and obtain the estimated result Then, the inverse propensity scoring (IPS) method is used to eliminate the bias. By combining the IPS method with the regression model, as long as the estimation results of any of the two models are accurate, the DRL model can obtain unbiased estimation results. Potential output results of the first stage

[0064]

[0065] Among them, Y i is the frequency of pedestrian-left-turning vehicle conflicts actually observed.

[0066] The second stage of the DRL model estimates the heterogeneous causal effect. At this point, the estimated result of the heterogeneous causal effect CATE is As shown in Formula 8:

[0067]

[0068] Among them, the similarity measurement index K(X c ) is achieved by using the target label and X c After obtaining the fitted DRL model, the heterogeneous causal effects of each signal control type can be further estimated.

[0069] like Figure 5 As shown, this embodiment provides the HTE of the protection-permit left turn phase signal control mode on Vol_Veh, Vol_Ped and Vol_Opp respectively. (1) Figure 5 (a) The linearity of Vol_Veh is evaluated using a univariate RCS (Restricted Cubic Spline, RCS) model. ANOVA results show that the 3-k knot RCS provides a better fit (P<0.001). Vol_Veh analysis shows that pedestrian-left-turn vehicle conflicts increase significantly with the increase in the amount of left turns. This phenomenon is similar to the permissive left-turn phase. It can be concluded that the presence of the green phase in the permissive left-turn phase signal control mode contributes to its increase.

[0070] (2) Figure 5 (b) in Figure 1 shows the Vol_Ped pedestrian-left-turning vehicle conflict HTE. The ANOVA value shows that the 3-k knot RCS fits better (P<0.01). The Vol_Ped analysis also shows that the pedestrian-left-turning vehicle conflict shows a clear inverse "U" trend with the increase in the number of pedestrians. Contrary to common sense, when Vol_Ped is higher than about 50veh / h at the 95% confidence level, the pedestrian-left-turning vehicle conflict is significantly reduced. It can be concluded that these pedestrians may cross the intersection in groups and cannot be concealed by the visual obstruction of the driver who is turning left, which may provide more time for pedestrians to cross safely.

[0071] (3) Figure 5 (c) in Figure 2 shows that the critical conflict increases with the increase of the oncoming traffic volume, but at a 95% confidence level, when Vol_Opp is higher than about 750veh / h, the critical conflict further decreases. It can be seen that the protection-permitted left turn phase always works in the protected stage, when the opposite direction traffic volume is large, which may further reduce the conflict between pedestrians and left-turn traffic.

[0072] It should also be noted that the various specific technical features described in the above specific embodiments can be combined in any suitable manner without contradiction. In order to avoid unnecessary repetition, the present invention will not further describe various possible combinations.

Claims

1. A quantification method for the risk factors of pedestrian-left-turning vehicle conflicts at intersections based on causal machine learning, characterized in that: Specifically: Step 1: Extract pedestrian-left-turn vehicle conflict data during the observation period; Step 2: Pedestrian-left-turning vehicle conflict data and signal control type T type and matching of safety influencing factors; Step 3: Set the signal control type to T type as treatment variables, safety influencing factors as confounding variables, and pedestrian-left-turning vehicle conflict frequency Y as output variable to construct a directed acyclic graph; Step 4: Based on the directed acyclic graph, a dual robust learning algorithm is used to construct a causal inference model under different signal control types, and factors related to pedestrian-left-turn vehicle conflicts are mined from safety influencing factors as conflict risk factors, and the heterogeneous causal effects of different signal control types on pedestrian-left-turn vehicle conflict risks are estimated.

2. The method for quantifying the risk factors of pedestrian-left-turning vehicle conflict at intersections based on causal machine learning according to claim 1 is characterized in that: The step 1 specifically includes: setting a post-intrusion time threshold, and defining a conflict in a video stream in which the post-intrusion time is less than the post-intrusion time threshold as a pedestrian-left-turning vehicle conflict.

3. The method for quantifying the risk factors of pedestrian-left-turning vehicle conflict at intersections based on causal machine learning according to claim 1 is characterized in that: Signal control type T in step 2 type Includes protected left-turn phase, permitted left-turn phase, and protected-permitted left-turn phase; Safety influencing factors include traffic volume attribute X vol , road geometry attributes X road , signal timing attribute X singnal And the basic attribute X basic ; The traffic volume attribute X vol Including left-turn traffic volume Vol_Veh, pedestrian traffic volume Vol_Ped, and the opposite straight-moving vehicle traffic volume Vol_Opp of left-turn vehicles; road geometric attributes X road Including: number of left-turn lanes LT, number of import lanes EntL, number of exit lanes ExitL, number of lanes for opposite traffic Thr_Opp, speed limit for left turn Slim and speed limit for opposite traffic Slim_Opp; signal timing attribute X signal Including the minimum green light duration GM, the average left turn green light duration AG, the maximum cycle MaxC of signal control, the minimum cycle MinC, the pedestrian walking time ExiW and the red light flashing time ExiFDW; basic attributes X basic Includes: weekdays, weekends, off-peak hours, and morning and evening peak hours.

4. The method for quantifying the risk factors of pedestrian-left-turning vehicle conflict at intersections based on causal machine learning according to claim 1 is characterized in that: In step 3, when constructing a directed acyclic graph, the variable T is processed type Any indirect path to the output variable Y is regarded as a backdoor path, that is, link T type ←X c →Y is the backdoor path, X c A safety factor.

5. The method for quantifying the risk factors of pedestrian-left-turning vehicle conflict at intersections based on causal machine learning according to claim 1, characterized in that: Estimating heterogeneous causal effects of different signal control types using a dual robust learning algorithm in, represents the expected value, X c is the safety influencing factor, K(X c ) represents the similarity metric, θ t represents the treatment effect, θ t (X c ) is: Among them, Y(T type =t) represents the frequency of pedestrian-left-turn vehicle conflicts of signal control type; The expression is as follows: Among them, Y i is the frequency of pedestrian-left-turning vehicle conflicts actually observed, and the observation interval is obtained by dividing the observation time period. g t (X c ), For p t (X c ), t = 0, 1, 2; when t = 0, it means that the signal control type is the protection type left turn phase; when t = 1, it means that the signal control type is the permission type left turn phase; when t = 2, it means that the signal control type is the protection-permission left turn phase; g t (X c ) and p t (X c ) is as follows: g t (X c )+ε t =Y(T type =t) g t (X c )+δ=Pr(T type =t|X c , Among them, ε t and δ are unobservable noises, Pr(T type =t|X c ) refers to the given X c Under the condition of , the probability of signal control type is predicted; based on the directed acyclic graph, the regression model is used to estimate g t (X c ), using the classification model to estimate p t (X c ).

6. The method for quantifying the risk factors of pedestrian-left-turning vehicle conflict at intersections based on causal machine learning according to claim 1, characterized in that: The method also includes a preliminary screening of safety influencing factors after step 2, specifically using the Pearson correlation coefficient to quantify the linear relationship between safety-related factors and remove multicollinearity features. Then, the BorutaSHAP method is used to eliminate safety-related factors with low contribution to conflict risk prediction.

Images