Lane-changing Risk Research Articles

Lane Change Behavior Patterns and Risk Analysis in Expressway Weaving Areas: Unsupervised Data-Mining Method

Lane Change Behavior Patterns and Risk Analysis in Expressway Weaving Areas: Unsupervised Data-Mining Method

Risk identification and prediction model for continuous‐lane‐change vehicles considering driving style

Lane change risk identification and prediction research is important for traffic safety, development of advanced driver assistance systems, traffic flow optimization. Among them, vehicle continuous‐lane‐change (CLC) risk identification and prediction is weak, but this element is important for vehicle decision-making and path planning in multi-lane, non-adjacent lane situations. To compensate for the shortcomings of risk identification based on both deterministic and probabilistic methods and address the issues of poor measurement accuracy and efficiency caused by manual tuning, this study established a risk identification and prediction model based on the Bayesian global optimization (BO) gated recurrent unit (GRU) neural network (BO-GRU) and instantiated the model using the trajectory data of 129 vehicles. Overall, the results showed that the accuracy of identifying CLC risks and driving-style was 99.33% and 97.44%, respectively, while the overall average accuracy of predicting potential CLC risks based on the identification of risks and predicted trajectories was 97.13%. The root-mean-square errors of CLC predicted trajectory for different driving-styles were 0.2503, 0.2331, 0.2093, and 0.2706, respectively, which were 84%−88% lower compared to 1.7361 when driving-styles were not considered. The performance of the BO-GRU model is comparable to that of parameter-optimized LSTM and its variant models, which highlights the significance of parameter optimization for neural network models. Overall, the use of a BO-GRU-based model for identifying and predicting continuous lane change risks in vehicles can aid in making driving decisions and planning routes, decrease the risk of collisions, enhance traffic flow efficiency, and encourage safe driving behavior.

Quantifying risks of lane-changing behavior in highways with vehicle trajectory data under different driving environments

Improper lane-changing behavior may have a great impact on the safety of the surrounding vehicles, and accurate risk assessment of lane-changing behavior can detect improper lane-changing behavior. Many existing risk assessment methods are based on the traditional minimum safe distance model as the theoretical foundation, not taking into account the effects of different weather and road conditions. Moreover, the initially calculated safe lane-changing distance through the model is generally the limit safety distance, which deviates to some extent from the initial distance maintained when the vehicle begins to change lanes during the actual driving process. The ratio of these two distances can reflect the degree of risk between the changing vehicle and its neighboring vehicles during lane-changing. For this reason, a lane-changing safety coefficient is defined and lane-changing risk assessment model based on the hyperbolic tangent function is constructed by combining the change characteristics of this coefficient. An environmental adjustment factor was introduced into the model to consider the influence of different driving weather and road conditions on the lane-changing risk assessment. Then, based on survey data from the survey questionnaire, the weights of the influencing factors were determined by using the hierarchical analysis method, and the environmental adjustment factor in the model was calibrated by using the fuzzy comprehensive assessment method. Finally, to verify the effectiveness of the model, the lane-changing trajectories of 373 vehicles were extracted from the HighD dataset. The risk assessment value of lane-changing was calculated by using the constructed model and was classified into high-risk, medium-risk and low-risk by using the K-means++ clustering algorithm. Various evaluation results were compared with the evaluation results from the expert evaluation method and the classical risk evaluation indexes, and the evaluation results are basically the same, which verifies the effectiveness of the lane-changing risk model established.

A Comprehensive Investigation of Lane-Changing Risk Recognition Framework of Multi-Vehicle Type Considering Key Features Based on Vehicles’ Trajectory Data

To comprehensively investigate the key features of lane-changing (LC) risk for different vehicle types during left and right LC, and to improve the accuracy of LC risk recognition, this paper proposes a key feature selection and risk recognition model based on vehicle trajectory data. Based on a HighD high-precision vehicle trajectory dataset, the trajectory data of LC vehicles and surrounding vehicles of each vehicle type are extracted. SDI (stop distance index) and CI (crash index) are selected as surrogate indicators to calculate the risk exposure level (REL) and risk severity level (RSL). The K-means algorithm is used to cluster the REL and RSL to obtain the LC risk level, which is divided into three levels. The combination of basic features and interaction features of LC vehicles and surrounding vehicles with LC risk levels is constructed as the LC risk feature dataset. Based on the LightGBM (light gradient boosting machine) algorithm, the importance of features is sorted. Finally, a CNN-BiLSTM-Attention model is established to recognize the LC risk of each vehicle type during left and right LC. The results indicate that significant differences exist among different vehicle types and LC directions. Compared with CNNs (convolutional neural networks), LSTM (long short-term memory), and BiLSTM (bi-directional long short-term memory), CNN-BiLSTM-Attention performs best in recognizing the risk of LC in all cases. Moreover, the key feature groups that have the optimal result of recognizing the risk of LC in different cases are obtained.

Modeling collision risk for unsafe lane-changing behavior: A lane-changing risk index approach

The lane-changing maneuvers are challenging and contributes to traffic accidents and crashes. They are complicated task that often lead to an increased risk of vehicle collisions and deteriorates traffic flow. This paper proposes a vehicle collision risk model based on vehicle lane-changing movement for autonomous vehicles using the probability threat assessment approach and the lane-changing risk index (LCRI). Given two vehicles, A and B, we first estimate the movements of vehicle B using a GPS device, which accurately identifies the vehicle while changing lanes. We then evaluate the collision risks between vehicles using the probabilistic assessment approach to determine whether a collision event occurs at a later stage. Then, we propose the LCRI, which aims to identify the risk level associated with vehicle lane-changing movement and determine the severity of the crash level. In this study, the HighD vehicle trajectory dataset is used to obtain accurate traffic information and help us investigating collision risks among vehicles. The results show that the proposed model can identify the risks of collision ahead of time. Furthermore, the random parameter ordered logit (RPOL) with heterogeneity model achieves better performance and provides a good fit model and measures for improving traffic safety.

A new lane change index for lane change conflicts at weaving segments

Objective Surrogate safety measures provide information about the safety of traffic facilities without waiting for crashes to occur. Most studies related to surrogate safety measures were performed at intersections. Traffic accident statistics show that sideswipe crashes have a considerable percentage of all crashes. Sideswipe crashes arising from lane-change conflicts are highly probable at weaving segments. This study focuses on lane-change conflicts at weaving segments and proposes a new index. Methods Considering the interactions between the subject vehicle and the surrounding vehicles, two new surrogate safety measures, time- and position-based, are recommended. Then, applying a fault tree analysis, these two measures are converted to a lane change risk index to estimate the crash severity. The proposed index is specific to weaving segments. Data from five weaving segments were extracted using deep learning detection and tracking algorithms. Results The results based on the relationship between the proposed indexes and speed showed that the probability and severity of a crash increased as the speed increased. The longer weaving length resulted in smaller values in the time-based index. Conclusions The weaving length is critical because it becomes difficult to perform a lane change if the length is too short. The proposed time and position-based indexes combine the effect of weaving length, stopping distance index, time to collision, and brake time. It is believed that the proposed lane change risk index can be used to detect the safety level of weaving segments.

Driving Behavior Risk Measurement and Cluster Analysis Driven by Vehicle Trajectory Data

The correct identification and timely pre-warning of driving behavior risks can remind drivers to correct their unsafe driving behaviors effectively. First of all, four risk evaluation indicators of driving behavior were defined based on lateral and longitudinal driving characteristics: the lateral stability indicator, the longitudinal stability indicator, the car-following risk indicator, and the lane-changing risk indicator. The Pearson correlation coefficient method was used to analyze the correlation of the four indicators, and the conclusion showed that the four indicators were very weakly correlated or presented an irrelevant correlation. Thus, the four indicators can describe different driving behavior risks. Secondly, the criteria importance through intercriteria correlation (CRITIC) method was used to determine the weight of each indicator, and a comprehensive measurement model of driving behavior risk was established. To test the model, this study preprocessed the trajectory data of small vehicles in Lanes 1–5 of the I-80 Expressway from the NGSIM dataset, collected statistical analysis results of vehicle speed and acceleration, and obtained the parameters data required for risk assessment. Then, based on the obtained trajectory data, the variation laws and the thresholds of the four indicators were determined by using the interquartile difference method. Finally, by using the K-means clustering algorithm, the risk types of driving behavior were divided into four categories, namely, dangerous, aggressive, safe, and conservative. The dangerous, aggressive, safe, and conservative driving behaviors accounted for 5.40%, 23.30%, 43.22%, and 28.08% of the total samples, respectively. The expert’s assessment results of the driving behavior risk aligned with the results obtained from the model measurements. This indicated that the driving behavior risk measurement model here described can evaluate a driver’s risk status in real time, provide safety tips for the driver, and offer theoretical support for driving safety warning systems.

A proactive crash risk prediction framework for lane-changing behavior incorporating individual driving styles

Driving style may have an important effect on traffic safety. Proactive crash risk prediction for lane-changing behaviors incorporating individual driving styles can help drivers make safe lane-changing decisions. However, the interaction between driving styles and lane-changing risk is still not fully understood, making it difficult for advanced driver-assistance systems (ADASs) to provide personalized lane-changing risk information services. This paper proposes a personalized risk lane-changing prediction framework that considers driving style. Several driving volatility indices based on vehicle interactive features have been proposed, and a dynamic clustering method is developed to determine the best identification time window and methods of driving style. The Light Gradient Boosting Machine (LightGBM) based on Shapley additive explanation is used to predict lane-changing risk for cautious, normal, and aggressive drivers and to analyze their risk factors. The highD trajectory dataset is used to evaluate the proposed framework. The obtained results show that i) spectral clustering and a time window of 3 s can accurately identify driving styles during the lane-changing intention process; ii) the LightGBM algorithm outperforms other machine learning methods in personalized lane-changing risk prediction; iii) aggressive drivers seek more individual driving freedom than cautious and normal drivers and tend to ignore the state of the car behind them in the target lane, with a greater lane-changing risk. The research conclusion can provide basic support for the development and application of personalized lane-changing warning systems in ADASs.

Iterative learning control for lane-changing trajectories upstream off-ramp bottlenecks and safety evaluation

This paper proposes an iterative learning control framework for lane changing to improve traffic operation and safety at a diverging area nearby a highway off-ramp in an environment with connected and automated vehicles (CAVs). This framework controls CAVs in the off-ramp bottlenecks by imitating the trajectories optimized by machine learning algorithms. Next Generation Simulation (NGSIM) dataset is utilized as the raw data and filtered by cost function. The traffic models, including lane-changing decision (LCD) models and lane-changing execution (LCE) models, are completed by Random Forest (RF) and Back Propagation Neural Network (BPNN) algorithms. Based on simulation results, simulation data satisfying the predetermined criterion will be added to dataset in the next iteration. Various metrics are considered to evaluate the proposed framework systematically from both lateral and longitudinal aspects, including time exposed time-to collision (TET), time integrated time-to-collision (TIT), rear-end collision risk indexes (RCRI) and lane-changing risk index (LCRI). The results present that the iterative framework can decrease the longitudinal risk of the system by a factor of two times, and can reduce the lateral risk by 28.7%. When the CAVs market penetration rate (MPR) reaches 100%, the longitudinal and lateral risk values of the off-ramp system can be reduced by 90% and 35%, respectively. However, it is worth noting that only when the CAVs MPR reaches 50% does the system's value at risk change significantly.

Enhanced index of risk assessment of lane change on expressway weaving segments: A case study of an expressway in China

Vehicles frequently change lanes at weaving segments, and there is a high probability of collision. To assess the risk of lane change, this study proposes a novel lane change risk assessment index (LCRAI), which takes both exposure time and conflict severity into consideration. First, the generalized time-to-collision (GTTC) and exposure-to-risk index (ERI) are proposed to evaluate conflicts during lane change, and then a spatiotemporal overlap analysis is applied to exclude the cases when two vehicles arrive at the conflict area at different times. Second, the change of velocity after a crash occurrence is calculated and used to evaluate the severity risk (SRI). Finally, ERI and SRI are combined to compute the LCRAI. A case study of a weaving segment is conducted, and the weaving segment is divided into four sections to compare their risks. Conflict frequency on the section close to the exit is the largest and it is smallest after passing the exit, while conflict severity is most serious just after entering the main line on the middle lane. As for both conflict frequency and severity, LCRAI shows that the middle section is the most dangerous while the last 100 m section is the safest in the weaving segment. The index proposed will contribute to the risk assessment of lane change in connected environments and improve safety in weaving segments of expressway combined with real-time safety countermeasures.

Attention-Based Lane Change and Crash Risk Prediction Model in Highways

Lane change and crash risk prediction are critical technologies for autonomous driving. An attention-based LSTM model is proposed in this paper for lane change behavior prediction in highways, considering both the surrounding vehicles’ information around the target vehicle at the current time and the historical trajectory data of the vehicle, and it shows higher accuracy and better interpretability than other models. There are two sections in this prediction model, including a pre-judgment model based on the C4.5 decision tree and bagging ensemble learning, and a multi-step lane change prediction model of LSTM with attention mechanism. In addition, the model is applied in the NGSIM datasets to test practicability and accuracy, and the precision of left lane change and right lane change is 98% and 94% respectively 1 second before the vehicle changes lane. Finally, to judge the safety of vehicles in the driving process, a crash risk prediction model based on Time-To-Collision is proposed, which further verifies the effectiveness of the method.

Impact of Driver Behavior and Vehicle Type on Safety of Vehicle Platoon Under Lane Change Situation

Lane changes are critical contributors to road traffic safety on highways. Among the safety indexes aimed at evaluating the risk associated with lane changes, the lane-change risk index (LCRI) is used to determine the collision probability of a platoon of vehicles during lane-change maneuvers. This study estimated the impact of driver behavior and vehicle type on the LCRI using individual vehicle trajectory data from the Next Generation Simulation (NGSIM) program. We define the subject vehicle (i.e., a vehicle changing lane) and its surrounding vehicles (i.e., front, rear, lead, and lag vehicles) as a platoon. Each vehicle type (i.e., truck, bus, car, and motorcycle) and driver behavior (i.e., aggressive, ordinary, and timid) were categorized for regression analysis. Driver behavior was classified through time–space deviations between each vehicle’s trajectories and expected trajectories using Newell’s car-following model. In addition, to take into account the heterogeneity among the lanes, this study used a linear mixed model, which reflected fixed and random effects. Two unique findings were that (i) we were able to quantify and analyze the complex interaction between vehicle type and driver behavior within the platoon during lane changes, and (ii) using the random parameter model, the influence of vehicle type and driver behavior in the platoon was heterogeneous, depending on the lane. The findings of this study are expected to provide detailed lane-change strategies for autonomous vehicles as well as to evaluate the causative factors of lane-change risk.

Lane-Change Risk When the Subject Vehicle Is Faster Than the Following Vehicle: A Case Study on the Lane-Changing Warning Model Considering Different Driving Styles

The research of early warning and control strategy considering driving styles during lane changes is a hotspot in the field of automatic driving. However, many lane-changing studies only emphasize the warning analysis when the following vehicle is faster than the subject vehicle, while neglecting the potential risk when the subject vehicle is faster than the following vehicle in the adjacent lane during lane changes. To study the lane-changing characteristics of drivers considering driving styles and to establish a personalized lane-changing warning model under different relative speed conditions, fifty participants (three females and forty-seven males) were recruited to carry out a real road driving test. A novel Gaussian mixture model with the results of k-means clustering was established to classify driving styles based on two-dimensional variables: average time gap and average minimum time to collision. The clustering result was then verified. In addition, by analyzing the relationship between the subject vehicle and the following vehicle in the adjacent lane during lane changes, a lane-changing warning model considering driving styles under different relative speed conditions was established. Results show that the clustering algorithm proposed in this paper has high separability between samples, achieving a much softer clustering result that can provide a reference for the parameter setting of the personalized driver assistance system. Furthermore, the overall recognition accuracy of the hazardous lane-changing behaviors improved after drivers were classified into different driving styles. The established lane-changing warning model has a better recognition performance for aggressive drivers when compared with the other two driver types. The results provide a basis for the algorithm design of the intelligent lane-changing warning system and can improve the user acceptance of an advanced driver assistance system for self-driving vehicles.

An Integrated Fuzzy Analytic Hierarchy Process (AHP) Model for Studying Significant Factors Associated with Frequent Lane Changing.

Frequent lane changes cause serious traffic safety concerns, which involve fatalities and serious injuries. This phenomenon is affected by several significant factors related to road safety. The detection and classification of significant factors affecting lane changing could help reduce frequent lane changing risk. The principal objective of this research is to estimate and prioritize the nominated crucial criteria and sub-criteria based on participants’ answers on a designated questionnaire survey. In doing so, this paper constructs a hierarchical lane-change model based on the concept of the analytic hierarchy process (AHP) with two levels of the most concerning attributes. Accordingly, the fuzzy analytic hierarchy process (FAHP) procedure was applied utilizing fuzzy scale to evaluate precisely the most influential factors affecting lane changing, which will decrease uncertainty in the evaluation process. Based on the final measured weights for level 1, FAHP model estimation results revealed that the most influential variable affecting lane-changing is ‘traffic characteristics’. In contrast, compared to other specified factors, ‘light conditions’ was found to be the least critical factor related to driver lane-change maneuvers. For level 2, the FAHP model results showed ‘traffic volume’ as the most critical factor influencing the lane changes operations, followed by ‘speed’. The objectivity of the model was supported by sensitivity analyses that examined a range for weights’ values and those corresponding to alternative values. Based on the evaluated results, stakeholders can determine strategic policy by considering and placing more emphasis on the highlighted risk factors associated with lane changing to improve road safety. In conclusion, the finding provides the usefulness of the fuzzy analytic hierarchy process to review lane-changing risks for road safety.

Lane-Changing Risk Level Prediction Considering Dynamic Decision Process: A Deep Learning Method Based on Spatial-Temporal Series Characteristics

Lane-Changing Risk Level Prediction Considering Dynamic Decision Process: A Deep Learning Method Based on Spatial-Temporal Series Characteristics

A proactive lane-changing risk prediction framework considering driving intention recognition and different lane-changing patterns

Proactive lane-changing (LC) risk prediction can assist driver’s LC decision-making to ensure driving safety. However, most previous studies on LC risk prediction did not consider the driver’s intention recognition, which made it difficult to guarantee the timeliness and practicability of LC risk prediction. Moreover, the difference in driving risks and its influencing factors between LC to left lane (LCL) and LC to right lane (LCR) have rarely been investigated. To bridge the above research gaps, this study proposes a proactive LC risk prediction framework which integrates the LC intention recognition module and LC risk prediction module. The Long Short-term Memory (LSTM) neural network with time-series input was employed to recognize the driver’s LC intention. The Light Gradient Boosting Machine (LGBM) algorithm was then applied to predict the LC risk. Feature importance analysis was lastly conducted to obtain the key features that affect the LC risk. The highD trajectory dataset was used for framework validation. Results show that the recognition accuracy of the driver’s LCL, LCR and lane-keeping (LK) intentions based on the proposed LSTM model are 97%, 96% and 97%, respectively. Meanwhile, the LGBM algorithm outperforms other machine learning algorithms in LC risk prediction. The results from feature importance analysis show that the interaction characteristics of the LC vehicle and its preceding vehicle in the current lane have the greatest impact on the LC risk. The proposed framework could potentially be implemented in advanced driver-assistance system (ADAS) or autonomous driving system for improved driving safety.

Assessment of Significant Factors Affecting Frequent Lane-Changing Related to Road Safety: An Integrated Approach of the AHP-BWM Model.

Frequent lane changes cause serious traffic safety concerns for road users. The detection and categorization of significant factors affecting frequent lane changing could help to reduce frequent lane-changing risk. The main objective of this research study is to assess and prioritize the significant factors and sub-factors affecting frequent lane changing designed in a three-level hierarchical structure. As a multi-criteria decision-making methodology (MCDM), this study utilizes the analytic hierarchy process (AHP) combined with the best–worst method (BWM) to compare and quantify the specified factors. To illustrate the applicability of the proposed model, a real-life decision-making problem is considered, prioritizing the most significant factors affecting lane changing based on the driver’s responses on a designated questionnaire survey. The proposed model observed fewer pairwise comparisons (PCs) with more consistent and reliable results than the conventional AHP. For level 1 of the three-level hierarchical structure, the AHP–BWM model results show “traffic characteristics” (0.5148) as the most significant factor affecting frequent lane changing, followed by “human” (0.2134), as second-ranked factor. For level 2, “traffic volume” (0.1771) was observed as the most significant factor, followed by “speed” (0.1521). For level 3, the model results show “average speed” (0.0783) as first-rank factor, followed by the factor “rural” (0.0764), as compared to other specified factors. The proposed integrated approach could help decision-makers to focus on highlighted significant factors affecting frequent lane-changing to improve road safety.

Reliability-Based Assessment of Potential Risk for Lane-Changing Maneuvers

Despite the urgent need for continuous risk assessments during autonomous driving, achieving reliable assessment results is still challenging because of the unpredictable behaviors of adjacent human drivers and the resulting complexity. Such complexity increases particularly during lane changes because several vehicles need to interact with other vehicles. Therefore, this paper proposes a new framework to analyze lane-changing risk on freeways considering the forecastability in adjacent vehicles. Virtual lane-change scenarios are constructed based on historical maneuvers in adjacent vehicles, and the risk of potential lane change is evaluated through the safety evaluation result of the scenario. Adjacent vehicles’ future maneuvers are predicted using a multivariate Bayesian structural time series model, and the forecastability is estimated as the standard error of the predicted values. The failure probability of those lane-changing scenarios is obtained through the first-order reliability method, assuming that failure occurred when any time-to-collision value for adjacent vehicles was less than a threshold at the end of the lane change. This study tested two scenarios with three levels of uncertainty to show the effect of uncertainty on the level of risk. The results showed that the reduced uncertainty allowed a clearer distinction between risky situations. The proposed framework differentiates itself from existing methods by estimating higher risk in an adjacent vehicle’s more significant uncertainties. It is expected that the outcome of this study will be valuable in developing reliable lane-change strategies in autonomous driving.

Modeling accident risks in different lane-changing behavioral patterns

Lane-changing is a complicated task and has a high probability of accident occurrence. Although a large body of literature has used vehicle trajectories to microscopically understand and model lane-changing behavior, most of these studies focus on lane-changing decision making and lane changing's impacts on surrounding vehicles, not on traffic safety. The contributing factors to lane-changing risks have not been fully explored from the perspective of microscopic behavior using vehicle trajectory data. This study investigates the contributing factors to accident risks in different lane-changing patterns with taking unobserved heterogeneity into account. A vehicle trajectory dataset, HighD is used and 4842 lane-changing vehicle groups are extracted for analysis. These vehicle groups are divided into sixteen patterns according to the vehicle type, and three major patterns are examined. A lane-changing risk index (LCRI) is proposed to evaluate the risk level of each vehicle group. Two methods are developed and compared for exploring lane-changing risks of the three patterns including (1) establishing the random parameters fractional logit models; and (2) classifying LCRI by k-means algorithm and establishing random parameters ordered logit models with heterogeneity in means and variances. The modeling results show that the latter method performs better and the risk level of the vehicle group is strongly associated with (1) the mean and standard deviation of the gap distance between vehicles; (2) the longitudinal velocities and acceleration of vehicles; and (3) the lane-changing direction and duration. However, different patterns are found to have different contributing variables and effects. The effects of gap distances vary considerably across different vehicle groups and the longitudinal velocity of vehicles are associated with the means of random parameters for gap distance.

A lane-changing risk profile analysis method based on time-series clustering

Lane-changing (LC) is an essential driving maneuver on roadways, and risky LC maneuvers account for a large number of crash accidents. This study investigates the LC risk profile during an LC process. A risk indicator based on driving safety field theory is employed to measure the instantaneous LC risk at each timestamp during an LC process and generate the LC risk profile. Then, Dynamic Time Warping (DTW) k-means clustering, as a time-series clustering method, is applied to partition the LC risk profiles into several categories. The Next Generation Simulation (NGSIM) US-101 dataset, which contains detailed records of vehicles’ trajectories, is used for case study. In the case study, the LC risk profiles are categorized into “uphill” shape, “bell” shape, and “downhill” shape. The LC risk profiles with “uphill” shape account for the majority of the LC risk profiles. Besides, we find that the LC process with “uphill” shaped risk profile generally has higher LC risk, and the crash risk between LC car and its preceding cars are more relevant to the LC risk. Those findings are likely due to the LC maneuver with the purpose to overtake the preceding car in the original lane. The risk indicator based on driving safety field theory can measure LC risk more comprehensively, compared to the conventional surrogate measures. The DTW k-means clustering method offers a promising approach to investigate the causation of risky LC maneuver based on the risk profile during an LC process.