Identification of anomalies in lane change behavior using one-class SVM

A major aspect in the development of advanced driving assistance systems (ADASs) is the research in developing human driving behavior prediction and recognition models. Recent contributions focus on developing these models for estimating different driving behaviors like lane or speed change. Thus, the models are incorporated into the ADAS to generate warnings and hints for safe maneuvers. Driving behavior recognition and prediction models are generally developed based on machine learning (ML) algorithms and are proven to generate accurate estimations. Previous review research contributions tend to focus on ML-based models for the prediction and recognition of speed change, trajectory change, and even driving styles. Due to high number of driving errors occurring during a lane change, a state-of-art review of different ML-based models for lane-changing behavior prediction and recognition is helpful to present a comparison between different models in terms of structure, influencing input variables, and performance. This enables the integration of the most efficient model for the development of ADASs to avoid accidents during a lane change. First, definitions and terms related to the model’s task and evaluation metrics used to evaluate the model’s performance are described to improve the readability. Then, the different input variables of the models affecting the lane-changing behaviors are presented. Next, a review of the models developed based on well-known approaches, such as artificial neural network (ANN), hidden Markov model (HMM), and support vector machine (SVM), using different input variables is given. Three lane-changing behaviors are focused on here: left/right lane change and lane keeping. The advantages and disadvantages of the different ML models with a comparison are summarized as well. Finally, the improvements required in the future are discussed.

Recent research on the prediction of driver’s lane-changing behaviour requires vehicle surrounding information, as it is believed that driver’s decision on lane changing is made consciously based on those information. However, current research has shown that the usage of such surrounding information leads to high false alarm rate of lane-changing predict system [1]. Therefore this paper contributes to developing a lane-changing prediction method which uses vehicle state information only. From the perspective of the observer’s daily experience, this paper selects vehicle’s lateral trajectory and the spectrum of its lateral trajectory as input to predict drivers’ lane-changing intention. A Direction Convolutional LSTM (DCLSTM) network has been developed to predict drivers’ lane-changing behaviours. Recent pure LSTM methods proposed by researchers provide high accuracy when predicting the generation of drivers’ lane-changing intentions, but they have relatively low accuracy in predicting drivers’ lane-changing direction. DCLSTM retains pure LSTM network’s high accuracy in the prediction of drivers’ lane-changing intentions, while its prediction of drivers’ lane-changing directions is also accurate. All the training and testing data are extracted from the NGSIM dataset.

Lane changing is one important aspect of vehicle maneuvers that has significant impacts on freeway operation. Most of the previous research on lane changing has focused on the microscopic modeling of lane change movements. Very few studies have investigated lane-changing behavior along high-occupancy vehicle (HOV) facilities, especially in the context of comparing different access types. This paper describes work that extracted lane change data with high resolution in both time and space from videos and investigated lane-changing behavior on freeways with different types of HOV access configurations. Furthermore, the extracted lane change data were correlated with lane-by-lane flow and occupancy data from the California Freeway Performance Measurement System. Compared with continuous-access HOV facilities, limited-access HOV facilities were found to have a higher number of lane changes per unit distance and a shorter time gap when the subject vehicle moved out of the HOV lane. Also, most of the lane changes on limited-access HOV facilities occurred within the first half of ingress–egress areas. The insights provided by these results on lane-changing maneuvers along HOV facilities can be used to support traffic operation analyses, calibrate driver behavioral logic in traffic simulation models, and inform the design of lane configurations and access control measures for managed lanes.

More than 90% of traffic accidents are caused by driver behavior, with lane change behavior being a major contributor. Recently, driving assistance systems are being introduced on vehicles to reduce traffic accidents, and a reliable vehicle lane change collision detection system is a key component of these systems. Besides, the foundation of the vehicle lane change detection system is the effective vehicle lane change detection model. In this paper, based on the support vector machine, we propose a model for detecting driver lane change maneuvers and take into account the real-time vehicle dynamic features transmitted via Vehicle to X (V2X) Communication. The accuracy is ideal for lane keep and lane change situations, and it is also robust for zigzag driving situations, according to tests conducted using the NGSIM real traffic dataset. The detection accuracy for left and right lane change maneuvers is 97.5% and 99.09%, respectively, while the false alarm rate is 8.56%. Additionally, the average advance detection time is 1.7 s, which is suitable for actual driving application scenarios.

Along with the rapid development of autonomous driving technology, autonomous vehicles are showing a trend of practicality and popularity. Autonomous vehicles perceive environmental information through sensors to provide a basis for the decision making of vehicles. Based on this, this paper investigates the lane-changing decision-making behavior of autonomous vehicles. First, the similarity between autonomous vehicles and moving molecules is sought based on a system-similarity analysis. The microscopic lane-changing behavior of vehicles is analyzed by the molecular-dynamics theory. Based on the objective quantification of the lane-changing intention, the interaction potential is further introduced to establish the molecular-dynamics lane-changing model. Second, the relationship between the lane-changing initial time and lane-changing completed time, and the dynamic influencing factors of the lane changing, were systematically analyzed to explore the influence of the microscopic lane-changing behavior on the macroscopic traffic flow. Finally, the SL2015 lane-changing model was compared with the molecular-dynamics lane-changing model using the SUMO platform. SUMO is an open-source and multimodal traffic experimental platform that can realize and evaluate traffic research. The results show that the speed fluctuation of autonomous vehicles under the molecular-dynamics lane-changing model was reduced by 15.45%, and the number of passed vehicles was increased by 5.93%, on average, which means that it has better safety, stability, and efficiency. The molecular-dynamics lane-changing model of autonomous vehicles takes into account the dynamic factors in the traffic scene, and it reasonably shows the characteristics of the lane-changing behavior for autonomous vehicles.

Lane changing maneuvers could have a substantial influence on traffic flow characteristics as a result of their interfering effect on surrounding vehicles. The interference effect of lane changing is more pronounced when heavy vehicles change lanes compared to when passenger cars undertake the same maneuver. This is due to the physical effects that the heavy vehicles impose on surrounding traffic. This paper investigates and compares the traffic flow characteristics which influence the lane changing behavior of heavy vehicle and passenger car drivers on freeways under heavy traffic conditions. A trajectory data set comprising 28 heavy vehicle and 28 passenger car lane changing maneuvers is analyzed in this study. The results suggest a substantial difference exists between the traffic characteristics influencing the lane changing behavior of heavy vehicle and passenger car drivers. Heavy vehicles' speed changes little during a lane changing maneuver. Heavy vehicle drivers mainly move into the slower lanes to prevent obstructing the fast moving vehicles which approach from the rear. However, passenger car drivers increase their speed according to the speeds of the lead and lag vehicles in the target lane. They more commonly move into the faster lanes to gain speed advantages.

Purpose Feature selection is crucial for machine learning to recognize lane-change (LC) maneuver as there exist a large number of feature candidates. Blindly using feature could take up large storage and excessive computation time, while insufficient feature selection would cause poor performance. Selecting high contributive features to classify LC and lane-keep behavior is effective for maneuver recognition. This paper aims to propose a feature selection method from a statistical view based on an analysis from naturalistic driving data. Design/methodology/approach In total, 1,375 LC cases are analyzed. To comprehensively select features, the authors extract the feature candidates from both time and frequency domains with various LC scenarios segmented by an occupancy schedule grid. Then the effect size (Cohen’s d) and p-value of every feature are computed to assess their contribution for each scenario. Findings It has been found that the common lateral features, e.g. yaw rate, lateral acceleration and time-to-lane crossing, are not strong features for recognition of LC maneuver as empirical knowledge. Finally, cross-validation tests are conducted to evaluate model performance using metrics of receiver operating characteristic. Experimental results show that the selected features can achieve better recognition performance than using all the features without purification. Originality/value In this paper, the authors investigate the contributions of each feature from the perspective of statistics based on big naturalistic driving data. The aim is to comprehensively figure out different types of features in LC maneuvers and select the most contributive features over various LC scenarios.

Driving intention recognition is an important aspect of Advanced Driving Assistance Systems (ADAS) for giving drivers suggestions to maneuver safely. The intention recognition algorithms in ADAS are often developed using Machine Learning-based models. The model's input, such as environmental (ENV) and eye-tracking (ET) features affect the model's recognition performance. In this contribution, an Artificial Neural Network-based state machine is used for lane changing intention recognition. Three lane changing behaviors are considered, left/right lane change and lane keeping. Here, data consisting of ENV and ET information are collected using a driving simulator and eye-tracker. The aim is to investigate the effect of different feature types on the model's intention recognition performance. First, a 10-cross validation is performed to evaluate the model's performance, using only ENV and both ENV and ET features. The validation results show that the model with only ENV features performs better with respect to different metrics. Thus in the test, only ENV features are used to evaluate the performance. Accuracy values of higher than 80 % are achieved. Furthermore, the recognition performance of the model is compared with other Machine Learning models. The approach introduced outperforms other models in most metrics.

Enhancing lane changing trajectory prediction on highways: A heuristic attention-based encoder-decoder model

Key findings are discussed regarding characteristics of lane-changing behavior based on observations of an urban street network. An in-depth exploration of observed lane-changing behavior and its modeling were conducted using vehicle trajectory data extracted from video observations using VEVID, a software package developed by the authors, integrated with a video-capture system. As a result, rules for modeling lane-changing behavior are proposed with respect to various types of lane changes. A lane-changing model consists of three components: a decision model, a condition model, and a maneuver model. Drivers’ decisions to change lanes depend on travel maneuver plans, the current lane type (i.e., the relationship between the current lane and the driver’s planned route), and traffic conditions in the current and adjacent lanes. A lane-changing condition model is the description of acceptable conditions for different types of lane changes. A lane-changing maneuver model describes a vehicle’s speed and duration when a certain type of lane change occurs. All of these models are established in a heuristic structure.

The driver lane change process is divided into two parts: lane change awareness formation and behavior implementation. Considering that the intrinsic factors of assessing the status and ability of drivers and the external traffic environment factors will affect the entire lane changing process independently rather than being independent and non-interfering, this paper chooses network AHP to analyze and identify the lane changing behaviors. The result shows that the accuracy of this method can reach 92.37% and the effect is better.

Objective: The aim of this study is to examine the effect of traffic density on drivers’ lane change and overtaking maneuvers. The differences between drivers’ left and right lane changing/overtaking maneuvers were also investigated.Method: A driving simulator experiment was conducted and 24 participants took part in this experiment. Based on the driving simulation data, lane change frequency, time duration, average speed, and acceleration were extracted as key variables of lane change maneuvers; overtaking frequency, overtaking duration, initial overtaking distance and headway, instantaneous speed, and acceleration before overtaking were analyzed as the key overtaking variables. One-way repeated measures analysis of variance (ANOVA), the Friedman test, and the Wilcoxon signed rank test were adopted for hypothesis tests with a significance level of .05. Further pairwise comparisons were performed with a Bonferroni correction for multiple comparisons.Results: Some significant differences in lane change and overtake behaviors were observed among different traffic densities: (1) both lane change and overtaking frequencies significantly increase with traffic density; (2) the average lane change acceleration and instantaneous overtaking acceleration significantly increase with traffic density; (3) as the traffic density increases, the initial overtaking distance and headway decrease. As for the effect of the directions of maneuvers, the (1) time duration of lane change and overtaking from the right side was significantly shorter than that from the left side; (2) right initial overtaking distance/headway was smaller than that of the left side; (3) right instantaneous overtaking acceleration was significantly higher than the left instantaneous acceleration.Conclusions: The results showed that as traffic density increases, drivers’ lane changing and overtaking intentions are enhanced. Both initial overtaking distance and headway decrease with traffic density, which might influence road safety. In addition, drivers do not show a preference on the directions of lane change or overtaking according to frequency. However, drivers tend to be more decisive and reckless when overtaking on the right because of a smaller distance/headway before overtaking, higher instantaneous acceleration, and a more restricted field of view compared with overtaking on the left.

The lane change maneuver is one of the most common driving behaviors in highways or rural roads. Each driver usually conducts at least one lane change maneuver during his trip. Therefore, it is chosen as the object behavior in this study and novel adaptive neuro-fuzzy inference models are proposed for this behavior. These models are able to simulate and predict the future behavior of a Driver-Vehicle-Unit in the lane change maneuver for various time delays. Using the field data, the outputs of the models are validated and compared with the real traffic data. The simulation results show that these models have a very close compatibility with the field data and reflect the situation of the traffic flow in a more realistic way.

Key feature selection and risk prediction for lane-changing behaviors based on vehicles’ trajectory data

According to the previous research, lane-changes are a major cause of serious traffic accidents. Thus, it is essential to build an efficient prediction algorithm for vehicles lane change on Advanced Driving Assistance System (ADAS) to ensure a safe and comfort driving for host vehicle. At present, many methods for lane change prediction have been proposed. However, most of them require a lot of data training to have a good prediction performance. Considering the practical applicability of the prediction algorithm in ADAS, this paper proposes a prediction method by probabilistic modelling. This method combines two aspects lane change evidence. On the one hand, model the lane change probability caused by the target vehicle's driving context. On the other hand, model the lane change probability reflected by vehicle posture in the road. The evaluation of the whole algorithms was done by using simulation data and real lane change data. The results show that the algorithm performs well in predicting accuracy and reducing false alarms.