A lane change prediction algorithm based on probabilistic modeling

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.

Advanced driver assistance systems are required to detect latent hazards posed by surrounding vehicles and generate an appropriate response to enhance safety. Lane changes constitute potentially risky maneuvers, as drivers involved encounter latent hazards due to surrounding vehicles. A careful study of lane change behavior is therefore essential in identifying potential abnormalities that may lead to various hazards, during the process of a lane change. In this study, an anomaly detection technique is used to compare snapshots of normal and dangerous lane change maneuvers, to identify the abnormal instances. A one-class support vector machine is used and tested for novelty identification of naturalistic driving study data. The results show that the technique is able to detect dangerous lane changes with high accuracy. In addition, results suggest that dangerous behavior could occur before, after or during a lane change maneuver.

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.

Vehicle lane changing is one of the most important topics in autonomous driving and is the behavior most likely to cause vehicle accidents. In order to optimize the performance of vehicle lane change by controlling the speed of the vehicle, which makes the lane change safer, more efficient, and more eco-friendly, a causal inference-based speed control framework is proposed in this study. First, variables affecting the lane change efficiency are selected and their treatment effects are obtained by conducting causal effect analysis and causal refutation analysis. Second, the conditional average treatment effect is estimated by taking the safety and eco-friendly requirements into consideration and applying the double machine learning version causal forest model. Finally, a controller is built, and grid search is used to optimize lane change decision-making. By conducting numerical experiments, the average lane change duration decreased by 5.9% and average velocity increased from 7.165 m/s to 7.791 m/s. The results show that the framework has good performance on improving the efficiency and environmental friendliness of a lane change process while ensuring safety. The proposed framework provides a new approach to speed control for discretionary lane-changing behavior. The approach can be well adapted to a vehicle-to-vehicle communication environment and is expected to be applied to vehicle-assisted driving systems in the future.

Driver Monitoring and Warning System for Active Safety Enhancement

High accuracy of lane changing prediction is beneficial to driver assistant system and fully autonomous cars. This paper proposes a lane changing prediction model based on combined method of Supporting Vector Machine (SVM) and Artificial Neural Network (ANN) at highway lane drops. The vehicle trajectory data are from Next Generation Simulation (NGSIM) data set on U.S. Highway 101 and Interstate 80. The SVM and ANN classifiers are adopted to predict the feasibility and suitability to change lane under certain environmental conditions. The environment data under consideration include speed difference, vehicle gap, and the positions. Three different classifiers to predict the lane changing are compared in this paper. The best performance is the proposed combined model with 94% accuracy for non-merge behavior and 78% accuracy for merge behavior, demonstrating the effectiveness of the proposed method and superior performance compared to other methods.

Expressway lane change strategy of autonomous driving based on prior knowledge and data-driven

With the rapid development of intelligent vehicles and Advanced Driver-Assistance Systems (ADAS), a new trend is that mixed levels of human driver engagements will be involved in the transportation system. Therefore, necessary visual guidance for drivers is vitally important under this situation to prevent potential risks. To advance the development of visual guidance systems, we introduce a novel vision-cloud data fusion methodology, integrating camera image and Digital Twin information from the cloud to help intelligent vehicles make better decisions. Target vehicle bounding box is drawn and matched with the help of the object detector (running on the ego-vehicle) and position information (received from the cloud). The best matching result, a 79.2% accuracy under 0.7 intersection over union threshold, is obtained with depth images served as an additional feature source. A case study on lane change prediction is conducted to show the effectiveness of the proposed data fusion methodology. In the case study, a multi-layer perceptron algorithm is proposed with modified lane change prediction approaches. Human-in-the-loop simulation results obtained from the Unity game engine reveal that the proposed model can improve highway driving performance significantly in terms of safety, comfort, and environmental sustainability.

Nowadays, Advanced Driver Assistance Systems (ADAS) play important roles in improving the safety of driving. ADASs along with new safety standards are now essential to improve the safety of automated driving. These standards differ from the safety standards in other industries because an autonomous vehicle rides in a very intricate stochastic environment where many details should be considered to maintain the safety. From one point of view, autonomous car failures are divided into two categories: hardware and software failures. According to the literature, if the reason of fault belongs to hardware, the troubleshooting will relatively be easier than software failure. In other words, if the fault is the subset of software, that would be more challenging task to detect potential fault and recover from the failure. In this paper, we propose a new approach to detect the software failures, which may be unpredictable using a typical safety protocol. A predictive machine learning method is developed to improve decision making process in order to avert the potential accidents occurred by software defects. The proposed method evaluates detected obstacle in the span of a specified number of frames to discern whether objects are detected correctly or not. Hence, it provides extra time to choose the suitable action before it reaches the danger, which includes lane changes, cut-in maneuvers, stopping the car, accelerating the car, slowing down, and allowing vehicles to pass. Results show that the new approach improve the safety by increasing the precision of failure detections.

Physiological signals are immediate and sensitive to neurological changes resulting from the mental workload induced by various driving environments and are considered a quantifying tool for understanding the association between neurological outcomes and driving cognitive workloads. Neurological assessment, outside of a highly-equipped clinical setting, requires an ambulatory electroencephalography (EEG) headset. This study aimed to quantify neurological biomarkers during a resting state and two different scenarios of driving states in a virtual driving environment. We investigated the neurological responses of seventeen healthy male drivers. EEG data were measured in an initial resting state, city-roadways driving state, and expressway driving state using a portable EEG headset in a driving simulator. During the experiment, the participants drove while experiencing cognitive workloads due to various driving environments, such as road traffic conditions, lane changes of surrounding vehicles, the speed limit, etc. The power of the beta and gamma bands decreased, and the power of the delta waves, theta, and frontal theta asymmetry increased in the driving state relative to the resting state. Delta-alpha ratio (DAR) and delta-theta ratio (DTR) showed a strong correlation with a resting state, city-roadways driving state, and expressway driving state. Binary machine-learning (ML) classification models showed a near-perfect accuracy between the resting state and driving state. Moderate classification performances were observed between the resting state, city-roadways state, and expressway state in multi-class classification. An EEG-based neurological state prediction approach may be utilized in an advanced driver-assistance system (ADAS).

In the automatic driving system, the external environment of the vehicle is perceived, in fact, there is also a perception sensor that has been silently dedicated in the system, that is, the positioning module. This paper explores the role of SLAM (Simultaneous Localization and Mapping) technology in autonomous vehicles, particularly in automatic lane change behavior prediction and environment perception. It emphasizes the limitations of traditional methods and the advantages of SLAM, especially visual SLAM, for accurate positioning and mapping. The discussion covers SLAM fundamentals, challenges, and the significance of visual SLAM's higher perception ability. Case studies on Waymo and Tesla illustrate the application of visual SLAM in achieving high-precision navigation and lane change prediction. The paper concludes by highlighting future research directions to enhance the intelligence and adaptability of automated lane change systems through advancements in AI and sensor technology, alongside optimizing SLAM algorithms for reliable driving in various scenarios.

With the development of intelligent connected vehicle and artificial intelligence technologies, mixed traffic scenarios where autonomous and human-driven vehicles coexist are becoming increasingly common. Autonomous vehicles need to accurately predict the lane change behavior of preceding vehicles to ensure safety. However, lane change behavior of human-driven vehicles is influenced by both environmental factors and driver preferences, which increases its uncertainty and makes prediction more difficult. To address this challenge, this paper focuses on the mining of driving preferences and the prediction of lane change behavior. We clarify the definition of driving preference and its relationship with driving style and construct a representation of driving operations based on vehicle dynamics parameters and statistical features. A preference feature extractor based on the SimCLR contrastive learning framework is designed to capture high-dimensional driving preference features through unsupervised learning, effectively distinguishing between aggressive, normal, and conservative driving styles. Furthermore, a dual-branch lane change prediction model is proposed, which fuses explicit temporal features of vehicle states with implicit driving preference features, enabling efficient integration of multi-source information. Experimental results on the HighD dataset show that the proposed model significantly outperforms traditional models such as Transformer and LSTM in lane change prediction accuracy, providing technical support for improving the safety and human-likeness of autonomous driving decision-making.

With the development of vehicle-to-vehicle (V2V) communication, it is possible to share information among multiple vehicles. However, the existing research on automated lane changes concentrates only on the single-vehicle lane change with self-detective information. Cooperative lane changes are still a new area with more complicated scenarios and can improve safety and lane-change efficiency. Therefore, a multi-vehicle cooperative automated lane-change maneuver based on V2V communication for scenarios of eight vehicles on three lanes was proposed. In these scenarios, same-direction and intersectant-direction cooperative lane changes were defined. The vehicle that made the cooperative decision obtained the information of surrounding vehicles that were used to cooperatively plan the trajectories, which was called cooperative trajectory planning. The cooperative safety spacing model was proposed to guarantee and improve the safety of all vehicles, and it essentially developed constraints for the trajectory-planning task. Trajectory planning was treated as an optimization problem with the objective of maximizing safety, comfort, and lane-change efficiency under the constraints of vehicle dynamics and the aforementioned safety spacing model. Trajectory tracking based on a model predictive control method was designed to minimize tracking errors and control increments. Finally, to verify the validity of the proposed maneuver, an integrated simulation platform combining MATLAB/Simulink with CarSim was established. Moreover, a hardware-in-the-loop test bench was performed for further verification. The results indicated that the proposed multi-vehicle cooperative automated lane-change maneuver can achieve lane changes of multiple vehicles and increase lane-change efficiency while guaranteeing safety and comfort.

Advanced Driver Assistance systems (ADAS) have seen increasing popularity due to their importance in automotive driver safety and autonomous driving. These systems analyze data from several sensors mounted on the vehicle to detect lanes, obstacles and traffic conditions to ensure safe driving. Lane markings on road with different color and structure provide information on safe drive zone and other traffic restrictions on road. Typical ADAS solutions depend on vision based sensors for lane detection. Here we propose an efficient algorithm for detecting type and color of the lane marks as this information plays critical role in taking the decision for safety features such as lane change and lane keep assist. Our algorithm is pluggable to any state-of-art lane detection algorithm and provides lane type and color for straight, curvy roads. The proposed method is tested on various challenging scenarios and results are promising.