Driver behavior quantitative models: Identification and classification of variables

Driver profiling – Data-based identification of driver behavior dimensions and affecting driver characteristics for multi-agent traffic simulation

Multi-scale driver behavior modeling based on deep spatial-temporal representation for intelligent vehicles

Inverse Reinforcement Learning Based Stochastic Driver Behavior Learning

Objective Before market introduction, the safety of highly automated driving systems needs to be assessed prospectively. BMW has developed a holistic approach for the assessment of the traffic safety impact by these systems in which stochastic traffic simulations play a significant role. A driver behavior model which represents realistic driver behavior ranging from performance in non-critical everyday driving toward performance in critical situations is key for this approach. To ensure trustworthy results, validation of the driver model is needed. The paper aims at demonstrating that the presented driver model acts realistically in different critical real-world traffic scenarios. Methods BMW has been developing the Stochastic Cognitive Model (SCM) which models cognitive processes in traffic situations. These processes range from information acquisition by gaze behavior, mental representation of the environment, recognition of situations from the visual information and reaction to the situation. The driver model combines these cognitive processes with stochastic driver parameters to obtain a variation in driver behavior in simulations. Especially visual attention modeling is key to realistic traffic interactions in simulations as this is the input for the sequential cognitive processes, i.e., the recognition of situations and the reaction to the situation. Modeling of driver’s gaze behavior with SCM is thus shown in this paper. Results SCM is applied in three critical real-world traffic scenarios in which gaze behavior, brake reaction times and time-to-collisions are evaluated and compared to the real-world data. Due to the stochastic approach not only a single SCM agent but a collective of virtual SCM test drivers is assessed. Results show that SCM is capable to simulate the influence of visual inattention on collision risk. Conclusion Realistic driver behavior in simulations can be achieved by using SCM. Especially in the presented critical scenarios SCM is able to represent real-world driving behavior which is determined particularly by its gaze behavior and subsequent reaction. Driving performance varies over different SCM agents which mean that different driving behavior can be simulated with SCM as well. However, the investigation in this paper included only three real-world cases. Therefore, further critical, and additionally non-critical scenarios need to be investigated in the future.

This paper describes a practicing method for enhancing driver performance, which it bases on cognitive driver behavior model of ACT-R--a dominant theory of human cognitive architecture. First, the paper elaborates the idea of driver behavior modeling in cognitive architecture. And then, it dedicates the implementation of driver's practice courses based on the cognitive architecture model. Finally, by comparing the experiments back and forth of the practice, the results indicate that the practice based on driver cognitive behavior model can improve the driver performances positively. The experiences of the practice also implied that both practice method is indeed an approach worthy of pursuit for enhancing driver performance at driving emergencies and driver behavior modeling in cognitive architecture is a substantial tool for practical applications in predicting and instructing driver behaviors.

Modeling driver behavior in dilemma zones: A discrete/continuous formulation with selectivity bias corrections

Risky driving is a leading cause of traffic accidents all over the world. Major factors contributing to risky driving include driver distraction (e.g. smart-phone usage) and an onset of driver drowsiness. As a result, improving road-safety requires modeling and detecting in-vehicle conditions indicative of risky driver behavior. Previous works towards driver behavior modeling and classification possess limitations such as increased expenditure and/or additional external infrastructure requirements. In this paper, we propose a novel driver behavior detection framework that at its core makes use of in-vehicle Wi-Fi signals. The main premise of the proposed framework is that risky behavior induces specific differentiable patterns in received WiFi signals - patterns that are then exploited to build an efficient classification system. More specifically, we classify drowsy and inattentive driving into four main gestures that reflect unsafe driving. These gestures include (a) Yawning, (b) Head Jerks, (c) Sideways motion, and (d) Smart-phone usage. Channel State Information (CSI) is used to determine the driver's gesture which is further used for behavior modeling. A number of low computational features are used to classify among different gestures. Experiments are performed in a real in-vehicle environment using software-defined radios. Using data collected from these experiments, a simple ensemble classifier is implemented which is shown to achieve an average accuracy of 88.64%.

For tackling with the autonomous driving tasks such as fast overtaking, traditional rule-based methods are inflexible and lack abilities of adapting to rapidly changing environments. However, human drivers performed well and have accumulated a large amount of driving behavior data which can be used as a reliable basis for learning intelligent driving behavior in these environments. The autonomous vehicle can gradually learn to obtain human-like behavior policies for complex driving tasks through imitation learning (IL). In this paper, a Bagging Gaussian Process Regression (Bagging GPR) method is proposed to imitate driver behaviors for dynamic complex driving tasks, which combined the Bagging with the Gaussian Process Regression (GPR). Human driver data are collected through the simulation platform Prescan, and different driver behavior models are trained and verified by collected data. Experiments show that compared with Multi-layer BP, ELM, Regression Tree Ensemble, SVR and GPR, the proposed method can further reduce state-action imitating errors and achieve more robust performance of the driver behavior learning.

Modeling driver behavior provides several advantages in the automotive industry, including prediction of electric vehicle energy consumption. Studies have shown that aggressive driving can consume up to 30% more energy than moderate driving, in certain driving scenarios. Machine learning methods are widely used for driver behavior classification, which, however, may yield some challenges such as sequence modeling on long time windows and lack of labeled data due to expensive annotation. To address the first challenge, passive learning of driver behavior, we investigate non-recurrent architectures such as self-attention models and convolutional neural networks with joint recurrence plots (JRP), and compare them with recurrent models. We find that self-attention models yield good performance, while JRP does not exhibit any significant improvement. However, with the window lengths of 5 and 10 seconds used in our study, none of the non-recurrent models outperform the recurrent models. To address the second challenge, we investigate several active learning methods with different informativeness measures. We evaluate uncertainty sampling, as well as more advanced methods, such as query by committee and active deep dropout. Our experiments demonstrate that some active sampling techniques can outperform random sampling, and therefore decrease the effort needed for annotation.

In order to enhance the traffic road safety, applying the artificial intelligence theory and the technology in road traffic control system, that is intelligent driving vehicle, may effectively decrease traffic accidents, which are caused by drivers' neglect, fatigue and so on. This article is based on cognitive science to analyze driving behaviors. First, we estimated the Information Processing Model of Intelligent Vehicle. Second, based on prototype pattern recognition theory, we also built Pattern Recognition Model of Intelligent Driving Behavior, which provided the advantageous basis for the further research on intelligent vehicle. Third, virtual scene simulation system was established by using Creator and Vega Prime. Finally, according to test data, we investigated the features of speed and latitudinal distance in both artificial and intelligent U-Turn driving behavior. Our results describe that the intelligent vehicle does have the ability of cognizance, and it can make correct reactions corresponding to the driving environment, but its intelligence still needs improving.

The present study proposes a decision-making model based on different models of driver behavior, aiming to ensure integration between road safety and crash reduction based on an examination of speed limitations under weather conditions. The present study investigated differences in road safety attitude, driver behavior, and weather conditions I-69 in Flint, Genesee County, Michigan, using the fuzzy logic approach. A questionnaire-based survey was conducted among a sample of Singaporean (n = 100) professional drivers. Safety level was assessed in relation to speed limits to determine whether the proposed speed limit contributed to a risky or safe situation. The experimental results show that the speed limits investigated on different roads/in different weather were based on the participants’ responses. The participants could increase or keep their current speed limit or reduce their speed limit a little or significantly. The study results were used to determine the speed limits needed on different roads/in different weather to reduce the number of crashes and to implement safe driving conditions based on the weather. Changing the speed limit from 80 mph to 70 mph reduced the number of crashes occurring under wet road conditions. According to the results of the fuzzy logic study algorithm, a driver’s emotions can predict outputs. For this study, the fuzzy logic algorithm evaluated drivers’ emotions according to the relation between the weather/road condition and the speed limit. The fuzzy logic would contribute to assessing a powerful feature of human control. The fuzzy logic algorithm can explain smooth relationships between the input and output. The input–output relationship estimated by fuzzy logic was used to understand differences in drivers’ feelings in varying road/weather conditions at different speed limits.

Understanding of mechanisms and factors responsible for the driver behavior on the road is the subject of ongoing interest to transportation psychologists, occupational doctors and engineers. Models of driver behavior are a key point for the understanding the mechanisms and factors which may cause limitations to the optimal functioning on the road. They also systematize knowledge about the factors responsible for the behavior of the driver and thus constitute a starting point for formulating empirical or diagnostic hypotheses. The aim of this study is to present models of driver behavior from the descriptive and functional perspectives. Med Pr 2017;68(3):401-411.

The use of driver behavior has been considered a complex way to solve road safety complications. Car drivers are usually involved in various risky driving factors which lead to accidents where people are fatally or seriously injured. The present study aims to dissect and rank the significant driver behavior factors related to road safety by applying an integrated multi-criteria decision-making (MCDM) model, which is structured as a hierarchy with at least one 5 × 5 (or bigger) pairwise comparison matrix (PCM). A real-world, complex decision-making problem was selected to evaluate the possible application of the proposed model (driver behavior preferences related to road safety problems). The application of the analytic hierarchy process (AHP) alone, by precluding layman participants, might cause a loss of reliable information in the case of the decision-making systems with big PCMs. Evading this tricky issue, we used the Best Worst Method (BWM) to make the layman’s evaluator task easier and timesaving. Therefore, the AHP-BWM model was found to be a suitable integration to evaluate risky driver behavior factors within a designed three-level hierarchical structure. The model results found the most significant driver behavior factors that influence road safety for each level, based on evaluator responses on the driver behavior questionnaire (DBQ). Moreover, the output vector of weights in the integrated model is more consistent, with results for 5 × 5 PCMs or bigger. The proposed AHP-BWM model can be used for PCMs with scientific data organized by traditional means.

From driver assistance in manual mode to takeover requests in highly automated mode, knowing the state of driver (e.g. sleeping, distracted, attentive) is critical for safe, comfortable and stress-free driving. Since driving is a visually demanding task, driver's gaze is especially important in estimating the state of driver; it has the potential to derive what the driver has attended to or is attending to and predict future actions. We developed a machine vision based framework to model driver's behavior by representing the gave dynamics over a time period using gaze fixations and transition frequencies. As a use case, we explore the driver's gaze patterns during maneuvers executed in freeway driving, namely, left lane change maneuver, right lane change maneuver and lane keep. It is shown that mapping gaze dynamics to gaze fixations and transition frequencies leads to recurring patterns based on driver activities. Furthermore, using data from on-road driving, we show that modeling these patterns show predictive powers in on-road driving maneuver detection around a few hundred milliseconds a priori.

As computing technology advances, the ability to integrate a wider range of personal services for in-vehicle environments increases. While these advances offer a diverse range of entertainment and information access opportunities, they generally are introduced into the vehicle with limited understanding of their impact to driver distraction and cognitive stress load. As the diversity of speech, video, biometric, and vehicle signals increases, improved corpora and system formulation are needed. In this study, we consider recent advances for in-vehicle human-machine systems for route navigation, noise suppression for robust speech recognition, and driver behavior modeling. Multi-microphone array processing is developed for noise suppression for hands-free communications as well as improved automatic speech recognition for route dialog interaction. Next, advances in modeling driver behavior are considered in the UTDrive project, which is focused on advancing smart vehicle technologies for improved safety while driving. Finally, a general discussion considers next generation advances for in-vehicle environments which sense driver cognitive stress/distraction to adapt interactive systems for improved safety.