Ryuta Terashima

On the Use of Stochastic Driver Behavior Model in Lane Departure Warning

In this paper, we propose a new framework for discriminating the initial maneuver of a lane-crossing event from a driver correction event, which is the primary reason for false warnings of lane departure prediction systems (LDPSs). The proposed algorithm validates the beginning episode of the trajectory of driving signals, i.e., whether it will cause a lane-crossing event, by employing driver behavior models of the directional sequence of piecewise lateral slopes (DSPLS) representing lane-crossing and driver correction events. The framework utilizes only common driving signals and allows the adaptation scheme of driver behavior models to better represent individual driving characteristics. The experimental evaluation shows that the proposed DSPLS framework has a detection error with as low as a 17% equal error rate. Furthermore, the proposed algorithm reduces the false-warning rate of the original lane departure prediction system with less tradeoff for the correct prediction.

Self-Coaching System Based on Recorded Driving Data: Learning From One's Experiences

This paper describes the development of a self-coaching system to improve driving behavior by allowing drivers to review a record of their own driving activity. By employing stochastic driver-behavior modeling, the proposed system is able to detect a wide range of potentially hazardous situations, which conventional event data recorders are not able to capture, including those involving latent risks, of which drivers themselves are unaware. By utilizing these automatically detected hazardous situations, our web-based system offers a user-friendly interface for drivers to navigate and review each hazardous situation in detail (e.g., driving scenes are categorized into different types of hazardous situations and are displayed with corresponding multimodal driving signals). Furthermore, the system provides feedback on each risky driving behavior and suggests how users can safely respond to such situations. The proposed system establishes a cooperative relationship between the driver, the vehicle, and the driving environment, leading to the development of the next generation of safety systems and paving the way for an alternative form of driving education that could further reduce the number of fatal accidents. The systems potential benefits are demonstrated through preliminary extensive evaluation of an on-road experiment, showing that safe-driving behavior can be significantly improved when drivers use the proposed system.

Improving driving behavior by allowing drivers to browse their own recorded driving data

In this paper, we present our on-going efforts to develop a self-diagnosis system to improve safe-driving behavior by allowing drivers to review a record of their own driving activity. By employing stochastic driver-behavior modeling, the proposed system is able to detect various types of potentially hazardous situations, which conventional event data recorders are not able to capture, or which drivers themselves are not aware of such latent risky situations. Utilizing these automatically detected hazardous situations, our web-based system offers a user-friendly interface for drivers to navigate and review each hazardous situation in detail (e.g., driving scenes are displayed with corresponding driving signals). Furthermore, the system provides feedback on each risky driving behavior and suggests how the users can appropriately respond to such situations in a safe manner. The proposed system establishes a cooperative relationship between the driver, the vehicle, and the driving environment in order to develop the next-generation of safety systems and pave the way for an alternative form of driver education that could further reduce the number of fatal accidents. The systems potential benefits are demonstrated through experimental evaluation, showing that safe-driving behavior improved significantly after using the proposed system.

Slow eye movement as a possible predictor of reaction delays to auditory warning alarms in a drowsy state

In recently developed intelligent vehicles, warning alarms are often used to prompt avoidance behaviours from drivers facing imminent hazardous situations. However, when critical reaction delays to auditory stimulation are anticipated, the alarm should be activated earlier to compensate for such delays. It was found that reaction times to an auditory stimulus significantly increased in the presence of slow eye movement (SEM), which is known to occur frequently during the wake–sleep transition. The reaction delay could not be attributed to temporal effects such as fatigue and was invariant regardless of response effectors (finger or foot). Moreover, it was found that applied pedal force decreased immediately after an auditory stimulus interrupted SEM. Consequently, it was concluded that SEM can be a good predictor of reaction delays to auditory warning alarms when drivers are in a drowsy state. Statement of Relevance:The present study demonstrated that simple auditory reaction time significantly increased when SEM emerged. In the design of vehicle safety systems using warning alarms to prompt avoidance behaviours from drivers, such reaction delays during SEM must be taken into account.

Relationship between utterances and enthusiasm in non-task-oriented conversational dialogue

The goal of this paper is to show how to accomplish a more enjoyable and enthusiastic dialogue through the analysis of human-to-human conversational dialogues. We first created a conversational dialogue corpus annotated with two types of tags: one type indicates the particular aspects of the utterance itself, while the other indicates the degree of enthusiasm. We then investigated the relationship between these tags. Our results indicate that affective and cooperative utterances are significant to enthusiastic dialogue.

Generating lane-change trajectories of individual drivers

This paper describes a method to generate vehicle trajectories of lane change paths for individual drivers. Although each driver has a consistent preferance in the lane change behavior, lane-changing time and vehicle trajectory are uncertain due to the presence of surrounding vehicles. To model this uncertainty, we propose a statistical driver model. We assume that a driver plans various vehicle trajectories depending on the surrounding vehicles and then selects a safe and comfortable trajectory. Lane change patterns of each driver are modeled with a hidden Markov model (HMM), which is trained using longitudinal vehicle velocity, lateral vehicle position, and their dynamic features. Vehicle trajectories are generated from the HMM in a maximum likelihood criterion at random lane-changing time and state duration. Experimental results show that vehicle trajectories generated from the HMM included a similar trajectory to that of a target driver.

Toward human-like lane following behavior in urban environment with a learning-based behavior-induction potential map

In order to achieve harmony in the mixed traffic, it is crucial to have autonomous vehicles behave like human drivers. This work addresses a vision-based approach toward human-like lane following behavior in complex urban environment. At first, a deep architecture is adopted to generate a set of vehicle hypotheses. Subsequently, a hybrid merging procedure is performed to jointly output the final detection results based on both the image evidence and the statistical support of vehicle hypotheses. After that, the detected vehicles are classified into six categories by Bayesian Network, i.e., leader vehicle, parking vehicle, tail-end vehicle, exiting vehicle, merging vehicle and other vehicle. With this information, a learning-based instance-level behavior-induction potential map is constructed to generate a safe as well as reasonable local path for following a predefined lane-level route. Experimental results in various typical but challenging urban traffic scenes substantiated the effectiveness of the proposed approach.

Discriminating subsequent lane-crossing and driver-correction events using trajectory models of lateral slopes

In this paper, we propose a new framework to discriminate the initial maneuver of lane-crossing event from driver-correction event, which is the primary reason for false warnings of the Lane Departure Prediction Systems. The proposed algorithm validates the beginning episode of the trajectory of driving signals whether it will cause a Lane Crossing Event or not, by employing driver behavior models of Directional Sequence of Piecewise Lateral Slopes (DSPLS) representing lane-crossing and driver-correction events. The framework utilizes only common driving signals, and allows adaptation scheme of driver behavior models to better represent individual driving characteristics. The experimental evaluation shows that the proposed DSPLS has detection error as low as 17% Equal Error Rate. Furthermore, the proposed algorithm reduces the False Alarm rate of the original Lane Departure Prediction System from 38.8% to 6.1% with less trade-off for the prediction accuracy.