A Review of UTDrive Studies: Learning Driver Behavior From Naturalistic Driving Data

Abstract

Intelligent vehicles and Advanced Driver Assistance Systems (ADAS) are being developed rapidly over the past few years. Many applications such as vehicle localization, environment perception, and path planning have shown promising potentialities. While there is great interest in migrating from complete human-controlled vehicles towards fully autonomous vehicles, it is natural that researchers spending more effort trying to understand the interaction between vehicles with various levels of automation in large-scale traffic scenarios. Next-generation vehicles are expected to have the capacity of evaluating driver conditions, vehicle capabilities, surrounding traffic contexts, and take advantage of such knowledge to ensure safe and efficient driving. Three general research questions are raised to achieve this goal, which are (i) how can we acquire sufficient data, (ii) how to evaluate and understand driving behavior, and (iii) how to deliver information effectively to drivers. In this article, we present a review of previous studies from the UTDrive project attempts to answer above questions.

Driver Profile and Driving Pattern Recognition for Road Safety Assessment: Main Challenges and Future Directions

“…Initial insights on how it can be defined can be found in [66]. As also stated in [67], [68], it is important to keep improving the safety aspects of intelligent transportation systems as we move forward into the next generation of intelligent vehicles.…”

Driver Visual Attention Estimation Using Head Pose and Eye Appearance Information

“…Driving is a challenging task requiring a high level of vigilance from the driver. Therefore, many researchers have studied the factors associated with driver behaviors and their effects on vehicle operation [32]. In their review of human behavior in an intelligent vehicle environment, Ohn-Bar and Trivedi [33] noted that multiple studies have analyzed drivers in terms of their intentions, behaviors, and actions for maneuvering control.…”

VTD-Visual and Tactile Database for Driver State and Behavior Perception

“…The state of a driver can be indirectly inferred by observing and evaluating their behaviors and measuring relevant physiological indices. Modeling and understanding the driver's state through driving behaviors is crucial to ensuring safety and assisted driving [38]. To improve driving safety, future intelligent vehicles should be capable of autonomously assessing the driver's driving behavior and ability with onboard sensors and the vehicle's operation information.…”

“…Natural driving data is a vital resource for learning and understanding driving behaviors [38]. Most datasets in Table 1 and Table 2 are dedicated exclusively to driving behavior learning.…”