Search Results

With the embedded sensors – typically Inertial Measurement Units (IMU) and GPS, the smartphone could be leveraged as a low-cost sensing platform for estimating vehicle dynamics. However, the orientation and relative movement of the smartphone inside the vehicle yields the main challenge for platform deployment. This study proposes a solution of converting the smartphone-referenced IMU readings into vehicle-referenced accelerations, which allows free-positioned smartphone for the in-vehicle dynamics sensing. The approach is consisted of (i) geometry coordinate transformation techniques, (ii) neural networks regression of IMU from GPS, and (iii) adaptive filtering processes. Experiment is conducted in three driving environments which cover high occurrence of vehicle dynamic movements in lateral, longitudinal, and vertical directions. The processing effectiveness at five typical positions (three fixed and two flexible) are examined.

The use of smart portable devices in vehicles creates the possibility to record useful data and helps develop a better understanding of driving behavior. In the past few years the UTDrive mobile App (a.k.a MobileUTDrive) has been developed with the goal of improving driver/passenger safety, while simultaneously maintaining the ability to establish monitoring techniques that can be used on mobile devices on various vehicles. In this study, we extend the ability of MobileUTDrive to understand the impact on driver performance on public roads in the presence of distraction from speech/voice based tasks versus tactile/hands-on tasks. Drivers are asked to interact with the device in both voice-based and hands-on modalities and their reaction time and comfort level are logged. To evaluate the driving patterns while handling the device by speech/hand, the signals from device inertial sensors are retrieved and used to construct Gaussian Mixture Models (GMM).

In-vehicle signal processing plays an increasingly important role in driving behavior and traffic modeling. Maneuvers, influenced by the driver's choice and traffic/road conditions, are useful in understanding variations in driving performance and to help rebuild the intended route. Since different maneuvers are executed in varied lengths of time, having a fixed time window for analysis could either miss part of maneuver or include consecutive maneuvers in it evaluation. This results in reduced accuracies in maneuver analysis. Therefore, with access to continuous real-time in-vehicles signals, a suitable framing strategy should be adopted for maneuver recognition. In this paper, a non-uniform time window analysis is presented.