Enhancing Mobile-UTDrive Capacity for Onboard Driver Assessment
- Delivery
- Available on this site
- Format
- Price
- Non-members (tax incl.):¥1,100 Members (tax incl.):¥880
- Publication code
- 20219005
- Paper/Info type
- Other International Conferences
- Pages
- 1-6(Total 6 p)
- Date of publication
- Sep 2021
- Publisher
- JSAE
- Language
- English
Detailed Information
Author(E) | 1) Bin Guo, 2) Yongkang Liu, 3) John H.L. Hansen |
---|---|
Affiliation(E) | 1) Center for Robust Speech Systems, UTDrive lab Dept. of Electrical and Computer Engineering University of Texas at Dallas, 2) Center for Robust Speech Systems, UTDrive lab Dept. of Electrical and Computer Engineering University of Texas at Dallas, 3) Center for Robust Speech Systems, UTDrive lab Dept. of Electrical and Computer Engineering University of Texas at Dallas |
Abstract(E) | With emerging trends in Advanced Driver Assistance Systems (ADAS) and autopilot vehicle development, the vehicle is expected to perform and achieve proactive warning abilities and proactive prediction of driver behavior. In this study, we construct an advanced driving behavior model that combines driving behavior, traffic conditions, and driver psychology which are expected to improve the understanding of driver behavior from both micro and macro views. In earlier studies, we develop the UTDrive-MOBILE-App as a mobile application that supports collection of driving behavior data. In this study, we propose to expand the functionality to support in-the-fly driver/driving behavior measurement and modeling within an Android mobile platform. The UTDrive-MOBILE-App data capture, modeling and assessment/scoring strategies will be presented. Specifically, we discuss the formulation of an initial driver measurement solution and ways to provide viable feedback in the form of data visualization. We also conduct several experiments to verify and compare results under a range of driving field conditions. Finally, the potential for real-time driving behavior data capture and on-the-fly measurement solution is combined with machine learning as a means to explore richer multi-modal driver research. |