Driver understanding based in Deep Learning in Autonomous Driving
Mentor: Luis Miguel Bergasa Pascual
Phone: (+34) 918856569
University: Universidad de Alcalá
Partner Host Institution: ATOS
Keywords: Driver understanding, deep learning, human factors, decision-making methods, manual/automatic control transfer, driver-vehicle interface

Driver understanding based in Deep Learning in Autonomous Driving

Intelligent vehicles technologies require a good understanding of human driver behaviors to guarantee safe, adjust to drivers’ needs and meet their preferences. Therefore, the driver understanding is essential for the development of these systems. Autonomous vehicles are coming to the world with the hope of increasing safety, decreasing congestion and reducing green-house gases in a general way. But, new open questions need to be answered: what will be the role of humans in such a rapidly approaching future? Would they seat as passive occupants, who fully trust their vehicles, or would there be a need for humans to “take over” control in some situations either triggered by the need perceived by the autonomous vehicle or desired by someone in the cabin?
This research line try to answer these questions monitoring driving behaviors by using the emerging deep learning approach, based on big data, which is revolutionizing the classical machine learning techniques, getting a breakthrough in the performance of complex classification and decision-making problems. Our proposal is to monitor driver behavior in real-time and to carry out decision making tasks, by using deep learning techniques, in order to implement a safe switching system between manual and automatic mode in the future V2U (Vehicle to User) interfaces for autonomous vehicles.

Departament: Electronics
Research Group: Robotics and e-Safety Unit
More Information:
Relevants projects on the area: Smart Driving Applications project (TEC2012-37104) funded by the Spanish MINECO from 2012 to 2015
Relevants publications on the area: 1.- L. M. Bergasa, J. Nuevo, M. A. Sotelo, R. Barea, E. López, Real-time system for monitoring driver vigilance, IEEE Transactions on Intelligent Transportation Systems, Vol. 7, No. 1, 63-77 (2006). Top 10 Best Research Papers (2000 to 2009) in IEEE Intelligent Transportation Systems.
2.- I.G. Daza, L.M. Bergasa, S. Bronte, J.J. Yebes, J. Almazán, R. Arroyo, Fusion of Optimized Indicators from Advanced Driver Assistance Systems (ADAS) for Driver Drowsiness Detection, Sensors, Vol 14, nº1, 1106-1131 (2014).