Dr. Lex Fridman is a postdoctoral associate working on Deep Learning and Computer Vision in the context of Shared Autonomy and Intelligent Vehicle Systems at the Massachusetts Institute of Technology (MIT).
Lex's group at MIT is running a new research study that analyzes advanced vehicle technology use in naturalistic driving. At the time of this presentation, they had so far instrumented 8 Tesla Model S vehicles with cameras and other sensors capturing not only the external world but driver state and vehicle state as well. Their goal is to continuously expand their fleet of instrumented Tesla vehicles, recording and analyzing driver interaction with Autopilot over thousands of miles.
In this TMC Connect 2016 conference session, Lex explains how his group uses computer vision and deep learning approaches to extract essential information about the car, the driver, and the external world during Tesla Autopilot use.