I'm a research scientist at MIT, working on human-centered AI and autonomous vehicles. Also, I teach courses on deep learning.

Connect with me (@lexfridman) on Twitter, LinkedIn, Medium, Instagram, Facebook, and YouTube.

Besides research and teaching, I enjoy playing guitar, practicing jiu jitsu, and engaging in deep meaningful conversations including on podcasts both as a guest (e.g., Joe Rogan Experience) and as a host (Artificial Intelligence podcast and Take It Uneasy podcast).

Research & Publications

Human-Centered Autonomous Vehicle Systems
Summary: We propose a set of shared autonomy principles for designing and building autonomous vehicle systems in a human-centered way, and demonstrate these principles on a full-scale semi-autonomous vehicle.
Arguing Machines: Human Supervision of Black Box AI Systems
MIT Autonomous Vehicle Technology Study
Cognitive Load Estimation in the Wild
Driver Gaze Region Estimation without Use of Eye Movement
What Can Be Predicted from 6 Seconds of Driver Glances?
DeepTraffic
Crowdsourced Assessment of External Vehicle-to-Pedestrian Displays
Driver Frustration Detection from Audio and Video in the Wild
Automated Synchronization of Driving Data Using Vibration and Steering Events
Active Authentication on Mobile Devices