Lex Fridman: I'm an AI researcher working on autonomous vehicles, human-robot interaction, and machine learning at MIT and beyond.
Teaching: deeplearning.mit.edu
Podcast: Artificial Intelligence Podcast
Sample Conversations: Elon Musk, Jack Dorsey, Richard Dawkins, Leonard Susskind, Noam Chomsky, Eric Weinstein, Roger Penrose, Stephen Wolfram, Sean Carroll, Bjarne Stroustrup, Donald Knuth, and my dad Alexander Fridman.

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

Outside of research and teaching, I enjoy:
- playing guitar & piano
- practicing jiu jitsu & judo
- challenging myself mentally & physically
- participating in long-form conversations, e.g., on JRE: #1188, #1292, #1422, and #1455.

Research & Publications (Google Scholar)

MIT Advanced Vehicle Technology Study
Website - Video - Paper (Cite: BibTeX, Scholar)
Summary: Large-scale real-world AI-assisted driving data collection study to understand how human-AI interaction in driving can be safe and enjoyable. The emphasis is on computer vision based analysis of driver behavior in the context of automation use.
Arguing Machines: Human Supervision of Black Box AI Systems
Video - Paper (Cite: BibTeX, Scholar)
Summary: Framework for providing human supervision of a black box AI system that makes life-critical decisions. We demonstrate this approach on two applications: (1) image classification and (2) real-world data of AI-assisted steering in Tesla vehicles.
Human-Centered Autonomous Vehicle Systems
Video - Paper (Cite: BibTeX, Scholar)
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.
Automated Synchronization of Driving Data Using Vibration and Steering Events
Video - Paper (Cite: BibTeX, Scholar)
Summary: A method for automated synchronization of vehicle sensors using accelerometer, telemetry, audio, and dense optical flow from three video sensors.
Driver Gaze Region Estimation without Use of Eye Movement
Video - Paper (Cite: BibTeX, Scholar)
Summary: We propose a simplification of the general gaze estimation task by framing it as a gaze region estimation task in the driving context, thereby making it amenable to machine learning approaches. We go on to describe and evaluate one such learning-based approach.
Active Authentication on Mobile Devices
Paper (Cite: BibTeX, Scholar)
Summary: An approach for verifying the identity of a smartphone user with with four biometric modalities. We evaluate the approach by collecting real-world behavioral biometrics data from smartphones of 200 subjects over a period of at least 30 days.
Crowdsourced Assessment of External Vehicle-to-Pedestrian Displays
Paper (Cite: BibTeX, Scholar)
Summary: 30 external vehicle-to-pedestrian display concepts for autonomous vehicles were evaluated. Simple, minimalist displays performed best.
Cognitive Load Estimation in the Wild
Paper (Cite: BibTeX, Scholar)
Summary: Winner of the CHI 2018 Honorable Mention Award. We propose two novel vision-based methods for cognitive load estimation and evaluate them on a large-scale dataset collected under real-world driving conditions.
DeepTraffic
Paper (Cite: BibTeX, Scholar)
Summary: Traffic simulation and optimization with deep reinforcement learning. Primary goal is to make the hands-on study of deep RL accessible to thousands of students, educators, and researchers.
What Can Be Predicted from 6 Seconds of Driver Glances?
Paper (Cite: BibTeX, Scholar)
Summary: Winner of the CHI 2017 Best Paper Award. We consider a dataset of real-world, on-road driving to explore the predictive power of driver glances.