lex fridman mit
Lex Fridman
I'm a research scientist at MIT, working on human-centered artificial intelligence. In particular, I'm interested in developing deep learning approaches for perception, planning, and human-robot interaction in the context of real-world shared autonomy systems.
Connect with me (@lexfridman) on Twitter, LinkedIn, Facebook, Instagram, and subscribe on YouTube.

Recent News

MIT 6.S094: Deep Learning for Self-Driving Cars

A course on the practice of deep learning explored through the theme of building a self-driving car. Course page is http://selfdrivingcars.mit.edu. Besides lectures and guest talks, it included a deep reinforcement learning competition (DeepTraffic) and an end-to-end driving simulation (DeepTesla).

Select Videos: Research, Demos, and Talks

We ran our new glance classification code on the driver-facing video from the tragic Uber crash in Arizona. Open source code and arXiv paper will be out soon. I hope it can help, in however small a way, make the roads safer for people inside and outside both manually-controlled and autonomous vehicles.
MIT-AVT study aims to understand, through large-scale real-world driving data collection and large-scale deep learning based parsing of that data, how human-AI interaction in driving can be safe and enjoyable. See website for more technical details (including paper).
A demonstration of our gaze region classification algorithm on five synchronized video streams in a Tesla while transfering control to Autopilot and taking control back.
We present a method for detecting driver frustration from both video and audio streams captured during the driver's interaction with an in-vehicle voice-based navigation system.
This is a demo for our automated synchronization algorithm for driving data that uses vibration and steering events to sync driving data within 13ms precision.

Publications

2018-fridman-autonomous
MIT Autonomous Vehicle Technology Study: Large-Scale Deep Learning Based Analysis of Driver Behavior and Interaction with Automation
Authors: Fridman, Brown, Glazer, Angell, Dodd, Jenik, et al.
Journal: IEEE Access
2018-fridman-arguing
Arguing Machines: Perception-Control System Redundancy and Edge Case Discovery in Real-World Autonomous Driving
Authors: Fridman, Jenik, Reimer
Conference: AAAI
2018-fridman-deeptraffic
DeepTraffic: Driving Fast through Dense Traffic with Deep Reinforcement Learning
Authors: Fridman, Jenik
Conference: AAAI
2018-kindelsberger-designing
Designing Toward Minimalism in Modern Vehicle HMI
Authors: Kindelsberger, Fridman, Glazer, Seppelt, Reimer
Conference: CHI
2018-brown-curvature
Road Curvature with Tesla Autopilot: Difference in Approach between Human and Machine
Authors: Brown, Fridman, Kindelsberger, Glazer, Reimer
Conference: CHI
2018-fridman-cognitive
Cognitive Load Estimation in the Wild
Authors: Fridman, Reimer, Mehler, Freeman
Conference: CHI
2017-toyoda-understanding
Understanding Non-Verbal Communication Between Vehicles and Pedestrians Toward Safer Automated Vehicles
Authors: Toyoda, Fridman, Jenik, Mehler, Reimer
Conference: FAST-Zero
2017-fridman-predicted
What Can Be Predicted from 6 Seconds of Driver Glances?
Authors: Fridman, Toyoda, Seaman, Seppelt, Angell, Lee, Mehler, et al.
Conference: CHI
2017-fridman-semiautomated
Semi-Automated Annotation of Discrete States in Large Video Datasets
Authors: Fridman, Reimer
Conference: AAAI
2017-fridman-sideeye
SideEye: A Generative Neural Network Based Simulator of Human Peripheral Vision
Authors: Fridman, Jenik, Keshvari, Bryan, Reimer, Zetzsche, et al.
Conference: CHI
2016-fridman-lizard
Owl and Lizard: Patterns of Head Pose
and Eye Pose in Driver Gaze Classification
Authors: Fridman, Lee, Reimer, Victor
Journal: IET Computer Vision
2016-fridman-automated
Automated Synchronization of Driving Data
Using Vibration and Steering Events
Authors: Fridman, Brown, Angell, Abdic, Reimer, Noh
Journal: Pattern Recognition Letters
2016-neverova-learning
Learning Human Identity From Motion Patterns
Authors: Neverova, Wolf, Lacey, Fridman, Chandra, Barbello, et al.
Journal: IEEE Access
2016-fridman-driver
Driver Gaze Region Estimation without Use of Eye Movement
Authors: Fridman, Langhans, Lee, Reimer
Journal: IEEE Intelligent Systems
2016-abdic-driver
Driver Frustration Detection from Audio and Video in the Wild
Authors: Abdic, Fridman, McDuff, Marchi, Reimer, Schuller
Conference: IJCAI
2016-lee-investigating
Investigating Drivers' Head and Glance Correspondence
Authors: Lee, Munoz, Fridman, Victor, Reimer, Mehler
Journal: PeerJ
2016-abdic-detecting
Detecting Road Surface Wetness from Audio: A Deep Learning Approach
Authors: Abdic, Fridman, Marchi, Brown, Angell, Reimer, Schuller
Conference: ICPR
2016-fridman-framework
A Framework for Robust Driver Gaze Classification
Authors: Fridman, Lee, Mehler, Reimer
Conference: SAE World Congress
2016-reimer-behavioral
Behavioral Impact of Drivers' Roles in Automated Driving
Authors: Reimer, Pettinato, Fridman, Lee, Mehler, Seppelt, Park, et al.
Conference: AutomotiveUI
2016-munoz-distinguishing
Distinguishing Patterns in Drivers' Visual Attention Allocation
Using Hidden Markov Models
Authors: Munoz, Reimer, Lee, Mehler, Fridman
Journal: Transportation Research Part F
2015-fridman-multimodal
Multi-modal Decision Fusion for Continuous Authentication
Authors: Fridman, Stolerman, Acharya, Brennan, Juola, Greenstadt, et al.
Journal: Computers and Electrical Engineering
2015-fridman-active
Active Authentication on Mobile Devices
via Stylometry, Application Usage, Web Browsing, and GPS Location
Authors: Fridman, Weber, Greenstadt, Kam
Journal: IEEE Systems Journal
2015-fridman-joint
On the Joint Impact of Bias and Power Control on Downlink Spectral Efficiency in Cellular Networks
Authors: Fridman, Wildman, Weber
Journal: IEEE/ACM Transactions on Networking
2014-stolerman-active
Active Linguistic Authentication Using Real-Time
Stylometric Evaluation for Multi-Modal Decision Fusion
Authors: Stolerman, Fridman, Greenstadt, Brennan, Juola
Conference: Advances in Digital Forensics
2013-fridman-decision
Decision Fusion for Multimodal Active Authentication
Authors: Fridman, Stolerman, Acharya, Brennan, Juola, Greenstadt, et al.
Journal: IEEE IT Professional
2013-acharya-authentication
User Authentication Through Biometric Sensors and Decision Fusion
Authors: Acharya, Fridman, Brennan, Juola, Greenstadt, Kam
Conference: CISS
2013-fridman-observations
Observations on Sum User Rate for Cellular Downlink
Authors: Fridman, Wildman, Weber
Conference: CROWNCOM
2012-fridman-oman
OMAN: A Mobile Ad Hoc Network Design System
Authors: Fridman, Weber, Graff, Breen, Dandekar, Kam
Journal: IEEE Transactions on Mobile Computing
2008-fridman-crosslayer
Cross-Layer Multicommodity Capacity Expansion
on Ad Hoc Wireless Networks of Cognitive Radios
Authors: Fridman, Weber, Dandekar, Kam
Conference: CISS
2008-fridman-cooperative
Cooperative Surveillance in Video Sensor Networks
Authors: Fridman, Primerano, Weber, Kam
Conference: ICDSC
2008-hennessey-simplification
A Simplification Algorithm for Visualizing
the Structure of Complex Graphs
Authors: Hennessey, Brooks, Fridman, Breen
Conference: International Conference on Information Visualisation
2008-fridman-distributed
Distributed Path Planning for Connectivity Under Uncertainty
by Ant Colony Optimization
Authors: Fridman, Weber, Kumar, Kam
Conference: American Control Conference (ACC)
2007-fridman-communicationbased
Communication-Based Motion Planning
Authors: Fridman, Modi, Weber, Kam
Conference: CISS
2007-fridman-planning
Path Planning for Network Performance
Authors: Fridman, Weber, Graff, Kam
Conference: GLOBECOM
2007-fridman-visualization
Visualization of Resource Allocation
in Large-Scale Mobile Ad Hoc Networks
Authors: Fridman, Hennessey, Breen, Weber, Kam
Conference: ISVC
2006-fridman-robust
Robust Optimal Power Control for Ad Hoc Networks
Authors: Fridman, Grote, Weber, Dandekar, Kam
Conference: CISS