Background
I am a Robotics Engineer, Startup Advisor, and Angel Investor. I love helping early stage companies tackling deep technical problems.
I currently serve as the Head of Simulation at Kodiak Robitics, leading a team of engineers creating tools to rigorously evaluate the safety and performance envelop of autonomous trucks.
At Lyft (acquired by Toyota's Woven Planet), I also focused on using Simulation and Machine Learning to improve the safety and comfort of autonomous taxis.
Previously, I was a co-founder and Chief Technology Officer of Limbix Health, a startup creating Immersive Technologies for Mental Healthcare.
At Google, I was a Senior Engineer focusing on "Teleportation", designing cameras and algorithms, and producing high-fidelity experiences with the Street View and Virtual Reality teams.
I completed a Ph.D. at Carnegie Mellon's Robotics Institute, focusing on Computer Vision and Machine Learning.
I am fortunate to have been advised by Martial Hebert at CMU, and Robert Pless at Washington University in St. Louis.
(academic ancestry)
Before focusing on computer vision and machine learning, I interned and then consulted at Bell Labs in Murray Hill, NJ and Bangalore, India. At Bell Labs, I worked on various projects involving new methods for mobile content delivery and network optimization.
I am an open source human. Download my Genome.
Contact Information
E-mail:
scott (at) satkin (dot) com
s.satkin (at) kodiak (dot) ai
Office:
Kodiak Robotics
1049 Terra Bella Ave
Mountain View, CA 94043
Publications
"3DNN: 3D Nearest Neighbor",
International Journal of Computer Vision (IJCV), 2014.
"3DNN: Viewpoint Invariant 3D Geometry Matching for Scene Understanding",
Proceedings of the International Conference on Computer Vision (ICCV), 2013.
"Data-Driven Scene Understanding from 3D Models",
British Machine Vision Conference (BMVC), 2012. (Oral)
"Building Interior Multi-Panorama Experiences at Scale",
SIGGRAPH Sketch, 2012.
"From 3D Scene Geometry to Human Workspace",
Proceedings of the International Conference on Computer Vision and Pattern Recognition (CVPR), 2011. VIDEO (Oral)
"Memory-Constrained Aggregate Computation over Data Streams",
Proceedings of the International Conference on Data Engineering (ICDE), 2011.
"Modeling the Temporal Extent of Actions",
Proceedings of the European Conference on Computer Vision (ECCV), 2010.
"A Savvy Robot Standup Comic: Online Learning through Audience Tracking"
Technology, Entertainment and Design (TED Women), 2010.
Tangible, Embedded and Embodied Interaction (TEI), 2011.
"Efficient Tracking of Many Objects in Structured Environments",
Proceedings of the IEEE International Workshop on Visual Surveillance (In conjunction with the International Conference on Computer Vision - ICCV), 2009.
"Efficient Aggregate Computation over Data Streams",
Proceedings of the International Conference on Data Engineering (ICDE), 2008.
"Geolocating Static Cameras",
Proceedings of the International Conference on Computer Vision (ICCV), 2007.
"Monitoring Infrastructure for Converged Networks and Services",
Bell Labs Technical Journal, Vol. 12, No. 2, 2007.
Education
Ph.D. in Robotics (July 2013)
Carnegie Mellon University
The Robotics Institute (School of Computer Science)
Advisor: Dr. Martial Hebert
M.S. in Computer Science (May 2008)
Washington University in St. Louis
Department of Computer Science
Advisor: Dr. Robert Pless
B.S. in Computer Science (May 2006)
Washington University in St. Louis
Department of Computer Science