Robust and Secure Perception for Automated Vehicles
- October 09, 2017
- 4:00 p.m.
- 117A Surge Building,
- Dr. Todd E. Humphreys, University of Texas at Austin
- Faculty Host: Dr. Mark Psaiki
Abstract: The next few decades will see automated vehicles become critical to the world economy. But daunting challenges must be overcome to ensure trustworthy operation: Even under fairly benign conditions it has proven difficult to ensure that automated vehicles can be trusted to locate themselves accurately and to avoid obstacles. In adverse weather, or|worse yet|under a deliberate sensory attack, the diculty is greatly magnied: How can automated vehicles reliably operate when facing both outliers and outlaws, both faults and fraud?
This talk will focus on reliable automated vehicle localization despite poor weather, dense urban environments, and sensor deception, including GPS/GNSS, visible light cameras, radar, and V2V sensing.
Biography: Todd E. Humphreys is an associate professor in the department of Aerospace Engineering and Engineering Mechanics at the University of Texas at Austin, and Director of the UT Radionavigation Laboratory. He received a B.S. and M.S. in Electrical and Computer Engineering from Utah State University and a Ph.D. in Aerospace Engineering from Cornell University. He specializes in the application of optimal detection and estimation techniques to problems in satellite navigation, automated systems, and signal processing. His recent focus has been on secure perception for automated systems, including navigation, timing, and collision avoidance, and on centimeter-accurate location for the mass market. Dr. Humphreys received the University of Texas Regeants' Outstanding Teaching Award in 2012, the National Science Foundation CAREER Award in 2015, and the Institute of Navigation Thurlow Award in 2015.