Robert C. Bolles is a program director in the Artificial Intelligence Center at SRI International. In this role, he leads the AIC’s Perception Program, which develops, evaluates, and transitions computer vision techniques to military and commercial customers. Bolles supervised DARPA’s Learning Applied to Ground Robots project, which developed techniques for outdoor robots, including visual odometry, mapping, planning, navigation, and control. He also supervised DARPA’s Video Verification of Identity project, which developed moving target detection techniques and ported them to the Predator unmanned aerial vehicle for testing by the U.S. Air Force.
Bolles developed analytic techniques for recognizing 2D and 3D industrial parts in robotics, interpreting range and intensity images, and detecting distinctive object features. He co-developed the RANSAC approach for fitting analytic models to sets of measurements containing a high percentage of “gross errors.” (RANSAC is used within the computer vision community to robustly fit models to measured data.) Bolles also developed the Epipolar-Plane Image Analysis technique for computing 3D structure from video data.
Previously, Bolles served as a lieutenant in the U.S. Navy Reserve, in which he was an instructor of computer science at the Naval Postgraduate School in Monterey, California. He has written numerous papers covering such areas as video analysis, moving object tracking, 3D object recognition, range data analysis, industrial robotics, outdoor obstacle detection and characterization, outdoor mapping, and structure from motion.
Bolles received his Ph.D. in computer science from Stanford University, and his M.S. in computer and information sciences from the University of Pennsylvania. He received his B.S. degree and graduated cum laude with honors in mathematics from Yale University.