Optimality and Robustness in Robotic Exploration

Ian Abraham, PhD
Assistant Professor
Yale University

Abstract: Effective exploration is a vital component in the success of robotic applications in the field. This talk presents a novel formulation of exploration that permits optimality criteria and performance guarantees for robotic exploration tasks. We define the problem of exploration as a coverage problem on continuous (infinite-dimensional) spaces based on ergodic theory and derive control methods that satisfy various notions of optimality and robustness such as asymptotic coverage, set-invariance, time-optimality, and robustness in exploration tasks. Last, we demonstrate successful execution of the approach on a range robotic systems and present an outlook on novel directions in robot learning.

Biography: Ian Abraham is an Assistant Professor in Mechanical Engineering with courtesy appointment in the Computer Science Department at Yale University. His research group is focused on developing real-time optimal control methods for data-efficient robotic learning and exploration. Before joining Yale, he was a postdoctoral researcher at the Robotics Institute at Carnegie Mellon University in the Biorobotics Lab. He received his PhD. and M.S. degrees from Northwestern University and the B.S. degree from Rutgers University. During his Ph.D. he also worked at the NVIDIA Seattle Robotics Lab where he worked on GPU accelerated robust modelbased control. His work has been recognized through several best paper awards and was awarded the 2023 NSF CAREER award.