Seminar - Safe Autonomy: Are We There Yet? Unifying Learning, Control, and Decision-Making through Formal Reasoning - Oct. 4
Morteza Lahijanian
Assistant Professor, Smead Aerospace
Friday, Oct. 4 | 10:40 a.m. | AERO 111
Abstract: As autonomous systems become increasingly prevalent in safety-critical domains, ensuring their safe operation remains a key challenge. This seminar examines the questions: Are we there yet? Have we achieved the level of safe autonomy needed for widespread deployment? ÌýThe talk will focus on integration of three foundational elements—learning, control, and decision-making—through the lens of formal reasoning.
I will discuss how machine learning enables adaptive behavior in dynamic environments, but often lacks guarantees needed for safety. Control theory provides robust frameworks for system stability but faces limitations when navigating complex, uncertain settings. Decision-making strategies offer high-level guidance, yet can struggle to align with real-world constraints. I argue that formal methods offer a powerful and critical solution to bridging these gaps, providing mathematical guarantees for system behavior while accounting for the uncertainties inherent in autonomous decision-making. Ìý
I will present our progress in unifying these approaches to enable safe autonomy, addressing both the theoretical advancements and practical challenges. Specifically, I will highlight our key contributions to enabling assured, reliable, and interactive autonomy.
Bio: Morteza Lahijanian is an assistant professor in the Aerospace Engineering Sciences department, an affiliated faculty at the Computer Science department and Robotics program, and the director of the Assured, Reliable, and Interactive Autonomous (ARIA) Systems group at the University of Colorado Boulder. He received his B.S. from the University of California, Berkeley, and his M.S. and Ph.D. in Mechanical Engineering from Boston University. He served as a postdoctoral scholar in Computer Science at Rice University. Prior to joining ¶¶ÒõÂÃÐÐÉä Boulder, he was a research scientist in the department of Computer Science at the University of Oxford.Ìý
Dr. Lahijanian's research interests span the areas of control theory, stochastic hybrid systems, formal methods, machine learning, and game theory with applications in robotics, particularly, motion planning, strategy synthesis, model checking, and human-robot interaction. His lab develops novel theoretical foundations and computational frameworks to enable reliable and intelligent autonomy. The emphasis is especially on safe autonomy through correct-by-construction algorithmic approaches.
Ìý