The Aerospace Autonomy and Intelligence (AAI) Laboratory at Seoul National University hosted an invited seminar on 23 September 2026 featuring Jason Jangho Choi from the University of California, Los Angeles. The one-hour seminar was held in Room 303, Building 301 at SNU and was also accessible via Zoom. The session was hosted by Prof. Namhoon Cho.
Choi, an Assistant Professor in UCLA’s Electrical and Computer Engineering Department and principal investigator of the Safety and Collective Intelligence (SCI) Autonomy Lab, reviewed his recent work slated to appear at IEEE CDC 2026. He earned his Ph.D. in Mechanical Engineering from UC Berkeley in 2025 and his bachelor’s degree from Seoul National University. His research focuses on safety assurance for learning-enabled autonomous systems and decentralized multi-agent intelligence; he was recognized as an RSS Pioneer in 2024.
The talk, titled “Benchmarking Safety Certificate Functions,” provided a tutorial on contemporary approaches to designing safety certificate functions. Choi compared classical foundations such as Hamilton–Jacobi reachability and Control Barrier Functions with recent learning-based extensions, including physics-informed neural network representations of reachability value functions, Neural CBFs, and deep reinforcement learning–based reachability methods. Through two case studies of differing complexity, he benchmarked these design frameworks and offered a unified perspective on their formulations, strengths, and limitations.
Choi concluded the seminar with an open discussion of remaining research directions, highlighting how these safety frameworks might interact with the emerging paradigm of foundation models. The event was organized by the AAI Laboratory and supported by the ERC-TRIPS research center.