Safety-Critical Intelligence: From Autonomous Driving to Human–AI Interaction
Abstract: What do the safety challenges faced by Waymo and ChatGPT have in common? This talk will explore how bridging AI capabilities with control theory principles can lay a strong foundation for verifiable safety in intelligent systems. We will start with safety-critical robotics and control, where game-theoretic reinforcement learning has significantly scaled the synthesis of safety filters—runtime schemes that monitor behavior and intervene to avoid hazards—enabling robust guarantees beyond the reach of purely model-based approaches. We will then turn our attention to human–AI systems, where preempting harm requires reasoning through dynamic interactions with people. Our recent experiments indicate that the same predictive tools that enable split-second recovery from human mistakes on the race track can also help align language models, curbing the emergence of manipulative behaviors. The talk will end with a vision for general human-centered AI systems that build accountability and public trust through proactive, human-auditable safety assessments.
Biography: Jaime Fernández Fisac is an Assistant Professor of Electrical and Computer Engineering at Princeton University, where he directs the Safe Robotics Laboratory and co-directs Princeton AI4ALL. His research integrates control systems, game theory, and artificial intelligence to equip robots with transparent safety assurances that users and the public can trust. Before joining Princeton, he was a Research Scientist at Waymo, where he pioneered new approaches to interaction planning that continue to shape how autonomous vehicles share the road today. He is also the co-founder of Vault Robotics, a startup developing agile delivery robots that work alongside human drivers. Prof. Fisac holds an Engineering Degree from Universidad Politécnica de Madrid, a Master’s in Aeronautics from Cranfield University, and a Ph.D. in Electrical Engineering and Computer Sciences from the University of California, Berkeley. His work has been featured in The Wall Street Journal and WIRED, and recognized with the Google and Sony faculty research awards and the NSF CAREER Award.