Robotics is entering a new era. Humanoids are becoming real deployment targets, and generative AI models are increasingly used to produce policies, plans, and even motor commands. Yet as the dimensionality and learning capacity of these systems grow, the question remains: how do we preserve safety guarantees?
This talk presents a historical and technical perspective on robot safety rooted in control theory and its evolution toward modern data-driven systems.
Changliu Liu,
Carnegie Mellon
We begin with classical analytical approaches for low-dimensional dynamical systems, including control barrier functions, safety indices, and Hamilton– Jacobi reachability analysis. These methods provide rigorous, state-space guarantees but traditionally scale poorly with system dimension. We then examine how safety analysis has expanded into the data-driven regime. Neural barrier functions and reinforcement learning-based Hamilton–Jacobi solvers extend safety reasoning to complex dynamics, but introduce new questions about correctness, generalization, and verifiability. As robots scale to humanoid platforms and multimodal perception–action pipelines, state-space abstractions become high-dimensional and partially learned, further challenging traditional safety tools.
To address these issues, we present three recent research directions. First, we show how formal verification of neural networks can restore safety guarantees for data-driven safety certificates. Second, we introduce λ-reachability, a scalable framework for safety analysis of arbitrarily high-dimensional systems. Finally, we discuss emerging methods for safety analysis of foundation models that mediate perception, planning, and control.
Changliu Liu is an associate professor in the Robotics Institute, School of Computer Science, Carnegie Mellon University (CMU), where she leads the Intelligent Control Lab. Prior to joining CMU in 2019, Dr. Liu was a postdoc at Stanford. She received her Ph.D. degree from University of California, Berkeley and her bachelor degree from Tsinghua University.
Her research interests lie in the design and verification of human-centered intelligent systems with applications to manufacturing and transportation and on various robot embodiments. Dr. Liu co-founded Instinct Robotics, a robotics company for intelligent manufacturing. Her work has been recognized by NSF Career Award, Amazon Research Award, Ford URP Award, Advanced Robotics for Manufacturing Champion Award, Young Investigator Award at International Symposium of Flexible Automation, IEEE RAS Early Academic Career Award in Robotics and Automation, IFAC Robotics Outstanding Young Researcher Award, and many best/outstanding paper awards.