IRIM Fall 2026 Seminar Series | The Dynamics of Fluid Physical Interaction: Safe, Adaptive, and Compliant Robot Intelligence

Abstract: For decades, we have envisioned robots that can move, adapt, and collaborate with humans as fluidly as we do with each other. Yet even the most advanced systems struggle to achieve what I call fluid physical interaction: a regime where motion, force, and intent predictions are continuously co-regulated through constraint-aware estimation, learning, and control; enabling safe, adaptive, and seamless exchanges of energy and information. Achieving this requires robots that are stable yet flexible, adaptive yet predictable, and compliant yet purposeful. In this talk, I will show how a dynamical-systems perspective provides a unifying foundation for realizing fluid physical interaction. By shaping robot behavior through stable vector fields, viability manifolds, and adaptive dynamics models, we can generate motion policies that remain reactive, safe, and consistent even under uncertainty. I will present recent results that demonstrate how this framework enables robots to generalize complex behaviors from minimal demonstrations, adapt online to changes in their dynamics and environment, avoid obstacles in real time, and maintain long-horizon safety during physical collaboration. I will also discuss new efforts that combine dynamical-systems principles with visuomotor learning to achieve stable, compliant, and force-aware behavior from simulation-guided data. Together, these developments move us closer to embodied, adaptive, and compliant robot intelligence that can truly flow with humans and the environments they inhabit.
 

Bio: Nadia Figueroa is the Shalini and Rajeev Misra Presidential Assistant Professor of Mechanical Engineering and Applied Mechanics at the University of Pennsylvania, with secondary appointments in Computer and Information Science and Electrical and Systems Engineering. She is a core faculty member of the GRASP Lab. Her research integrates learning, control, and estimation to enable safe, adaptive, and fluid human–robot interaction and collaboration. Her work bridges control theory, machine learning, perception, and biomechanics, with an emphasis on formal guarantees for robot behavior in dynamic, human-centered environments. Before joining Penn, she was a Postdoctoral Associate in MIT’s CSAIL. She earned her Ph.D. in Robotics, Control, and Intelligent Systems from EPFL and conducted research at the German Aerospace Center (DLR) and NYU Abu Dhabi. She holds a B.Sc. in Mechatronics Engineering from Tecnológico de Monterrey and an M.Sc. in Automation and Robotics from TU Dortmund. She received a 2025 NSF CAREER Award and was a finalist for the 2020 Georges Giralt Ph.D. Award and the 2017 KUKA Innovation Award. Her publications have received multiple best paper honors at ICRA, CASE, RSS, and IEEE Transactions on Robotics. She chairs the IEEE RAS Women in Engineering Committee, leading global efforts to recognize and celebrate women in robotics.