[ICON Fall26 Seminar] Johannes Lachner (Purdue) #robotics #control #physicalai

Date/Time: Sep. 4, 2026, Friday, 3:00 - 4:30 pm, ET Presenter: Johannes Lachner, Assistant Professor, Purdue University Title: Physics-Grounded AI: A Unifying Framework for Stable, Safe, and Human-Mimetic Robotic Physical Interaction Abstract: Humans outperform robots in physical interaction, despite current advances in robot learning and control. AI-driven approaches are intrinsically unidirectional, constrained only by temporal causality and boundedness. Physical interaction, however, is dictated by reactive behavior governed by energy conservation, entropy, etc. Robot learning algorithms for physical interaction must therefore interface the information domain with the energy domain. In this talk, I present physics-grounded AI, a unifying framework that integrates coordinate-invariant, energy-consistent robot dynamics with imitation learning and generative AI to enable safe, stable, and human-mimetic physical interaction. Inspired by human motor control, the framework enables modular robot control via motor primitives that form a compositional control language, allowing robots to learn interaction strategies from demonstrations while preserving physical consistency. I will present my recent work on diffusion-based impedance learning, which bridges generative modeling with interactive control, enabling robots to adapt stiffness and damping autonomously, even across unseen tasks and hardware configurations. I will present our current pilot clinical trials that use this framework to learn how physical therapists provide physical support to post-stroke patients. Bio: Johannes Lachner is an Assistant Professor in Purdue University’s Elmore Family School of Electrical and Computer Engineering, with a courtesy appointment in Mechanical Engineering. His research combines robotics, motor neuroscience, and AI to develop physically intelligent robots for contact-rich manipulation and robot-assisted rehabilitation. Before joining Purdue, he was a postdoctoral fellow and lecturer at MIT and spent nine years at KUKA, where he led research on physical human–robot interaction and contact-rich manipulation. He received his Ph.D. with the highest distinction from the University of Twente.