InformatiKOM, Bldg. 50.19, Atrium, Adenauerring 12, 76131 Karlsruhe

31. July 2024, 16:00

Katherine J. Kuchenbecker is a Director at the Max Planck Institute for Intelligent Systems (MPI-IS) in Stuttgart, Germany, and an Honorary Professor at the University of Stuttgart. She earned her Ph.D. at Stanford University in 2006, did postdoctoral research at the Johns Hopkins University, and was an engineering professor in the GRASP Lab at the University of Pennsylvania from 2007 to 2016. Her research blends haptics, teleoperation, physical human-robot interaction, tactile sensing, and medical applications. She delivered a TEDYouth talk on haptics in 2012 and has been honored with a 2009 NSF CAREER Award, the 2012 IEEE RAS Academic Early Career Award, a 2014 Penn Lindback Award for Distinguished Teaching, elevation to IEEE Fellow in 2021, and 19 best paper, poster, demonstration, and reviewer awards. She co-chaired the IEEE Haptics Symposium in 2016 and 2018 and is Editor-in-Chief of the 2025 IEEE World Haptics Conference. Furthermore, she has led the International Max Planck Research School for Intelligent Systems (IMPRS-IS) since its founding in 2017 and is the Robotics Institute Germany (RIG) Spokesperson for MPI-IS.

Abstract:

The sense of touch plays a crucial role in the sensorimotor systems of humans and animals. In contrast, today's robotic systems rarely have any tactile sensing capabilities because artificial skin tends to be complex, bulky, rigid, delicate, unreliable, and/or expensive. To safely complete useful tasks in everyday humanenvironments, robots should be able to feel contacts that occur across all their body surfaces, not just at their fingertips. Furthermore, tactile sensors need to be soft to cushion contact and transmit loads, and their spatial and temporal resolutions should match the requirements of the task. We are thus working to create tactile sensors that provide useful contact information across different robot body parts, along with touch-processing algorithms that quickly and accurately interpret the resulting streams of measurements, often using machine learning. Here, we are interested not only in autonomous robots that can physically interact with the world but also in practical high-fidelity teleoperation, where a human remotely controls a robot to accomplish tasks. Importantly, good tactile perception is not enough:robots also need good movement and social skills to work effectively with and around humans. I will elucidate these ideas of haptic intelligence by showcasing several robotic systems we have created and evaluated in recent years, including Minsight, the Haptic Empathetic Robot Animal (HERA), HuggieBot, AiroTouch, OCRA, and the Robot Interaction Studio.