What Should Robots Learn from Us?

Apstrakt:

Recent technology developments enable robots to safely share a common workspace with humans. Europe is currently leading the robotic market for safety-certified robots by providing tools that can react to unintentional contacts. However, in human-robot physical collaboration, robots still face a shortcoming due to their limitations in observing human dynamics. This further results in inefficient collaboration and unergonomic interaction. In the seminar I will introduce the work of my Laboratory for Advancing Collaborative Robot Behaviors in Physical Human-Robot Interaction Scenarios (CoBoTaT) that aims to leverage these technologies by providing tools that can efficiently observe human dynamics in real time by learning anticipatory models from datasets and incorporating these models in on-line control of robots to make collaboration more efficient.

O predavaču:

Tadej Petrič is currently a head of CoBoTaT laboratory and a research associate at the Department for Automation, Biocybernetics and Robotics at the Jožef Stefan Institute. He is also an assistant professor at Jožef Stefan International Postgraduate School, Slovenia.In 2015 he was a Postdoctoral Fellow with the Biorob (prof. Auke Ijspeert lab), at the Écolepolytechniquefédérale de Lausanne (EPFL).In 2013 he received the D.Sc. degree in robotics from the Faculty of Electrical Engineering at the University of Ljubljana. He performed a part of his doctoral research at the Department of Robotic Systems for Dynamic Control of Legged Humanoid Robots at German Aerospace Center (DLR) in Germany. In 2013 he was a visiting researcher at ATR Computational Neuroscience Laboratories in Japan. His research interests include human-like robotic movement and mostly control of dynamical systems.