BEGIN:VCALENDAR
VERSION:2.0
PRODID:OpenCms 20.0.18
BEGIN:VTIMEZONE
TZID:Europe/Berlin
X-LIC-LOCATION:Europe/Berlin
BEGIN:DAYLIGHT
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
TZNAME:CEST
DTSTART:19700329T020000
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=3
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
TZNAME:CET
DTSTART:19701025T030000
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=10
END:STANDARD
END:VTIMEZONE				
BEGIN:VEVENT
DTSTAMP:20190117T155826
UID:580208ec-1a68-11e9-b632-000e0c3db68b
SUMMARY:Vortrag von Prof. Stefan Schaal
DESCRIPTION:Prof. Stefan Schaal\nMax-Planck-Institute for Intelligent Systems,\nTübingen, Germany  \nTuesday 2017-11-21 16:00\n IST-Seminar-Room 2.255 - Pfaffenwaldring 9 - Campus Stuttgart-Vaihingen  \nAbstract\nAutonomous robot systems have to make perceptual and control decisions at every moment of time,\nand have to learn and adapt to improve the system’s performance. In order to address autonomous\nskillful movement generation in complex robot and task scenarios, we have been working on a variety\nof sub problems to facilitate robust task achievement. Among these topics are general\nrepresentations for movement in form of movement primitives, trajectory-based reinforcement\nlearning with path integral reinforcement learning, and inverse reinforcement learning to extract\nthe “intent” of observed behavior. However, this “action centric” view of skill acquisition needs\nto be extended with a stronger perceptual component, as in the end the entire perception-action\nlearning loop could be considered the key element to address, rather than isolated components of\nthis loop. In some tentative initial research, we have been exploring Associative Skill Memories,\ni.e., the simple idea to start memorizing all sensory events and their statistics together with\neach movement skill. This concepts opens a wide spectrum of adding predictive, corrective, and\nswitching behaviors in motor skills, and may create an interesting foundation to automatically\ngenerate the graphs underlying complex sequential motor skills.  \n  \n   \n  \nBiographical Information\nStefan Schaal is Professor of Computer Science, Neuroscience, and Biomedical Engineering at the\nUniversity of Southern California, and a Founding Director of the Max-Planck-Insitute for\nIntelligent Systems in Tuebingen, Germany. Dr. Schaal's research interests include topics of\nstatistical and machine learning, neural networks, computational neuroscience, functional brain\nimaging, nonlinear dynamics, nonlinear control theory, and biomimetic robotics. He applies his\nresearch to problems of artificial and biological motor control and motor learning, focusing on\nboth theoretical investigations and experiments with human subjects and anthropomorphic robot\nequipment. Dr. Schaal is a member of the German National Academic Foundation (Studienstiftung des\nDeutschen Volkes), the Alexander von Humboldt Foundation, the Society For Neuroscience, the Society\nfor Neural Control of Movement, the AAAS, and a Fellow of the IEEE.\n    \n\n  
DTSTART;TZID=Europe/Berlin;VALUE=DATE:20171121
URL;VALUE=URI:https://www.ist.uni-stuttgart.de/de/veranstaltungen/Vortrag-von-Prof-00001.-Stefan-Schaal/
END:VEVENT
END:VCALENDAR