BEGIN:VCALENDAR
VERSION:2.0
PRODID:OpenCms 21.0.11
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:20190117T155825
UID:5738022a-1a68-11e9-b632-000e0c3db68b
SUMMARY:Vortrag von Dr. Ludovic Righetti
DESCRIPTION:Dr. Ludovic Righetti   \n Max-Planck Institute for Intelligent Systems\nTübingen, Germany  \nTuesday, 2016-11-08 16:00\n IST-Seminar-Room V9.22 - Pfaffenwaldring 9 - Campus Stuttgart-Vaihingen  \nAbstract  \nWhat are the algorithmic principles that would allow a robot to run through a rocky terrain,\nlift a couch while reaching for an object that rolled under it or manipulate a screwdriver while\nbalancing on top of a ladder? Our research tries to answer this seemingly naive question, which in\nfact resorts to under-standing the fundamental principles of robotic locomotion and manipulation.\nOne important aspect of our work focuses on the optimal exploitation of contact interactions\nbetween the robot and its environment to create more robust and efficient behaviors in uncertain\nand constantly changing environments.\n In this presentation, I will present our recent research results on the optimal control of\ncontact inter-actions for robotic locomotion and manipulation. In particular, I will show how\noptimization techniques can be used in fast control loops to create complex balancing and walking\nbehaviors. Then I will present our recent work on the optimal control of contact forces and robot\nmotions where we exploit the structure of the robot dynamics to develop computationally efficient\nalgorithms. I will use these examples to argue that the structure of the optimal control problems\nrelated to multi-contact legged locomotion can and should be exploited to create more efficient\nnumerical solvers that allow receding horizon control with manageable computational complexity. In\nthe second part of the talk, I will present some of our research on learning control. In\nparticular, I will show how the use of multi-modal sensory information can complement optimal\ncontrol approaches to create more reactive behaviors and to learn contact interactions using\nreinforcement learning.\n   \n  \nBiographical Information  \nLudovic Righetti leads the Movement Generation and Control group at the Max-Planck Institute for\nIntelligent Systems (Tübingen, Germany) since September 2012 and holds a W2 group leader position\nsince October 2015. Before, he was a postdoctoral fellow at the University of Southern California\n(2009-2012). He studied at the Ecole Polytechnique Fédérale de Lausanne (Switzerland) where he\nreceived a diploma in Computer Science in 2004 and a Doctorate in Science in 2008. He has received\na few awards, most notably the 2010 Georges Giralt PhD Award given by the European Robotics\nResearch Network (EURON) for the best robotics thesis in Europe, the 2011 IEEE/RSJ International\nConference on Intelligent Robots and Systems (IROS) Best Paper Award, the 2016 IEEE Robotics and\nAutomation Society Early Career Award and the 2016 Heinz Maier-Leibnitz Prize from the German\nResearch Foundation. His research focuses on the planning and control of movements for autonomous\nrobotic locomotion and manipulation with larger interests at the intersection between automatic\ncontrol, optimization, applied dynamical systems and machine learning. Website:\nhttp://motiongroup.is.tuebingen.mpg.de/   \n\n  
DTSTART;TZID=Europe/Berlin;VALUE=DATE:20161108
URL;VALUE=URI:https://www.ist.uni-stuttgart.de/de/veranstaltungen/Vortrag-von-Dr.-Ludovic-Righetti/
END:VEVENT
END:VCALENDAR