BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Exploiting Variable Impedance for Robotics: Mimic or Optimize? - S
 ethu Vijayakumar\, Department of Informatics\, University of Edinburgh
DTSTART:20120214T140000Z
DTEND:20120214T150000Z
UID:TALK36355@talks.cam.ac.uk
CONTACT:Microsoft Research Cambridge Talks Admins
DESCRIPTION:It is the year of the London Olympics and appropriately\, this
  talk is about making robots run faster\, jump higher and throw further. V
 ariable Impedance refers to the ability to change stiffness and damping du
 ring task execution. With novel prototype robotic actuators capable of fas
 t impedance modulation\, the obvious question is how we can maximally expl
 oit this capability in an automatic and data driven manner? In this talk\,
  I will look at impedance modulation in three different classes of movemen
 ts: point-to-point tasks like reaching\, explosive movement tasks like thr
 owing and rhythmic movement tasks such as walking and running. I will desc
 ribe an optimal control based formulation of optimizing both the temporal 
 profile of movement and impedance modulation in a way that is tuned to the
  dynamics of the plant. Several hardware tests will serve to highlight the
  benefits. Further\, I will illustrates the pitfalls of naively mimicking 
 impedance profiles across heterogeneous systems (e.g.\, human limb to VS j
 oints or MACCEPA actuators) and describe a framework that is capable of ab
 stracting out the specific plant dynamics while ensuring task optimality. 
 This talk will draw upon concepts of optimal feedback control\, apprentice
 ship learning and model free reinforcement learning besides fundamentals o
 f dynamics representation and learning.
LOCATION:Small public lecture room\, Microsoft Research Ltd\, 7 J J Thomso
 n Avenue (Off Madingley Road)\, Cambridge
END:VEVENT
END:VCALENDAR