BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:When will we have intelligent robots? - Professor Jitendra Malik\,
  Berkeley 
DTSTART:20240507T140000Z
DTEND:20240507T150000Z
UID:TALK216592@talks.cam.ac.uk
CONTACT:Kimberly Cole
DESCRIPTION:Deep learning has resulted in remarkable breakthroughs in fiel
 ds such as speech recognition\, computer vision\, natural language process
 ing\, and protein structure prediction. Robotics has proved to be much mor
 e challenging as there are no pre-existing repositories of behavior to dra
 w upon\; rather the robot has to learn from its own trial and error in its
  own specific body\, and it has to generalize and adapt.  I believe that t
 he most promising approach for this is to train robot skills in simulation
  and then transfer them to the real world.  I will show multiple examples 
 of skills - legged locomotion (quadruped and humanoid)\, navigation\, and 
 dexterous manipulation such as  in-hand rotation and twisting caps off bot
 tles - acquired in this paradigm. Along the way\, we developed “Rapid Mo
 tor Adaptation”\, a method for adaptive control in the framework of deep
  reinforcement learning. Looking to the future\, I believe that there are 
 multiple insights from the development of motor skills in children  that a
 re relevant to robotics\; I will sketch some examples and partial results.
   While we are many years away from having robots with the skills of a fiv
 e year old\, progress in the last few years has been remarkable and substa
 ntial.
LOCATION:Department of Engineering - LR4
END:VEVENT
END:VCALENDAR