So, Where’s My Robot?

Thoughts on Social Machine Learning

ICDL 2010

Last week I attended the IEEE International Conference on Development and Learning, held at the University of Michigan.  This is an interesting conference that I’ve been going to for the past few years.  It’s goal is to very explicitly mingle researchers working on Machine Learning and Robotics with researchers working on understanding human learning and development.

My lab had two presentations

  • “Optimality of Human Teachers for Robot Learners” (M. Cakmak, A. L. Thomaz):  Here we take the notion of teaching in Machine Learning Theory, and analyze the extent to which people teaching our robot are adhering to theoretically optimal strategies.  Turns out they teach about positive examples optimally, but not negative.  And we can use active learning in the negative space to make up for people’s non-optimality.
  • “Batch vs. Interactive Learning by Demonstration” (P. Zang, R. Tian, A.L. Thomaz, C. Isbell): We show the computational benefits of collecting LbD examples online rather than in a batch fashion.  In an interactive setting people automatically improve their teaching strategy when it is sub-optimal.

And here are some cool things I learned at ICDL.

Keynote speaker, Felix Warneken, gave a really interesting talk about the origins of cooperative behavior in humans.  Are people helpful and good at teamwork because you learn it, or do we have some predisposition?  His work takes you through a series of great experiments with young children, showing that helping and cooperation are things we are at least partly hardwired to do.

Chen Yu, from Indiana, does some really nice research looking into how babies look around a scene, and how this is different than adults or even older children.  They do this by having them wear headbands with cameras, then they can do some nice correlations across multiple video streams and audio streams to analyze the data.  For younger children, visual selection is very tied to manual selection.  And the success of word learning is determined by the visual dominance of the named target.

Vollmer et al, from Bielefeld, did an analysis of their motionese video corpus, and showed the different ways that a child learner gives feedback to an adult teacher.  Particularly that this changes from being dominated by gaze behaviors, to more complex anticipatory gestures between the ages of 8mo to 30 mo.

Several papers touched on the topic of Intrinsic motivation for robots, as inspired by babies and other natural learners.   Over the past few years there has been growing interest in this idea.  People have gone from focusing on curiosity and novelty, to competence and mastery.   There were papers on this topic from Barto’s lab, and from Oudeyer’s.  The IM CLeVeR project was also presented, this is a large EU funded collaboration that aims to address intrinsic motivation for robots.

August 27th, 2010 Posted by | Conferences, GT Lab Updates | no comments

Robots 2012, Your Tax Dollars at Work

Exciting news recently in the realm of robotics and public policy. Robotics is recommended as a Science and Technology Priority for the 2012 budget.  The recent OSTP/OMB memo lists six challenge areas, the first of which is “Promoting sustainable economic growth and job creation,” and one of the three recommendations in this section is:

“Support R&D in advanced manufacturing to strengthen U.S. robotics, cyber-physical systems, and flexible manufacturing.”

Congratulations to Henrik Christensen and all of those in the robotics community that have worked hard over the past couple of years to educate the science and technology policy makers about the ways in which robotics research and development can have a positive impact on the U.S. economy and society.

August 9th, 2010 Posted by | Industry | no comments

Autom’s On the Way

Autom the weight loss coach has been on a media tour of late, running up to the first release later this year.  She was looking good on a “Fox and Friends” segment this past weekend.  And the great pic on the left is from some recent coverage in the Tech Review.  You can also check the Robots podcast episode with Autom inventor, Cory Kidd, to hear more about the science behind their design of a social robot for healthcare.

Looks like you’ll be able to get your own Autom from Intuitive Automata for $500 in just a few months. Looking forward to seeing how people do with them!

August 2nd, 2010 Posted by | In the News, Industry | no comments