NIPS*95 Post-Conference Workshop on Robot Learning

[Maja Mataric]

----------------------------------------------------------------

CALL FOR PARTICIPATION:

Robot Learning III -- Learning in the "Real World"

A NIPS*95 Post-conference Workshop
Vail, Colorado, Dec 1, 1995

----------------------------------------------------------------
The goal of this one-day workshop is to provide a forum for
researchers active in the area of robot learning. Due to the limited
time available, we will focus on one major issue: the difficulty of
going from theory and simulation to practice and actual implementation
of robot learning.

A wide variety of algorithms have been developed for learning in
robots and, in simulation, many of them work quite well. However,
physical robots are faced with sensor noise, control error,
non-stationary environments, inconsistent feedback, and the need to
operate robustly in real time. Most of these aspects are difficult to
simulate accurately, yet have a critical effect on the learning
performance.  Unfortunately, very few of the developed learning
algorithms have been empirically tested on actual robots, and of those
even fewer have repeated the success found in simulated domains.

Some of the specific questions we plan to discuss are:

   How can we handle noise in sensing and action without a priori models?
   How do we build in a priori knowledge?
   How can we learn in real time with exploration in real time?
   How can we construct richer reward functions, incorporating feedback,
     shaping, multi-model reinforcement, etc?

This workshop is intended to serve as a followup to previous years'
post-NIPS workshops on robot learning. The morning session of the
workshop will consist of short presentations of problems faced when
implementing learning in physical robots, followed by a general
discussion guided by a moderator. The afternoon session will
concentrate on actual implementations, with video (and hopefully live)
demonstrations where possible. As time permits, we will also attempt
to create an updated "Where do we go from here?" list, following the
example of the previous years' workshops. The list will attempt to
characterize the problems that must be solved next in order to make
progress in applied robot learning.

Talks by:

   Stefan Schaal, Georgia Tech, ATR
     "How Hard Is It To Balance a Real Pole With a Real Arm?"

   Sebastian Thrun, Carnegie Mellon University,
     "Learning More from Less Data: Experiments in Lifelong Robot Learning" 

   Maja Mataric, Brandeis University
     "Complete Systems Learning in Dynamic Environments" 

   Marcos Salganicoff, University of Delaware, A.I. Dupont Institute 
     "Robots are from Mars, Learning Algorithms are from Venus:
      A practical guide to getting what you want in a relationship
      with your robot learning implementation"

The targeted audience for the workshop are those researchers who are
interested in robot learning and robots in general. We expect to draw
an eclectic audience, so every attempt will be made to ensure that
presentations are accessible to people without any specific background
in the field.

-----------------------------------------------------------------------
Organized by: Maja Mataric, Brandeis University    maja at cs.brandeis.edu
              David Cohn, MIT and Harlequin, Inc.  cohn at harlequin.com