No subject

Marcus Quintana Mitchell marcus at dope.caltech.edu
Thu Oct 20 15:07:25 EDT 1994


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

                      NIPS*94 Workshop:


     OPEN AND CLOSED PROBLEMS IN NEURAL NETWORK ROBOTICS
     ---------------------------------------------------
 
                  Organizer: Marcus Mitchell

                    CALL FOR PARTICIPATION
                    ---------------------- 


Introduction
-------------

Many of the presumed tenets of neural computation -- nonlinearity,
parallelism, adaptation, real-time performance -- suggest that a
"neuromorphic" approach to robotics problems could succeed where previous
approaches have failed. Further, the amazing motor performance of humans
and animals provides additional arguments for the potential benefits of "a
sideways look" towards neurobiology. Spurred on by these and other factors,
researchers from a variety of backgrounds have produced almost 15 years of
research intended to elaborate a biologically-inspired robotics. This 
workshop will ask the questions "What has been accomplished so far?" and
"What is to be done next?"

Aims
----

For all the research attempts to apply neural network ideas to robotics, it
is still difficult to get clear answers to questions like "Can you use a
neural network to control a 6 d.o.f. arm?" or "Do reinforcement learning
learning and dynamic programming methods get killed by the curse of
dimensionality?" In addition, robotics is an area with a vast and intimidating 
"non-neural" literature which must be considered. The main goal of this
workshop is to stimulate discussion about what problems have been
successfully attacked and what the most important current open problems
entail. A secondary goal of the workshop is to produce a short consensus
list of problem descriptions and their status. 

Schedule for Saturday, December 3, 1994
---------------------------------------
(subject to change)

7:30 - 8:00     Opening Remarks
                Marcus Mitchell, Caltech

8:00 - 8:25     Why it's harder to control your robot than your arm:
                closed, open and irrelevant issues in inverse kinematics
                Dave Demers, UCSD

8:25 - 9:00     Discussion

9:00 - 9:25     Open Problem:  Optimal Motor Hidden Units
                Terry Sanger, JPL

9:25 - 10:00     Discussion

10:00 - 10:25   Neural Network Vision for Outdoor Robot Navigation
                Dean Pomerleau, CMU

10:25 - 11:00   Discussion

11:00 - 4:30     FREE TIME

4:30 - 4:55     Learning New Representations and Strategies 
                Chris Atkeson, Georgia Tech

4:55 - 5:30     Discussion

5:30 - 5:55     A Semi-Crisis for Neural Network Robotics:
                Formal Specification of Robot Learning Tasks
                Andrew Moore, CMU

5:55 - 6:30     Discussion

6:30 - 6:35     Closing Remarks


Related workshop on control
---------------------------

A complementary workshop, titled "Novel Control Techniques from Biological
Inspiration", organized by Jim Schwaber et al., may be of interest to 
participants. None of the presentations in that session will be on robotics, 
and its main focus will be on nonlinear dynamical systems, e.g. in chemical 
processes and in neural systems. It is a one day workshop to be held Friday,
December 2, 1994.
For more information contact Richard Braatz (rdb at beethoven.che.caltech.edu). 

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

Marcus Q. Mitchell
Computation and Neural Systems, Mail Code 139-74
California Institute of Technology 
Pasadena, CA 91125
Phone: (818) 395-2805 FAX: (818) 792-7402
email: marcus at hope.caltech.edu



More information about the Connectionists mailing list