From: Eugene Leitl (Eugene.Leitl@lrz.uni-muenchen.de)
Date: Sat Jun 28 1997 - 03:40:31 MDT
---------- Forwarded message ----------
Date: Fri, 27 Jun 1997 10:50:54 +0200
From: Patrick van der Smagt <smagt@dlr.de>
To: connectionists@cs.cmu.edu
Newgroups: comp.ai.neural-nets
Subject: NIPS*97 Workshop: robots & cerebellum
NIPS'97 Postconference Workshop
===============================
Can Artificial Cerebellar Models Compete to Control Robots?
http://www.op.dlr.de/FF-DR-RS/CONFERENCES/nips-workshop/
Objective:
----------
Recent successes in robotics have broadened the field of application
and acceptation of robots. Nevertheless, industrial robotics still
has to go a long way. While the applicability of classical robots
remains limited to factory floors, research lab robotics is moving
towards novel actuators for constructing light-weight, compliant robot
arms. Hereto actuators are needed which consist of agonist-antagonist
drive pairs for maintaining accurate positioning without recalibration,
as well as for controlling the stiffness of a joint. However, when
these joints are combined to construct a robot arm, existing
algorithms can only inaccurately control the arm at low velocities.
Starting from Albus' model from the 70's, neuro-computational models
of the cerebellum have been advocated as possible candidates for the
control of complex robot systems. Unfortunately, there have been very
few applications of cerebellar models to the control of real robot
manipulators with at least 6 degrees of freedom. Cerebellar models
have become more refined through specialised investigations based on
details of the biological cerebellar system, while insufficient
attention has been given to applicability of these refinements in
robotics. In the development of these methodologies, there are few
examples of successful integration of neuro-computational models.
In this workshop we want to investigate how neuro-computational models
might be incorporated as a standard part of robotics. We want to
address two questions: How reasonable is the desire for such an
amalgamation? What prerequisites are there for having cerebellar
models successfully compete with alternative approaches to control of
real robots?
These questions will be addressed through the presentation of papers
which:
1. describe biologically plausible models of sensory-motor control;
2. apply cerebellar models to the control of robot manipulators;
3. describe robot control methodologies that can incorporate
cerebellar or other neuro-computational model (e.g., vision);
4. provide a case history illustrating barriers to successful
competition by cerebellar models for robot control.
Call for Contributions
======================
For the workshop we will be looking for talks and papers which:
* describe research applying cerebellar models to robot
applications implemented on real robots;
* describe biologically plausible models of
sensory-motor control;
* describe robot control methodologies that can incorporate
cerebellar or other neuro-computational model (e.g., vision);
* provide a case history illustrating barriers to successful
competition by cerebellar models for robot control.
Please send your proposals [with a paper or extended abstract]
by August 15, 1997. For more information about submission visit
http://www.op.dlr.de/FF-DR-RS/CONFERENCES/nips-workshop/
Workshop organisers:
====================
Patrick van der Smagt
Institute of Robotics and System Dynamics
German Aerospace Research (DLR)
Wessling, Germany
mailto:smagt@dlr.de
Daniel Bullock
Cognitive and Neural Systems Department
Boston University
Boston, MA 02215
mailto:danb@cns.bu.edu
-- dr Patrick van der Smagt phone +49 8153 281152 DLR/Institute of Robotics and Systems Dynamics fax +49 8153 281134 P.O. Box 1116, 82230 Wessling, Germany email <smagt@dlr.de>
This archive was generated by hypermail 2.1.5 : Fri Nov 01 2002 - 14:44:32 MST