[robotics-worldwide] Deadline Extended JFR Special Issue Machine Learning Based Robotics in Unstructured Environments

Jane Mulligan jane.mulligan at colorado.edu
Wed Feb 22 08:42:41 PST 2006



Journal of Field Robotics
Special Issue on Machine Learning Based Robotics in Unstructured 
Environments
http://journalfieldrobotics.org

Guest Editors: Jane Mulligan, Greg Grudic, University of Colorado at 
Boulder

EXTENDED SUBMISSION DEADLINE: March 31, 2006

This special issue follows the successful NIPS 2005 workshop on the
same topic (http://www.cs.colorado.edu/~janem/NipsMLR.html).

Robots have been successful in tasks where they can be rigidly
programmed for highly structured environments like factory assembly
lines. However, the dream of robots that work alongside or in lieu of
people in natural environments has long evaded researchers in
Artificial Intelligence. Although, progress has been made on robots
that move in stable man-made environments such as offices and
factories, many applications such as search and rescue, security or
even elder care could be addressed if robots could operate robustly in
unknown, dynamic and unstructured spaces. Recent developments in
Machine Learning for complex domains may offer insight into tackling
the problem of mapping many high dimensional sensor readings into
coherent action in these domains.

Submissions to this special issue should investigate and propose
Machine Learning based approaches to autonomous robotic problems in
unstructured environments. As you prepare your submission keep in mind
that JFR emphasizes papers that are backed up with significant results
from the field as opposed to simulation or lab experiments. Full
papers should be submitted via the Journal's online submission page by
March 31, 2006.



Possible topics include:

   -- The use of human teleoperation data to learn autonomous robot
   controllers.

   -- Manifold mapping techniques for identifying the low dimensional
   sensor and actuator space where the robot operates.

   -- Semi-supervised learning techniques for reducing the number of
   training examples required to learn autonomous robot controller
   models.

   -- Reinforcement Learning algorithms for very high dimensional
   spaces where the number of rewards received is very limited.

   -- Identification of what features (extracted from raw sensory data)
   are useful for tasks in unstructured environments.


All articles for the Journal of Field Robotics special issue "Machine
Learning Based Robotics in Unstructured Environments" are to be
submitted through Manuscript Central
(http://mc.manuscriptcentral.com/rob).  Submission through Manuscript
Central is fairly simple and straightforward, and the process is
self-explanatory.

Authors will submit papers as they would to any other Journal of Field
Robotics issue, with two exceptions.

1) Authors will need to click "yes" to a question on the first page: "Is
this submission for a special issue?", and
2) Authors will need to copy and paste (from the instructions on page 5 in
the submission process) the title of the special issue to which they are
submitting.



For complete instructions regarding the regular submission process,
please visit http://www.journalfieldrobotics.org/info.html.  That page
also contains information about file types and reference formatting
for final paper versions.

If you encounter any problems with the submission process, please
email managing editor Dale James: dale at cs.cmu.edu.

We look forward to reading your papers!

Jane & Greg

Extended Submission deadline: March 31, 2006.



More information about the robotics-worldwide mailing list