[robotics-worldwide] CALL FOR POSTER SUBMISSIONS: RSS Workshop on combining discrete and continuous representations for robotics

Dana Kulic dana at ynl.t.u-tokyo.ac.jp
Wed Mar 18 02:36:43 PDT 2009


CALL FOR POSTER SUBMISSIONS

RSS 2009 Workshop on bridging the gap between high-level discrete
representations and low-level continuous behaviors

http://learning-robots.de/TC/RSS2009

Sunday, June 28, 2009 in Seattle, WA 
As part of the Robotics: Science and Systems Conference
(www.roboticsconference.org) 

Important Dates

April 20, 2009  Poster Abstract Submission Deadline
May 15, 2009  Notification of Acceptance
June 28, 2009  Workshop

Introduction

Recently, robotics researchers have been investigating the modeling of human
and robot behavior in terms of motion primitives. This research direction,
based on biological and neuroscience findings, posits that human behavior is
composed of motor primitive units, which can be acquired by a robot through
imitation learning or practice. Motion primitives offer an approach for
discretizing continuous behavior, representing a "bottom-up" approach for
organizing robot behavior.  On the other hand, in AI and planning fields,
there has been a longstanding area of research in planning and acting in the
discrete domain, or through modeling changes in the world as an
instantaneous change in discrete state. This approach can be thought of as a
"top-down" approach for organizing robot behavior. In this workshop, we hope
to bring together researchers from both areas to discuss approaches for
"bridging the gap" and combining continuous domain approaches with discrete
representations.

Topics of Interest

We invite poster submissions from researchers working on combining discrete
representations with continuous behaviors for robotic systems.  Specific
topics of interest include: 
  
-          motion primitive representations and task abstractions 
-          learning and parsing sequences and plans of motion primitives 
-          imitation learning and learning from observation based on motion
primitives 
-          hierarchical reinforcement learning 
-          apprenticeship learning of composed tasks 
-          hybrid task control 
-          hierarchical organization of behaviors 
-          learning operator conditions for primitives 
-          plan recognition 
-          plan generation and modification 

Submission Guidelines

Authors should submit a 1-2 page abstract of their poster by email to
postersubmissions at learning-robots.de, by April 20, 2009.


Workshop Organizers 
Dana Kulić 
Department of Mechano-Informatics 
University of Tokyo 
dana at learning-robots.de

Pieter Abbeel 
Department of Electrical Engineering and Computer Science 
University of California at Berkeley 
pabbeel at cs.berkeley.edu 

Jan Peters 
Department for Empirical Inference and Machine Learning 
Max Planck Institute of Biological Cybernetics 
mail at jan-peters.net 





More information about the robotics-worldwide mailing list