[robotics-worldwide] [meetings] Deadline Extension: R:SS 2016 - Bootstrapping Manipulation Skills Workshop

Oliver Kroemer oliverkro at googlemail.com
Mon Apr 25 13:28:12 PDT 2016


Deadline Extension for Abstracts and Posters

==================================
R:SS 2016 Workshop on
Bootstrapping Manipulation Skills
==================================

Website: www.bootstrapping-manipulation.com

Important Dates :

New submission deadline: 26 May 2016
New notification of acceptance: 31 May 2016
Workshop date: 19 June 2016


Abstract :

When we talk about "learning a manipulation skill" in robotics, the robot
is often learning only one component of the skill. For example, "learning
to grasp" often focuses on learning a suitable grasp frame, while assuming
that the grasp controller and the success conditions are predefined. In
this manner, the predefined components define the learning problem for the
remaining component. However, relying on predefined components limits the
autonomy of the robot. Instead, robots should bootstrap the skill
acquisition process and learn multiple components together.

In recent years, researchers have proposed different paradigms for learning
multiple skill components. These approaches include learning components
sequentially using scaffolding, decomposing demonstrations using
segmentation, and sharing components between skills using transfer
learning. Researchers have also been exploring different information
sources for bootstrapping skills, such as learning from demonstration,
crowdsourcing, learning from planning, and self-exploration.

In this workshop, we want to bring together researchers to discuss
different approaches for bootstrapping the skill learning process. Central
to the discussion will be three key questions:

1. What are the different components of manipulation skills that robots can
learn?

2. What (external) information sources can be used to initialize skill
bootstrapping?

3. Which learning frameworks can be used to acquire multiple components
together?

In order to encourage discussion, the workshop will include morning and
afternoon poster sessions, a brainstorming session, and invited talks that
cover different aspects of skill bootstrapping. The ultimate goal of the
workshop is to identify taxonomies of information sources, paradigms for
bootstrapping manipulation skills, and open problems.


Invited Speakers :

Michael Beetz (University of Bremen)
Maya Cakmak (University of Washington)
Sonia Chernova (Georgia Institute of Technology)
Kris Hauser (Duke University)
Ashutosh Saxena (Cornell University and Stanford University)
Stefanie Tellex (Brown University)
Emre Ugur (Boğaziçi University and Innsbruck University)


Submissions :

We are soliciting submissions of extended abstracts of 1-2 pages on recent
work that is relevant to the workshop. We welcome any work that explores
learning for manipulation skills. We especially encourage submissions that
investigate learning multiple skill components, or a novel source of
information for bootstrapping the learning process. Abstracts should be
submitted as PDF files using the same format as for the main R:SS
conference submissions.

Submissions should be submitted by email to:
submissions at bootstrapping-manipulation.com

Abstracts will be single-blind reviewed on the basis of relevance,
significance, and clarity. The accepted contributions will be presented as
posters during the workshop. The authors will also have the chance to give
a short spotlight presentation of their work.

Submission deadline: 26 May 2016
Notification of acceptance: 31 May 2016

Submitted abstracts will be reviewed as soon as possible. Authors that
submit their abstract early may therefore also receive the notification of
acceptance earlier.


Organizers:

Oliver Kroemer, University of Southern California
Scott Niekum, University of Texas at Austin
George Konidaris, Duke University
Manuel Lopes, INRIA


More information about the robotics-worldwide mailing list