NNR 2016 - 2016 Workshop on Nature vs. Nurture in Robotics

2016 Workshop on Nature vs. Nurture in Robotics*
Friday, May 20 2016 in Stockholm, Sweden
http://mobilemanipulation.org/nvsn/
===
CALL FOR POSTERS
We call for posters on nature vs. nurture (or engineering vs. machine
learning) in robotics. We solicit submissions from a broad spectrum of
contributions including but not limited to descriptions of robotic
systems, technical advances, experimental results, theoretical results,
and philosophical arguments. These contributions can pertain to robotics
in general or to specific subfields, e.g. computer vision, planning,
control, manipulation, or navigation.
To participate, please submit a short abstract as PDF via email to
rico.jonschkowski-AT-tu-berlin.de. Accepted contributions will be presented
in a one-minute spotlight talk and during a 30 minute poster session.
===
IMPORTANT DATES
March 30th: Submission deadline
April 6th: Acceptance notification
May 20th: Workshop
===
NATURE VS. NURTURE IN ROBOTICS
The nature versus nurture debate concerns how much an individual is
defined by innate properties versus how much it is shaped by experience.
Concerning humans, there is a consensus in psychology that we are the
product of the interaction of both, nature and nurture. We believe that
the same must be true for intelligent robots, where nature corresponds
to engineered solutions and nurture corresponds to machine learning.
Therefore, also in our field, it is essential to study the interaction
of nature and nurture?or rather engineering and learning: How can we
decide which parts of an intelligent robot should be engineered by
humans and which should be left unspecified to be learned by the robot?
We think that this is an essential question that needs to be discussed
to identify promising research directions towards creating intelligent
robots. This matter is especially pressing right now, as machine
learning approaches become more common in robotics and it is unclear how
to best combine them with engineering approaches. With the recent
advances in deep learning, other fields like computer vision seem to
switch from an engineering paradigm to a learning-only paradigm. It
stands to debate if this approach is promising.
===
INVITED SPEAKERS
- Pieter Abbeel: "Deep Reinforcement Learning in Robotics"
- Jonas Buchli: "It's All Just Optimization..."
- George Konidaris: "Avoiding Learning by Exploiting Structure"
- Jan Peters: "Encoding or Learning Structure?"
- Marc Toussaint: "Without Nature no Nurture!"