ACTIVE LEARNING IN ROBOTICS
We invite interested researchers to submit abstracts to the Humanoids 2014
workshop on Active Learning in Robotics: Exploration Strategies in Complex
Environments. The workshop will take place on November 18th, in Madrid,
Spain.
SUMMARY
The design of agents that can learn complex skills by themselves is still
in its
infancy. One bottleneck is the lack of labelled data. Datasets are often
limited
in size and coverage, since they need experiments on robots or expensive
simulations. Thus an important capability of every robot in complex
environments
is to gather new data.
To do this efficiently, intelligent robots need to be able to identify which
task-relevant information is still missing. Only this ability enables
agents to
actively work towards a better understanding of the environment, the agent's
state, and the task at hand, which will eventually lead to better
performance.
Active learning is an approach to gain this ability. Within this paradigm
the
agent chooses the next data point to achieve the best learning result with
as
few data points as possible. Such strategies can shorten the process of data
gathering significantly and also lead to the important information more
quickly.
OBJECTIVES
In this workshop, we want to discuss the state of the art of active
learning in
robotics, but also address important open questions, such as:
* What representation of knowledge allows efficient reasoning about it?
* What are successful strategies based on these representations?
* How can we generalize or transfer experiences to decrease the need of
data?
* How to explore safely without damaging the robot and its environment?
* How can existing approaches be `scaled up' to real world domains?
We aim for this variety of topics to be represented by participants from the
robotics and machine learning communities.
CALL FOR POSTERS
We invite authors who work on topics related to the workshop to submit
1-2-page
abstracts. All abstracts will be considered for a poster session.
Submissions
should be send to
active-learning-in-robot...@ipvs.uni-stuttgart.de
before October 7th, 2014.
Both theoretical findings as well as experimental results are encouraged to
be
submitted. The abstracts will be reviewed by the organizing committee. The
review process is non-blind. We encourage work-in-progress to be submitted
and
will take this into account in the review process. Notifications of
acceptance
will be given by October 21st.
DATE AND LOCATION
November 18th 2014
IEEE-RAS International Conference on Humanoid Robots
Hotel Melia Castilla, Madrid, Spain
WEBSITE AND SCHEDULE
All information regarding the workshop will be published on the website
http://www.robot-learning.de/Workshops/Humanoids2014ActiveLearning. Soon,
the workshop schedule will be posted there as well.
ACKNOWLEDGMENT
The workshop will be funded by the DFG (German Science Foundation) within
the
priority program "Autonomous Learning" (SPP 1527).
ORGANIZING COMMITTEE
Johannes Kulick, University of Stuttgart
Herke van Hoof, Technische Universität Darmstadt
Marc Toussaint, University of Stuttgart
and Jan Peters, Technische Universität Darmstadt &
Max Planck Institute for Intelligent Systems
_______________________________________________
uai mailing list
uai@ENGR.ORST.EDU
https://secure.engr.oregonstate.edu/mailman/listinfo/uai
