Skip navigation.

Call for Papers - RSS 2008 Workshop - Interactive Robot Learning

[pdf]

http://www.dfki.de/cosy/www/events/InteractiveRobotLearning2008/

The organizers invite you to submit a research abstract for review to the RSS 2008 Workshop on Interactive Robot Learning. The workshop will take place on Saturday, June 28th at the Swiss Federal Institute of Technology Zurich in Zurich, Switzerland.

Important Dates:

submission deadline - April 30th

notification of acceptance - May 15th

workshop - June 28th


Description:

This workshop on Interactive Robot Learning will span the breadth of research questions at the intersection of Machine Learning and Human-Robot Interaction.

Many future applications for autonomous robots bring them into human environments as helpful assistants to untrained users in homes, offices, hospitals, and more. These applications will often require robots to flexibly adapt to the dynamic needs of human users. Rather than being pre-programmed at the factory with a fixed repertoire of skills, these personal robots will need to be able to quickly learn how to perform new tasks and skills from natural human instruction. While there are numerous examples of successful applications of Machine Learning algorithms, this scenario poses new problems for the field. Learning in real-time from everyday people, unfamiliar with Machine Learning or robotics, is a new domain with new challenges for the field.

There are several open research questions in Interactive Robot Learning, these are some of the topics we hope to address in this full-day workshop:

  • Typical metrics of Machine Learning success may not be appropriate for interactive robot learning. In addition to speed and efficiency of the learning process, there are other dimensions of success like the ease of interaction and the transparency of the process for the human. 
  • What kinds of input can one expect a human partner to provide? Often input channels are specified by the robot learning designer, but we need to also consider whether or not this will be intuitive for an everyday human user.
  • How to best integrate human input into Machine Learning algorithms. A fundamental question is: Do we need new algorithms, or reformulations of existing algorithms?
  • A significant topic for the workshop will be highlighting new work and state-of-the-art approaches to robots learning from people: Learning by demonstration, Learning by imitation, Reinforcement Learning, among others.

Keywords:

  • Human-Robot Interaction
  • Machine Learning
  • Learning by demonstration
  • Learning by imitation
  • Reinforcement learning with human input
  • Active Learning
  • Communication of knowledge and metaknowledge
  • Identification of new requirements for ML in social domains
  • Identification of suitable metrics for interactive learning
  • User studies in interactive robot learning
  • ...

Submission:

All accepted abstracts will be published in a workshop proceedings. New results are welcome. We also encourage researchers with relevant work to retarget previously published results to the workshop topic. Authors will be asked to present their work as a talk or poster.

All submissions should be a research abstract in PDF format using the RSS template ( http://www.roboticsconference.org/doc/rss2008_paper_template.tgz). Abstracts should be two pages in length and describe the material to be presented at the workshop.

Submissions should be emailed to athomaz_@_cc_._gatech_._edu by April 30th. Notification of acceptance will be given on or before May 15th.

Organizers:

  • Andrea L. Thomaz (Georgia Institute of Techonolgy)
  • Geert-Jan M. Kruijff (Language Technology Lab, DFKI GmbH)
  • Henrik Jacobsson (Language Technology Lab, DFKI Gm
  • Danijel Skocaj (University of Ljubljana)

SUBMISSION DEADLINE: APRIL 30, 2008

News


April 3, 2008
Preliminary website up

April 4, 2008
CFP distributed

May 26, 2008
Program created

July 20, 2008
Program updated

August 30, 2008
Proceedings uploaded