<html><head></head><body style="word-wrap: break-word; -webkit-nbsp-mode: space; -webkit-line-break: after-white-space; "><div><br></div><div><div>IEEE Transactions on Autonomous Mental Development</div><div>Special Issue on</div><div>Behavior Understanding and Developmental Robotics</div><div> </div><div>Call for Papers</div><div> </div><div>We solicit papers that inspect scientific, technological and application</div><div>challenges that arise from the mutual interaction of developmental robotics</div><div>and computational human behavior understanding. While some of the existing</div><div>techniques of multimodal behavior analysis and modeling can be readily</div><div>re-used for robots, novel scientific and technological challenges arise</div><div>when one aims to achieve human behavior understanding in the context of</div><div>natural and life-long human-robot interaction. We seek contributions that</div><div>deal with the two sides of this problem:</div><div> </div><div>1- Behavior analysis for developmental robotics: Robots need to be capable</div><div>to learn dynamically and incrementally how to interpret, and thus</div><div>understand multimodal human behavior. This includes for example learning</div><div>the meaning of new linguistic constructs used by a human, learning to</div><div>interpret the emotional state of particular users from para-linguistic or</div><div>non-verbal behavior, characterizing properties of the interaction or</div><div>learning to guess the intention, and potentially the structure of goals of</div><div>a human based on its overt behavior. Furthermore, robots need in particular</div><div>to be capable of learning new tasks through interaction with humans, for</div><div>example using imitation learning or learning by demonstration. This heavily</div><div>involves the capacity for learning how to decode teaching behavior,</div><div>including linguistic and non-linguistic cues, feedback and guidance</div><div>provided by humans, as well as inferring reusable primitives in human</div><div>behavior.</div><div> </div><div>2- Behavior analysis through developmental robotics: Developmental social</div><div>robots can offer stimulating opportunities for improving scientific</div><div>understanding of human behavior, and especially to allow a deeper analysis</div><div>of the semantics and structure of human behavior. Humans tend to interpret</div><div>the meaning and the structure of other's behaviors in terms of their own</div><div>action repertoire, which acts as a strong helping prior for this complex</div><div>inference problem. Since robots are also embodied and have an action</div><div>repertoire, this can be used leveraged as an experimental and theoretical</div><div>tool to investigate human behavior, and in particular, the development and</div><div>change of behavior over time.</div><div> </div><div>Topics include the following, among others:</div><div>Adaptive human-robot interaction</div><div>Action and language understanding</div><div>Sensing human behavior</div><div>Incremental learning of human behavior</div><div>Learning by demonstration</div><div>Intrinsic motivation</div><div>Robotic platforms for behavior analysis</div><div>Multimodal interaction</div><div>Human-robot games</div><div>Semiotics for robots</div><div>Social and affective signals</div><div>Imitation</div><div> </div><div>Contributions can exemplify diverse approaches to behavior analysis, but</div><div>the relevance to developmental robotics should be clear and explicitly</div><div>argumented. In particular, it should involve one of the following: 1)</div><div>incremental and developmental learning techniques, 2) techniques that allow</div><div>adapting to changes in human behavior, 3) techniques that study evolution</div><div>and change in human behavior. Interested parties are encouraged to contact</div><div>the editors with questions about the suitability of a manuscript.</div><div> </div><div>Editors:</div><div>• Albert Ali Salah, Bogaziçi University, </div><a href="mailto:salah@boun.edu.tr">salah@boun.edu.tr</a><div><br></div><div>• Pierre-Yves Oudeyer, INRIA, </div>pierre-yves.oudeyer@inria.fr<div><br></div><div>• Çetin Meriçli, Carnegie Mellon University, </div>cetin@cmu.edu<div><br></div><div>• Javier Ruiz-del-Solar, Universidad de Chile, </div>jruizd@ing.uchile.cl<div><br></div><div> </div><div>Three kinds of submissions are possible:</div><div>• Regular papers, up to 15 double column pages, should describe new</div><div>empirical findings that utilize innovative methodological and/or analytic</div><div>techniques.</div><div>• Correspondence papers, up to 8 double column pages, can focus on a</div><div>limited set of relevant aspects in depth.</div><div>• Survey papers, describing classes of behavior analysis approaches in</div><div>developmental robotics. Before submitting a survey paper, the authors</div><div>should contact the guest editors.</div><div> </div><div>Instructions for authors:</div><br class="Apple-interchange-newline"><a href="http://cis.ieee.org/ieee-transactions-on-autonomous-mental-development.html">http://cis.ieee.org/ieee-transactions-on-autonomous-mental-development.html</a><br><div><br></div><div>We are accepting submissions through Manuscript Central at</div><br class="Apple-interchange-newline"><a href="http://mc.manuscriptcentral.com/tamd-ieee">http://mc.manuscriptcentral.com/tamd-ieee</a><br><div> (please select “Human Behavior</div><div>Understanding” as the submission type)</div><div>When submitting your manuscript, please also cc it to the editors.</div><div> </div><div>Timeline:</div><div> </div><div>30 April 2013: Deadline for paper submission</div><div>15 July 2013: Notification of the first round of review results</div><div>15 October 2013: Final version</div><div>20 October 2013: Electronic publication</div><div>December 2013: Printed publication</div><br class="Apple-interchange-newline"><br></div></body></html>