Sie sind auf Seite 1von 27

IEEE

ICDL-EPIROB
2013
sponsored by:
The Third Joint IEEE International
Conference on Development and Learning
and on Epigenetic Robotics
Osaka City Central Public Hall,
Osaka, Japan
August 18-22, 2013
Conference Booklet
Welcome Address 1
Organization 2
Sponsors 4
Invited Speakers 5
Program 9
Venue 17
Getting there 21
Internet 22
Author List 23
Table of Contents
1
Welcome Address
Welcome to the third IEEE International Conference on Development and Learning and on
Epigenetic Robotics in Osaka. The conference brings a diverse group of researchers across the
globe spanning computational, developmental, and brain sciences. While some of us are
concerned primarily with using computational simulations and embodied robotics as models of
development and learning processes in humans as part of a larger science of development that
includes behavioral and neuroscientific studies of humans from infancy to adulthood, others
emphasize the important role development may have in artificial agents regardless of how well
such systems model anything that occurs in human beings. Such developmental processes may
still be the best way to achieve intelligent, embodied agents, biological or not.
ICDL-EpiRob is organized with a single presentation track, designed to encourage cross-
disciplinary interaction and discussion. It features four keynote addresses from prominent
experts, 41 full papers and 13 short papers of which 21 oral and 33 poster presentations were
selected. In the spirit of the interdisciplinary nature of both ICDL and EpiRob, we ensured that
each paper was assigned to program committee members (meta-reviewers) and reviewers from
both natural intelligence and computational intelligence backgrounds. The reviews were careful,
extensive, and helpful to the authors, whatever the outcome of the review process. Final
decisions were made by the Program Chairs, based on the reviews and suggestions of the meta-
reviewers. Papers accepted for oral presentation were selected from a larger subset of the highest
ranks papers after the review to ensure broad coverage of the diverse topics represented at this
conference.
In addition, for the organizing and review, ICDL-EpiRob relied on the effort of a large number of
people. Publicity Co-Chairs Testuya Ogata and Gedeon Deak helped publicize the conference.
Publication Co-Chairs Joschka Boedecker, Matthias Rolf and Lars Schillingmann assembled the
Proceedings USB stick and worked with IEEE to publish and archive your excellent work. Hiroki
Mori and Hisashi Ishihara worked hard on various local arrangements including creation and
updates of the conference webpage. Bridge Co-Chairs Minoru Asada, Giulio Sandini, and Linda
Smith facilitated communication across multiple disciplines and across the continents. We would
also like to thank the many anonymous people who contributed to the success of this conference.
Jun Tani, Program Chair,
Giorgio Metta, Program Chair,
Yukie Nagai, General Chair,
Angelo Cangelosi, General Chair,
Chen Yu, General Chair
2
Organization
Organization committee
General chairs:
Bridge chairs:
Program chairs:
Publicity chairs:
Publication chairs:
Local and Finance chairs:
Program Committee
Christian Balkenius, Lund University
TonyBelpaeme, University of Plymouth
Alexandre Bernardino, Istituto Superior Tecnico, Lisbon
Luc Berthouze, University of Sussex
AnnaBorghi, University of Bologna
Kerstin Dautenhahn, University of Hertfordshire
Philippe Gaussier, University of Cergy Pontoise
Frank Guerin, Aberdeen University
Serena Ivaldi, ISIR - CNRS & University Pierre et Marie Curie
Bruno Lara, Universidad Autonoma del Estado de Morelos
Mark Lee, University of Aberystwyth
Manuel Lopes, INRIA Bordeaux
Giorgio Metta, Italian Institute of Technology
Clayton Morrison, University of Arizona
Yukie Nagai, Osaka University
Lorenzo Natale, Italian Institute of Technology
Stefano Nolfi, CNR
Francesco Nori, Italian Institute of Technology
Tim Oates, University of Maryland Baltimore County
Pierre-Yves Oudeyer, INRIA Bordeaux Sud-Ouest
Erhan Oztop, Ozyegin University
Yukie Nagai, Osaka University
Angelo Cangelosi, Plymouth University
Chen Yu, Indiana University
Minoru Asada, Osaka University
Giulio Sandini, IIT
Linda Smith, Indiana University
Jun Tani, KAIST
Giorgio Metta, IIT
Tetsuya Ogata, Waseda University
Gedeon Deak, UCSD
Joschka Boedecker, University of Freiburg
Matthias Rolf, Osaka University
Lars Schillingmann, Osaka University
Hiroki Mori, Osaka University
Hisashi Ishihara, Osaka University
3
Katharina Rohlfing, Bielefeld University
Erol Sahin, Middle East Technical University
Albert A. Salah, Boazii University
Brian Scassellati, Yale University
Matthew Schlesinger, Southern Illinois University
Jochen Triesch, FIAS
Hanako Yoshida, University of Houston
Zhengyou Zhang, Communication and Collaboration Systems Group, Microsoft Research
List of Reviewers
Adams, S.
Alex, P.
Altun, K.
Andry, P.
Balkenius, C.
Baxter, P.
Belpaeme, T.
Berenson, D.
Bernardino, A.
Berthouze, L.
Beuls, K.
Borghi, A.
Bryson, J.
Burling, J.M.
Caligiore, D.
Cangelosi, A.
Caruana, F.
Cederborg, T.
Celikkanat, H.
Cheng, G.
Ciliberto, C.
Connolly, C.
Crick, C.
Da Rold, F.
Dani, S.
Dautenhahn, K.
Dawson, C.R.
de Greeff, J.
Prete, A.
Demiris, Y.
Droniou, A.
Duran, B.
Fanello, S.
Fasel, I.
Feil-Seifer, D.
Foerster, F.
Gardiner, B.
Gaspers, J.
Gaussier, P.
Gerbella, M.
Gogate, L.
Gordon, G.
Gori, I.
Grizou, J.
Grosjean, M.
Grupen, R.
Guerin, F.
Hart, S.
Hart, J.
Hermosillo, J.
Hove, M.
Howard, I.
Ishihara, H.
Ivaldi, S.
Johansson, B.
Kalkan, S.
Kirtay, M.
Klein, M.
Kober, J.
Kose, H.
Kkylmaz, A.
Kuniyoshi, Y.
Lara, B.
Lee, M.
Leyzberg, D.
Lopes, M.
Lopez-Juarez, I.
Lyons, J.
Madden, C.
Mancas, M.
Martius, G.
Mathias, Q.
Metta, G.
Mori, H.
Morlino, G.
Morrison, C.
Mostafaoui, G.
Moulin-Frier, C.
Movellan, J.
Nagai, Y.
Natale, L.
Nguyen, M.
Nolfi, S.
Nori, F.
Noris, B.
O'Reagan, K.
Oates, T.
Ogata, T.
Oudeyer, P-Y.
Oztop, E.
Pastra, K.
Pauw, S.
Pezzulo, G.
Rea, F.
Rebguns, A.
Rohlfing, K.
Rolf, M.
Rossano, F.
Rucinski, M.
Saez, J.
Sahin, E.
Salah, A.A.
Salvi, G.
Sandini, G.
Santucci, V.
Saunders, J.
Scassellati, B.
Schilling, M.
Schillingmann, L.
Schlesinger, M.
Schmill, M.
Sen, S.
Sigaud, O.
Sirois, S.
Solveig Lohan, K.
Stoytchev, A.
Stramandinoli, F.
4
Thill, S.
Tikhanoff, V.
Toussaint, M.
Tran, A.X.
Triesch, J.
Ugur, E.
Sponsors & Supporters
Thanks to the following institutions and companies for their generous support of IEEE ICDL-
EpiRob 2013 in Osaka:
von Hofsten, C.
Walters, M.L.
Weng, J.
Westermann, G.
Wrede, B.
Wright, J.B.
Wykowska, A.
Yoshida, H.
Yu, C.
Ycel, Z.
Zamani, M.A.
Zhang, Z.
Our thanks also go to the following supporters of the conference:
5
Invited Speakers
Anne Fernald, Stanford University, USA
"Cultural variability in adult speech to children: How does it matter?"
Abstract
Research on the early development of cognitive and language capacities has focused almost
exclusively on infants from middle-class families in affluent countries in the U.S., Europe, and
Asia. As a consequence, broad conclusions about what infants know and how parents behave
are typically based on small selective samples of the worlds children, ignoring millions of
children in less affluent countries who fail to achieve their developmental potential. These
studies also typically exclude children growing up in poverty within industrialized societies
whose language growth is also compromised, in part because they experience less cognitive
stimulation in the first years of life. In this presentation we focus on characteristics and
consequences of child-directed-speech (CDS) in different cultures, also exploring variability in
CDS related to differences in socio-economic status (SES) among families within the U.S. In our
longitudinal research on the early development of efficiency in language understanding, we find
robust relations between verbal processing speed in infancy and long-term language outcomes.
However, we also find that significant disparities in vocabulary and language processing
efficiency are already evident at 18 months between infants from higher- and lower-SES families,
and by 24 months there is a 6- month gap between SES groups in processing skills critical to
language development. What accounts for such striking differences among children in their early
language growth? Observational studies have shown that the sheer amount and quality of
caregivers verbal engagement with infants and toddlers are linked to later cognitive and non-
cognitive outcomes and school success. We present new experimental research exploring the
mechanisms that underlie these powerful effects of early experience on language learning, with
the goal of examining their origins, consequences, and social policy implications. By examining
variability in speech to children both between and within diverse cultural groups, we can gain
deeper insight into the potentially powerful contributions of environmental support to the
ontogeny of cognitive and language abilities.
Short biography
Anne Fernald, Ph.D. is the Josephine Knotts Knowles Professor of Human Biology at Stanford
University. As director of the Language Learning Lab in the Department of Psychology, she
conducts experimental studies of language processing by young children, as well as observational
studies of parent-infant interaction. Fernald has developed high-resolution measures of the time
course of infants understanding as they learn to interpret language from moment to moment. In
longitudinal studies with English- and Spanish-learning children from advantaged and
disadvantaged families, this research reveals the vital role of early language experience in
strengthening speech processing efficiency, which in turn faciliates language learning. Fernald is
also conducting research in West Africa, examining speech to children in relation to childrens
language learning in rural villages in Senegal. A central goal of this research program is to help
parents understand that they play a crucial role in providing their infant with early linguistic
nutrition and language exercise.
6
Herbert Jaeger, Jacobs University Bremen, Germany
"Shaping concepts in the dynamics of recurrent neural networks"
Abstract
Humans can process concepts. They can learn, store and retrieve discrete memory items, connect
them by logical operations, classify sensor input in terms of categories, attach symbolic labels to
represented items, and carry out so many more fascinating "high-level" information processing
operations. Humans do this with their brains, and these brains are dynamical systems of
supreme complexity nonlinear, high-dimensional, stochastic, multiscale, adaptive all in one.
Since decades this has fuelled a scientific quest to understand how neurodynamical systems can
support conceptual information processing. This question has been approached from many
angles, using a wealth of methods and levels of description and analysis. In my talk I will outline
yet another approach to model how conceptual information processing can arise in the dynamics
of recurrent neural networks. The core of this approach is to employ certain linear operators,
called conceptors, which constrain the evolving dynamics of a recurrent neural network. These
operators can be identified with "concepts" represented in the ongoing neural dynamics.
Conceptors can be morphed and combined with Boolean operations. This endows recurrent
neural networks with mechanisms to store and retrieve, generate, logically combine, morph,
abstract and focus dynamical patterns. I will give an intuitive introduction to the formal theory of
conceptor dynamics, and present a set of exemplary simulation studies.
Short biography
Herbert Jaeger studied mathematics and psychology at the University of Freiburg, and obtained
his PhD in Computer Science at the University of Bielefeld. After a 5-year postdoctoral fellowship
at the German National Research Center for Computer Science (Sankt Augustin, Germany) he
headed the "Intelligent Dynamical Systems" group at the Fraunhofer Institute for Autonomous
Intelligent Systems AIS (Sankt Augustin, Germany; now Fraunhofer IAIS). Since 2003 he is
Associate Professor for Computational Science at Jacobs University Bremen. His research is
concerned with the modelling of complex, nonlinear, stochastic systems with applications in
machine learning, engineering, and robotics.
7
Yasuo Kuniyoshi, The University of Tokyo, Japan
"Simulating Human Fetal Development"
Abstract
Development is a continuous bootstrap process of complex interaction between genes, body,
nervous system and environment. Therefore investigating the global structure of the process
from the beginning is crucial for understanding the fundamental principles of human
development. With the advent of 4D ultrasound imaging and fetal MRI, a burst of data has
been accumulating about human fetal development. Also, increasing number of reports suggest
that perturbation of fetal development may be relevant to later developmental disorders.
Besides, compared to infants/toddlers in extremely complex environment, fetuses may allow
more principled way of modeling. We constructed a simulation model of a human fetus. It
consists of a musculo- skeletal body, uterus, and basic nervous system. It exhibits spontaneous
motor development and sensory-motor map organization comparable to human data. Also, by
changing the model parameters, we can simulate abnormal development. In 2012, we started a
project called Constructive Developmental Science, collaboration by roboticists, psychologists,
medical scientists, and Tojisha, the researchers investigating own developmental disorders as
internal observers. The fetal development simulation serves as a platform for integrating the
interdisciplinary data and experimenting on the effect of early genetic/environmental conditions
on the courses of development. The project aims at revealing the fundamental principles of
human development, in particular, how embodied sensory-motor processes relates to social
cognition, and new understanding of how developmental disorders emerge.
Short biography
Yasuo Kuniyoshi is a Professor at the Department of Mechano-Informatics, School of
Information Science and Technology, The University of Tokyo, Japan. He received B.E. in
applied physics, and M.Eng. and Ph.D. in information technology from the University of Tokyo
in 1985, 1988 and 1991, respectively. From 1991 to 2000, he was a Research Scientist and then a
Senior Research Scientist of Intelligent Systems Division, Electrotechnical Laboratory, AIST,
MITI, Japan. From 1996 to 1997 he was a Visiting Scholar at MIT AI Lab., being a member of
ZOO hosted by Prof. Rodney A. Brooks. In 2001, he joined the University of Tokyo as an
associate professor. Since 2005 he has been a Professor there. Since 2012 he has been serving as
Director of Social ICT Research Center, School of Information Science and Technology, The
University of Tokyo. Also since 2012, he has been jointly appointed as Director of RIKEN BSI-
Toyota Collaboration Center (BTCC). His research interests include constructive developmental
science, emergence and development of embodied cognition, and humanoid robotics. He is the
author of over 500 technical publications, editorials and books. He received Outstanding Paper
Award from International Joint Conference on Artificial Intelligence, Best Paper Awards from
Robotics Society of Japan, Sato Memorial Award for Intelligent Robotics Research, Okawa
Publication Prize, Gold Medal of Tokyo Techno Forum21, and other awards. He is a member of
IEEE, Science Council of Japan (affiliate member), Robotics Society of Japan (Fellow), Japan
Society for Artificial Intelligence, Japanese Society of Baby Science, and other societies.
8
Ichiro Tsuda, Research Institute for Electronic Science Hokkaido University,
Sapporo, Hokkaido, Japan
"Classes of Mathematical Modeling for Brain Dynamics"
Abstract
We report 10 classes of mathematical modeling from neurons to a society of brains. Various
mathematical models at hierarchical levels of function from a single neuron to a society of brains,
namely, a level of communication have been proposed so far in the field of cognitive
neuroscience. However, no clear classification of such mathematical models has been made. To
clarify the functional significance of the mathematical models at each level, we present typical
models for each class. Although our present classification may not be sufficient, and the
examples provided may be limited, as they do not cover all important contributions, the
importance of mathematical modeling in complex brain dynamics and neural correlates of
functions will be shown clearly. In particular, the following type of mathematical modeling is
challenging, as it may elucidate the mechanism of functional differentiation in the mammalian
cortex. From the viewpoint of systems development, it is important to investigate the manner in
which components emerge in a network system consisting of interacting units. In this respect, we
report two mathematical models: one treats the emergence of neuron-like components from
interacting maps, and the other addresses the emergence of hierarchical module-like
components from interacting neuron-like units. In both models, maximum transmission of
information was used as a variational principle. All mathematical models described in the
present talk will probably be useful for future studies in the field of developmental robotics.
Short biography
Ichiro Tsuda holds the position of Professor in the Research Institute for Electronic Science
(RIES) and is the director of Research Center for Integrative Mathematics of Hokkaido
University, as well as an invited professor at Department of Mechanical Engineering of Osaka
University. He is also a member of the Advisory Board of Complex Systems Institute at
Kalamazoo College, USA. He was a visiting professor at the Japan Advanced Institute of Science
and Technology (JAIST), and was the group leader of the Basic Design Group, National
Bioholonics Project of Exploratory Research for Advanced Technology (ERATO), Research
Development Corporation of Japan (currently named JST). He has published widely in the field
of chaotic dynamical systems and brain sciences. His research interest is mathematical modeling
of higher brain function, including memory dynamics, thoughts, and inference processes, and
also numerical studies of chaotic dynamical systems. He constructed a one-dimensional map to
explain chaos and bifurcation structure in the BZ reaction sufficiently and found noise-induced
order in this model. He also constructed neural network models for dynamic associative memory
and for episodic memory based on physiological data concerning class I neurons and different
types of synapses. In the former, he found a new dynamical state, termed chaotic itinerancy (the
recent contribution is available in [1]) and proposed its dynamical interpretation in terms of a
Milnor attractor, and for the latter, he proposed a new coding scheme, termed Cantor coding, for
episodic memory formation.
[1] http://www.scholarpedia.org/article/Chaotic_itinerary
9
Program
Sunday, August 18 2013 - Tutorials and Special Sessions
9:00 Registration opens (Large meeting room)
Large Meeting Room (B1F 84) Exhibition Room(B1F 63)
9:30 - 10:50 Special Session 1:
Constructive Developmental Science: Two
Endeavors toward Understanding Human
Development
Yukie Nagai (Osaka University), Yasuo
Kuniyoshi (University of Tokyo), Minoru Asada
(Osaka University)
9:30 - 10:50 Tutorial 1:
Introduction to Computational brain-mind
Juyang Weng (Michigan State
University)
10:50 Coffee break
Large Meeting Room (B1F 84) Exhibition Room(B1F 63)
11:10 - 12:30 Special Session 1:
Constructive Developmental Science: Two
Endeavors toward Understanding Human
Development
Yukie Nagai (Osaka University), Yasuo
Kuniyoshi (University of Tokyo), Minoru Asada
(Osaka University)
11:10 - 12:30 Tutorial 1:
Introduction to Computational brain-mind
Juyang Weng (Michigan State
University)
12:30 - 13:50 Lunch (not provided)
Large Meeting Room (B1F 84) Exhibition Room(B1F 63)
13:50 - 15:50 Special Session 2:
Training in Robotics for Development of
Cognition (RobotDoC)
Anna-Lisa Vollmer, Marek Rucinski (Plymouth
University), Cristiano Alessandro (Zurich
University), Nicholas Wilkinson (IIT), Nicolas
Navarro-Guerrero (Hamburg University),
Andrea Handl (Uppsala University)
13:50 - 15:50 Special Session 3:
Constructing empathy: An Interdisciplinary
Investigation
Luisa Damiano (University of Bergamo), Paul
Dumouchel (Ritsumeikan University), Hagen
Lehmann (University of Hertfordshire)
10
Monday, August 19 2013
9:00 Registration (Special room, 3F)
9:30 Opening
9:50 - 10:50 Keynote 1: Herbert Jaeger
10:50 Coffee break
11:10 Attentional Constraints and Statistics in Toddlers' Word Learning
Sumarga Suanda (Indiana University), Seth Foster (Indiana University), Linda Smith
(Indiana University), Chen Yu (Indiana University)
11:30 Understanding Embodied Visual Attention in Child-Parent Interaction
Sven Bambach (Indiana University), David Crandall (Indiana University), Chen Yu
(Indiana University)
11:50 Do beliefs about a robot's capabilities influence alignment to its actions?
Anna-Lisa Vollmer (Plymouth University), Britta Wrede (Bielefeld University),
Katharina Rohlfing (Bielefeld University), Angelo Cangelosi (Plymouth University)
12:10 Robot Learning Simultaneously a Task and How to Interpret Human Instructions
Jonathan Grizou (INRIA), Manuel Lopes (INRIA Bordeaux), Pierre-Yves Oudeyer
(INRIA Bordeaux Sud-Ouest)
12:30 - 13:50 Lunch (not provided)
13:50 Salience-based reinforcement of a spiking neural network leads to increased
syllable production
Anne Warlaumont (University of California, Merc)
Large Meeting Room (B1F 84) Exhibition Room(B1F 63)
16:10 - 18:10 Tutorial 2:
Language Acquisition and the Influence of
Action Learning
Katrin Solveig Lohan (IIT), Katharina Rohlfing
(Bielefeld University), Angelo Cangelosi
(Plymouth University), Lars Schillingmann
(Osaka University), Giorgio Metta (IIT)
16:10 - 18:10 Tutorial 3:
Action-Perception Cycles: Neuro-Dynamic
Modeling and Robotics Experiments
Jun Tani (KAIST)
15:50 Coffee break
11
Tuesday, August 20 2013
14:10 Learning Versatile Sensorimotor Coordination with Goal Babbling and Neural
Associative Dynamics
Felix Rene Reinhart (CoR-Lab, Bielefeld University), Matthias Rolf (CoR-Lab, Bielefeld
University)
14:30 Goal Babbling with Unknown Ranges: A Direction-Sampling Approach
Matthias Rolf (CoR-Lab, Bielefeld University)
14:50 Developing Learnability the Case for Reduced Dimensionality
Naveen Kuppuswamy (A.I Lab, University of Zrich), Christopher Harris (Plymouth
University)
15:10 Coffee break
15:30 Do humans need learning to read humanoid lifting actions?
Alessandra Sciutti (IIT), Laura Patan (Italian Institute of Technology), Francesco Nori
(Italian Institute of Technology), Giulio Sandini (IIT)
15:50 Exploration strategies in developmental robotics: a unified probabilistic framework
Clment Moulin-Frier (INRIA), Pierre-Yves Oudeyer (INRIA Bordeaux Sud-Ouest)
16:10 Learning Stable Pushing Locations
Tucker Hermans (Georgia Institute of Technolog), Fuxin Li (Georgia Institute of
Technology), James Rehg (Georgia Institute of Technology), Aaron Bobick (Georgia
Institute of Technology)
16:30 Coffee break
16:50 - 18:20 Poster session 1 (with spotlights)
18:50 - 20:20 Banquet at the "Heian", 4th floor, ANA Crowne Plaza, Osaka
9:00 Registration (Special room, 3F)
9:30 -10:30 Keynote 2: Anne Fernald
10:30 Coffee break
10:50 Epigenetic adaptation through hormone modulation in autonomous robots
John Lones (University of Hertfordshire), Lola Caamero (University of Hertfordshire)
11:10 Impacts of environment, nervous system and movements of preterms on body map
development: Fetus simulation with spiking neural network
Yasunori Yamada (The Univ. of Tokyo), Keiko Fujii (The Univ. of Tokyo), Yasuo Kuniyoshi
(The Univ. of Tokyo)
12
11:30 Structural bootstrapping at the sensorimotor level for the fast acquisition of action
knowledge for cognitive robots
Eren Aksoy (Goettingen University), Minija Tamosiunaite, Rok Vuga, Ales Ude,
Christopher Geib, Mark Steedman, Florentin Woergoetter
11:50 Coffee break
12:10 Temporal Emphasis for Goal Extraction in Task Demonstration to a Humanoid
Robot by Naive Users
Konstantinos Theofilis (University of Hertfordshire), Katrin Solveig Lohan, Kerstin
Dautenhahn (University of Hertfordshire), Britta Wrede (University of Bielefeld),
Chrystopher Nehaniv (University of Hertfordshire)
12:30 Estimating Dynamic Properties of Objects fromAppearance
Walter Talbott (UC San Diego), Tingfan Wu (UCSD), Javier Movellan (UCSD)
12:50 -14:00 Lunch (not provided)
14:00 - 15:00 Keynote 3: Yasuo Kuniyoshi
15:00 Coffee break
15:20 A generative probabilistic framework for learning spatial language
Colin Dawson (University of Arizona), Jeremy Wright (University of Arizona), Antons
Rebguns (University of Arizona), Marco Valenzuela Escrcega (University of Arizona),
Daniel Fried (University of Arizona), Paul Cohen (University of Arizona)
15:40 Co-learning nouns and adjectives
Guner Orhan, Sertac Olgunsoylu, Erol Sahin, Sinan Kalkan (METU)
16:00 Grounded Lexicon Acquisition - Case Studies in Spatial Language
Michael Spranger (Sony CSL Paris)
16:20 Talk by Aldebaran
16:40 Coffee break
17:00 - 18:30 Poster session 2 (with spotlights)
Wednesday, August 21 2013
9:00 Registration (Special room, 3F)
9:30 - 10:30 Keynote 4: Ichiro Tsuda
10:30 Coffee break
10:50 Reinforcement Learning with State-Dependent Discount Factor
Naoto Yoshida (NAIST), Eiji Uchibe (OIST), Kenji Doya (OIST)
13
Thursday, August 22 2013
11:10 Transfer Learning for Direct Policy Search: a Reward Shaping Approach
Stephane Doncieux (ISIR/UPMC-CNRS)
11:30 - 12:00 Closing & award ceremony (Small Assembly Hall)
13:00 - 17:00 AMDTC-ICDL GB meeting (Meeting Room No. 4, B1F 24)
Poster Session 1 (Monday, August 19, 16:50 - 18:20)
Lab-Tour at Osaka University
The following labs will be included in the tour:
1. Intelligent Robotics Laboratory, directed by Prof. Hiroshi Ishiguro
2. Human Interface Laboratory, directed by Prof. Koh Hosoda
3. Emergent Robotics Laboratory, directed by Prof. Minoru Asada.
Please check the schedule on the conference webpage for detailed information about the tour.
Full papers with spotlight presentation
Mon-1 Learning to Reproduce Fluctuating Behavioral Sequences Using a Dynamic
Neural Network Model with Time-Varying Variance Estimation Mechanism
Shingo Murata (Waseda University), Jun Namikawa (RIKEN), Hiroaki Arie (Waseda
University), Jun Tani (KAIST), Shigeki Sugano (Waseda University)
Mon-2 An Enactive Approach to Autonomous Agent and Robot Learning
Olivier Georgeon (Universit de Lyon), Christian Wolf (Universit de Lyon), Simon
Gay (Universit de Lyon)
Mon-3 Learning the rules of a game: neural conditioning in human-robot interaction
with delayed rewards
Andrea Soltoggio (Bielefeld University), Felix Rene Reinhart (CoR-Lab, Bielefeld
University), Andre Lemme (Bielefeld University), Jochen Steil (Bielefeld University)
Mon-4 Predictive coding and self-organization for unsupervised development of
object recognition skills
Alexander Gepperth (ENSTA ParisTech)
Mon-5 Emergence of Flexible Prediction-Based Discrete Decision Making and
Continuous Motion Generation through Actor-Q-Learning
Katsunari Shibata (Oita University), Kenta Goto
Mon-6 Learning to recognize objects through curiosity-driven manipulation
Serena Ivaldi (ISIR - CNRS & University Pierre et Marie Curie), Alain Droniou
(ISIR- UMR7222CNRS&UPMC), Olivier Sigaud(ISIR- UMR7222CNRS&
UPMC), Vincent Padois (ISIR - UMR 7222 CNRS & UPMC), David Filliat (ENSTA -
ParisTech), Natalia Lyubova (ENSTA - ParisTech), Damien Gerardeaux,
Pierre-Yves Oudeyer (INRIA Bordeaux Sud-Ouest), Mai Nguyen (INRIA)
14
Mon-7 Towards a robotic model of the mirror neuron system
Kristna Rebrov (Comenius University SR), Matej Pech (Comenius University in
Bratislava), Igor Farka (Comenius University in Bratislava)
Mon-8 Autonomous learning of active multi-scale binocular vision
Luca Lonini (FIAS - Goethe University), Yu Zhao (Hong Kong University of Science
And Technology), Pramod Chandrashekhariah (FIAS - Goethe University), Bertram
Shi (Hong Kong University of Science And Technology), Jochen Triesch (FIAS)
Mon-9 Aquila 2.0 - Software Architecture for Cognitive Robotics
Martin Peniak (Plymouth University), Anthony Morse (University of Plymouth),
Angelo Cangelosi (Plymouth University)
Mon-10 Building Specific Contexts for On-line Learning of Dynamical Tasks through
Non-verbal Interaction
Antoine De Rengerve (ETIS), Souheil Hanoune (ETIS), Pierre Andry (ETIS), Quoy
Mathias (ETIS Lab), Philippe Gaussier (University of Cergy Pontoise)
Abstracts and short papers
Mon-11 Grounding Abstract Action Words through the Hierarchical Organization of
Motor Primitives
Francesca Stramandinoli (Plymouth University), Davide Marocco, Angelo
Cangelosi (Plymouth University)
Mon-12 The Significance of Social Input, Early Motion Experiences, and Attentional
Selection
Joseph Burling (University of Houston), Hanako Yoshida (University of Houston),
Yukie Nagai (Osaka University)
Mon-13 Intrinsically Motivated Reinforcement Learning in Socio-Economic Systems:
the Dynamical Analysis
Arkady Zgonnikov (University of Aizu), Ihor Lubashevsky (University of Aizu)
Mon-14 Explaining Neonate Facial Imitation from the Sensory Alignment in the
Superior Colliculus
Alex Pitti (ETIS Lab, Univ. of Cergy), Yasuo Kuniyoshi (University of Tokyo), Quoy
Mathias (ETIS Lab), Philippe Gaussier (University of Cergy Pontoise)
Mon-15 Adaptive Reachability Assessment in the Humanoid Robot iCub
Salomon Ramirez-Contla (Plymouth University), Davide Marocco
Mon-16 Extracting image features in static images for depth estimation
Masaki Ogino (Kansai University), Junji Suzuki (Osaka University), Minoru Asada
(Osaka University)
Mon-17 Continuous Adaptive Reinforcement Learning with the Evolution of Self
Organizing Classifiers
Danilo Vargas (Kyushu University), Hirotaka Takano, Junichi Murata
15
Poster Session 2 (Tuesday, August 20, 17:00 - 18:30)
Full papers with spotlight presentation
Tue-1 Action Understanding using an Adaptive Liquid State Machine based on
Environmental Ambiguity
Jimmy Baraglia, Yukie Nagai (Osaka University), Minoru Asada (Osaka University)
Tue-2 Tactile stimuli from amniotic fluid guides the development of somatosensory
cortex with hierarchical structure using human fetus simulation
Ryosuke Sasaki (University of Tokyo), Yasunori Yamada (University of Tokyo),
Yuki Tsukahara (University of Tokyo), Yasuo Kuniyoshi (University of Tokyo)
Tue-3 Autonomous Reuse of Motor Exploration Trajectories
Fabien Benureau (Inria), Pierre-Yves Oudeyer (INRIA Bordeaux Sud-Ouest)
Tue-4 Touch and Emotion: Modeling of developmental differentiation of emotion
lead by tactile dominance
Takato Horii (Osaka University), Yukie Nagai (Osaka University), Minoru Asada
(Osaka University)
Tue-5 Improving Implicit Communication In Mixed Human-Robot Teams With Social
Force Detection
Bradley Hayes (Yale University), Brian Scassellati (Yale University)
Tue-6 Learning Semantic Components from Subsymbolic Multimodal Perception
Olivier Mangin (INRIA), Pierre-Yves Oudeyer (INRIA Bordeaux Sud-Ouest)
Tue-7 A Robot to Study the Development of Artwork Appreciation Through Social
Interactions.
Ali Karaouzene (ETIS), Philippe Gaussier (University of Cergy Pontoise), Denis
Vidal (IRD - URMIS - Paris Diderot)
Tue-8 Intuitive Human Robot Interaction based on unintentional synchrony: a
psycho-experimental study
Syed-Khursheed Hasnain, Ghiles Mostafaoui (ETIS), Robin Salesse, Ludovic
Marin, Philippe Gaussier (University of Cergy Pontoise)
Tue-9 Autonomous Learning of Domain Models using Two-Dimensional Probability
Distributions
Witold Sowiski (University of Aberdeen), Frank Guerin (Aberdeen University)
Tue-10 Frustration as a way toward autonomy and self-improvement in robotic
navigation.
Adrien Jauffret (ETIS Laboratory), Marwen Belkaid (ETIS), Nicolas Cuperlier
(ETIS), Philippe Gaussier (University of Cergy Pontoise), Philippe Tarroux (LIMSI)
16
Abstracts and short papers
Tue-11 Development of self-monitoring essential for vocal interactions in marmoset
monkeys
Daniel Takahashi (Princeton University), Darshana Narayanan (Princeton
University), Asif Ghazanfar (Princeton University)
Tue-12 Towards understanding the origin of infant directed speech: A vocal robot
with infant-like articulation
Yuki Sasamoto (Osaka Univ.), Naoto Nishijima (Osaka University), Minoru Asada
(Osaka University)
Tue-13 Dynamic shift in isolating referents: From social to self-generated input
Hanako Yoshida (University of Houston), Joseph Burling (University of Houston)
Tue-14 Autonomous Learning Based on Depth Perception and Behavior Generation
Sungmoon Jeong (JAIST, Kyungpook National University), Yunjung Park
(Kyungpook National University), Minho Lee (Kyungpook National University)
Tue-15 Learning Spatial Relations between Objects From 3D Scenes
Severin Fichtl (Uni Aberdeen), Frank Guerin (Aberdeen University), Norbert
Krueger (SDU), John Alexander (Uni of Aberdeen), Mustafa Wail (Southern
Denmark University), Dirk Kraft (Southern Denmark University)
Tue-16 Combining Synchrony and shape detection to sustain the robot focus of
attention on a selected human partner
Caroline Grand, Ghiles Mostafaoui (ETIS), Syed-Khursheed Hasnain, Philippe
Gaussier (University of Cergy Pontoise)
17
Venue
The conference will be held at Osaka City Central Public Hall, Osaka, Japan, which is well known
as elegant Neo-Renaissance architecture with red brick wall and dome-shaped bronze roof built
in 1918. The venue is located about one and a half hours from Kansai International Airport by
train.
Osaka City Central Public Hall
Address: 1-1-27 Nakanoshima,Kita-ku,Osaka
Phone: +81-6-6208-2002
http://osaka-chuokokaido.jp/english/index.html
Different views of the conference venue:
18
19
20
21
Getting there
From JR Osaka station
Take the Subway Midosuji Line from Umeda station to Yodoyabashi station and leave the station
at exit #1 (Time: 2 min.; Cost: JPY200). Walk 5 min., see Walk Route.
Or take a taxi (Time: approx. 10 min.; Cost: JPY800)
From JR Shin-Osaka station
Take the Subway Midosuiji Line to Yodoyanbashi station (Time: 9min.; Cost: JPY230)
From Osaka (Itami) Airport
Take the Osaka Monorail to Senri-chuo station, there change to the Midosuji Line (Total time: 44
min.; Cost: JPY710)
Or take the Airport Limousine Bus to the Hotel New Hankyu, which is close to the JR Osaka
station (Time: 35min.; Cost: JPY620), see Timetable.
From Kansai International Airport
Take the Airport Limousine Bus to the Hotel New Hankyu, which is close to the JR Osaka station
(Time: 60min.; Cost: JPY1500), see Timetable.
Or take the JR Kansai Airport Rapid Service to JR Osaka station (Time: 70min.; Cost: JPY1160).
Or you can change the train to the Subway Midosuji Line at Tennoji.
22
Internet
Please ask the local conference staff for a ticket with information on how to access the internet at
the conference venue.
Food
23
Author List
Aksoy, E. 12
Alexander, J. 16
Andry, P. 14
Arie, H. 13
Asada, M. 14, 15, 16
Bambach, S. 10
Baraglia, J. 15
Belkaid, M. 15
Benureau, F. 15
Bobick, A. 11
Burling, J. 14, 16
Cangelosi, A. 10, 14
Caamero, L. 11
Chandrashekhariah, P. 14
Cohen, P. 12
Crandall, D. 10
Cuperlier, N. 15
Dautenhahn, K. 12
Dawson, C. 12
De Rengerve, A. 14
Doncieux, S. 13
Doya, K. 12
Droniou, A. 13
Escrcega, M. V. 12
Farka, I. 14
Fichtl, S. 16
Filliat, D. 13
Foster, S. 10
Fried, D. 12
Fujii, K. 11, 15
Gaussier, P. 14, 15, 16
Gay, S. 13
Geib, C. 12
Georgeon, O. 13
Gepperth, A. 13
Gerardeaux, D. 13
Ghazanfar, A. 16
Goto, K. 13
Grand, C. 16
Grizou, J. 10
Guerin, F. 15, 16
Hanoune, S. 14
Harris, C. 11
Hasnain, S.-K. 15, 16
Hayes, B. 15
Hermans, T. 11
Horii, T. 15
Ivaldi, S. 13
Jauffret, A. 15
Jeong, S. 16
Kalkan, S. 12
Karaouzene, A. 15
Kraft, D. 16
Krueger, N. 16
Kuniyoshi, Y. 11, 14, 15
Kuppuswamy, N. 11
Lee, M. 16
Lemme, A. 13
Li, F. 11
Lones, J. 11
Lonini, L. 14
Lopes, M. 10
Lubashevsky, I. 14
Lyubova, N. 13
Mangin, O. 15
Marin, L. 15
Marocco, D. 14
Mathias, Q. 14
Morse, A. 14
Mostafaoui, G. 15, 16
Moulin-Frier, C. 11
Movellan, J. 12
Murata, J. 14
Murata, S. 13
Nagai, Y. 14, 15
Namikawa, J. 13
Narayanan, D. 16
Nehaniv, C. 12
Nguyen, M. 13
Nishijima, N. 16
Nori, F. 11
Ogino, M. 14
Olgunsoylu, S. 12
Orhan, G. 12
Oudeyer, P.-Y. 10, 11, 13, 15
Padois, V. 13
Park, Y. 16
Patan, L. 11
Pech, M. 14
Peniak, M. 14
Pitti, A. 14
Ramirez-Contla, S. 14
Rebguns, A. 12
Rebrov, K. 14
Rehg, J. 11
Reinhart, F. R. 11, 13
Rohlfing, K. 10
Rolf, M. 11
Sahin, E. 12
Salesse, R. 15
Sandini, G. 11
Sasaki, R. 15
Sasamoto, Y. 16
Scassellati, B. 15
Sciutti, A. 11
Shi, B. 14
Shibata, K. 13
Sigaud, O. 13
Smith, L. 10
Soltoggio, A. 13
Solveig Lohan, K. 12
Spranger, M. 12
Steedman, M. 12
Steil, J. 13
Stramandinoli, F. 14
Suanda, S. 10
Sugano, S. 13
Suzuki, J. 14
Sowiski, W. 15
Takahashi, D. 16
Takano, H. 14
Talbott, W. 12
Tamosiunaite, M. 12
Tani, J. 13
Tarroux, P. 15
Theofilis, K. 12
Triesch, J. 14
Tsukahara, Y. 15
Uchibe, E. 12
Ude, A. 12
Vargas, D. 14
Vidal, D. 15
Vollmer, A.-L. 10
Vuga, R. 12
Wail, M. 16
Warlaumont, A. 10
Woergoetter, F. 12
Wolf, C. 13
Wrede, B. 10, 12
Wright, J. 12
Wu, T. 12
Yamada, Y. 11, 15
Yoshida, H. 14, 16
Yoshida, N. 12
Yu, C. 10
Zgonnikov, A. 14
Zhao, Y. 14

Das könnte Ihnen auch gefallen