IURS12

 

12th International AERFAI/UJI Robotics School IURS 2012

 

Perceptual Robotics for Humanoids

 

September 17-21, 2012

Bonaire Hotel, Benicasim, Spain

 

 

Aims and Scope

Advances in computer engineering and artificial intelligence have led to design robots which assist people with a variety of tasks such as, for instance, education, assistance, social or service tasks. Thus, on the way to intelligent social robots, particularly humanoid ones, a key issue is how to perceive the environment to properly move and act on. In addition, there is significant interest in linking low-level sensory information such as visual, auditory or haptic feedback to higher-level symbolic representations for a robot concerning how it should act in the world.

 

In this context, we will focus on the grand challenge to provide humanoid robots with cognitive and social skills from their perception. For that, this issue will be covered from different points of view. Firstly, developing real-time perception strategies that, combined with efficient planning and robust execution, enable humanoid robots to autonomously navigate, manipulate and interact in daily environments. In addition, we will also study robot learning by imitation and robot programming through demonstration since they need the development of robust algorithms for motor control and learning, gesture recognition and visuo-motor integration, so important for a reliable, useful human-robot interaction. We take into account that in order for robots to learn from humans, or to learn through their own exploration of the world, they need to be able to share their understanding and representation of the world with their human counterparts. Another important issue to be considered is the technical requirements for including these robots in real-life applications.

 

Furthermore, another big challenge involves to properly exploiting the generality and flexibility of the humanoid platform for fully autonomous operation in obstacle-filled and dynamically changing environments. On this matter, NAO robot platform will be considered for laboratory sessions. So, this 57-cm tall humanoid robot will allow the assistants to put into practice the theoretical concepts presented in the morning technical sessions.

 

The purpose of this symposium is to give the students a general background on these main topics. To achieve this goal, world-wide known lecturers will introduce the students the basic concepts of humanoid perception and programming. The lecturers have been selected not only because of their knowledge in particular topics related with humanoid robots, but also for their valuable experience in real humanoid robots, and by their outstanding teaching experience.

 

The participants will get in touch with other young researchers in the field and will have the opportunity to improve their knowledge through the interaction with experts. Another important goal is to provide graduate students in robotics with a unique training opportunity in this emergent and fast-evolving domain. Students will closely interact for one week with some of the top-level researchers in the world in this domain. They will also have the opportunity to discuss their research work with them, as well as with other students.

List of Lecturers with short CV

Sylvain Calinon (Italian Institute of Technology (IIT), Italy)

 
He is the team leader of the Learning and Interaction Group (established in 2009) at the Department of Advanced Robotics, Italian Institute of Technology (IIT), Genova, Italy. He is also a visiting research fellow at the Learning Algorithms and Systems Laboratory (LASA), Ecole Polytechnique Federale de Lausanne (EPFL), Switzerland, where he received his PhD in 2007.
His research interests cover robot learning by imitation, machine learning and human-robot interaction. He also maintains the Programming-by-demonstration.org website, which provides an open access to researchers working in learning by imitation to post announcements, links, and publications. 

   

 

Emilia Barakova (Technische Universiteit Eindhoven, The Netherlands)

 
Dr. Emilia Barakova has expertise in behavioral robotics and functional brain modeling, on artificial intelligence, and human centered interaction design. Currently she is working on human-robot social interaction and robotics for behavioral training of autistic children, that includes measuring, and analyzing human behavior and interaction, use of machine learning and brain-inspired computational models to create interactive behaviors for robots and human-centered design to design interactive scenarios that are based on advanced therapeutic practices. She has: Masters Degree in Electronics and Automation from Technical University of Sofia (Bulgaria) and PhD in Mathematics and Physics from Groningen University (The Netherlands, 1999). She has worked at RIKEN Brain Science Institute (Japan), the GMD-Japan Research Laboratory (Japan), the Eindhoven University of Technology (The Netherlands), Starlab (Belgium), and the Bulgarian Academy of Science. She has been a project leader of several multidisciplinary projects, coordinated the Robotics and Social robots educational and research team at ID department of TU/e, and has served as an interim director of GMD-JRL lab. Barakova is an Editor of Journal of Integrative Neuroscience, and Associate editor of Personal and Ubiquitous Computing and has organized international conferences and has served as a program chair of IEEE and ACM conferences.
   

 

Haris Dindo (Università degli Studi di Palermo, Italy)

 
He received his Ph.D. in Computer Science from the University of Palermo in 2007 with the doctoral dissertation entitled Cognitive Imitation in Robotic Systems.
Currently, he is Assistant
 Professor
 at 
the 
Department
 of 
Computer
 Science
 Engineering
 at the 
University
 of
 Palermo,
 Italy.
 His 
main
 research
 interest
 stays 
at
 the 
intersection 
of
 robotics
 and 
machine
 learning:
 how
 can
 robots
 learn
 advanced
 individual
 and
 social
 behaviours through
 direct
 experience 
and
 by
 observing
 and
 imitating
 others?
 His is
 an
 interdisciplinary
 research 
with
 contributions 
ranging
 from
 artificial
 intelligence,
 machine
 learning
 and 
robotics
 to
 cognitive
 sciences,
 biology
 and
 neuroscience.
 He is currently
 focused on
 developing
 a
 novel computational and
 architectural
 framework for
 intentional and
 joint action embodied
 in
 a
 humanoid 
robotic 
platform.
 The 
research 
has
 been
 inspired
 by 
recent
 findings 
in 
neurology
 (i.e.
 the
 discovery
 of 
canonical
 and
 mirror 
neurons)
 and 
cognitive 
sciences
(i.e.
the
 theories 
of
 motor
 cognition
 and
 sensorimotor 
emulation).
He has published
 more
 than
 40
 articles
 in
 international
 journals
 and
 peer‐reviewed
 conference 
proceedings.
 He is currently team
 leader
 and
 member
 of
 the
 scientific
 board
 of 
the
 EU‐funded
 project
 HUMANOBS:
 Humanoids
 that
 Learn
 Socio‐Communicative
 Skills
 by
 Observation 
(FP7‐ICT‐231453).
 He teaches 
Robotics
 and
 Machine
 Learning 
(for 
graduates) 
and
 Operating
Systems
 (for 
undergraduates).

   

 

Juan Francisco Blanes Noguera (Instituto de Automática e Informática Industrial (ai2), Spain)

 
He is Assistant Professor at Computer Science School in the Universitat Politècnica de València (Spain) since 1999, teaching real-time control, embedded systems and distributed control with field buses. He received his degree in Computer Science in 1994 and his Ph.D. degree in 2000 with a thesis about Robotics sensor fusion. Since the beginning of his research, he has been working in real-time robot architectures with special emphasis in humanoid robots and real-time robot control with limited resources in embedded systems.
Currently he has been focused in Robocup Standard Platform League, with participation in the Los Hidalgos Spanish joint team with the Universidad de Murcia, and the international joint team L3M.
   

 

Domènec Puig (Rovira i Virgili University, Spain)

 
Dr. Domenec Puig received the M.S. and Ph.D. degrees in computer science from Polytechnic University of Catalonia, Barcelona, Spain, in 1992 and 2004, respectively. In 1992, he joined the Department of Computer Science and Mathematics, Rovira i Virgili University (URV), Tarragona, Spain, where he is currently Associate Professor. Since July 2006, he is the Head of the Intelligent Robotics and Computer Vision Group at the same university. His research interests include image processing, texture analysis, perceptual models for image analysis, scene analysis, and mobile robotics. He has participated or managed over 15 funded research projects related to his topics of interest. He has published in the last recent years more than 20 ISI-JCR journal papers and 25 papers in international conferences. He has led a group in the URV that has participated in several editions of the Robocup Standard Platform League, being part of the SPIteam in cooperation with the University Rey Juan Carlos and the University of Leon.
   

 

Filiberto Pla Bañón (Jaume-I University, Spain)

 
He is a Full Professor at the Department of Lenguajes y Sistemas Informáticos and member of the Research Institute of New Imaging Technologies of the Jaume-I University, Castellón, Spain. He is also the Coordinator of the Computer Vision Group. He has led various research projects and published papers in different conferences and journals in Image Processing, Computer Vision and Pattern Recognition.
His current research interests are colour and spectral image analysis, visual motion analysis, active vision and pattern recognition techniques applied to image processing.
In addition, he teaches different subjects in undergraduate Computer Engineering Degrees, the MSc Degree on Intelligent Systems and the MSc Degree on GeoSpatial Information.
   

 

Enric Cervera i Mateu (Jaume-I University, Spain)

 
Dr. Cervera has 18 years research experience in robotics and artificial intelligence. After completing his Ph.D. in Computer Science in 1997, he achieved a position as Associate Professor of Computer Science and Artificial Intelligence at Jaume-I University in 1999. Since then, he has leaded several research projects funded by the Spanish Government and the Valencian Regional Government. He has published several research articles in international journals, conference proceedings and book chapters. He leads, together with Prof. Philippe Martinet, an Interest Group of Euron on Visual Servoing, which has organized different workshops and tutorials (IROS'02, IROS'04). He has served as reviewer of several top international journals, and in the program committee of several international conferences (IROS'04-06, IASTED). He worked on the FP6 European Project GUARDIANS, from December 2006 to January 2010. His current research interests include sensor-based control of robots, multirobot cooperative tasks, and humanoid robotics.
   

 

Laboratory workshops

 

Monday, 17th September

 
 
 
 
Enric Cervera i Mateu
Robotic Intelligence Lab
Jaume-I Univesity, Castellón, Spain
ecervera@uji.es
 
Vicente Castello Martínez
Robotic Intelligence Lab
Jaume-I Univesity, Castellón, Spain
castellv@uji.es
 

 

Tuesday, 18th September

 
 
 
 
Juan Francisco Blanes Noguera
Instituto de Automática e Informática Industrial (ai2)
Universitat Politècnica de València, Valencia, Spain
pblanes@disca.upv.es
 
Manuel Muñoz Alcobendas
Instituto de Automática e Informática Industrial (ai2)
Universitat Politècnica de València, Valencia, Spain
mmunoz@ai2.upv.es
 

 

Wednesday, 19th September

 
 
 
 
Domènec Puig
Intelligent Robotics and Computer Vision Group
Rovira i Virgili University, Tarragona, Spain
domenec.puig@urv.cat
 
Julian Cristiano Rodriguez
Intelligent Robotics and Computer Vision Group
Rovira i Virgili University, Tarragona, Spain
julianefren.cristiano@estudiants.urv.cat
 
 
 
 
 
Francisco Martín Rico
Robotics Lab - GSyC department
Universidad Rey Juan Carlos, Madrid, Spain
francisco.rico@urjc.es
 
Carlos E. Agüero Durán
Robotics Lab - GSyC department
Universidad Rey Juan Carlos, Madrid, Spain
carlos.aguero@urjc.es