IEEE
Ro-Man 2010
Sep. 12th - Sept. 15th, 2010
Principe di Piemonte - Viareggio (LU), Italy

Special Sessions

  Group: Program   


 
    Cognition for Interactive Robots
       Organizers: Martin Buss (TUM), Kolja Kühnlenz (TUM)
       Schedule: MoP2T2 and MoP3T2
       Abstract
 
 

Cognitive technical systems are equipped with artificial sensors and actuators, integrated and embedded into physical systems, and act in a physical world. They differ from other technical systems in that they perform cognitive control and have cognitive capabilities. Cognitive control orchestrates reflexive and habitual behavior in accord with longterm intentions. Cognitive capabilities such as perception, reasoning, learning, and planning turn technical systems into ones that "know what they are doing". More specifically, a cognitive technical system becomes a technical system "that can reason
using substantial amounts of appropriately represented knowledge, learn from its experience so that it performs better tomorrow than it did today, explain itself and be told what to do, be aware of its own capabilities and reflect on its own behavior, and respond robustly to surprise". Technical systems that are cognitive in this sense will be
much easier to interact and cooperate with, be robust, flexible, and efficient. Although today we are still far away from robots capable of acting for many years in the real-world together with humans without supervision, this session tries to bring together various aspects in the field of cognition for interactive robots from psychology and linguistics to computer science and engineering in order to foster the network and stimulate discussion

 
    Robotics in Music and Art
       Organizers: Jorge Solis (Waseda University), Gil Weinberg (Georgia Tech)
       Schedule: WeP1T2
       Abstract
 
 

The relation between the human and the music has a long history dating from the antiquity, during which poetry,dancing and music were inseparable and constitute an important mean of communication of everyday life. In addition, during the golden area of automata, music also served as a tool for understanding the human motor control while performing highly skilful task. Thanks to recent advances in computer science, electronics, audio visual processing and artificial intelligence, the musical/ art technology research has not been limited to only developing human-computer interaction systems and sound-making devices. In fact, for several decades, researchers have been developing more natural interfaces for musical/art analysis and composition as well as robots for imitating musical performance.


 
    Brain Engineering and Science
       Organizers: Satoshi Suzuki (Tokyo Denki University, Japan), Fumio Harashima (Tokyo Metropolitan University, Japan)
       Schedule: MoP2T3 and MoP3T3
       Abstract
 
  In recent years, study on mechatronics gadget utilizing human brain activity, such as BMI, are quite active. For realization of such intelligent mechatronics, an advanced blend of the system engineering fields and the cognitive science research fields are required. Based on such convictions, we propose a special session: "Brain Engineering and Science", to discuss the following key technologies by considering human brain activity for intelligent mechatronics system.
- Signal processing and measurement of brain biosignal
- Controller design of mechatronics utilizing biosignal
- Analysis of human cognitive action such as intention and interest
- Verbal and social communication analysis
This session is sequel of former special session, "Cognitive Intelligent Mechatronics", that was appeared in RO-MAN2009.

 
    Human-Agent Interaction
       Organizers: Michita Imai (Keio University), Seiji Yamada (NII), Tetsuo Ono (Hokkaido University)
       Schedule: MoP2T1 and MoP3T1
       Abstract
 
  Currently various agents including home robots, life-like agents have been developed and are coming into common use in our daily life. Many people enjoy playing and do cooperative tasks with them. In the situation, we consider that the key property is the design of interaction, that is, the agents should behave as if it recognizes the situation and the emotional state of a user, and makes her/him engage in the interaction. In HAI field, it is necessary to design the character of an agent and the way of its interaction by considering them on a variety of embodiment from interactive CG characters to actual communicative robots. The researches on the variety of the embodiments find out the essences of the interaction which have a lot of designing theory in common with many types of interactive agents. We, robotics, embodied communicative agents, AI, and cognitive science researchers need to contribute to investigate the nature of the interaction between humans and the agents. Previous Instances have been a session named IDEA (Interaction DEsign for Adaptation) from RO-MAN 2005. This year, we change the topic to HAI in order to focus more on the design of agents and its interaction, and hold an organized session which focuses on HAI in RO-MAN 2010

 
    The Role of Tactile Sensing in Human-Robot Interaction
       Organizers: Giorgio Cannata (UNIGE), Fulvio Mastrogiovanni (UNIGE)
       Schedule: WeP1T1
       Abstract
 
  The aim of this Special Session is to foster research on a range of new robot capabilities based on the tactile feedback provided by robotic skin from large areas of robots bodies. During the past few years, a principled investigation of these topics has been limited by the lack of tactile sensing technologies enabling large scale experimental activities, since so far skin technologies and embedded tactile sensors have been mostly demonstrated only at the prototypal stage. It is widely accepted that the new capabilities will improve the ability of robots to operate effectively and safely in unconstrained environments and also their ability to communicate and co-operate with each other and with humans. Two are the research directions that are deemed important to support this aim: on one side, the investigation of methods and technologies enabling the implementation of skin sensors that can be used with existing robots; on the other side, the development of new structures for representing and integrating tactile data with existing cognitive architectures in order to support skin-based cognition, behaviour and communication.

 
    Advanced haptic interaction systems
       Organizers: Manuel Ferre (UPM), Angelika Peer (TUM)
       Schedule: TuP2T1
       Abstract
 
  The goal of this session is to show the main results of the IMMERSENCE IP (FP6- IST-2006-027141)

 
    Multimodal Interfaces for Capturing and Transfer of Skills
       Organizers: Teresa Gutiérrez (LABEIN)
       Schedule: TuP1T1
       Abstract
 
  The modelling and transfer of human skills represent a challenge in some fieldsof research such as cognitive science, psychology, robotics, biomechanics and other behaviour-related studies. The proposed special session will address the integration of Multimodal Interfaces (combining Robotic devices with other Virtual/Augmented Environments technologies) and Learning strategies for the human skills transfer. This ranges from the multimodal capture of a human task, the analysis of the task in terms of skills, to the rendering of the skill using multimodal technologies and the assessment of the user’s performance. The goal is to support people during the execution of complex tasks, help them to do things well or better, and make them more skilful in the execution of activities, overall augmenting the capability of human action and performance. Specifically, this session will introduce some examples of multimodal platforms developed for the skills transfer in different applications and domains: rowing (sports), juggling (entertainment), minimally invasive technologies surgery (medicine), robot programming-by-demonstration and industrial maintenance & assembly (industrial). The description of these platforms will be supported by videos and hands on demos of some of them.

 
 
    Re-thinking interaction with robots
       Organizers: Patrizia Marti (UNISI), Kerstin Dautenhahn (UHERTS)
       Schedule: TuP1T2 and TuP2T2
       Abstract
 
  Robotics has recently produced technologies that have made interdisciplinary studies possible and opened up interesting and new prospects. Nowadays robot technology has the ambition of achieving autonomous “bonding” and sustained socialization with people and the concept of sociality in robots takes on a wide variety of nuances and meanings. The special session “Re-thinking interaction with robots” explores such variety of meanings and interaction issues from a multidisciplinary perspective to gain a better understanding of the psychological, sociological, philosophical and design aspects defining a meaningful interaction experience with robots. The session welcomes theoretical studies as well as research and design cases providing insightful reflections on how people interact with robots, communicate with them, understand and share intentions with them, engage in meaningful and qualitative interaction with robots in their daily lives. We also welcome contributions that critically reflect on different meanings and models of relationships envisaged for current robots, e.g. companions. The goal of the special session is to bring together participants from many different fields of research and involve participants in engaging and idiosyncratic discussions and reflections to re-think human-robot interaction from a multidisciplinary viewpoint. The session is expected to cover state-of-the-art theoretical and design concepts, field studies, longitudinal evaluation studies, ongoing research projects and innovative applications of social robots. It encourages cross-disciplinary contributions from interaction designers, philosophers, psychologists, researchers and practitioners to address new trends and challenges that require interdisciplinary collaborations across the traditional boundaries of established robotics and computer sciences disciplines.

 
    Internal Models and Prediction in Humanoid Robots
       Organizers: Paolo Dario (SSSA), Alain Berthoz (College de France)
       Links: RoboSom and Humanoid Robotics
       Schedule: TuP2T3
       Abstract
 
  It is nowadays widely recognized how biology can represent an inspiration source in robotics, both for the development of biomimetic components and for new control principles for robotic systems (Brooks, 1991; Dario et al.,2005) to the final aim of developing robots with better sensory motor performance, especially in real world scenarios (Laschi et al., 2008; Guglielmelli et al., 2007; Pfeifer et al., 2007). According to neurophysiological findings, human motor control is based on sensory predictions more than on sensory feedback (Berthoz, 2002; Johansson, 1998). Due to the delays in the transmission of the nervous signals, fast and coordinated movements cannot be explained by pure feedback (Kawato, 1999; Miall et al, 1993; Wolpert et al, 1998). Current neuroscientific literature provides a rich landscape of anticipation-based possibilities of explanation, for various aspects of sensory-motor coordination. Generally speaking, anticipation is regarded as a way for overcoming a significant difficulty related to feedback-based models, when they are used for explaining sensory-motor coordination capabilities in humans and animals in general. The rapidity of sensory-motor coordination in humans and animals is unlikely to be explained by feedback based models, as sensory signal conduction and processing in the CNS requires too much time. If motor commands were generated only on the basis of the last sensory feedbacks perceived by the subject, reaction to external stimuli would be always late with respect to the actual event that caused the sensory stimulation. This issue, diffusely discussed in (Wolpert et al., 1998), can be retrieved in several models of locomotion and gaze control. In fact, prediction is a mandatory factor during smooth pursuit eye movements. During maintained smooth pursuit, the lag in eye movements can be reduced or even cancelled if the target trajectory can be predicted (Fukushima et al. 2002).


 
Copyrights © Ro-man 2010