Workshops & Tutorials (preliminary)
[hide abstracts]
Workshops and Tutorials will take place on the first symposium day. A detailed schedule will be published soon. Please click on a title for more details..
Imitation and Robotics - Background, Theories, and Practice
Aris Alissandrakis, Joe Saunders
Imitation is a powerful mechanism that allows agents to learn via their interactions within a social context. An artificial system that is capable of exploiting this imitative learning capability would be able to acquire new skills and tasks from interaction with another agent (typically a human or another robot). Imitative social learning therefore presents a very interesting paradigm in robotics and computer science and within this paradigm robotics researchers are heavily influenced from interdisciplinary studies typically in biology, ethology and psychology. This tutorial takes such an interdisciplinary approach and aims to present the background and theories of imitation from biology, ethology and psychology together with some of their practical implementations in robotics. The aim of tutorial is to disseminate this research field to a wider audience.
Who should attend: Anyone with an interest in Robotics and Social Learning. Participants with diverse backgrounds are especially welcome as this tutorial aims to give an interdisciplinary perspective to the
research area of how to design artificial adaptive systems that can learn from observing and interacting with humans.
Cognition for Technical Systems
Michael Beetz, Dirk Wollherr, Uwe Haass
A major goal in current robotics research is to tear down currently existing barrier between human and robot in order to enable tight interaction and close collaboration between human and robot. Such systems can pave the way to highly flexible production methods in industry, more efficient support by technical systems in service applications, or personal buttlers in private homes. Such challenging goals can only be achieved, if robots are capable to perceive their environment, reflect on it, and autonomously decide on the most appropriate action in the given situation. Such closed perception-reflection-action loop requires skills from the robot which are commonly referred to as cognitive abilities. Closing the perception-reflection-action loop also closes a loop through many formerly strictly separated research disciplines like neuro-cognitive sciences, psychology, computer science, mathematics, and engineering. This workshop will discuss requirements for cognitive technical systems from the persepctive of different research disciplines following the goal to make a big step towards pushing cross-disciplinary exchange and discussion to enable cognitive technical systems.
Ethics of Interaction for a New Generation of Intelligent Robots
David J. Bruemmer, Douglas A. Few, Curtis Nielson
This tutorial provides a forum for open minded discussion regarding one of the most important technology issues facing our world today:" How will human interactions with robots change the way humans interact with each other?" There are many questions which can be considered under the auspices of this discussion: What kind of relationships are appropriate between humans and robots? What can be done to prevent robots from interfering with human relationships? Will robots become more human-like or will they evolve along an entirely different trajectory? Or perhaps will humans become more like robots?
Robots are supposed to make life better... Do they? Will they? Is our research directed primarily to improve life, or are we simply making new technology? How will this new technology change the way we view our human nature, and our interactions with each other? Increasingly, the media and the public are debating these issues with little understanding of the fundamental challenges of robotics in general or the last decade of research in human-robot interaction in particular. This tutorial will educate the audience as well as provide a means for exchanging ideas. It will be appropriate for the public and media participation as well as providing a scholarly perspective on the art of the possible.
Nonverbal Communication: Importance, Achievements, and Challenges
Berthold Färber, Gerhard Rigoll, Frank Wallhoff
What makes a robot genuinely intelligent and user-friendly? How can we make cognitive systems understand and react to social and emotional humane signals? What are the relevant human states that need to be taken into account? What causes them and how are they best dealt with? Which methods of signal processing or pattern classification best suit to this kind of data? Normally, these questions are being investigated in separate research fields, with psychology focussing questions of important emotional states and their underlying dimensions, causes, and implications, while electrical engineers and computer scientists concentrate on robot control and data analysing methods. Even though specialized in-depth knowledge surely is important, efficient collaboration needs at least basic insights into related research areas.
The workshop brings together experts and researchers from both fields, to provide a holistic view on HRI and to learn from each other. Participants cannot only learn from the experts, but also discuss their problems and experiences with colleagues from different disciplines. Target audience are researchers from all disciplines concerned with HRI, who are interested in a fruitful interdisciplinary exchange.
"being in touch" - Workshop on Haptic Human-Robot Interaction
Sandra Hirche, Angelika Peer
“Touch” is an indispensable component of human interaction in collaborative environments. The important role of haptics manifests in different forms ranging from assistance in physical task to social interaction.
For the seamless incorporation of robots in human environments the ability to physically interact with them in a meaningful way is essential. Haptics enriches the interaction capabilities towards intuitive full multimodal interaction and improves task performance. While research in other fields of human-robot interaction such as communication via speech and gestures is rather advanced, the topic of haptic interaction is still largely underrepresented.
This workshop is dedicated to the most recent developments in the field of haptic human-robot interaction. Topics presented by world-renowned scientist include human-human haptic interaction paradigms, haptic language, intention identification, emerging strategies in physical cooperation, application and evaluation in robotic systems ranging from teleoperated to fully autonomous robots.
Towards Natural Human-Robot Joint Action
Alois Knoll, Mary Ellen Foster, Manuel Giuliani, Thomas Müller, Markus Rickert
The success of the human species critically depends on our ability to engage in joint action. Our perceptions, decisions and behavior are tuned to that of others with whom we share beliefs, intentions and goals, and thus form a group. Studying the cognitive, neural, and communicative aspects of human-human joint action produces insights -- and, often, implementable models -- that can be used in building robot systems that are able to cooperate naturally and intelligently with human partners.
This workshop will bring together practitioners from two distinct research areas: those who study the cognitive, neural, and communicative aspects of human-human joint action, and those who aim to implement robot systems that are able to cooperate intelligently with a human partner. The presentations will include results from a range of human-human studies as well as descriptions of concrete human-robot systems. The overall goals of the workshop are twofold: to explore the range of phenomena found in human-human collaborative interactions, and to investigate how findings from these studies can be applied to the development of robot systems that are designed to support intelligent collaboration with humans on mutual tasks.
Skills Capture and Transfer
Carsten Preusche, Carlo A. Avizzano, Emanuele Ruffaldi
Multimodal Skills Capture and Transfer is a challenging topic of research that is aimed to analyze and transfer the skilled component of human activities with the use of multimodal technologies. This field requires the contribution of researches from neuroscience, psychophysics, capturing technologies and rendering technologies. It 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 human modalities, e.g. through haptic interfaces and advanced visualization techniques. At the same time the data acquired in real time is processed by machine learning algorithms for the identification of performance, comparing the user with an existing database of skilled user, producing as an outcome the required stimuli for improving the user task.
The workshop will be structured around a set of talks from selected speakers of the SKILL IP (www.skills-ip.eu) Consortium and external speakers with specific expertises on the topic. The presentations will be organized around three main areas: analysis, capturing and rendering of skills. The talks will show the integration of skills modeling and analysis with technologies in the area of multimodal interfaces.
The Impact of Fictional Robots on Robot Interaction Design
William D. Smart, Lara Bovilsky
Most people have never met a real robot. They have, however, almost certainly encountered fictional robots, in movies and books. Fictional robots do whatever the fiction requires, and are not bound by practical limitations in the real field of robotics. While this is good for writers, directors, and their audiences, it means that public preconceptions about what real robots are like and can do are often very different from reality: e.g. more fearful or more optimistic about robot abilities than is warranted. Understanding, and possibly taking advantage of, these preconceptions will be a vital part of designing effective human-robot interactions as members of the general public are increasingly exposed to robots in their everyday lives.
This tutorial will present an overview of the use of robots in literature and film, providing brief exemplary readings and movie clips. For each example and trend, we will give an interpretation of the role of the fictional robot, a comparison of its capabilities and functions to the current state of the art in robotics, an assessment of the preconceptions that this robot might engender and their practical implications for robot design, and propose a set of experiments that will test these hypotheses.
Robots as Social Actors: Evaluating Social Acceptance and Societal Impact of Robotic Agents
Manfred Tscheligi, Astrid Weiss, Aude Billard, Kerstin Dautenhahn
This workshop “Robots as Social Actors: Evaluating Social Acceptance and Societal Impact of Robotic Agents” will discuss possible methodological approaches for evaluating social acceptance and societal impact of Human Robot Interaction (HRI) with a special focus on collaborative working environments. Advantages and disadvantages of existing evaluation methods should be discussed to develop new variations and advancements for assessing social acceptance and societal impact of robotic agents.
The main challenge of the workshop is to develop instruments for measuring social acceptance and societal impact in the field in HRI.
Submissions are expected in the form of 4 page position papers, describing the area of research, specific work (empirical or theoretical) on the workshop topic and the innovative character of the presented work. Insightful essays about the topic are also welcomed. We will select participants with diverse backgrounds based upon the relevance, insightfulness, and originality of their submissions based on a peer review process. At least one author of accepted papers needs to register for the workshop and for one day of the conference itself.