[with apologies for multiple copies] =========================================================================== Call for Papers and Participation AAAI 2007 Spring Symposium on INTERACTION CHALLENGES FOR INTELLIGENT ASSISTANTS 26-28 March 2007, Stanford University, CA, USA =========================================================================== Motivation: In an increasingly complex world, a new wave of intelligent artificial assistants have the potential to simplify and amplify our everyday personal and professional lives. These assistants will help us in mundane tasks from purchasing groceries to organizing meetings; in background tasks from providing reminders to monitoring our health; and in complex, open-ended tasks from writing a report to locating survivors in a collapsed building. Some will offer tutelage or provide recommendations. Whether robotic embodiments or software processes, these assistive agents will help us manage our time and budgets, knowledge and workflow as they assist us in our homes, offices, cars, and public spaces. To realize the vision of truly useful assistants, four broad requirements must be met. First, our assistants must be personalized: they must learn and be advised about our preferences and adapt to our way of working. Second, they must be capable of learning from us new methods to solve existing or novel problems in their application domain, and to correct their behaviour when mistakes are made. Third, as a consequence, our intelligent assistants must engender our trust over an extended period of time, because their behaviour will materially affect our interests and well-being (and even our own behaviour). Fourth, they must become our partners, able to engage in joint, collaborative problem solving and decision making. In all these capabilities, an essential aspect of the success of our intelligent assistants is their interaction with us and with other humans and agents in natural ways that are no more obtrusive than necessary. Moreover, this interaction must be uniform and coherent over the various functions of the assistant, and be sensitive to the user's available time and cognitive focus, the interaction conditions and modalities, and subjective factors such as the user's mood. Description: This symposium will bring together practitioners and researchers of artificial intelligence, human-computer interaction, cognitive science, robotics, assistive and agent technologies, and fields that address complex socio-technical systems. We hope to foster interactions among this highly interdisciplinary set of participants by including presentations from distinct perspectives and by allocating ample time for discussions. Developing intelligent assistants is a challenge that demands collaboration across disciplines. Designing interaction with these assistants challenges us at the level both of fundamental concepts in human-agent communication and of applied research in system building. Hence, from a multi-disciplinary perspective, the symposium will identify the critical issues raised by interaction with personal assistants, the specific challenges faced, and the current state of the art. The ultimate goal is to progress towards the most useful paradigms, methodologies, and implementations for human interaction with intelligent artificial assistants. Specific topics of interest include, but are not limited to: - Collaborative Problem Solving: conversational case-based reasoning; failure recovery; introspection; joint intentions and intention management; knowledge capture; learning for the assistive agent; managing local autonomy in collaborative activities; mixed-initiative interaction and initiative sharing; negotiation and delegation; planning, and task and plan recognition; proactive and opportunistic actions; user modelling over time; - Interaction Principles and Modalities: dialogue management and discourse grammars; human-computer collaboration principles for agent systems; human-robot interaction; imitating human behaviour; modalities of interaction; supporting users with impaired capabilities; verbal and non-verbal interaction; - Trust: advisability and adjustable autonomy; engendering trust and influencing behaviour over extended operation; ethical, legal, and safety issues for human assistants; explanation; personalization; psychological factors; relational agents; robust and secure agents; - Studies and Comparisons of Systems: agent interfaces and architectures; case studies of deployed systems; characterization of domains amenable to assistive agents; comparisons of systems and architectures; evaluation methodologies, metrics, and measures; novel approaches and applications; user studies. A joint session will be shared with the co-located Symposium on Multidisciplinary Collaboration for Socially Assistive Robotics. Submission Information: Potential participants are invited to submit either a full paper (up to eight pages) addressing these and related questions, or a position paper (up to two pages) outlining their relevant research activities and how they would like to contribute to the symposium. Submissions, in PDF format, should be sent no later than 23 October 2006 to nysmith AT ai.sri.com (remove the spaces) using the subject line "SSS'07 Submission". All submissions should conform to the AAAI style format. Papers will be reviewed by at least two referees. Important Dates: Submission deadline (extended) 23 October 2006 Notice of acceptance 20 November 2006 Student travel grant applications 1 December 2006 Camera-ready deadline 26 January 2007 Registration deadline 9 February 2007 Final (open) registration deadline 2 March 2007 Spring Symposium Series 26-28 March 2007 Further Information: Symposium website: http://www.ai.sri.com/~nysmith/organizing/sss07/ Spring Symposium Series: http://www.aaai.org/Symposia/Spring/sss07.php Please email inquiries to the symposium chair at: nysmith AT ai.sri.com (remove the spaces). Organizing Committee: Pauline Berry, SRI International Timothy Bickmore, Northeastern University Mihai Boicu, George Mason University Justine Cassell, Northwestern University Ed H. Chi, Palo Alto Research Center Michael T. Cox, BBN Technologies John Gersh, John Hopkins University Jihie Kim, USC/Information Sciences Institute Pragnesh Jay Modi, Drexel University Donald J. Patterson, University of California at Irvine Debra Schreckenghost, NASA Johnson Space Center/Metrica Inc. Richard Simpson, University of Pittsburgh Stephen F. Smith, Carnegie-Mellon University Sashank Varma, Stanford Neil Yorke-Smith, SRI International (chair) ===========================================================================