Skip to main content

Über dieses Buch

In most scenarios of the future a personalized virtual butler appears. This butler not only performs communication and coordination tasks but also gives recommendations on how to handle everyday problems. The aim of this book is to explore the prerequisites of such a personalized virtual butler by asking: what is known about the capacities and the needs of aging people; which information and communication technologies have been used in assisting/conversing with persons, especially older ones, and what were the results; what are the advantages/disadvantages of virtual butlers as mainly software programs compared robots as butlers; and which methods, especially in artificial intelligence, have to be developed further and in which direction in order to create a virtual butler in the foreseeable future?



Introduction: From Jeeves to Jeannie to Siri, and Then?

Introduction: From Jeeves to Jeannie to Siri, and Then?

Servants and butlers always have been playing an important role, not only in books of history but also in fiction, such as fairy tales, novels, plays, operas, and films. Three types of them are discussed: "Natural Servants", i.e. human ones, who understand the wishes of their masters well but, in any case, their mental and physical capabilities cannot exceed those of humans. "Ghost Servants" like genies with capabilities we humans can only dream of, and "Robotic Servants" that have a machine as a body and sensors and actuators controlled by complex, often smart programs. Several examples of each type are presented, relating them to the aims of a "virtual butler". Finally, the contribution of every chapter of this volume to the "making-of" is highlighted.
Robert Trappl

Part I:Psychological and Social Considerations


Would a Virtual Butler Do a Good Job for Old People? Psychological Considerations about Benefits and Risks of Technological Assistance

Psychological theories and knowledge are discussed within the scenario of “Tina and her butler” in order to consider benefits and risks of a virtual assistant with artificial intelligence. With the issue of cognitive functionality in old age learning and training aspects of daily life routine are argued to be diminished if too much assistance is offered. Since social participation and maintenance of social contacts are necessary factors for well-being in old age these aspects are discussed regarding an increased use of virtual conversations instead of real visits. Finally ethical considerations of the use of artificial intelligence and an outlook of future scientific research are given.
Claudia Oppenauer-Meerskraut

Framing the Invisible – The Social Background of Trust

A butler is part of your personal surrounding – a person you can trust. If information and communication technology (ICT) shall become a virtual butler, trust is needed. But - trust has many meanings. Very often the focus is put on a cognitive model of trust. According to our studies, in healthcare and tourism this definition has to be broadened. People should not (only) be seen as rational problem solvers nor should human action be described as a chain of sequential and hierarchical step-by-step decisions. Emotional and social aspects have to be considered, too. Trust should be seen as integral part of interpersonal relationships that are shaped by cultural conditions. Referring to Goffman’s frame analysis, we will discuss if and how ICT, especially the virtual butler, can be framed in a way that trust is possible.
Kerstin Heuwinkel

Part II:Experiences with/Prerequisites for Virtual or Robotic Companions


Virtual Butler: What Can We Learn from Adaptive User Interfaces?

In this paper, we discuss approaches and results from the field of User-Adaptive Interfaces that we believe can help advance the research on virtual butlers in general, and for the elderly in particular. We list principles underlying the design of effective mixed-initiative interactions that call for formal approaches to dealing both with the uncertainty on modeling relevant cognitive states of the user (e.g., goals, beliefs, preferences), as well as with the tradeoff between costs and benefits of the agent’s actions under uncertainty. We also discuss the need for virtual butlers to understand the affective states of their users, and to what extent they need to be transparent by providing means for their users to understand the rationale underlying their adaptive interventions.
Cristina Conati

Towards Affect Sensitive and Socially Perceptive Companions

This chapter investigates affect sensitivity as an important requirement for socially perceptive companions. Challenges and issues arising in the design of an affect recognition framework for artificial companions are identified. A multi-level approach to the analysis of non-verbal affective expressions in human-companion interaction is also presented. The chapter ends with a discussion on the importance of affect recognition for the generation of empathic reactions and the establishment of long-term human-companion relationships.
Ginevra Castellano, Peter W. McOwan

Before We Get There, Where Are We Going?

Fictional stories abound where artificial intelligence gives rise to man-made servants that make our lives a holiday (or a nightmare). Naturally, the optimist has a strong motive to ask: How might we design and implement an artificial servant? We regularly operate under the notion that one agent helps another by doing something for the other. However, the story behind this is much more complicated. In this position paper, we explore two questions: What is the nature of service that is helpful or “good”? and What will it take to design and implement agents that provide “good” service? We start by describing our current understanding of the nature of service, consisting of a number of dimensions along which service may be measured and compared, and three modes in which service may be delivered. With these dimensions and modes setting the stage, we consider the technical and social requirements for implementing artificial servants. We find that while many prerequisites are either already available or could reasonably be developed from the current state of the art, both technical and social challenges remain that are expected to be very difficult to overcome. Our experimental work attempts to generate and evaluate the fundamental elements of helpful assistance, and we provide a brief overview of our work. One surprising empirical result reminds us of a common understanding about help: providing assistance is a two-way street. Developing that two-way street may prove to be one of the most significant obstacles to realizing an artificial personal servant.
Wayne Iba

Virtual Helper or Virtual Card Player? Contrasting Responses of Older Users

In the NETCARITY project, we conducted several complementary investigation activities with elderly people revolving around the design of technology for the home environment. In this paper, we investigate the potential impact of virtual characters in making the interaction with the technology-enhanced home more effective and engaging. We briefly discuss two experiences in using a virtual agent as an interface metaphor for a computer system targeted to elderly people with very low computer skill. The lesson that can be learned from those experiences is that a virtual agent may sometimes be effectively used to improve the acceptance of new technologies for this class of users. In particular, in settings characterized by a social interaction, where emotional stress is low (as with entertainment applications), the presence of a virtual character facilitates the acceptance of the technology by helping it to fit into the social environment. In the opposite case, in contexts where trust is an important factor or in life-threatening situations, a virtual agent is less likely to be credible.
Massimo Zancanaro, Silvia Gabrielli, Anthony Jameson, Chiara Leonardi, Elena Not, Fabio Pianesi

Scenarios for Companions

This paper is concerned with understanding the needs of Companion owners (the people formerly known as ‘users’). The problem with developing technologies such as companions is in knowing what the requirements are. People cannot really be expected to express their needs for companions before the technology that will drive the idea has been invented. Yet we know that the technology that will provide the sort of personalised, persistent interactions that characterise companions is coming, the question we are interested in is how requirements for companions can be generated. We are concerned with the whole interaction design, not just the speech recognition and language understanding, the gestures, or the inferences the companion can make. We are interested in how the companion will learn, or be instructed, so that the interaction can evolve and develop with the individual. We are concerned with the whole interaction experience and with how the different components fit together. In this chapter we present a conceptualisation of the companion idea and then illustrate how the development of personas and scenarios in the context of companion technologies can help us generate the requirements for these technologies. Finally we comment on some of today’s technologies that already starting to demonstrate the characteristics of companions.
David Benyon, Oli Mival

Care-O-bot® 3 – Vision of a Robot Butler

This chapter promotes the idea of a robot butler and investigates the advantages and disadvantages of embodiment for the proposed scenario,,Tina and her butler“. In order to make the discussion more tangible, Care-O-bot® 3 is introduced, which is the newest version of the Care-O-bot® series developed by the Fraunhofer Institute for Manufacturing Engineering and Automation IPA in Stuttgart, Germany. Remarkably, the prominent role of this robot was chosen to be a butler’s. A brief overview is given of current human-robot interaction research, focusing on how users react to the idea of a robot companion. The results of different user studies provided inspiration during the design phase of Care-O-bot® 3, in particular with respect to the robot’s appearance and the user interaction concept. The technological aspects are covered shortly before user interaction scenarios embedded in research projects related with Care-O-bot® 3 are presented. Results from real life trials conducted in an elderly care facility are given afterwards. Against the background of these scenarios, the benefits and drawbacks of embodiment for the virtual butler scenario are discussed using the example of Care-O-bot® 3.
Ulrich Reiser, Theo Jacobs, Georg Arbeiter, Christopher Parlitz, Kerstin Dautenhahn

Part III:Further Developments


Spoken Language Processing: Where Do We Go from Here?

Recent years have seen steady improvements in the quality and performance of speech-based human-machine interaction driven by a significant convergence in the methods and techniques employed. However, the quantity of training data required to improve state-of-the-art systems seems to be growing exponentially, and yet performance appears to be reaching an asymptote that is not only well short of human performance, but which may also be inadequate for many real-world applications. This situation suggests that there may be a fundamental flaw in the underlying architecture of contemporary speech-based systems, and the future direction for research into spoken language processing is currently uncertain. This chapter addresses these issues by stepping outside the familiar domains of speech science and technology, and instead draws inspiration from recent findings in fields of research that are concerned with the neurobiology of living systems in general. In particular, four areas are highlighted: the growing evidence for an intimate relationship between sensor and motor behaviour in living organisms, the power of negative feedback control to accommodate unpredictable disturbances in real-world environments, mechanisms for imitation and mental imagery for learning and modelling, and hierarchical models of temporal memory for predicting future behaviour and anticipating the outcome of events. The chapter shows how these results point towards a novel architecture for speech-based human-machine interaction that blurs the distinction between the core components of a traditional spoken language dialogue system; an architecture in which cooperative and communicative behaviour emerges as a by-product of a model of interaction where the system has in mind the needs and intentions of a user, and a user has in mind the needs and intentions of the system. It concludes with a roadmap of technical pre-requisites and desiderata that would seem to be necessary if voice-based interaction with an autonomous agent such as a virtual butler is to become a practical reality.
Roger K. Moore

Virtual Butlers and Real People: Styles and Practices in Long-Term Use of a Companion

In this chapter, we argue that it is already possible, with existing technologies, to go beyond fictional scenarios of virtual butlers or assistive robot companions, and that realistic, long-term studies of their use contribute much needed knowledge about user styles and hence design requirements. Such a study, undertaken by the EU project SERA (Social Engagement with Robots and Agents) is reported, and the data collected are presented, compared, and discussed. The striking difference between idealized personae (such as "Tina") and real users motivated a detailed case study about the frequently observed issue of initiative and floor management. The case study shows the considerable degree to which users shape human-robot interaction with their individual styles. In conclusion, a few such user styles, together with design consequences, are outlined on the basis of the data analysis, with the aim of enriching future scenario descriptions with more realistic personae.
Sabine Payr

What Issue Should Your Virtual Butler Solve Next?

In this chapter, a scenario-based analysis of the guiding vision of a virtual butler is presented. After introducing the concept of scenario-based analysis for comparing agent-based technology design, we use the characterization of the scenario hinted at in the vision document to discuss several technological issues that arise from it. By disregarding non-technical issues, we arrive at problems (or rather challenges) of technology in a wide sense that could be steps in the direction of the virtual butler. The order of presentation of these challenges is based on a subjective estimation of the complexity involved in arriving at the competence required for a virtual butler.
Stefan Rank


Weitere Informationen

Premium Partner