Social Engagement for Robots and Agents (SERA)

The Nabaztag robot from Violet Most recently I was employed as Principle Investigator at Sheffield on the SERA project.

The public web site is here.

SERA - A project funded by the European Community's Seventh Framework Programme [FP7/2007-2013] under grant agreement no. 231868.

Proposal abstract

Getting people to engage with robotic and virtual artifacts is easy, but keeping them engaged over time is hard: robots and agents lack some fundamental capabilities which can be summarized as sociability. Sociability involves perceptiveness of and responsiveness to individuals' and groups' needs, moods, habits, situations, cultural background, social norms and conventions. The research community has realized the problem, but approaches, so far, have been dispersed and disjoint. If robots and agents are to become companions in people's lives, with assistive, coaching, monitoring, or educational roles, they will have to blend into these lives seamlessly.

SERA is innovative in that it addresses sociability holistically, by advancing knowledge about what sociability in robots and agents entails, by developing methodology to analyze and evaluate it, and by making available research resoures and platforms. SERA will, to this purpose, undertake real-life extended field studies of users¿ engagement with robotic devices.

Sociablity has also to be built into robot and agent architectures from scratch. The goal here is to research and to implement an architecture that caters for both background (cultural, normative etc.) and situational individual (theory of mind, adaptivity, responsiveness) practices and needs of users, with the guiding principle of pervasive affectivity. Assistive robots and agents who are to become true companions, e.g. for elderly or homebound people, have to be versatile in functionality and identity (style, personality) depending on the service they are required to deliver, such as (reactive) social mediators, as (in turn reactive and proactive) information assistants, or as (proactive) coaches or monitors e.g. with health-related tasks. SERA will develop pilots of such intertwined interactive service applications for a robotic device.

Partners

Publications

"A Robot in the Kitchen" Peter Wallis ACL10, WS12, Companionable Dialog Systems Uppsala, July 2010
A technology demonstrator is one thing but having people use a technology is another, and the result reported here is that people often ignore our lovingly crafted handiwork. The SERA project - Social Engagement with Robots and Agents - was set up to look explicitly at what happens when a robot companion is put in someone's home. Even if things worked perfectly, there are times when a companion's human is simply not engaged. As a result we have separated our ``dialog manager'' into two parts: the dialog manager itself that determines what to say next, and an ``interaction manager'' that determines when to say it. This paper details the design of this SALT-E architecture. full paper
"Conversation in Context: what should a robot companion say?" Wallis (Peter) Viktoria Maier, Sarah Creer and Stuart Cunningham EMCSR 2010
Language as used by humans is a truly amazing thing with multiple roles in our lives. Academics have tended to focus on the way languages convey meaning, and disciplines that come new to the problem such as computer science tend to start with reference semantics and progress to models of meaning that look mathematical and hence solidly academic. Language as used is however beautifully messy. People sing, they lie and swear, they use metaphor and poetry, play word games and talk to themselves. Is there a better way to look at language? Interdisciplinary research is hard not only because each discipline has its own terminology, but also because they usually have different interests. Those of us interested in spoken language interfaces (computer science) however have a shared interest with applied linguistics in how language works in situ. This paper outlines a theory about how language works from applied linguistics and shows how the theory can be used to guide the design of a robot companion.
Robots in Ourspace Peter Wallis (presentation) RMIT, Australia, December 2010
The image of robots in fiction is closely aligned with the future and space travel and industrial robots capture our image of robots as super human being immensely strong and precise. Putting a robot in a domestic setting raises a different set of issues. Of course a perfect android would simply be like us, but real domestic robots such as the Roomba will evolve to fill a niche in the domestic setting. Robots working with people is one theme on the European Commission's science funding scheme and one observation they funded was that robots among people occupy, not just a shared physical space, but also our social space. The FP7 SERA project took a rather dull robot and put it in people's homes to see what happens. People might dress their Roombas, but when their robot talks to them, people talk back. We have recorded what people say to their robots and the data we collected is rich and detailed. In this talk I will identify a few gaps in our knowledge of how to build social robots - attention and floor management being two technical issues we have tried to address with our dialog manager, but perhaps the biggest gap is that quantitative methods don't capture half of what seems to be going on. The next grant will, with luck, find a way to convince those interested in computer interfaces other than a screen and keyboard that some form of qualitative data analysis is valid science and the way ahead. slides