CORDIS
EU research results

CORDIS

English EN
Embodied Believable Agents

Embodied Believable Agents

Objective

Design a believable conversational interface agent, which makes use of gaze, facial expression, gesture and body posture as well as speech in a synchronised fashion;
Evaluate the use of the conversational agent in laboratory conditions to determine which aspects of the embodied agent are important for what types of human-computer interaction;
Develop and document the agent architecture and components to enable other research and development teams to prototype and evaluate new versions of the agent interface in new domains and for novel tasks.

Design a believable conversational interface agent, which makes use of gaze, facial expression, gesture and body posture as well as speech in a synchronised fashion;
Evaluate the use of the conversational agent in laboratory conditions to determine which aspects of the embodied agent are important for what types of human-computer interaction;
Develop and document the agent architecture and components to enable other research and development teams to prototype and evaluate new versions of the agent interface in new domains and for novel tasks.

DESCRIPTION OF WORK
Believable animation:
to develop an agent, which displays natural or believable movement. This includes modelling not only voluntary movement (e.g. walking) and involuntary movement (e.g. blinking), but also movements, which correlate with communicative acts (e.g. limb gestures, body posture and facial expressions). Whereas research in computer animation has actively studied these different classes of human movement, it is still difficult to procedurally generate believable natural movements within the later class. Our goal is to explore this problem in the area of facial and non-facial animation.
Believable conversation:
to develop an agent, which can perform conversational functions such as repair, feedback or turn-taking in a believable way, using verbal and non-verbal signals. This work will build on empirical and descriptive work on person-to-person dialogue, as well as on computational work on end-to-end spoken dialogue systems, and integrate it with work on simulated agents. Of particular concern, there will be the development of a formalism that allows us to synchronise the different information signals, rather than assume that a particular channel is always the dominant one.
Believable information delivery:
to develop an agent, which can deliver information in a contentful and contextually appropriate way. This work will build on earlier work on the generation of spoken and written messages, integrated with work on animation. To increase the believability of the agent, we want to pay particular attention to the generation of messages in a linguistic style, which projects the right kind of "personality" for the animated agent.
Evaluation:
to evaluate the use of believable agents in information delivery. Throughout the project various aspects of believability will be developed and instantiated in different combinations in subsequent prototypes. This will allow us to evaluate the effects of different types of believable agents in different contexts. However, because the technology itself is novel, we also want to work on the further development of the evaluation methodology for MAGICSTER-style technology.

Leaflet | Map data © OpenStreetMap contributors, Credit: EC-GISCO, © EuroGeographics for the administrative boundaries

Coordinator

THE UNIVERSITY OF EDINBURGH

Address

Old College, South Bridge
Edinburgh

United Kingdom

Administrative Contact

Marc MOENS

Participants (5)

Sort alphabetically

Expand all

AVATARME LTD

United Kingdom

DEUTSCHES FORSCHUNGSZENTRUM FUER KUENSTLICHE INTELLIGENZ GMBH

Germany

SICS, SWEDISH INSTITUTE OF COMPUTER SCIENCE AB

Sweden

UNIVERSITA DEGLI STUDI DI BARI

Italy

UNIVERSITA DEGLI STUDI DI ROMA "LA SAPIENZA"

Italy

Project information

Grant agreement ID: IST-1999-29078

  • Start date

    1 December 2000

  • End date

    30 November 2003

Funded under:

FP5-IST

  • Overall budget:

    € 2 549 237

  • EU contribution

    € 1 560 000

Coordinated by:

THE UNIVERSITY OF EDINBURGH

United Kingdom