Daniel Ballin

Integrating Autonomous Behavior and User Control for Believable Agents

Autonomous agents can help users by taking on a substantial workload, and performing tasks that are too complex for a human. However, in some systems complete autonomy is undesirable as it removes control from the user. It is therefore important to include some user control while maintaining the reduced workload associated with an autonomous system. This is particularly true of user avatars in virtual worlds, appropriate non-verbal communication is too complex to be directed explicitly and should therefore be controlled by an agent. However, the non-verbal communication should express the feelings of the user, so a degree of human input is needed. This paper presents Demeanour, an autonomous system for generating body language in avatars, which integrates user input based on a three level methodology of customization and control.

A Model of Interpersonal Attitude and Posture Generation

We present a model of interpersonal attitude used for generating expressive postures for computer animated characters. Our model consists of two principle dimensions, affiliation and status. It takes into account the relationships between the attitudes of two characters and allows for a large degree of variation between characters, both in how they react to other characters’ behaviour and in the ways in which they express attitude.

Direct manipulation like tools for designing intelligent virtual agents

If intelligent virtual agents are to become widely adopted it is vital that they can be designed using the user friendly graphical tools that are used in other areas of graphics. However, extending this sort of tool to autonomous, interactive behaviour, an area with more in common with artificial intelligence, is not trivial. This paper discusses the issues involved in creating user-friendly design tools for IVAs and proposes an extension of the direct manipulation methodology to IVAs. It also presents an initial implementation of this methodology.

Affective interactions between expressive characters

When people meet in virtual worlds they are represented by computer animated characters that lack a variety of expression and can seem stiff and robotic. By comparison human bodies are highly expressive; a casual observation of a group of people mil reveals a large diversity of behavior, different postures, gestures and complex patterns of eye gaze. In order to make computer mediated communication between people more like real face-to-face communication, it is necessary to add an affective dimension. This paper presents Demeanour, an affective semi-autonomous system for the generation of realistic body language in avatars. Users control their avatars that in turn interact autonomously with other avatars to produce expressive behaviour. This allows people to have affectively rich interactions via their avatars.

Towards autonomous characters for interactive media

This chapter describes a project to develop virtual environment-based Teletubby characters, as in the childrens television programme. The differences between the media are considered and the requirements for character development. The multi-level architecture adopted, BALSA (Behavioural Architecture for Life-like Synthetic Agents), is described in detail and future developments are proposed.

Editorial message: special track on virtual reality, digital media, and computer games

Co-Chair: Daniel Ballin Radical Multimedia Lab BTexact Technologies Ross PP1, Adastral Park, Ipswich, IP5 3RE, United Kingdom (0)1473 632250 daniel.ballin @ bt.com Co-Chair: Ruth Aylett Centre for Virtual Environments. Business House, University of Salford, Salford, M5 4WT, United Kingdom +44 (0)161 295 2912 r.s.aylett @ salford.ac.uk Co-Chair: Marc Cavazza Computing & Mathematics. University of Teesside, Borough Road, Middlesborough, TS1 3BA United Kingdom +44 (0)1642 342 6Sl m.o.cavazza @ tees.ac.uk