Abstract
Truly smart systems need to interface with the behaviour of human and non human actors in their surroundings. Systems with such interfaces could prove beneficial in supporting those with non standard communication practices, the elderly living alone, people with disabilities, and many others. While the benefits are clear, the means of achieving true behavioural interfaces are yet unclear. In this paper we outline how semiotics helps us to understand behaviour. We show how such an approach may be put to use in modelling the intention to walk through a door. We begin by outlining the semiotic approach and then discuss the behaviours which need to be described to model intention. We also discuss how this varies according to context and suggest the potential for a more general model of behaviour.
Original language | English |
---|---|
Title of host publication | Proceedings of the Norwegian Artificial Intelligence Society Symposium (NAIS 2009) |
Publication status | Published - Dec 2009 |
Keywords
- Behavioural interfaces
- Artificial Intelligence (AI)
- Intention detection
- multimodal-data fusion
Fields of Science and Technology Classification 2012
- 102 Computer Sciences