Work Description

The research in SAFIRA is being done along the three fundamental phases of affective computing:

The Affective Sensory for Autonomous Agents, where we will develop some affective sensing techniques mainly through the use of external objects (toys) and interpret the input from the user thought the development of techniques for affective user modeling.
Affective Reasoning, Planning and Learning, where the problem of embedding emotion and cognition in a machine (being it a synthetic character, an agent or even a robot) will be handled. This entails the development of techniques for affective planning, affective reasoning and decision making, personality and emotions development, learning and emergence.
Affective Communication and Expression, where new techniques for conveying emotions in a believable way will be developed.

These three parts form the core research and also the components that will become part of an emotion-based architecture.

We will integrate these components in a general toolkit that can be used in any application to achieve affective interactions with the users. To illustrate this use we will develop a set of concept demonstrators. Such demonstrators will be test cases for the verification of which conditions the hypothesis that emotion, as well as other affective phenomena, contributes to improve rationality and general intelligent behaviour of the synthetic characters thus leading to more believable interactions between humans and computers.