Paper Info
Title
Towards modelling affect and emotions in autonomous agents with recurrent fuzzy systems
Abstract
In this paper, we present a computational model of the elicitation and the dynamics of affective states in autonomous agents based on fuzzy methodology. Fuzzy logic has been used in computational modelling of affect for 15 years, but has not yet been employed to bridge the particular benefits of fuzzy modelling with dynamical systems approaches to understanding emotions. The information-processing architecture scheme we propose for the calculations which are involved in affective processes can be instantiated in a distributed fashion. This enables `programming' of the agent's affective interpretation of its relationship with its environment with respect to different objects and their behavior towards the agent, as well as its own internal motivational states. In our simulations, we emphasize dynamic properties of affective processes and behaviors resulting therefrom. In addition, we sketch theoretical ideas of internal effects of different affective states that we are currently implementing.
Year
DOI
Venue
2014
10.1109/SMC.2014.6973880
Systems, Man and Cybernetics
Keywords
Field
DocType
fuzzy reasoning,recurrent neural nets,affect modelling,affective processes,affective state dynamics,agent affective interpretation programming,autonomous agents,computational elicitation model,dynamic properties,dynamical system approach,emotion modelling,fuzzy logic,fuzzy methodology,information-processing architecture scheme,internal motivational states,recurrent fuzzy systems
Autonomous agent,Computer science,Artificial intelligence,Fuzzy control system,Machine learning
Conference
ISSN
Citations 
PageRank 
1062-922X
6
0.48
References 
Authors
6
2
Name
Order
Citations
PageRank
Moritz Schneider172.19
Jürgen Adamy219239.49