Towards an emotion core based on a hidden Markov model

An emotion core for autonomous robots based on a hidden Markov model is proposed. Different emotional robot characters can be designed by tuning state transition probabilities. Perception of stimuli has an impact on emotional state transitions, and, thus, affects emotion dynamics and observable expressions/actions. This work proposes the methodology of design and implementation, and shows integration into a decision and control architecture. The application potential in an emotion-based human-robot interaction is discussed.

[1]  Brian Scassellati,et al.  Infant-like Social Interactions between a Robot and a Human Caregiver , 2000, Adapt. Behav..

[2]  Sandra Clara Gadanho,et al.  Learning Behavior-Selection by Emotions and Cognition in a Multi-Goal Robot Task , 2003, J. Mach. Learn. Res..

[3]  John B. Moore,et al.  Hidden Markov Models: Estimation and Control , 1994 .

[4]  T. Fukuda,et al.  Model based emotional status simulation , 2002, Proceedings. 11th IEEE International Workshop on Robot and Human Interactive Communication.

[5]  Taichi Shiiba,et al.  Realization of realistic and rich facial expressions by face robot , 2004, IEEE Conference on Robotics and Automation, 2004. TExCRA Technical Exhibition Based..

[6]  Brian Scassellati,et al.  Alternative Essences of Intelligence , 1998, AAAI/IAAI.

[7]  M. Posner.  The Brain and Emotion , 1999, Nature Medicine.

[8]  Toshio Fukuda,et al.  Individuality of agent with emotional algorithm , 2001, Proceedings 2001 IEEE/RSJ International Conference on Intelligent Robots and Systems. Expanding the Societal Role of Robotics in the the Next Millennium (Cat. No.01CH37180).

[9]  Cynthia Breazeal,et al.  Function meets style: insights from emotion theory applied to HRI , 2004, IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews).