In this paper is illustrated the cognitive architecture of a humanoid robot based on the proposed paradigm of Latent Semantic Analysis (LSA). This paradigm is a step towards the simulation of an emotional behavior of a robot interacting with humans. The LSA approach allows the creation and the use of a data driven high-dimensional conceptual space. We developed an architecture based on three main areas: Sub-conceptual, Emotional and Behavioral. The first area analyzes perceptual data coming from the sensors. The second area builds the sub-symbolic representation of emotions in a conceptual space of emotional states. The last area triggers a latent semantic behavior which is related to the humanoid emotional state. The robot shows its overall behavior also taking into account its "personality". We implemented the system on a Aldebaran NAO humanoid robot and we tested the emotional interaction with humans through the use of a mobile phone as an interface.
|Titolo della pubblicazione ospite||AI*IA 2011:
Around Man and Beyond
XIIth International Conference
of the Italian Association for Artificial Intelligence|
|Numero di pagine||10|
|Stato di pubblicazione||Published - 2011|
|Nome||LECTURE NOTES IN COMPUTER SCIENCE|