Language and Cognitive Robotics

The course focuses on artificial cognitive systems and in particular on robots, with a special emphasis on the role of natural language within such systems. It is an interdisciplinary course which brings together theories, findings and methodologies from Cognitive Science, Neuroscience, Theoretical and Computational Linguistics and Multimedia Systems.   

In using multimodal and multisensory communication examples, the idiosyncratic characteristics and the semantic interaction of natural language with perception and action is presented. This interaction takes place -among others- through “syntax”, a fundamental cognitive mechanism. Syntax is shown to be core not only in verbal but also in sensorimotor behaviour; its relation to long term memory is specifically presented and a semantic memory model for cognitive agents is explained in detail. The latter involves getting familiar with multimodal, referential, and recursive semantic networks.  Within this framework, natural language processing is revisited, rendering reference a core requirement in language analysis, that forms a bridge with the sensorimotor aspects of a cognitive system. The course is enriched with examples from two robotic applications: (a) verbal human-robot interaction in everyday life, and (b) visual scene understanding and verbalization.

INSTRUCTOR

kpastraatathenarc [dot] gr (Katerina Pastra)

COURSE CODE
C20
SEMESTER
Fall
COURSE TYPE
Postgraduate (PG)
ECTS
6