Integrating Language and Cognition in Grounded Adaptive Agents

EOARD Grant # 053060

 


 

 

Objectives & Work Plan:

The general aim of this project is to integrate language and cognitive capabilities in cognitive systems through the combination of grounded adaptive agents and MFT techniques. In the first year, this will be achieved through the following objectives:

 

  • To scale up the MFT algorithm presented at KIMAS 2005 (Fontanari J.(2005) Meaning Creation and Modeling Field Theory) and to test its capacity to withstand the augmentation.

  • To adapt the MFT algorithm for the acquisition of linguistics, cognitive and sensorimotor abilities in adaptive agents

  • To design and implement a computer simulator for linguistic agents with MFT controller

  • To execute a series of simulation experiments on the integration of language and cognitive abilities in collaborative tasks (e.g. object manipulation and navigation tasks)

  • To do further simulation aiming at he scale up of the agents lexicon in terms of higher number of lexical entries and types of syntactic categories.

Work Plan:

The work plan will be based on a series of simulation experiments on language-cognition interaction with grounded adaptive agents.