Integrating Language and Cognition in Grounded Adaptive Agents

EOARD Grant # 053060

 


 

 

Summary

   In future, machine agents will be able to communicate among themselves and with humans with the flexibility of human language. Recent research in autonomous cognitive systems has focused on the close integration (grounding) of communication with perception, categorization and action. Such systems are designed to assist humans in a variety of situations including everyday tasks (e.g. service/household robotics), and highly-specialised situations such as with autonomous systems for defence (e.g. collaborative and multi-agent distributed tasks for exploration and navigation in unknown terrains).

   The project has the aim of combining research on grounded autonomous cognitive systems with Modelling Field Theory (MFT; Perlovsky 2001). This will permit the integration of bottom-up information (e.g. phonetic signals, tactile and perceptual input) and internal concept-models that the agent creates during its interaction with the world. The combination of MFT with grounded agents will deal with the combinatorial complexity barrier currently faced by linguistic cognitive systems.

   The main objective consists in the investigation of the benefits of MFT for the development and scaling up of communication abilities in autonomous systems. This will be achieved through a series of simulation robotic experiments on the integration of language and cognitive abilities in collaborative tasks.

   The potential impact of this research for the development of intelligent systems is great, also in the field of defence interests. Cognitive systems are essential for integrated multi-platform systems capable of sensing and communicating. In future systems, robots and autonomous agents will be able to learn language and world understanding from humans. In the area of internet/text search engines the capability of truly "understanding" the language query and corpora being used will permit the design of more efficient search and data-mining systems. In the area of intelligent agents for defence, the design of cognitive systems able to develop autonomously their own grounded lexicons will be beneficial in collaborative and distributed tasks. (e.g. multi-agent exploration and navigation in unknown terrains, etc.)

People

Dr. Leonid Perlovsky

Prof. Angelo Cangelosi

Mr. Vadim Tikhanoff

Collaborator

Prof. Jose Fernando Fontanari

Related links

Centre for Interactive Intelligent Systems

Adaptive Behaviour and Cognition Research Group

IJCNN2006 – Special Session on “Modeling the Evolution and Acquisition of Language”

The 6th International Conference on the Evolution of Language (Evolang6)

The 16th International Conference on Artificial Neural Networks (ICANN 06)