The Evolution and Grounding of Language in Cognitive Agents and Robots
School of Computing, Communications and Electronics, Univers
Last modified: October 18, 2007
Computational approaches to modeling adaptive behavior and cognition, such as artificial life and multi-agent systems, are advantageous when studying the evolution of language and communication. In these models, the level of description of the communicating agents and their environment varies significantly. This constitutes a continuum from ungrounded, abstract agent models to grounded multi-agent and robotic approaches. This talk focuses on the use of adaptive grounded agents where (i) symbols are directly grounded in the agentsí own sensorimotor and cognitive abilities and (ii) the communicative/linguistic behavior evolves through the interaction of agents in their physical and social environment. In such grounded adaptive agent models, the perceptual, motor, cognitive and linguistic capabilities of the agents are controlled by evolving neural networks. Various models and simulations on the evolution and emergence of linguistic communication will be discussed.