Integrating Language and Cognition in Grounded Adaptive Agents
Abstract
In future, machine agents will be able to communicate among themselves and with humans with the flexibility and complexity of human language. Leonid Perlovsky proposed Modeling Field Theory (MFT) as a new method for overcoming the exponential growth of combinatorial complexity (CC) in computational intelligent techniques currently used in cognitive systems design. MFT uses fuzzy dynamic logic to avoid CC and computes similarity measures between internal concept-models and the perceptual and linguistic signals. More recently, Perlovsky (2004) has suggested the use of MFT specifically to model linguistic abilities. By using concept-models with multiple sensorimotor modalities, a MFT system can integrate language-specific signals with other internal cognitive representations. The general aim of this project is to integrate language and cognitive capabilities in cognitive systems through the combination of grounded adaptive agent and MFT techniques. This will be achieved through the following objectives: 1. To adapt the MFT algorithm for the acquisition of linguistic, cognitive and sensorimotor abilities in adaptive agents 2. To design and implement a computer simulator for linguistic agents with MFT controller 3. 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) 4. To do further simulation aiming at the scaling up of the agents lexicon in terms of high number of lexical entries and types of syntactic categories.
Document Details
- Document Type
- Technical Report
- Publication Date
- Nov 21, 2008
- Accession Number
- ADA492889
Entities
People
- Angelo Cangelosi
- Vadim Tikhanoff
Organizations
- University of Plymouth