Current Projects
LIDA
LIDA (Learning IDA) adds various mode of human-like learning to the IDA architecture (see IDA description below), including perceptual, episodic, procedural and attentional learning.

Integrated LIDA: Parameter Tuning
forthcoming

Integrated LIDA: Tyrell's World
forthcoming

LIDA Working Memory

This project aims to develop a more detailed and comprehensive computational model of working memory in LIDA. Roughly speaking, working memory in LIDA is implemented via the workspace, perceptual, episodic, and declarative memory buffers, and relational and structure-building codelets. Part of the project is to flesh out a new component of the workspace called the Model which contains the agent's representational model of its current situation. Some of the questions involved in this research are how to model the memory buffers, how to update the model with new percepts and cued memory, and how to implement top-down processes to build relations in the workspace based on lower-level perceptual information. In short, the LIDA Working Memory Project aims to design, implement, and test mechanisms that give LIDA an understanding of its current situation.


Past Projects
LIDA-AV
In the realm of cognitive robotics, LIDA-AV aims to control an autonomous vehicle with the LIDA technology. click here

IDA
Intelligent Distribution Agent addresses the Navy's problem of job distribution using the Conscious Agent Framework. IDA is a very complex agent that perceives e-mails from sailors, deliberates on the right jobs for the sailor and negotiates with the sailor in the context of sailor's preferences and Navy's policies. This project is funded by ONR (Office of Naval Research) and NPRST (Naval Personnel Research, Studies, and Technology).

CMattie
CMattie is the first attempt to design and implement an intelligent agent under the framework of Bernard Baars' Global Workspace Theory. She is a successor to Virtual Mattie and performs the same function in the same environment as VMattie.

VMattie

Virtual Mattie, to actively gather information from humans, compose announcements of next week's seminars, and mail them each week to a list that she keeps updated, all without the supervision of a human. VMattie's architecture combines Maes' behavior net architecture and Hofstadter and Mitchell’s Copycat architecture and significantly extends them. "Living'' in a UNIX environment, VMattie's communication with humans is entirely via email with no agreed upon protocol.
Copyright © 2008 Cognitive Computing Research Group All rights reserved