A COGNITIVE-MAP-BASED APPROACH TO THE COORDINATION OF DISTRIBUTED COOPERATIVE AGENTS

A partial taxonomy for cognitive maps is provided; the notions of NPN (Negative-Positive-Neural) logic, NPN relations, coupled-type neurons, and coupled-type neural networks are introduced, which lay out a framework for cognitive map modeling. Based on this framework, D-POOL, a cognitive-map-based architecture for the coordination of distributed cooperative agents, is presented. D-POOL consists of a collection of distributed nodes. Each node is a cognitive-map-based metalevel system coupled with a local expert/database system (or agent). To solve a problem, a local node first pools cognitive maps from relevant agents into an NPN relation that retains both negative and positive assertions. Then new cognitive maps are derived and focuses of attentions are generated. With the focuses, a solution is proposed by the local node and passed to the remote systems. Based on their view points, the remote systems respond to the proposal and D-POOL strives for a cooperative or compromised solution through coherent communication and perspective sharing. The potential utility of D-POOL is demonstrated using two application examples in distributed group decision support. This approach bridges the gap between neural network study and symbolic DAI systems. It distinguishes itself from others with its underlying cognitive integrity, transparency, and simplicity.