Here we discuss the role of modules and representations into cognitive architectures by comparing the “unified” approach of SOAR and ACT-R with the “decentralized” one of the Society of Mind. We introduce AKIRA, an open-source hybrid architecture and show how to exploit its features, namely distributed representations and parallel, concurrent processing for agent based cognitive modeling.

In this paper, we present APOC, an agent architecture framework intended for the analysis, comparison, and evaluation of agent architectures. We demonstrate how four main architectures, GRL, ICARUS, PRODIGY, and SOAR can be translated into APOC and briefly discuss how these translations could be used to compare architectures and possibly integrate features from these different architectures wit...

Training in ight simulators will be more eeective if the agents involved in the simulation behave realistically. Accomplishing this requires that the automated agents be under autonomous, intelligent control. We are using the Soar cognitive architecture to implement intelligent agents that behave as much like humans as possible. In order to approximate human behavior, the agents must integrate ...

BACKGROUND Many avian species soar and glide over land. Evidence from large birds (m(b)>0.9 kg) suggests that soaring-gliding is considerably cheaper in terms of energy than flapping flight, and costs about two to three times the basal metabolic rate (BMR). Yet, soaring-gliding is considered unfavorable for small birds because migration speed in small birds during soaring-gliding is believed to...