Schema-based design and the AKIRA Schema Library

This is a gentle introduction to schema-based design.

Abstract. We present a theoretical analysis of schema-based design (SBD), a methodology for designing autonomous agents architectures. We also provide an overview of the AKIRA Schema Language (AKSL), which permits to design schema-based architectures for anticipatory behavior experiments and simulations. Several simulations using AKSL are reviewed, highlighting the relations between pragmatic and epistemic aspects of behavior. Anticipation is crucial in realizing several functionalities with AKSL, such as selecting actions, orienting attention, categorizing and grounding declarative knowledge.

Pezzulo, G. & Calvi. Schema-based design and the AKIRA Schema Language: An Overview. In G.Butz, M.; Sigaud, O.; Pezzulo, G. & Baldassarre, G. (ed.) Anticipatory Behavior in Adaptive Learning Systems: Advances in Anticipatory Processing, Springer LNAI 4520, 2007

Toward a Perceptual Symbol System

This is my first attempt to simulate some aspects of Barsalou's perceptual symbol system theory.

Abstract: We explore the possibility for a situated system to evolve what Barsalou calls a perceptual symbol system (PSS). We describe the peculiarities of perceptual symbols and point out the main capabilities of organized, multimodal frames of perceptual symbols called simulators. We present a case study in which perceptual symbols and simulators are evolved and exploited for categorization, prediction and abstraction.

Pezzulo, G. & Calvi, G. Toward a Perceptual Symbol System Proceedings of the Sixth International Conference on Epigenetic Robotics: Modeling Cognitive Development in Robotic Systems, Lund University Cognitive Science Studies 118, 2006

DiPRA: Distributed Practical Reasoning Architecture

This is my first simulative work describing how to extend a sensorimotor system to include elements of high-level cognition.

Abstract: DiPRA (Distributed Practical Reasoning Architecture) implements the main principles of practical reasoning via the distributed action selection paradigm. We introduce and motivate the underlying theoretical and computational peculiarities of DiPRA and we describe its components, also providing as a case study a guards-and-thieves task.

Pezzulo, G.; Calvi, G. & Castelfranchi, C. DiPRA: Distributed Practical Reasoning Architecture Proceedings of the Twentieth International Joint Conference on Artificial Intelligence, 2007, 1458-1464

Dynamic Computation and Context Effects in the Hybrid Architecture AKIRA

A discussion of the principles of the framework AKIRA, also comparing it with related models such as Hofstadter's Copycat

Abstract: We present AKIRA, an agent-based hybrid architecture designed for cognitive modeling. We describe some of the underlying ideas motivating its development, such as the possibility of exploiting distributed representations and performing parallel, dynamic and context aware computation. We illustrate its main components and capabilities and compare it with some related cognitive architectures, such as DUAL and Copycat. We present also a sample simulation in the visual search domain, exploiting AKIRA’s peculiarities for cognitive modeling.

Pezzulo, G. & Calvi, G. Dynamic Computation and Context Effects in the Hybrid Architecture AKIRA Modeling and Using Context: 5th International and Interdisciplinary Conference CONTEXT 2005, Springer LNAI 3554., 2005, 368-381

A Schema Based Model of the Praying Mantis

My first simulative work about the integration of a sensorimotor system with a simple motivational system, inspired by ethology

Abstract. We present a schema-based agent architecture which is inspired by an ethological model of the praying mantis. It includes an inner state, perceptual and motor schemas, several routines, a fovea and a motor. We describe the design and implementation of the architecture and we use it for comparing two models: the former uses reactive, stimulus-response schemas; the latter involves also forward models, which are used by the schemas for generating predictions. Our results show an advantage in using anticipatory components inside the schemas.

Pezzulo, G. & Calvi, G. A Schema Based Model of the Praying Mantis LNAI, From animals to animats 9: Proceedings of the Ninth International Conference on Simulation of Adaptive Behaviour, Springer Verlag, 2006, LNAI 4095, 211-223

The framework AKIRA

Since 2003 Gianguglielmo Calvi and I have been developing a computational system called AKIRA It is an open-source project, developed under sourceforge sourceforge and it permits to implement modular systems. We have used AKIRA for designing and implementing several cognitive systems, that have all the same underlying design philosophy -behavior and cognition arise from "the competition and cooperation among multiple concurrent processes", as we think that it is the case in the brain, much in the spirit of Marvin Minsky's Society of Mind.