Robert E. Wray

Synthetic adversaries for urban combat training

This paper describes requirements for synthetic adversaries for urban combat training and MOUTBots, a prototype application. The MOUTBots use a commercial computer game to define, implement and test basic behavior representation requirements and the Soar architecture as the engine for knowledge representation and execution. We describe how these components aided the development of the prototype and present an initial evaluation against competence, taskability, fidelity, variability, transparency, and efficiency requirements.

Ontologies for corporate web applications

In this article, we discuss some issues that arise when ontologies are used to support corporate application domains such as electronic commerce (e-commerce) and some technical problems in deploying ontologies for real-world use. In particular, we focus on issues of ontology integration and the related problem of semantic mapping, that is, the mapping of ontologies and taxonomies to reference ontologies to preserve semantics. Along the way, we discuss what typically constitutes an ontology architecture. We situate the discussion in the domain of business-to-business (B2B) e-commerce. By its very nature, B2B e-commerce must try to interlink buyers and sellers from multiple companies with disparate product-description terminologies and meanings, thus serving as a paradigmatic case for the use of ontologies to support corporate applications.

Comparative analysis of frameworks for knowledge-intensive intelligent agents

A recurring requirement for human-level artificial intelligence is the incorporation of vast amounts of knowledge into a software agent that can use the knowledge in an efficient and organized fashion. This article discusses representations and processes for agents and behavior models that integrate large, diverse knowledge stores, are long-lived, and exhibit high degrees of competence and flexibility while interacting with complex environments. There are many different approaches to building such agents, and understanding the important commonalities and differences between approaches is often difficult. We introduce a new approach to comparing frameworks based on the notions of commitment, reconsideration, and a categorization of representations and processes. We review four agent frameworks, concentrating on the major representations and processes each directly supports. By organizing the approaches according to a common nomenclature, the analysis highlights points of similarity and difference and suggests directions for integrating and unifying disparate approaches and for incorporating research results from one framework into alternatives

Cognition and Multi-Agent Interaction: Considering Soar As An Agent Architecture

INTRODUCTION The Soar architecture was created to explore the requirements for general intelligence and to demonstrate general intelligent behavior (Laird, Newell, & Rosenbloom, 1987; Laird & Rosenbloom, 1995; Newell, 1990). As a platform for developing intelligent systems, Soar has been used across a wide spectrum of domains and applications, including expert systems (Rosenbloom, Laird, McDermott, Newell, & Orciuch, 1985;Washington & Rosenbloom, 1993), intelligent control (Laird, Yager, Hucka, & Tuck, 1991; Pearson, Huffman,Willis, Laird,& Jones, 1993), natural language (Lehman, Dyke, & Rubinoff, 1995; Lehman, Lewis, & Newell, 1998), and executable models of human behavior for simulation systems (Jones et al., 1999;Wray, Laird, Nuxoll, Stokes, & Kerfoot, 2004). Soar is also used to explore the integration of learning and performance, including concept learning in conjunction with performance (Chong & Wray, to appear; Miller & Laird, 1996), learning by instruction (Huffman & Laird, 1995), learning to correct errors in performance knowledge (Pearson & Laird, 1998), and episodic learning (Altmann & John, 1999; Nuxoll & Laird, 2004). This chapter will introduce Soar as a platform for the development of intelligent systems (see also Chapters 2 and 4). Soar can be viewed as a theory of general intelligence, as a theory of human cognition, as an agent architecture, and as a programming language. This chapter reviews the theory underlying Soar but considers Soar primarily as an agent architecture. The architecture point-of-view is useful because Soar integrates a number of different algorithms common in artificial intelligence, demonstrating how they can be used together to achieve general intelligent behaviour.

Adaptive Perceptual Training in a Virtual Environment

The United States military’s strategic position is evolving, and as a result, the Services are emphasizing the importance of sociocultural pattern recognition, sensemaking in ambiguous urban contexts, and understanding of patterns of life. In fact, military personnel at increasingly lower echelons are expected to possess these nuanced psychosocial perception and decision-making skills. To facilitate training of these complex competencies, the authors are developing a Virtual Observation Platform, an immersive virtual environment designed to adaptively train US Marine Corps personnel in sustained observation, sociocultural pattern recognition, anomaly detection, and other perceptual–cognitive skills. This paper briefly describes the purpose of the system and then covers its adaptive instructional tailoring in detail. The Platform’s adaptive features include information quality/quantity manipulation and instructional scaffolding in the form of communications from a virtual squad (i.e., peers) that are intrinsic to the narrative of the scenario.

An architectural approach to ensuring consistency in hierarchical execution

Hierarchical task decomposition is a method used in many agent systems to organize agent knowledge. This work shows how the combination of a hierarchy and persistent assertions of knowledge can lead to difficulty in maintaining logical consistency in asserted knowledge. We explore the problematic consequences of persistent assumptions in the reasoning process and introduce novel potential solutions. Having implemented one of the possible solutions, Dynamic Hierarchical Justification, its effectiveness is demonstrated with an empirical analysis.

Bracketing Human Performance to Support Automation for Workload Reduction: A Case Study

Semi-automated Forces (SAFs) are commonly used in training simulation. SAFs often require human intervention to ensure that appropriate, individual training opportunities are presented to trainees. We cast this situation as a supervisory control challenge and are developing automation designed to support human operators, reduce workload, and improve training outcomes. This paper summarizes a combined analytic and empirical verification study that identified specific situations in the overall space of possible scenarios where automation may be particularly helpful. By bracketing “high performance” and “low performance” conditions, this method illuminates salient points in the space of operational performance for future human-in-the-loop studies.

Ontologies for Semantically Interoperable Electronic Commerce

In this paper we discuss the use of ontologies to support semantically interop- erable B2B electronic cotnmerce. First, we describe the nature of B2B and the kinds of applications used. Second, we present arguments towards why B2B needs ontologies and the nature of the problems faced. Finally, we discuss the interaction of ontologists and domain experts in the building of ontologies for business, and some of the tools available for developing ontologies.

Instrumenting a Perceptual Training Environment to Support Dynamic Tailoring

Simulation-based practice environments would be more valuable for learning if they supported adaptive, targeted responses to students as they proceed thru the experiences afforded by the environment. However, many adaptation strategies require a richer interpretation of the student’s actions and attitudes than is available thru the typical simulation interface. Further, creating extended interfaces for a single application solely to support adaptation is often cost-prohibitive. In response, we are developing “learner instrumentation middleware” that seeks to provide a generalized representation of learner state via reusable algorithms, design patterns, and software.

Design principles for heavy intelligent agents

A variety of frameworks exist for designing intelligent agents and behavior models. Although they have different emphases, these frameworks each provide coherent, high-level views of intelligent agency. However, more pragmatically, much of the complexity of building intelligent agents is in the low-level details, especially when building agents that exhibit high degrees of competence while interacting in complex environments. We call such agents “heavy”, to distinguish them from “light”, single-task agents (e.g., service brokers) that are often fielded in multi-agent systems. Good examples of fielded heavy agents include a real-time fault diagnosis system on the Space Shuttle [1] and a real-time model of combat pilots [4].