This paper focuses on challenges to improving the realism of socially intelligent agents and attempts to reflect the state of the art in human behavior modeling with particular attention to the impact of personality/cultural values and affect as well as biology/stress upon individual coping and group decision making. The first section offers an assessment of the state of the practice and of the need to integrate valid human performance moderator functions (PMFs) from traditionally separated subfields of the behavioral literature. The second section pursues this goal by postulating a unifying architecture and principles for integrating existing PMF theories and models. It also illustrates a PMF testbed called PMFserv created for implementating and studying how PMFs may contribute to such an architecture. To date it interconnects versions of PMFs on physiology and stress; personality, cultural and emotive processes (Cognitive Appraisal-OCC, value systems); perception (Gibsonian affordance); social processes (relations, identity, trust, nested intentionality); and cognition (affect- and stress-augmented decision theory, bounded rationality). The third section summarizes several usage case studies (asymmetric warfare, civil unrest, and political leaders) and concludes with lessons learned. Implementing and interoperating this broad collection of PMFs helps to open the agenda for research on syntheses that can help the field reach a greater level of maturity. The companion paper, Part II, presents a case study in using PMFserv for rapid scenario composability and realistic agent behavior.

Many producers and consumers of legacy training simulator and game environments are beginning to envision a new era where psycho-socio-physiologic models could be interoperated to enhance their environments' simulation of human agents. This paper explores whether we could embed our behavior modeling framework (described in the companion paper, Part 1) behind a legacy first person shooter 3D game environment to recreate portions of the Black Hawk Down scenario. Section 1 amplifies the interoperability needs and challenges confronting the field, presents the questions that are examined, and describes the test scenario. Sections 2 and 3 review the software and knowledge engineering methodology, respectively, needed to create the system and populate it with bots. Results (Section 4) and discussion (Section 5) reveal that we were able to generate plausible and adaptive recreations of Somalian crowds, militia, women acting as shields, suicide bombers, and more. Also, there are specific lessons learned about ways to advance the field so that such interoperabilities will become more affordable and widespread. Philadelphia, PA 19104-6315, USA. e-mail: barryg@seas.upenn.edu ABSTRACT Many producers and consumers of legacy training simulator and game environments are beginning to envision a new era where psych-socio-physiologic models could be interoperated to enhance their environments' simulation of human agents. This article explores whether we could embed our behavior modeling framework (described in Part I) behind a legacy first person shooter 3-D game environment to recreate portions of the Black Hawk Down scenario. Section One amplifies on the inter-operability needs and challenges confronting the field, presents the questions that are examined, and describes the test scenario. Sections 2 and 3 review the software and knowledge engineering methodology, respectively, needed to create the system and populate it with bots. Results (Section 4) and discussion (Section 5) reveal that we were able to generate plausible and adaptive recreations of Somalian crowds, militia, women acting as shields, suicide bombers, and more. Also, there are specific lessons learned about ways to advance the field so that such inter-operabilities will become more affordable and widespread.

Abstract

Arguments about whether a robot could ever be conscious have been conducted up to now in the factually impoverished arena of what is ‘possible in principle’. A team at MIT, of which I am a part, is now embarking on a longterm project to design and build a humanoid robot, Cog, whose cognitive talents will include speech, eye-coordinated manipulation of objects, and a host of self-protective, self-regulatory and self-exploring activities. The aim of the project is not to make a conscious robot, but to make a robot that can interact with human beings in a robust and versatile manner in real time, take care of itself, and tell its designers things about itself that would otherwise be extremely difficult if not impossible to determine by examination. Many of the details of Cog’s ‘neural’ organization will parallel what is known (or presumed known) about their counterparts in the human brain, but the intended realism of Cog as a model is relatively coarse-grained, varying opportunistically as a function of what we think we know, what we think we can build, and what we think doesn’t matter. Much of what we think will of course prove to be mistaken; that is one advantage of real experiments over thought experiments.

Today many workers spend too much of their time translating their co-workers' requests into structures that information systems can understand. This paper presents the novel interaction design and evaluation of VIO, an agent that helps workers translate request. VIO monitors requests and makes suggestions to speed up the translation. VIO allows users to quickly correct agent errors. These corrections are used to improve agent performance as it learns to automate work. Our evaluations demonstrate that this type of agent can significantly reduce task completion time, freeing workers from mundane tasks.