Developing INOTS to support interpersonal skills practice

Campbell, Julia; Core, Mark G.; Artstein, Ron; Armstrong, Lindsay; Hartholt, Arno; Wilson, Cyrus A.; Georgila, Kallirroi; Morbini, Fabrizio; Haynes, Edward; Gomboc, Dave; Birch, Mike; Bobrow, Jonathan; Lane, H. Chad; Gerten, Jillian; Leuski, Anton; Traum, David; Trimmer, Matthew; DiNinni, Rich; Bosack, Matthew; Jones, Timothy; Clark, Richard E.; Yates, Kenneth A.

doi:10.1109/aero.2011.5747535

Cited by 17 publications

(10 citation statements)

References 14 publications

(11 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The first one replicated the mind of a deployed but cognitively rather simple agent that provided training for junior Naval officers in interpersonal communication skills (Campbell et al 2011). The control structure of this agent is a discourse model based on a directed acyclic network of states and utterances, where an utterance classifier determined what was said, and therefore which response to make at each point.…”

Section: Example Sigma Virtual Humansmentioning

confidence: 99%

Building high fidelity human behavior models in the Sigma cognitive architecture

Ustun¹,

Rosenbloom²,

Kim³

et al. 2015

2015 Winter Simulation Conference (WSC)

View full text Add to dashboard Cite

Many agent simulations involve computational models of intelligent human behavior. In a variety of cases, these behavior models should be high-fidelity to provide the required realism and credibility. Cognitive architectures may assist the generation of such high-fidelity models as they specify the fixed structure underlying an intelligent cognitive system that does not change over time and across domains. Existing symbolic architectures, such as Soar and ACT-R, have been used in this way, but here the focus is on a new architecture, Sigma (!), that leverages probabilistic graphical models towards a uniform grand unification of not only the traditional cognitive capabilities but also key non-cognitive aspects, and which thus yields unique opportunities for construction of new kinds of non-modular high-fidelity behavior models. Here, we briefly introduce Sigma along with two disparate proof-of-concept virtual humans -one conversational and the other a pair of ambulatory agents -that demonstrate its diverse capabilities. INTRODUCTIONSigma (Rosenbloom 2013) is being built as a computational model of general intelligence with the longterm goal to understand and replicate the architecture of the mind; i.e., the fixed structure underlying intelligent behavior in both natural and artificial systems. This ambitious goal strives for high-fidelity control of virtual humans (VHs) that behave as closely as possible to humans, primarily by developing and integrating not only crucial cognitive capabilities but also key non-cognitive capabilities, such as perception, motor control, and affect. In pursuing this goal, Sigma brings together ideas from over three decades of independent research in traditional symbolic cognitive architectures and probabilistic graphical models. Most of the work to date on Sigma has individually explored particular capabilities for learning, memory and knowledge, decision making and problem solving, perception and imagery, speech, Theory of Mind, and emotions. These individual capabilities are important in building human-like intelligence but getting them to work together is particularly challenging. Sigma's non-modular, hybrid (discrete + continuous) mixed (symbolic + probabilistic) character supports attempting a deep integration across cognitive and non-cognitive capabilities, straddling the traditional boundary between symbolic cognitive processing and numeric sub-cognitive processing. This short paper very briefly introduces Sigma and then provides two examples of VHs that utilize and integrate quite different sets of capabilities. 3124 978-1-4673-9743-8/15/$31.00 ©2015 IEEE

show abstract

Section: Example Sigma Virtual Humansmentioning

confidence: 99%

Building high fidelity human behavior models in the Sigma cognitive architecture

Ustun¹,

Rosenbloom²,

Kim³

et al. 2015

2015 Winter Simulation Conference (WSC)

View full text Add to dashboard Cite

show abstract

“…Steve [20] is an early example of a demonstration based pedagogical agent to train people to operate ship engines. INOTS [7] teaches communication and leadership skills to naval officers. The agent is questioned about a case by officers during training, and their performance is evaluated by rest of the class watching this interaction.…”

Section: Related Work On Pedagogical Agentsmentioning

confidence: 99%

Pedagogical Agents to Support Embodied, Discovery-Based Learning

Abdullah

Adil

Rosenbaum

et al. 2017

Lecture Notes in Computer Science

View full text Add to dashboard Cite

This paper presents a pedagogical agent designed to support students in an embodied, discovery-based learning environment. Discovery-based learning guides students through a set of activities designed to foster particular insights. In this case, the animated agent explains how to use the Mathematical Imagery Trainer for Proportionality, provides performance feedback, leads students to have different experiences and provides remedial instruction when required. It is a challenging task for agent technology as the amount of concrete feedback from the learner is very limited, here restricted to the location of two markers on the screen. A Dynamic Decision Network is used to automatically determine agent behavior, based on a deep understanding of the tutorial protocol. A pilot evaluation showed that all participants developed movement schemes supporting proto-proportional reasoning. They were able to provide verbal proto-proportional expressions for one of the taught strategies, but not the other.

show abstract

“…The counselee's animated behaviors are designed to match the verbal utterances and communicate a nonverbal message warranted by the instructional design. 12 With the design of the system focusing on both the verbal and nonverbal messages, ELITE-Lite not only trains counselors on what to say but it also places emphasis on the importance of paying visual attention to the nonverbal cues of a counselee during a counseling session.…”

Section: Introductionmentioning

confidence: 99%

Behaving socially with a virtual human role-player in a simulated counseling session

Hart

Proctor²

2019

Journal of Defense Modeling & Simulation

View full text Add to dashboard Cite

Visual attention is an essential social element in face-to-face conversations between people. The Army is now using virtual environments with virtual human role-players to provide for the development and practice of leader counseling skills. While literature indicates that virtual humans positively impact learning outcomes, this research contributes to the understanding of how people interact with virtual humans. Specifically, the research investigates a person’s social behavior toward a virtual human in a simulated counseling session. Utilizing a computer-based training environment, this research tracked visual attention toward and acceptance of a virtual human role-player by 120 military counselors. Behavior moderators included attentional influences on the counselor from the level of expression and full-body or close-up views of the virtual human. Results indicate trainees do practice appropriate social attention when the virtual human is speaking. Results also indicate counselors attended to an active more than a static full-body view indicating there is value in nonverbal communication channels. Switching from a full-body to a close-up view did not result in significant changes of the counselor’s visual attention. Further, the research indicates switching views may undermine the perception of a natural interaction. Counselors considered the experience useful. The research suggests study and design considerations to enhance future social skills training environments.

show abstract

Developing INOTS to support interpersonal skills practice

Cited by 17 publications

References 14 publications

Building high fidelity human behavior models in the Sigma cognitive architecture

Building high fidelity human behavior models in the Sigma cognitive architecture

Pedagogical Agents to Support Embodied, Discovery-Based Learning

Behaving socially with a virtual human role-player in a simulated counseling session

Contact Info

Product

Resources

About