Using Artificial Team Members for Team Training in Virtual Environments

Diggelen, J. van; Muller, T.J.; Bosch, Karel Van den

doi:10.1007/978-3-642-15892-6_3

Cited by 6 publications

(6 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Research in this domain primarily focuses on the deployment of virtual agents and mixed-reality environments within HATs. Van Diggelen, et al [64] have formulated an approach that leverages a virtual learning environment, wherein IAs contribute to team training. Barange, et al [65] have investigated both task-oriented and pedagogical behaviors of agents in virtual environments, aiming to enable proactivity and improve engagement.…”

Section: Team Virtualitymentioning

confidence: 99%

“…Information sharing in HATs is significantly reduced compared to human-only teams [64]. For effective teamwork and to maintain common ground in teams, team members should actively share relevant pieces of information.…”

Section: Information Sharingmentioning

confidence: 99%

“…Phan, et al [67] went a step further by creating a test bed specifically designed for training HATs, aiming to improve human-agent interactions and help humans acclimate to working with IAs. Van Diggelen, et al [64] also contributed to this area by developing an IA designed to train human team members, with the primary objective of enhancing human participants' team skills. Johnson, et al [127] conducted experiments on entrainment-based coordination training (i.e., training for "a spontaneous coupling and synchronization of the timing and content of teammate communication") and trust calibration training in HATs, revealing improvements in task efficiency and trust building compared to the control group.…”

Section: H Team Interventionsmentioning

confidence: 99%

See 2 more Smart Citations

Human–Agent Team Dynamics: A Review and Future Research Opportunities

Iftikhar,

Chiu,

Khan

et al. 2024

IEEE Trans. Eng. Manage.

View full text Add to dashboard Cite

Humans teaming with intelligent autonomous agents are becoming indispensable in work environments.However, human-agent teams pose significant challenges as team dynamics are complex arising from the task and social aspects of human-agent interactions. To improve our understanding of human-agent team dynamics, we conducted a systematic literature review. Drawing on Mathieu et al.'s (2019) teamwork model developed for all-human teams, we map the landscape of research to human-agent team dynamics, including structural features, compositional features, mediating mechanisms, and the interplay of the above features and mechanisms. We reveal that the development of human-agent team dynamics is still nascent, with a particular focus on information sharing, trust development, agents' human likeness behaviors, shared cognitions, situation awareness, and function allocation. Gaps remain in many areas of team dynamics, such as team processes, adaptability, shared leadership, and team diversity. We offer various interdisciplinary pathways to advance research on human-agent teams.

show abstract

Section: Team Virtualitymentioning

confidence: 99%

Section: Information Sharingmentioning

confidence: 99%

Section: H Team Interventionsmentioning

confidence: 99%

See 1 more Smart Citation

Human–Agent Team Dynamics: A Review and Future Research Opportunities

Iftikhar,

Chiu,

Khan

et al. 2024

IEEE Trans. Eng. Manage.

View full text Add to dashboard Cite

show abstract

“…Using the example of 'LeadSim', we demonstrate how single-player simulations can address important didactic and organizational concerns associated with existing formats of leadership education and, thus, provide a promising alternative or a supplement to them. Single-player simulations offer equal learning opportunities to all students, can be accessed at any time (e.g., as a self-learning tool), and result in significantly lower coordination and organizational costs than multiplayer formats (DIGGELEN et al, 2010).…”

Section: Wwwzfheatmentioning

confidence: 99%

Leadership simulations as a teaching and learning tool at universities: A single-player example

Hennicke,

Boettcher,

Gieselmann

et al. 2023

ZFHE

View full text Add to dashboard Cite

Computer-based simulations are important didactic tools that allow connections between theory and practice, making them particularly valuable in the field of leaderhip. However, the predominant multiplayer format hinders their widespread use in undergraduate and postgraduate business education. We present a single-player simulation in progress ‘LeadSim’ which focuses on team leadership rather than a general business context. ‘LeadSim’ aims to develop personal competence and provide feedback on the consequences of individual decisions. Moreover, its design makes it convenient to use. Here, we discuss the advantages and limitations of this format in the context of leadership education in universities.

show abstract

“…One potential solution to the challenges listed above involves incorporating artificial agents (AAs) as synthetic teammates into team training simulations (Nalepka, Gregory-Dunsmore, et al, 2021;O'Neill et al, 2020). Indeed, human-artificial-agent team training systems not only have the potential to both reduce the economic and logistical challenges of traditional team training, but also provide individuals with the opportunity to engage in more frequent and targeted training exercises (Van Diggelen et al, 2010). Accordingly, there is now a growing body of research directed towards investigating the degree to which human team members and human trainers could be replaced or enhanced by interactive artificial agents or AAs (Cappuccio et al, 2021;Huskens et al, 2013;Kostrubiec et al, 2015;Kümmel et al, 2014;Maity, 2019;Mohan et al, 2019;Tsiakas et al, 2017), more recently referred to as human-autonomy teaming (Demir et al, 2017(Demir et al, , 2020(Demir et al, , 2018McNeese et al, 2018).…”

Section: Introductionmentioning

confidence: 99%

A Comparison of Dynamical Perceptual-Motor Primitives and Deep Reinforcement Learning for Human-Artificial Agent Training Systems

Rigoli

Patil

Nalepka

et al. 2022

Journal of Cognitive Engineering and Decision Making

View full text Add to dashboard Cite

Effective team performance often requires that individuals engage in team training exercises. However, organizing team-training scenarios presents economic and logistical challenges and can be prone to trainer bias and fatigue. Accordingly, a growing body of research is investigating the effectiveness of employing artificial agents (AAs) as synthetic teammates in team training simulations, and, relatedly, how to best develop AAs capable of robust, human-like behavioral interaction. Motivated by these challenges, the current study examined whether task dynamical models of expert human herding behavior could be embedded in the control architecture of AAs to train novice actors to perform a complex multiagent herding task. Training outcomes were compared to human-expert trainers, novice baseline performance, and AAs developed using deep reinforcement learning (DRL). Participants’ subjective preferences for the AAs developed using DRL or dynamical models of human performance were also investigated. The results revealed that AAs controlled by dynamical models of human expert performance could train novice actors at levels equivalent to expert human trainers and were also preferred over AAs developed using DRL. The implications for the development of AAs for robust human-AA interaction and training are discussed, including the potential benefits of employing hybrid Dynamical-DRL techniques for AA development.

show abstract

Using Artificial Team Members for Team Training in Virtual Environments

Cited by 6 publications

References 9 publications

Human–Agent Team Dynamics: A Review and Future Research Opportunities

Human–Agent Team Dynamics: A Review and Future Research Opportunities

Leadership simulations as a teaching and learning tool at universities: A single-player example

A Comparison of Dynamical Perceptual-Motor Primitives and Deep Reinforcement Learning for Human-Artificial Agent Training Systems

Contact Info

Product

Resources

About