Supporting teamwork in hybrid multi-team systems

Schraagen, Jan Maarten; Barnhoorn, Jonathan; Schendel, Jef van; Vught, Willeke van

doi:10.1080/1463922x.2021.1936277

Cited by 4 publications

(4 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the workshop with human factors experts, a human factors evaluation method that was developed in-house was used. This evaluation followed an 'outside-in' approach: the demonstrator was compared with a broad set of elements that compose a hybrid multi-team system (Schraagen, Barnhoorn, van Schendel, van Vught, 2021) with a focus on scientific value, taking the design patterns in account too.…”

Section: Discussionmentioning

confidence: 99%

IMMENS: Integrated Multi-Manager Environment for Naval Ships

Barnhoorn¹,

Rakhorst-Oudendijk²,

Veltman³

et al. 2022

Preprint

View full text Add to dashboard Cite

The Royal Netherlands Navy is moving towards more autonomous ships to cope with the increasingly complex naval operations while sailing with a reduced manning. The strong expansion of automation and autonomous systems on board requires new solutions for optimal collaboration between the crew and the extensive set of ship systems. We are developing a concept for an Integrated Multi-Manager Environment for Naval Ships: IMMENS. IMMENS aims to be an intelligent ship system that supports the crews of future ship classes, while enabling these crews to exercise and maintain meaningful human control. The ship's subsystems are integrated in a multi-agent system that formulates and proposes plans to the command team based on an internal representation of the ship's goals and the current situation. These plans consist of actions that are to be executed in order to achieve the mission goals. The system's computational design, combined with specific human-machine teaming functionality facilitates the crew and IMMENS to work as a joint cognitive system. This paper shortly introduces IMMENS but reports mainly on the development and application of humanmachine teaming concepts that support cooperation between the crew and IMMENS. The first concept offers interaction based on a human-machine language using Goals, Tasks, Constraints and Resources as shared knowledge elements. Since both human and machine understand these elements, human comprehension of the machine's inner workings is supported. The second concept provides the explication of relationships between goals, tasks, constraints, resources and/or external world as a means of intuitively explaining the machine's reasoning by providing transparency regarding, for instance, to which goals certain tasks contribute. Thirdly, we applied and extended on the concept of play-based delegation. A play is a plan-template that allows a user to quickly delegate a complex task to the systems, without the need to drill down, while leaving room for system intelligence to fill in the details. These concepts have been applied in an integrated interactive demonstrator of IMMENS. An evaluation with subject matter experts from the Royal Netherlands Navy and senior human factors researchers was conducted based on a scenario of a frigate escorting a high-value asset. During the design, implementation and evaluation of the demonstrator, we learned that the first concept provided a workable shared knowledge model and indeed fitted with the IMMENS architecture on the one hand, and was intuitive to the users on the other hand. Explicating relationships provided the users with relevant insights, allowing them to understand, for instance, by means of which tasks and resources IMMENS expects to achieve the mission goals. Play-based delegation was found this a clear and valuable concept. Many opportunities for future research were identified, the most important of which concerns the feasibility of constructing a valid, complete and generic goal representation for IMMENS that takes into account the comp...

show abstract

Section: Discussionmentioning

confidence: 99%

IMMENS: Integrated Multi-Manager Environment for Naval Ships

Barnhoorn¹,

Rakhorst-Oudendijk²,

Veltman³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Thus, HATs also exist in a larger context and work in dependence with other teams. These human-AI multi teams are called hybrid multi-team systems (HMTS) and refer to “multiple teams consisting of n-number of humans and n-number of semi-autonomous agents [i.e., AI] having interdependence relationships with each other” (Schraagen et al, 2022 , p. 202). They consist of sub-teams, with each individual and team striving to achieve hierarchically structured goals.…”

Section: Human-ai Multi-team Systemsmentioning

confidence: 99%

“…Marks et al, 2001 ). Such planning activities are a major challenge, especially in multi-team systems, since between-team coordination is more difficult to achieve than within-team coordination, but it is also more important for effective multi-team system teamwork (Schraagen et al, 2022 ). Thus, the responsiveness of the agents will be important for a team-centered AI (see upper left corner in the model), meaning that the agents are able to align their goals and interaction strategies to the shifting goals and intentions of others as well as the environment (Lyons et al, 2022 ).…”

Section: Human-ai Multi-team Systemsmentioning

confidence: 99%

“…Thus, it is important that the artificial agents have agency , i.e., they can have control over their actions and the decision authority to execute these actions (Lyons et al, 2022 ). For an effective collaboration of humans and agents, the HMTS needs a flexible decision-making authority , that is, authority dynamically shifting among the humans and agents in response to complex and changing situations (Calhoun, 2022 ; Schraagen et al, 2022 ). Requirements in this phase include task prioritization and distribution as well as re-prioritization and distribution of tasks according to changes in the situation or plan (Waller et al, 2004 ).…”

Section: Human-ai Multi-team Systemsmentioning

confidence: 99%

See 1 more Smart Citation

Human-AI teams—Challenges for a team-centered AI at work

Hagemann,

Rieth,

Suresh

et al. 2023

Front. Artif. Intell.

View full text Add to dashboard Cite

As part of the Special Issue topic “Human-Centered AI at Work: Common Ground in Theories and Methods,” we present a perspective article that looks at human-AI teamwork from a team-centered AI perspective, i. e., we highlight important design aspects that the technology needs to fulfill in order to be accepted by humans and to be fully utilized in the role of a team member in teamwork. Drawing from the model of an idealized teamwork process, we discuss the teamwork requirements for successful human-AI teaming in interdependent and complex work domains, including e.g., responsiveness, situation awareness, and flexible decision-making. We emphasize the need for team-centered AI that aligns goals, communication, and decision making with humans, and outline the requirements for such team-centered AI from a technical perspective, such as cognitive competence, reinforcement learning, and semantic communication. In doing so, we highlight the challenges and open questions associated with its implementation that need to be solved in order to enable effective human-AI teaming.

show abstract