Practical Modelling of Dynamic Decision Making [book] (2019)
Abstract: This book presents TDF (Tactics Development Framework), a practical methodology for eliciting and engineering models of expert decision-making in dynamic domains. The authors apply the BDI (Beliefs, Desires, Intentions) paradigm to the elicitation and modelling of dynamic decision making expertise, including team behaviour, and map it to a diagrammatic representation that is intuitive to domain experts.
Citation: Evertsz, Rick, John Thangarajah, and Thanh Ly. Practical Modelling of Dynamic Decision Making. Springer International Publishing, 2019. [Download]
A Framework for Engineering Human/Agent Teaming Systems (2020)
Abstract: The increasing capabilities of autonomous systems offer the potential for more effective teaming with humans. Effective human/agent teaming is facilitated by a mutual understanding of the team objective and how that objective is decomposed into team roles. This paper presents a framework for engineering human/agent teams that delineates the key human/agent teaming components, using TDF-T diagrams to \emph{design} the agents/teams and then \emph{present} contextualised team cognition to the human team members at runtime. Our hypothesis is that this facilitates effective human/agent teaming by enhancing the human's understanding of their role in the team and their coordination requirements. To evaluate this hypothesis we conducted a study with human participants using our user interface for the StarCraft strategy game, which presents pertinent, instantiated TDF-T diagrams to the human at runtime. The performance of human participants in the study indicates that their ability to work in concert with the non-player characters in the game is significantly enhanced by the timely presentation of a diagrammatic representation of team cognition.
Citation: Evertsz, Rick, and John Thangarajah. "A Framework for Engineering Human/Agent Teaming Systems." In Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34, no. 03, pp. 2477-2484. 2020. [PDF]
The Conceptual Modelling of Dynamic Teams for Autonomous Systems (2017)
Abstract: The concept of a 'team' is key in multi-agent decision-making applications such as for combat operations and disaster management. Although there are a number of team-oriented agent programming approaches, conceptual modelling of teams is not fully addressed. In this paper we present TDF-T, an extension of the TDF agent design methodology that addresses the requirements of team oriented modelling; in particular, team hierarchies, dynamic team formation, and team coordination. These concepts encapsulate team tactical behaviour which is essential to our user community who need to build and deploy complex team-based simulation applications. We show positive results in a user study that evaluates comprehension and maintainability of TDF-T models.
Citation: Evertsz, Rick, John Thangarajah, and Michael Papasimeon. "The Conceptual Modelling of Dynamic Teams for Autonomous Systems." In International Conference on Conceptual Modeling, pp. 311-324. Springer, Cham, 2017. [Download]
A Framework for Modelling Tactical Decision-Making in Autonomous Systems (2015)
Abstract: There is an increasing need for autonomous systems that exhibit effective decision-making in unpredictable environments. However, the design of autonomous decision-making systems presents considerable challenges, particularly when they have to achieve their goals within a dynamic context. Tactics designed to handle unexpected environmental change, or attack by an adversary, must balance the need for reactivity with that of remaining focused on the system's overall goal. The lack of a design methodology and supporting tools for representing tactics makes them difficult to understand, maintain and reuse. This is a significant problem in the design of tactical decision-making systems. We describe a methodology and accompanying tool, TDF (Tactics Development Framework), based on the BDI (Beliefs, Desires, Intentions) paradigm. TDF supports structural modelling of missions, goals, scenarios, input/output, messaging and procedures, and generates skeleton code that reflects the overall design. TDF has been evaluated through comparison with UML, indicating that it provides significant benefits to those building autonomous, tactical decision-making systems.
Citation: Evertsz, Rick, John Thangarajah, Nitin Yadav, and Thanh Ly. "A Framework for Modelling Tactical Decision-Making in Autonomous Systems." Journal of Systems and Software 110 (2015): 222-238. [PDF]
Agent Oriented Modelling of Tactical Decision Making (2015)
Abstract: A key requirement in military simulation is to have executable models of tactical decision-making. Such models are used to simulate the behaviour of human entities such as submarine commanders, fighter pilots and infantry, with a view to producing realistic predictions about tactical outcomes. Tactics specify the means of achieving mission objectives, and should capture both reactive and deliberative behaviour. The lack of a methodology and supporting tools for designing computer-based models of tactics makes them difficult to create, maintain and reuse, and this is now a significant problem in military simulation domains. To address this, we have developed TDF (Tactics Development Framework), a tactics modelling methodology and tool based on the BDI (Beliefs, Desires, Intentions) paradigm, that supports agent-oriented structural modelling of tactics and related artefacts including missions, storylines, goals and plans. The methodology was initially assessed by analysts in the undersea warfare domain, and was subsequently evaluated using a simple scenario in the autonomous unmanned aerial vehicles domain. The latter evaluation involved a comparison with UML designs, indicating that our methodology provides significant benefits to those building and maintaining models of tactical decision-making.
Citation: Evertsz, Rick, John Thangarajah, Nitin Yadav, and Thanh Ly. Evertsz, Rick, John Thangarajah, Nitin Yadav, and Thanh Chi Ly. "Agent Oriented Modelling of Tactical Decision Making." In AAMAS, pp. 1051-1060. 2015. [PDF]
Using Agent-Based Tactics Models to Control Virtual Actors in VBS3 (2015)
Abstract: The computer-based simulation of military tactics has largely involved the use of platform-dependent scripting resulting in behaviour that is limited, and difficult to debug and reuse. The Tactics Development Framework (TDF) addresses these shortcomings by providing design-level support for tactics modelling. Its integration with VBS3 is reported here.
Citation: Evertsz, Rick, John Thangarajah, and Nik Ambukovski. "Using Agent-Based Tactics Models to Control Virtual Actors in VBS3 (Demonstration)" In Proceedings of the 2015 International Conference on Autonomous Agents and Multiagent Systems, pp. 1929-1930. 2015. [PDF]
Tactics Development Framework (2014)
Abstract: The Tactics Development Framework (TDF) is a tactics modelling application that extends the Prometheus Design Tool with tactics design patterns, plan diagrams, a mission concept, and richer goal hierarchies.
Citation: Evertsz, Rick, John Thangarajah, Nitin Yadav, and Thanh Li. "TactiCs Development Framework. (Demonstration)" In Proceedings of the 2014 International Conference on Autonomous Agents and Multi-Agent Systems, pp. 1639-1640. 2014. [PDF]