Air Combat Tactics Implementation in the Smart Whole AiR Mission Model (SWARMM)

Operational Research computer models must model both the relevant physical systems and the behaviour of their operators. The simulation requirements for these two components and the techniques used for developing, designing, validating and verifying them are quite different. In air combat these differences are heightened by the complexity of the physical systems and the wide variation in operator behaviour. Overall tactical behaviour is based on standard operating procedures and threat intelligence, but must cope with deviations from the original brief. Overlaying the baseline tactical behaviour are variations in employment of the combat systems, subject to factors such as crew experience, operational currency, workload, fatigue and anxiety. Development, modification and validation of tactics is extremely difficult in programs written in traditional scientific languages such as Fortran. Modelling human decision making is more complex and difficult than modelling the physics of combat. SWARMM splits the physics of combat and pilot reasoning into two separate entities which are modelled, validated, and implemented in completely different ways. This paper describes the use of an agent-oriented approach to tactical reasoning using the distributed Multi-Agent Reasoning System (dMARS). dMARS is combined with physical system models into the Smart Whole AiR Mission Model (SWARMM); AAII and DSTO-AMRL are the primary participants in this project in the CRC for Intelligent Decision Systems. The advantages in using dMARS to model tactics are described and the paper outlines the way in which the design of the pilot reasoning model was driven by operational knowledge gained from close association with RAAF pilots. SWARMM’s tactical design is described from the basis of the operational requirements which include individual and team behaviour, prioritisation of responses to conflicting demands, the concept of underlying mission goals, and a return to appropriate goal-directed behaviour following short-term reactive responses. 1 This research was supported in part by the Cooperative Research Centre for Intelligent Decision Systems under the Australian Government's Cooperative Research Centres Program. 2 dMARS is proprietary software belonging to the Australian Artificial Intelligence Institute (AAII)