Abstract : Computer Generated Forces (CGFs) are a key component in constructive simulations and are being increasingly used to control multiple entities in Synthetic Environments (SEs). Being a cost-effective way to providing extra players in SEs, they are becoming a possible alternative in various activities, such as Concept, Development and Experimentation (CD&E), analysis, training, tactic development, and mission rehearsal. The predictable nature of many current CGFs behaviour is one of their biggest problems, making it easy for the trainee to distinguish between human-controlled and computer-controlled entities in the simulation environment. This can result in negative or ineffective training as the trainee quickly learns to predict the behaviour of the CGF entity and easily defeats it in a way that would not happen with a human opponent. This results in a requirement for humans to control synthetic entities, thus limiting simulation exercises by the availability of operators. If instead the Artificial Intelligence (AI) of these entities could be improved, the number of operators required will, thus, be reduced. The first step in such an effort is evaluating the AI capabilities commonly available in CGFs. Such an analysis was performed at the Defence Research & Development Canada (DRDC), revealing the common strengths and weaknesses of available CGFs, and suggesting which might be most useful as a platform for further AI research. This document presents the methods and results of this analysis.
The Department of Defense (DoD) strives to improve Live, Virtual, and Constructive Integrated Architectures (LVCIA) with the objective to assemble models and simulations (M&S) that create representations of a credible operating environment. Changes in the operating environment and the needs of the warfighter require a continued focus on developing corporate and cross-cutting business practices which improve visibility; accessibility; commonality; reuse and interoperability of M&S tools; and data and services. A robust M&S capability enables the Department to meet operational and support objectives across the diverse activities of the services, combatant commands, and agencies more effectively. The ability to determine the success of the strategic vision for DoD. M&S depends on the ability to identify those measures that capture the attributes that empower DoD with M&S capabilities which effectively and efficiently support the full spectrum of the Department’s activities and operations. This paper examines the current gaps in an M&S LVCIA and what is required to enable an effective LVCIA. It does so by examining the interaction between people, processes and technologies in the DoD M&S community. The needs and objectives of the LVCIA are readily available and there are many successes using LVCIA in training and testing. It has not been as successful in acquisition, analysis, experimentation and other communities. By examining architectural software patterns, software paradigms and ongoing interoperability standards, this paper identifies those measures that provide a better understanding of the M&S enablers. These measures of effectiveness will guide the M&S communities to satisfy the current needs of the LVCIA community.
