Adaptive CGFs Based on Grammatical Evolution

Abstract

Computer generated forces (CGFs) play blue or red units in military simulations for personnel training and weapon systems evaluation. Traditionally, CGFs are controlled through rule-based scripts, despite the doctrine-driven behavior of CGFs being rigid and predictable. Furthermore, CGFs are often tricked by trainees or fail to adapt to new situations (e.g., changes in battle field or update in weapon systems), and, in most cases, the subject matter experts (SMEs) review and redesign a large amount of CGF scripts for new scenarios or training tasks, which is both challenging and time-consuming. In an effort to overcome these limitations and move toward more true-to-life scenarios, a study using grammatical evolution (GE) to generate adaptive CGFs for air combat simulations has been conducted. Expert knowledge is encoded with modular behavior trees (BTs) for compatibility with the operators in genetic algorithm (GA). GE maps CGFs, represented with BTs to binary strings, and uses GA to evolve CGFs with performance feedback from the simulation. Beyond-visual-range air combat experiments between adaptive CGFs and nonadaptive baseline CGFs have been conducted to observe and study this evolutionary process. The experimental results show that the GE is an efficient framework to generate CGFs in BTs formalism and evolve CGFs via GA.

Handling Concurrency in Behavior Trees

“…Example 4. The BT in Figure 11(a) shows a BT for a missile evasion tactic, taken from the literature [59]. The BT has three sub-BTs that run in parallel: "Turn on Countermeasure Maneuvers", "Countermeasure Maneuvers once", "Dispense Chaff and Flares Every 10 Seconds", "Turn Clockwise if an Enemy on a Range".…”

“…The authors of [59] did not address the concurrency issue above. However, taking advantage of the composability of BTs, we did the modification easily.…”

Engagement Decision Support for Beyond Visual Range Air Combat

“…Many of them use game theory to model air combat [7], [8], [9], [10]. Other approaches found in the literature are as follows: Bayesian Networks [11], [12], [13], [14], fuzzy logic [15], [16], agent-based modeling [17], influence diagrams [18], reinforcement learning [19], [20], [21], [22], artificial neural networks [23], [24], evolutionary algorithms [25], [26], minimax method [27], and behavior trees [28].…”