Computer-Generated Forces Team Behavior Within Air Combat Simulations: Coordinated Path Planning With Constraints
Fabian Reinisch, Michael Strohal, Peter Stütz · 2025
The modeling and simulation domain increasingly requires higher accuracy levels of the adversary computer-generated forces (CGF), especially for use in training simulations. To achieve this, it is substantial to not only replicate and simulate the physical properties of the entities to a sufficient degree, but also to provide them with situationally adaptive, tactically intelligent behavior. In order to implement adaptive team tactics, we must be capable of synchronizing the CGF. To achieve this, this paper introduces a coordinated CGF path planning approach with the goal of simultaneous arrival on target positions. We commence by formulating the path planning problem, including its various constraints and follow by proposing a solution consisting of three phases: First, we generate Dubins paths to obtain traversable trajectories for each entity. Following, we are equalizing the path lengths by varying curvature using a binary search algorithm. Finally, to incorporate additional constraints like avoiding obstacles as well as maintaining a mutual minimum separation distance, we leverage an optimizer using sequential quadratic programming (SQP). The presented methodology was verified in CGF simulations, demonstrating its capability to gather the CGF at defined targets. Future work will focus on integrating the results from this paper to model various CGF team tactics.