Sensitivity-Augmented Iterative Best-Response MPC in a Three Player Orbital Differential Game

This paper presents a framework for autonomous planning and control of an attacker in the orbital target guarding game, where an attacker seeks to capture a target while evading interception by a Defender. The challenge lies in computing strategies in a non-cooperative orbital environment, particularly when the defender’s strategy is unknown. To address this, we introduce the Iterative Best Response Model Predictive Control (iBR-MPC) framework, which enables the Bandit to iteratively refine its trajectory based on the observed Guard’s behavior. The algorithm is implemented and validated using a Kerbal Space Program-based differential game simulation suite, demonstrating its effectiveness in dynamic, adversarial engagements. Additionally, the framework was tested in a competition setting, where it secured first place in the 2nd Annual AIAA Non-Cooperative Space Operations Challenge, outperforming alternative methods.