Learning-Based Resilience Optimization of Human-on-the-Loop Multiple-Unmanned-Aerial-System Positioning Using Mean Field Games

Authors:

Abstract
This article presents a learning-based game-theoretic approach for resilience optimization of human-on-the-loop (HotL) positioning for multiple unmanned aerial systems (UASs). In particular, mean field games (MFGs) are used to obtain the [ ]-Nash equilibrium policies for a large population of non-cooperative UASs that compete for limited human resources to maintain high positioning accuracy. The resilience dynamics model is learned from the HotL multi-UAS positioning system data. Furthermore, an improved actor–critic–mass algorithm is proposed to enhance the learning efficiency of the near-optimal policies. Then, the policies are exploited to guide human–machine interactions. Simulations of a HotL multi-UAS positioning system demonstrate that the proposed MFG-resilient optimization of the multi-UAS approach enhances the system’s resilience and increases the success rate of navigating to the desired positions compared to the approaches without using the MFG policies.
Funding Information
  • Air Force Research Lab (FA9453-23-P-A019)