Event-Triggered Optimal Formation Tracking Control Using Reinforcement Learning for Large-Scale UAV Systems

TL;DR

This paper introduces an event-triggered optimal control method using reinforcement learning for large-scale UAV formations, improving efficiency and safety in complex scenarios like light shows.

Contribution

It develops a novel event-triggered control framework combining Hungarian algorithm and actor-critic neural networks for large-scale UAV systems.

Findings

Effective formation tracking achieved in large-scale UAV experiments.

Reduced computational load and improved control performance.

Validated on a mixed reality platform simulating real-world conditions.

Abstract

Large-scale UAV switching formation tracking control has been widely applied in many fields such as search and rescue, cooperative transportation, and UAV light shows. In order to optimize the control performance and reduce the computational burden of the system, this study proposes an event-triggered optimal formation tracking controller for discrete-time large-scale UAV systems (UASs). And an optimal decision - optimal control framework is completed by introducing the Hungarian algorithm and actor-critic neural networks (NNs) implementation. Finally, a large-scale mixed reality experimental platform is built to verify the effectiveness of the proposed algorithm, which includes large-scale virtual UAV nodes and limited physical UAV nodes. This compensates for the limitations of the experimental field and equipment in realworld scenario, ensures the experimental safety, significantly reduces the experimental cost, and is suitable for realizing largescale UAV formation light shows.