Robust Tracking Control of Underactuated UAVs Based on Zero-Sum Differential Games

• Published in: Drones (Basel) Vol. 9; no. 7; p. 477
• Main Authors: Guo, Yaning, Sun, Qi, Pan, Quan
• Format: Journal Article
• Language: English
• Published: Basel MDPI AG 01.07.2025
• Subjects: Algorithms; Closed loops; Control methods; Control systems; Controllers; Convergence; Design; Differential games; Disturbances; Drone aircraft; Dynamical systems; Feedback control; Game theory; Games; integral reinforcement learning (IRL); Machine learning; Methods; Neural networks; Parameter estimation; Robust control; robust tracking control; Subsystems; Systems stability; Tracking control; Tracking problem; Tracking systems; unmanned aerial vehicle (UAV); Unmanned aerial vehicles; Zero sum games; China
• ISSN: 2504-446X; 2504-446X
• DOI: 10.3390/drones9070477

This paper investigates the robust tracking control of unmanned aerial vehicles (UAVs) against external time-varying disturbances. First, by introducing a virtual position controller, we innovatively decouple the UAV dynamics into independent position and attitude error subsystems, transforming the robust tracking problem into two zero-sum differential games. This approach contrasts with conventional methods by treating disturbances as strategic “players”, enabling a systematic framework to address both external disturbances and model uncertainties. Second, we develop an integral reinforcement learning (IRL) framework that approximates the optimal solution to the Hamilton–Jacobi–Isaacs (HJI) equations without relying on precise system models. This model-free strategy overcomes the limitation of traditional robust control methods that require known disturbance bounds or accurate dynamics, offering superior adaptability to complex environments. Third, the proposed recursive Ridge regression with a forgetting factor (R3F2 ) algorithm updates actor-critic-disturbance neural network (NN) weights in real time, ensuring both computational efficiency and convergence stability. Theoretical analyses rigorously prove the closed-loop system stability and algorithm convergence, which fills a gap in existing data-driven control studies lacking rigorous stability guarantees. Finally, numerical results validate that the method outperforms state-of-the-art model-based and model-free approaches in tracking accuracy and disturbance rejection, demonstrating its practical utility for engineering applications.