Prescribed Performance Optimized Control of UAV With Robust Approximate Dynamic Programming Under Disturbance

This study proposes an integrated control framework that combines prescribed performance backstepping with reinforcement learning (RL) optimization for quadrotor unmanned aerial vehicles (QUAVs) operating under disturbances. The key innovation lies in enforcing guaranteed transient and steady-state tracking performance while achieving optimal control behavior through online learning. A systematic two-stage control architecture is developed: An outer-loop position controller incorporating prescribed performance bounds handles the underactuated dynamics, complemented by an innerloop attitude controller ensuring desired orientation tracking. The inner-loop controller employs critic–actor neural networks (NNs) to approximate optimal solutions of the Hamilton-Jacobi-Bellman (HJB) equation, while the outer-loop controller optimizes position tracking performance through Hamilton-Jacobi-Isaacs (HJI) equation solutions. Rigorous stability analysis establishes uniformly ultimately bounded (UUB) convergence for all tracking errors and NN weight estimation errors using Lyapunov theory under the prescribed performance constraints. The efficacy of the proposed framework is validated through comprehensive numerical simulations, demonstrating exceptional tracking precision with position errors under prescribed performance.