<p>In this paper, we investigate the problem of aircraft maintenance routing. The optimization of aircraft maintenance routing can help airlines improve their resource scheduling and flight efficiency. However, the effects of flight interruption and potential delays are often overlooked. First, we construct the aircraft maintenance routing model by considering multiple maintenance requirements. The profits between the flight connection revenues and the aircraft maintenance costs are maximized. Then, based on the delay time and delay probability, we construct a robust aircraft maintenance routing model. The risk of delays while planning aircraft routes is reduced. Moreover, we design an adaptive reinforcement learning-based algorithm for model solving. The experimental results show that the robust aircraft maintenance routing model can be effective in solving the integration of aircraft maintenance and flight connection. The algorithm is advanced in terms of solution speed and accuracy. The proposed method can be applied in multiple environments and can provide reasonable decisions.</p>