MDP-based high-level decision-making for combining safety and optimality: autonomous overtaking

<p dir="ltr">This paper presents a novel solution for optimal high-level decision-making in autonomous<br>overtaking on two-lane roads, considering both opposite-direction and same-direction traffic. The proposed<br>solution accounts for key factors such as safety and optimality, while also ensuring recursive feasibility<br>and stability. To safely complete overtaking maneuvers, the solution is built on a constrained Markov<br>decision process (MDP) that generates optimal decisions for path planners. By combining MDP with<br>model predictive control (MPC), the approach guarantees recursive feasibility and stability through a<br>baseline control policy that calculates the terminal cost and is incorporated into a constructed Lyapunov<br>function. The proposed solution is validated through five simulated driving scenarios, demonstrating its<br>robustness in handling diverse interactions within dynamic and complex traffic conditions.</p>