Lane-Keeping Assistance System Based on Model Predictive Control With Smooth Transitions Between Operational Modes

The lane-keeping assistance system (LKAS) is one of the core functions of advanced driver assistance systems (ADAS) that prevents unintended lane departures. LKAS widely utilizes shared steering control, in which both the driver and the vehicle controller share lane-keeping control by integrating the driver into the control loop. The shared control approach can be formulated as a multi-objective optimization problem that optimizes between maintaining driver control and reducing driving burden, while preventing unintended lane departures. A model predictive control (MPC)-based method effectively can address multi-objective optimization problems in shared control. In addition, it provides the advantage of switching the operational mode by adjusting the weights in the cost function according to assessed risk. However, an abrupt transition between operational modes can cause unstable motion such as severe lateral jerk or hysteresis, resulting in driver discomfort. To address this issue, we propose a shared control framework that ensures smooth transitions between operational modes by applying a softly switched MPC method, in which the weights are modulated over the prediction horizon. Unlike existing approaches, the proposed method with the soft-switching scheme could enhance path-tracking accuracy, maintain steering stability, and suppress unstable lateral motion while improving driver comfort during switching between operational modes. Simulation experiments with various maneuvers and road curvatures demonstrated that the proposed framework could substantially suppress unstable lateral motion during mode transitions, even in severe cases, while complying with safety regulations.