Uncertainty-Aware Safe Trajectory Planner Based on Model Predictive Control for Autonomous Driving

Safe trajectory planning in uncertain environments is critical for autonomous driving. However, keeping the safety of vehicles under uncertainty is an open and challenging problem. The key challenges are how to predict and quantify the trajectory uncertainty of other traffic participants, and perform high-quality real-time trajectory planning in dynamic and complex environments. To address these challenges, this paper presents an uncertainty-aware safe trajectory planner based on model predictive control, which considers the uncertain trajectory of the target vehicle and enhances the system safety. To predict the trajectory uncertainty of the target vehicle, a trajectory prediction method combining kinematics and reachable set is proposed, which can reduce the conservatism compared to robust invariant set. To ensure vehicle safety in uncertain environments, an uncertainty-aware safe trajectory planner is established, which extend the control barrier function to uncertain system, and the control barrier function safety constraints are constructed based on the probabilistic n-step reachable set of the target vehicle trajectory. In addition, safety constraints including safe distance from the target vehicle, vehicle handling stability, road boundary, actuator saturation constraints are taken into account. Finally, simulation results show that the proposed planner can improve the system safety and feasibility in uncertain environments compared with other baseline methods. Additionally, its robustness is validated by analyzing the impact of different levels of uncertainty in complex scenarios. Moreover, the real-time performance is verified by the hardware-in-the-loop experiment, which proves that the planner can be applied in real-world autonomous vehicle systems.