Occluded intersections pose challenges and potential danger for autonomous vehicles (AVs) operating in partly unknown environments. The limited visibility caused by occlusions introduces uncertainties and risks in decision-making processes. This paper proposes a Model Predictive Control (MPC)-based motion planning approach for AVs at occluded intersections, aiming to ensure safety while maximizing travel efficiency. The proposed approach guarantees safety by considering the worstcase scenario, reducing computational complexity and avoiding subjective tolerance of collision risk. It integrates risk assessment into the MPC-based motion planning process, allowing the AV to actively learn the environment and optimize its path. By consistently updating environmental information, the AV gradually eliminates risks. Simulation results demonstrate the effectiveness of the proposed method in achieving safe and efficient navigation at occluded intersections.
Unveiling the Road Ahead: An MPC-Based Approach for Autonomous Intersection Navigation with Occlusion
2023-10-16
2545325 byte
Conference paper
Electronic Resource
English
Navigation based on detected occlusion overlapping a road entrance
European Patent Office | 2023
|