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.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Unveiling the Road Ahead: An MPC-Based Approach for Autonomous Intersection Navigation with Occlusion


    Contributors:


    Publication date :

    2023-10-16


    Size :

    2545325 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    An online approach for intersection navigation of autonomous vehicle

    Bai, Yang / Chong, Zhuang Jie / Ang, Marcelo H. et al. | IEEE | 2014


    Navigation based on detected occlusion overlapping a road entrance

    SHALEV-SHWARTZ SHAI / SHASHUA AMNON / STEIN GIDEON et al. | European Patent Office | 2023

    Free access

    AUTONOMOUS NAVIGATION BASED ON ROAD SIGNATURES

    STEIN GIDEON / SPRINGER OFER / FERENCZ ANDRAS | European Patent Office | 2017

    Free access

    Autonomous navigation based on road signatures

    STEIN GIDEON / SPRINGER OFER / FERENCZ ANDRAS | European Patent Office | 2021

    Free access