Human drivers navigate by continuously predicting the intent of road users and interacting with them. For safe autonomous driving, research about predicting future trajectory of vehicles and motion planning based on these predictions has drawn attention in recent years. Most of these studies, however, did not take into account driver’s intentions or any interdependence with other vehicles. In order to drive safely in real complex driving situations, it is essential to plan a path based on other driver’s intentions and simultaneously to estimate the intentions of other road user with different characteristics as human drivers do. We aim to tackle the above challenges on highway merge scenario where the intention of other road users should be understood. In this study, we propose an intention aware motion planning method using finite state machine and model predictive control without any vehicle-to-vehicle (V2V) or vehicle-to-infrastructure (V2I) communications. The key idea is to design the behavioral planner that control the possible modes like human drivers do. This behavioral planner contains “negotiate” state which could inform my intent to other road users and estimate the other user’s intention from their reaction. The model predictive controller generates an optimized trajectory for merging in terms of safety, efficiency and comfort with directly reflecting the estimated intention of the road users. In order to verify the proposed framework, the complex highway merging scenario is implemented where various road users with different intention and characteristic exist by using IDM (Intelligent Driver Model).


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Intention Aware Motion Planning with Model Predictive Control in Highway Merge Scenario


    Additional title:

    Sae Technical Papers


    Contributors:
    Kim, Dongchan (author) / Kim, Hayoung (author) / Huh, Kunsoo (author)

    Conference:

    Asia-Pacific Automotive Engineering Conference ; 2019



    Publication date :

    2019-03-25




    Type of media :

    Conference paper


    Type of material :

    Print


    Language :

    English




    Intention Aware Motion Planning with Model Predictive Control in Highway Merge Scenario

    Kim, Hayoung / Kim, Dongchan / Huh, Kunsoo | British Library Conference Proceedings | 2019


    Probabilistic Model for Interaction Aware Planning in Merge Scenarios

    Ward, Erik / Evestedt, Niclas / Axehill, Daniel et al. | IEEE | 2017


    Heuristics Based Cooperative Planning for Highway On-Ramp Merge

    Shen, Minghao / Hu, Hanyang / Sun, Bohua et al. | IEEE | 2018



    Model Predictive Control based Automated Driving Lane Change Control Algorithm for Merge Situation on Highway Intersection

    Chae, Heungseok / Min, Kyong Chan / Yi, Kyongsu | British Library Conference Proceedings | 2017