Lane changing (LC), a fundamental driving technique, has an enormous effect on traffic safety and accident prevention. Several algorithms based on deep learning have been constructed to forecast lane changes. However, due to the intricacies and unpredictable nature of driving habits, there is still a need for progress in the construction of an accurate and efficient lane change prediction system. To solve this issue, a novel deep learning-driven smart system for Lane change decision-making is presented for efficient lane change prediction. A Deep Belief Network (DBN) is used for modeling the lane change to make lane change. Improved Grey Wolf Optimization is presented for optimum use of the hyper parameters of the LSTM model, which efficiently forecasts the vehicle’s longitudinal and lateral positions. The Next Generation Simulation (NGSIM) is being used to assess the novel deep learning system. The novel deep learning system can precisely forecast the lane change. A novel deep learning-driven smart system for Lane change decision-making attained an accuracy of 98.3%. The proposed model can predict lane change, longitudinal and lateral location effectively.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    A Novel Deep Learning-Driven Smart System for Lane Change Decision-Making


    Additional title:

    Int. J. ITS Res.


    Contributors:


    Publication date :

    2024-12-01


    Size :

    12 pages




    Type of media :

    Article (Journal)


    Type of material :

    Electronic Resource


    Language :

    English




    A Novel Deep Learning-Driven Smart System for Lane Change Decision-Making

    Hema, D. Deva / Jaison, T. Rajeeth | Springer Verlag | 2024


    Automated Speed and Lane Change Decision Making using Deep Reinforcement Learning

    Hoel, Carl-Johan / Wolff, Krister / Laine, Leo | IEEE | 2018


    Autonomous Lane Change Decision Making Using Different Deep Reinforcement Learning Methods

    Feng, Xidong / Hu, Jianming / Huo, Yusen et al. | ASCE | 2019