This study proposes an integrated approach that uses machine learning and ROS2 as a combined tool to provide effective path planning and cruise control capabilities in self-driving cars. For object identification and environment perception, the suggested system makes use of Convolutional Neural Networks (CNN) and Haarcascade algorithm. As well as A* and Dijkstra algorithms are applied for finding optimal path and navigation through challenging situations such as T-junctions and cross intersections. Reliable autonomous navigation is demonstrated by the system's efficient integration of motion planning and lane assistance. The model can improve self-driving capabilities, leading to safer and more effective autonomous driving solutions, as demonstrated by experimental findings.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Efficient Path Planning and Cruise Control Features In Self-Driving Cars Using ROS2 & Machine Learning




    Publication date :

    2024-11-29


    Size :

    1058255 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    ROS2 for beginners

    Renard, Edouard / Manning (Firm), | TIBKAT | 2022


    An Enhanced Safe and Reliable Autonomous Driving Platform Using ROS2

    Cui, Hang / Zhang, Jiaming / Norris, William R. | British Library Conference Proceedings | 2020


    Dynamic Path Planning of a mobile robot adopting a costmap layer approach in ROS2

    Cen Cheng, Pangcheng David / Indri, Marina / Sibona, Fiorella et al. | BASE | 2022

    Free access

    An Educational Kit for Simulated Robot Learning in ROS2

    Almeida, Filipe / Leão, Gonçalo / Sousa, Armando | TIBKAT | 2024


    Cyber Attack Detection On Self-Driving Cars Using Machine Learning Techniques

    Pawar, Yashaswini S / Honnavalli, Prasad / Eswaran, Sivaraman | IEEE | 2022