Autonomous racing serves as a critical platform for evaluating automated driving systems and enhancing vehicle mobility intelligence. This work investigates offline reinforcement learning methods to train agents within the dynamic F1tenth racing environment. The study begins by exploring the challenges of online training in the Austria race track environment, where agents consistently fail to complete the laps. Consequently, this research pivots towards an offline strategy, leveraging 'expert' demonstration dataset to facilitate agent training. A waypoint-based suboptimal controller is developed to gather data with successful lap episodes. This data is then employed to train offline learning-based algorithms, with a subsequent analysis of the agents' cross-track performance, evaluating their zero-shot transferability from seen to unseen scenarios and their capacity to adapt to changes in environment dynamics. Beyond mere algorithm benchmarking in autonomous racing scenarios, this study also introduces and describes the machinery of our return-conditioned decision treebased policy, comparing its performance with methods that employ fully connected neural networks, Transformers, and Diffusion Policies and highlighting some insights into method selection for training autonomous agents in driving interactions.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    F1tenth Autonomous Racing With Offline Reinforcement Learning Methods


    Contributors:


    Publication date :

    2024-09-24


    Size :

    9484338 byte





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Reactive Control Algorithm for F1TENTH Autonomous Vehicles in Unknown Dynamic Environments

    Morys - Magiera, Artur / Lis, Aleksandra / Pudlo, Jakub et al. | Springer Verlag | 2023


    AUTONOMOUS VEHICLE TESTING OPTIMIZATION USING OFFLINE REINFORCEMENT LEARNING

    LEE RITCHIE | European Patent Office | 2024

    Free access

    A LiDAR-based approach to autonomous racing with model-free reinforcement learning

    Hell, Mate / Hajgato, Gergely / Bogar-Nemeth, Armin et al. | IEEE | 2024


    Offline Reinforcement Learning for Autonomous Driving with Real World Driving Data

    Fang, Xing / Zhang, Qichao / Gao, Yinfeng et al. | IEEE | 2022


    Trajectory Planning Using Reinforcement Learning for Interactive Overtaking Maneuvers in Autonomous Racing Scenarios

    Ögretmen, Levent / Chen, Mo / Pitschi, Phillip et al. | ArXiv | 2024

    Free access