• Login
    View Item 
    •   FFI Publications Home
    • Publications
    • Articles
    • View Item
    •   FFI Publications Home
    • Publications
    • Articles
    • View Item
    JavaScript is disabled for your browser. Some features of this site may not work without it.

    Generative Adversarial Immitation Learning for Steering an Unmanned Surface Vehicle

    View/Open
    1883515.pdf (551.2Kb)
    Date
    2020-02
    Author
    Vedeler, Alexandra Skau
    Warakagoda, Narada Dilp
    Metadata
    Show full item record
    Abstract
    The task of obstacle avoidance using maritime vessels, such as Unmanned Surface Vehicles (USV), has traditionally been solved using specialized modules that are designed and optimized separately. However, this approach requires a deep insight into the environment, the vessel, and their complex dynamics. We propose an alternative method using Imitation Learning (IL) through Deep Reinforcement Learning (RL) and Deep Inverse Reinforcement Learning (IRL) and present a system that learns an end-to-end steering model capable of mapping radar-like images directly to steering actions in an obstacle avoidance scenario. The USV used in the work is equipped with a Radar sensor and we studied the problem of generating a single action parameter, heading. We apply an IL algorithm known as generative adversarial imitation learning (GAIL) to develop an end-to-end steering model for a scenario where avoidance of an obstacle is the goal. The performance of the system was studied for different design choices and compared to that of a system that is based on pure RL. The IL system produces results that indicate it is able to grasp the concept of the task and that in many ways are on par with the RL system. We deem this to be promising for future use in tasks that are not as easily described by a reward function.
    URI
    http://hdl.handle.net/20.500.12242/2842
    DOI
    10.7557/18.5147
    Description
    Vedeler, Alexandra Skau; Warakagoda, Narada Dilp. Generative Adversarial Immitation Learning for Steering an Unmanned Surface Vehicle. Proceedings of the Northern Lights Deep Learning Workshop 2020 ;Volum 1.
    Collections
    • Articles

    Browse

    All of FFI PublicationsCommunities & CollectionsBy Issue DateAuthorsTitlesThis CollectionBy Issue DateAuthorsTitles

    My Account

    Login

    CONTACT US

    • FFI Kjeller
      FFI, PO Box 25, 2027 Kjeller
    • Office Address: Instituttvn 20,
      Phone 63 80 70 00
    • biblioteket@ffi.no

    HELPFUL

    • About FFI
    • Career
    • Reports

    Sitemap

    • About cookies (cookies)
    • Newsletter
    • Sitemap

    FOLLOW US

     

     

    © Copyright Norwegian Defence Research Establishment
    Powered by KnowledgeArc