Advanced capabilities planned for the next generation of autonomous and increasingly autonomous air vehicles will include non-traditional components based on artificial intelligence, machine learning, and complex optimization and planning algorithms. These complex components will be used to provide enhanced safety and high-level decision-making functions. However, there are serious barriers to the deployment of autonomous aircraft in the National Airspace System (NAS). Current civil aviation certification processes are based on the concept that the correct behavior of a system or a component must be completely specified and verified prior to operation. This report from the Autonomy Verification and Validation (V&V) Roadmap and Vision 2045 project presents the most recent effort to build a comprehensive list of verification challenges and needs for autonomous aircraft, a roadmap to meet those autonomy V&V needs, the services they can enable, and point to the certification gaps they fill. To accomplish these goals, we assembled a team of world-class researchers from the aerospace industry (Boeing, Collins Aerospace, and GeneralElectric) and academia (University of Michigan, University of Texas, and Massachusetts Institute of Technology) with deep expertise in autonomy, aerospace systems, and assurance of Artificial Intelligence/machine learning systems.


    Access

    Access via TIB

    Check availability in my library


    Export, share and cite



    Title :

    Autonomy Verification & Validation Roadmap and Vision 2045


    Contributors:

    Publication date :

    2023-01-31


    Type of media :

    Report


    Type of material :

    No indication


    Language :

    English





    Nr. 2045

    DataCite | 1884


    Airspace Operations: Vision for 2045 and Beyond

    Kopardekar, Parimal H. | NTRS | 2020


    New trains for 2045

    Walmsley, Ian | IuD Bahn | 2007


    Verification and Validation of Autonomy Requirements

    Vassev, Emil / Hinchey, Mike | Springer Verlag | 2014