Research into safety in autonomous and semi-autonomous vehicles has, so far, largely been focused on testing and validation through simulation. Due to the fact that failure of these autonomous systems is potentially life-endangering, formal methods arise as a complementary approach. This paper studies the application of formal methods to the verification of a human driver model built using the cognitive architecture ACT-R, and to the design of correct-by- construction Advanced Driver Assistance Systems (ADAS). The novelty lies in the integration of ACT-R in the formal analysis and an abstraction technique that enables finite representation of a large dimensional, continuous system in the form of a Markov process. The situation considered is a multi-lane highway driving scenario and the interactions that arise. The efficacy of the method is illustrated in two case studies with various driving conditions.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Correct-by-Construction Advanced Driver Assistance Systems Based on a Cognitive Architecture


    Contributors:


    Publication date :

    2019-09-01


    Size :

    1760761 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English




    Advanced Driver Assistance Systems

    Paul, Aneesh / Chauhan, Rohan / Srivastava, Rituraj et al. | British Library Conference Proceedings | 2016


    Advanced Driver Assistance Systems

    Rob E.C.M. van der Heijden / Vincent A.W.J. Marchau | DOAJ | 2005

    Free access

    Advanced Driver Assistance Systems

    Hilgers, Michael / Achenbach, Wilfried | Springer Verlag | 2021


    Advanced Driver Assistance Systems

    Haas, Roland Erik / Bhattacharjee, Shambo / Möller, Dietmar P. F. | Springer Verlag | 2019