In this paper statistical decision making applied to automotive collision avoidance has been discussed. A criterion that explicitly uses an approximation of the statistical properties of the risk metric has been simulated and analyzed. To compute the approximation the estimated tracking noise covariance (which was assumed to be Gaussian) was used. The main reason for this criterion was to be able to deal with changing uncertainty of the risk metric without having to evaluate the entire PDF. The criterion is motivated by properties of the Gaussian distribution, for Gaussian distributed variables the criterion corresponds to a hypothesis test. It was shown that one particular risk metric can be considered to be Gaussian under certain circumstances. In head-on collision scenarios where the assumption of gaussianity holds (v > 25 km/h), the discussed criterion applied to proposed equation keeps the risk of a faulty intervention at a relatively constant level. However, a careful comparison of the results shows a slight change in that risk level. For the criterion the risk of a faulty intervention is changed more significantly as the measurement noise is increased. For scenarios where the assumptions do not hold (e.g. at low speeds) the discussed criterion becomes too cautious, causing braking to be too late. Bad performance at low speeds are also caused by the fact that the risk metric used does not account for the brake system dynamics, here the second risk metric discussed in Section 3 can offer significant improvements.


    Access

    Access via TIB

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Dealing with uncertainty in automotive collision avoidance


    Additional title:

    Ein Beitrag zur Abschätzung der Risikoparameter zur Vermeidung von Fahrzeugunfällen


    Contributors:
    Jansson, J. (author)


    Publication date :

    2004


    Size :

    16 Seiten, 7 Bilder, 1 Tabelle, 6 Quellen



    Type of media :

    Conference paper


    Type of material :

    Print


    Language :

    English




    AUTOMOTIVE COLLISION AVOIDANCE SENSOR

    MOON BYOUNG JOON / KIM KYUNG SIK | European Patent Office | 2016

    Free access

    Automotive Collision Avoidance System: A Review

    Rammohan, A. / Chavhan, Suresh / Chidambaram, Ramesh Kumar et al. | Springer Verlag | 2022



    Machine Learning Algorithm for Automotive Collision Avoidance

    Koganti, Ramakrishna / Jha, Shambhavi / Polisetti, Sai Pranathi et al. | British Library Conference Proceedings | 2021


    Microwave Based Sensors for Automotive Collision Avoidance

    Williams, H. S. | British Library Conference Proceedings | 1997