Dynamic representations for autonomous driving

J.S. Olier Jauregui, P. Marin, D. Martin (Supervisor), L. Marcenaro (Supervisor), E.I. Barakova (Supervisor), G.W.M. Rauterberg (Supervisor), C. Regazzoni (Supervisor)

    Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

    6 Citations (Scopus)
    3 Downloads (Pure)

    Abstract

    This paper presents a method for observational learning in autonomous agents. A formalism based on deep learning implementations of variational methods and Bayesian filtering theory is presented. It is explained how the proposed method is capable of modeling the environment to mimic behaviors in an observed interaction by building internal representations and discovering temporal and causal relations. The method is evaluated in a typical surveillance scenario, i.e., perimeter monitoring. It is shown that the vehicle learns how to drive itself by simultaneously observing its surroundings and the actions taken by a human driver for a given task. That is achieved by embedding knowledge regarding perception-action couplings in dynamic representational states used to produce action flows. Thereby, representations link sensory data to control signals. In particular, the representational states associate visual features to stable action concepts such as turning or going straight.

    Original languageEnglish
    Title of host publication2017 14th IEEE International Conference on Advanced Video and Signal Based Surveillance, AVSS 2017
    Place of PublicationPiscataway
    PublisherInstitute of Electrical and Electronics Engineers
    ISBN (Electronic)978-1-5386-2939-0
    ISBN (Print)978-1-5386-2940-6
    DOIs
    Publication statusPublished - 20 Oct 2017
    Event14th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS 2017) - Carlo V Castle, Lecce, Italy
    Duration: 29 Aug 20171 Sep 2017
    Conference number: 14
    http://www.avss2017.org/

    Conference

    Conference14th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS 2017)
    Abbreviated titleAVSS 2017
    Country/TerritoryItaly
    CityLecce
    Period29/08/171/09/17
    Internet address

    Fingerprint

    Dive into the research topics of 'Dynamic representations for autonomous driving'. Together they form a unique fingerprint.

    Cite this