Using convolutional neural networks we extend the work by Dugdale's group on socially relevant multi-agent systems in crisis and emergency situations by giving the artificial agent the ability to precisely recognize escape signs, doors and stairs for escape route planning. We build an efficient recognition module consisting of three blocks of a depth-wise separable convolutional layer, a max-pooling layer, and a batch-normalization layer before dense, dropout and classifying the image. A rigorous evaluation based on the MCIndoor20000 dataset shows excellent performance values (e.g. over 99.81 percent accuracy). In addition, our module architecture is 78 times smaller than the MCIndoor20000 benchmark - making it suitable for embedding in operational drones and robots.


    Access

    Download


    Export, share and cite



    Title :

    A Highly Effective Deep Learning Based Escape Route Recognition Module for Autonomous Robots in Crisis and Emergency Situations


    Contributors:

    Publication date :

    2019-01-08



    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Classification :

    DDC:    006 / 629




    Conveying car comprising autonomous power supply for emergency situations

    STEHR ROLAND | European Patent Office | 2018

    Free access

    Autonomous vehicle emergency route guidance

    SMITH ALEX J / AYOUB ALI A / HILLIGARDT STEFAN T | European Patent Office | 2022

    Free access

    EMERGENCY BRAKING OF AUTONOMOUS VEHICLE/ROBOTS

    NICHOLLS ELLIOT / ZHANG CHAO | European Patent Office | 2021

    Free access

    AUTONOMOUS VEHICLE EMERGENCY ROUTE GUIDANCE

    SMITH ALEX J / AYOUB ALI A / HILLIGARDT STEFAN T | European Patent Office | 2021

    Free access

    Analysis of driver behaviour in autonomous emergency hazard braking situations

    Fecher,N. / Hoffmann,J. / Winner,H. et al. | Automotive engineering | 2008