Please use this identifier to cite or link to this item: http://hdl.handle.net/10125/59506

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

File Size Format  
0066.pdf 2.43 MB Adobe PDF View/Open

Item Summary

Title:A Highly Effective Deep Learning Based Escape Route Recognition Module for Autonomous Robots in Crisis and Emergency Situations
Authors:Buettner, Ricardo
Baumgartl, Hermann
Keywords:ICT and Artificial Intelligence for Crisis and Emergency Management
Collaboration Systems and Technologies
convolutional neural networks, deep learning, emergency situations, escape route planning, multi-agent systems
Date Issued:08 Jan 2019
Abstract: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.
Pages/Duration:8 pages
URI/DOI:http://hdl.handle.net/10125/59506
ISBN:978-0-9981331-2-6
Rights:Attribution-NonCommercial-NoDerivatives 4.0 International
https://creativecommons.org/licenses/by-nc-nd/4.0/
Appears in Collections: ICT and Artificial Intelligence for Crisis and Emergency Management


Please email libraryada-l@lists.hawaii.edu if you need this content in ADA-compliant format.

This item is licensed under a Creative Commons License Creative Commons