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

Simple item page
dc.contributor.authorBuettner, Ricardo
dc.contributor.authorBaumgartl, Hermann
dc.date.accessioned2019-01-02T23:44:05Z
dc.date.available2019-01-02T23:44:05Z
dc.date.issued2019-01-08
dc.description.abstractUsing 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.
dc.format.extent8 pages
dc.identifier.doi10.24251/HICSS.2019.081
dc.identifier.isbn978-0-9981331-2-6
dc.identifier.urihttp://hdl.handle.net/10125/59506
dc.language.isoeng
dc.relation.ispartofProceedings of the 52nd Hawaii International Conference on System Sciences
dc.rightsAttribution-NonCommercial-NoDerivatives 4.0 International
dc.rights.urihttps://creativecommons.org/licenses/by-nc-nd/4.0/
dc.subjectICT and Artificial Intelligence for Crisis and Emergency Management
dc.subjectCollaboration Systems and Technologies
dc.subjectconvolutional neural networks, deep learning, emergency situations, escape route planning, multi-agent systems
dc.titleA Highly Effective Deep Learning Based Escape Route Recognition Module for Autonomous Robots in Crisis and Emergency Situations
dc.typeConference Paper
dc.type.dcmiText

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
0066.pdf
Size:
2.37 MB
Format:
Adobe Portable Document Format
Download

Collections

ICT and Artificial Intelligence for Crisis and Emergency Management