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.
A Highly Effective Deep Learning Based Escape Route Recognition Module for Autonomous Robots in Crisis and Emergency Situations
2019-01-08
Conference paper
Electronic Resource
English
Conveying car comprising autonomous power supply for emergency situations
European Patent Office | 2018
|Analysis of driver behaviour in autonomous emergency hazard braking situations
Automotive engineering | 2008
|