In this paper we extensively explore the suitability of YOLO architectures to monitor the process flow across a Fischertechnik industry 4.0 application. Specifically, different YOLO architectures in terms of size and complexity design along with different prior-shapes assignment strategies are adopted. To simulate the real world factory environment, we prepared a rich dataset augmented with different distortions that highly enhance and in some cases degrade our image qualities. The degradation is performed to account for environmental variations and enhancements opt to compensate the color correlations that we face while preparing our dataset. The analysis of our conducted experiments shows the effectiveness of the presented approach evaluated using different measures along with the training and validation strategies that we tailored to tackle the unavoidable color correlations that the problem at hand inherits by nature.

This directory contains code of the backend which was used to run evaluation of NIPS17 Adversarial Competition. This file describes how to run and use the code. For more details about the competition refer to our publication and to Kaggle competition page. This code is provided AS IS. At the time of publishing this code was well tested and was working for evaluation of the competition.

It is finally resonating with me that incorporating Deep Learning at the Edge has the potential to create a paradigm shift in the way robots are deployed in manufacturing operations. FANUC's aggressive move to integrated Deep Learning technologies could revolutionize the way robotic systems are deployed. When you consider how robots are deployed in manufacturing operations today, the application programs employ traditional procedural and function programming methods. But as robots increasingly rely upon vision systems to identify and locate geometric patterns on a work piece, the logic and decision making no longer has to be all pre-programmed in order to process the workpiece. Today, every robotic application program applies the experiential knowledge of a human expert to account for every possible situation that may arise in the manufacturing operation.

What is normal for a machine (or the System under observation) is environment-dependent and ever-changing in real life!