Pradalier, Cédric; Juan, Pierre-Alexandre; McCabe, Rodney J.; Capolungo, Laurent; A Graph Theory-Based Automated Twin Recognition Technique for Electron Backscatter Diffraction Analysis. Integrating Materials and Manufacturing Innovation, 1-16, 2018. Draft version.The end result of our software is extracting the grains and internal twins as illustrated below for magnesium. Grains are delineated in yellow and twins in brown. Relation between a grain can be either tensile (green links) or compressive (magenta). Our software works mostly automatically but allows the user to correct misclassification of twinning relations. It then output all the statistics between grains, twins, neighbours, etc… inside an sqlite database.
Figure 1 illustrates the method on a dummy task. The task environment is rasterized into a 2D map and the expert provides the task solutions as a set of positions on the map. These are rasterized by drawing 2D gaussians around the expert solutions. Given a set of demonstrations, a Fully Convolutional Network (FCN) is trained to generate utility functions which maxima correspond to the expert solution.
This method is applied to two exploration toy cases, the art gallery problem and the fortress problem, and UAV network deployment.
© 2019 DREAM Lab – Georgia Tech Lorraine