Abstract: The present invention is directed to a Spatiotemporal scene-graph embedding methodology that models scene-graphs and resolves safety-focused tasks for autonomous vehicles. The present invention features a computing system comprising instructions for accepting the one or more images, extracting one or more objects from each image, computing an inverse-perspective mapping transformation of the image to generate a bird's-eye view (BEV) representation of each image, calculating relations between each object for each image, and generating a scene-graph for each image based on the aforementioned calculations. The system may further comprise instructions for calculating a confidence value for whether or not a collision will occur through the generation of a spatio-temporal graph embedding based on a spatial graph embedding and a temporal model.

Abstract: Method and system for creating a control-flow structure which represents control logic for use in a manufacturing system based on the system's timing bar chart are described. A modular representation of the control logic is described. In the setting of a high volume transfer line, each station of the line is considered as a module and a simple method to generate a Petri net representation from the timing bar chart is described. Modified reduction rule and locality property are applied to compose the logic of a Petri net module. Using the well known properties of the marked graph which is one of the subclasses of Petri nets, the qualitative characteristics of the logic controller of the system such as liveness, boundedness (safeness) and recoverability can be verified. A live and safe marked graph can be directly transformed into Grafcet (which is one of the EC 1131-3 languages) and, using this Grafcet representation, a logic controller can be implemented directly.

Abstract: A method of machine control including the recreation of a tone reproduction curve by providing a look up table. The look up table incorporates a covariance matrix of elements containing n tone reproduction samples. A matrix multiplier responds to sensed developed patch samples and to the look up table to reproduce a complete tone reproduction curve. A control reacts to the reproduced tone reproduction curve to adjust machine quality.

Abstract: Fundamental machine functions such as the Tone Reproduction Curve need to be divided into regions of smaller units so that each unit can be interrelated to some aspects of the internal machine process. A first step toward that is by decomposing measured TRC in terms of what are known as "orthogonal basis functions". Two significant applications for orthogonal basis functions may be extensive use in color controls to maintain color consistency for every page, every time and all the time. The use of basis functions might also lead to a new soft sensor for use in certain machines.