Abstract: Training deep neural networks requires a large amount of labeled training data. Conventionally, labeled training data is generated by gathering real images that are manually labelled which is very time-consuming. Instead of manually labelling a training dataset, domain randomization technique is used generate training data that is automatically labeled. The generated training data may be used to train neural networks for object detection and segmentation (labelling) tasks. In an embodiment, the generated training data includes synthetic input images generated by rendering three-dimensional (3D) objects of interest in a 3D scene. In an embodiment, the generated training data includes synthetic input images generated by rendering 3D objects of interest on a 2D background image. The 3D objects of interest are objects that a neural network is trained to detect and/or label.

Abstract: Various embodiments enable a robot, or other autonomous or semi-autonomous device or system, to receive data involving the performance of a task in the physical world. The data can be provided as input to a perception network to infer a set of percepts about the task, which can correspond to relationships between objects observed during the performance. The percepts can be provided as input to a plan generation network, which can infer a set of actions as part of a plan. Each action can correspond to one of the observed relationships. The plan can be reviewed and any corrections made, either manually or through another demonstration of the task. Once the plan is verified as correct, the plan (and any related data) can be provided as input to an execution network that can infer instructions to cause the robot, and/or another robot, to perform the task.

Abstract: An electronic device includes a first field effect transistor that includes a first gate electrode, a first drain electrode, and a first source electrode; a second field effect transistor that includes a second gate electrode, a second drain electrode, and a second source electrode, the first and second gate electrodes being at least one of electrically connected or integral, and the first and second source electrodes being at least one of electrically connected or integral; an input electrode electrically connected to the first and second gate electrodes; and an output electrode electrically connected to the first and second source electrodes. The first field effect transistor also includes a first semiconductor material. The second field effect transistor further also incudes a second semiconductor material.

Abstract: An electronic sign with multiple direction positionable rear access doors, wherein sliding rear access doors are utilized to provide for access to the inner regions of the electronic sign while maintaining a thin profile. One or more of a plurality of sliding rear access doors can be disengaged from a back panel and urged rearwardly a minimal distance and then positioned laterally and unobtrusively along the length of a top track opposing a bottom track allowing the electronic sign to maintain a thin and unobtrusive profile.