Abstract: The present technology is directed to presenting a 3-D representation of an object, which is captured in a 2-D image of the object in an environment in a 3-D simulation of the environment. The present technology can receive 3-D data representing the environment including image data of the object in the environment, and a label identifying the object. The present technology can further locate a position of the object in the 3-D simulation of the environment based on determining a depth and an orientation of the object in the environment based on a semantic database of attributes associated with the object, obtain a 3-D representation of the object from the semantic database of attributes associated with the object, and project the 3-D representation of the object into the 3-D simulation of the environment at the determined position for the object.

Abstract: The present technology pertains to increasing diversity of simulated autonomous vehicle (AV) environment scenes to be used for training machine learning (ML) models. Such an increase in diversity may be achieved by selecting objects from simulated AV environemnt scenes, and determining whether to add attachments to attachment points of the objects based on probabilities associated with the attachment points. When an attachment is to be added to an attachment point, the particular attachment is selected from among a set of compatible attachments.

Abstract: Disclosed herein are systems and methods including a method for improving how real assets are presented in simulations of street scenes. The method includes generating a simulation of a physical scene, the simulation having a first object with a first label and a second object with a second label, determining, via a model that applies a reaction map and a reaction distance, whether the first object and the second object should be clustered together such that the first label and the second label are replaced with a third label and outputting, from the model and based on the reaction map and the reaction distance being applicable to the first object and the second object, the third label for the first object and the second object.

Abstract: Disclosed herein are systems and methods including a method for determining how real assets are in simulations of street scenes. The method includes generating a simulation in a meaningful way, the simulation having an asset, processing the simulation via a machine learning model, the machine learning model being trained to identify which classifications of assets are present in the simulation and output a quantitative number as a proxy for how real the asset would appear to a human viewer, determining, via the machine learning model, that the asset is a classification identified by the machine learning model and outputting, from the machine learning model, the quantitative number as the proxy for how real the asset would appear to the human viewer.

Abstract: A classification model can be trained by using an augmented scene. The augmented scene may be generated by placing augmentation objects into a simulated scene that is a virtual representation of a real-world scene. The augmentation objects are virtual objects representing a category for which a reference classification model has a poor performance. The reference classification model may be a simulated model trained by using a simulated scene or a real-world model trained by using a real-world scene. A training set, which includes simulated sensor data of the augmentation objects and labels of the augmentation objects, can be used to train the augmented model. The augmented model can be used by an AV to classify objects in the surrounding environment of the AV. The augmented model can have a better accuracy in classifying objects in the category than the reference classification model.

Abstract: The present technology is directed to presenting a 3-D representation of an object, which is captured in a 2-D image of the object in an environment in a 3-D simulation of the environment. The present technology can receive 3-D data representing the environment including image data of the object in the environment, and a label identifying the object. The present technology can further locate a position of the object in the 3-D simulation of the environment based on determining a depth and an orientation of the object in the environment based on a semantic database of attributes associated with the object, obtain a 3-D representation of the object from the semantic database of attributes associated with the object, and project the 3-D representation of the object into the 3-D simulation of the environment at the determined position for the object.

Abstract: Methods and systems are provided for augmenting simulations with machine learning data. In some aspects, a process can include steps for detecting a lack of data relating to a scenario in a real world environment, generating a simulation of the real world environment based on the detecting of the lack of data relating to the scenario, adding at least one asset to the simulation to satisfy the lack of data relating to the scenario, generating output data based on the simulation with the at least one asset, and updating a machine learning model based on the output data relating to the simulation with the at least one asset.

Abstract: The independent claims of this patent signify a concise description of embodiments. Disclosed is technology, roughly described, in which a semiconductor structure includes a substrate supporting a column of at least one (and preferably more than one) horizontally-oriented nanosheet transistor, each having a respective channel segment of semiconductor crystalline nanosheet material (preferably silicon or a silicon alloy) sheathed by gate stack material, wherein the channel segments have a diamond cubic crystal structure and are oriented such that the {111} planes are horizontal. Also disclosed is a method for fabricating such a structure, and a corrugated substrate that may be formed as an intermediate product. This Abstract is not intended to limit the scope of the claims.

Abstract: The independent claims of this patent signify a concise description of embodiments. Disclosed is technology, roughly described, in which a semiconductor structure includes a substrate supporting a column of at least one (and preferably more than one) horizontally-oriented nanosheet transistor, each having a respective channel segment of semiconductor crystalline nanosheet material (preferably silicon or a silicon alloy) sheathed by gate stack material, wherein the channel segments have a diamond cubic crystal structure and are oriented such that the {111} planes are horizontal. Also disclosed is a method for fabricating such a structure, and a corrugated substrate that may be formed as an intermediate product. This Abstract is not intended to limit the scope of the claims.

Abstract: The independent claims of this patent signify a concise description of embodiments. Disclosed is technology, roughly described, in which a semiconductor structure includes a substrate supporting a column of at least one (and preferably more than one) horizontally-oriented nanosheet transistor, each having a respective channel segment of semiconductor crystalline nanosheet material (preferably silicon or a silicon alloy) sheathed by gate stack material, wherein the channel segments have a diamond cubic crystal structure and are oriented such that the {111} planes are horizontal. Also disclosed is a method for fabricating such a structure, and a corrugated substrate that may be formed as an intermediate product. This Abstract is not intended to limit the scope of the claims.

Abstract: A method for simulating an epitaxial process in a body having a crystal lattice structure. Roughly described, an enlarged version of the crystal lattice structure is formed, having a lattice constant increased by a lattice enlargement factor N>1. The subject fabrication process is simulated by a Lattice Kinetic Monte Carlo algorithm in which various factors have been scaled in accordance with N. The simulation speed increases by a factor around N3, without significantly degrading the accuracy of the resulting simulated structure. The simulated epitaxial process can later be performed on a physical crystalline body.

Abstract: The independent claims of this patent signify a concise description of embodiments. Disclosed is technology, roughly described, in which a semiconductor structure includes a substrate supporting a column of at least one (and preferably more than one) horizontally-oriented nanosheet transistor, each having a respective channel segment of semiconductor crystalline nanosheet material (preferably silicon or a silicon alloy) sheathed by gate stack material, wherein the channel segments have a diamond cubic crystal structure and are oriented such that the {111} planes are horizontal. Also disclosed is a method for fabricating such a structure, and a corrugated substrate that may be formed as an intermediate product. This Abstract is not intended to limit the scope of the claims.

Abstract: A method for simulating an epitaxial process in a body having a crystal lattice structure. Roughly described, an enlarged version of the crystal lattice structure is formed, having a lattice constant increased by a lattice enlargement factor N>1. The subject fabrication process is simulated by a Lattice Kinetic Monte Carlo algorithm in which various factors have been scaled in accordance with N. The simulation speed increases by a factor around N3, without significantly degrading the accuracy of the resulting simulated structure. The simulated epitaxial process can later be performed on a physical crystalline body.