One embodiment of the present invention sets forth a technique for controlling the execution of a physical process. The technique includes receiving, as input to a machine learning model that is configured to adapt a simulation of the physical process executing in a virtual environment to a physical world, simulated output for controlling how the physical process performs a task in the virtual environment and real-world data collected from the physical process performing the task in the physical world. The technique also includes performing, by the machine learning model, one or more operations on the simulated output and the real-world data to generate augmented output. The technique further includes transmitting the augmented output to the physical process to control how the physical process performs the task in the physical world.

One embodiment of the present invention sets forth a technique for controlling the execution of a physical process. The technique includes receiving, as input to a machine learning model that is configured to adapt a simulation of the physical process executing in a virtual environment to a physical world, simulated output for controlling how the physical process performs a task in the virtual environment and real-world data collected from the physical process performing the task in the physical world. The technique also includes performing, by the machine learning model, one or more operations on the simulated output and the real-world data to generate augmented output. The technique further includes transmitting the augmented output to the physical process to control how the physical process performs the task in the physical world.

One embodiment of the present invention sets forth a technique for generating simulated training data for a physical process. The technique includes receiving, as input to at least one machine learning model, a first simulated image of a first object, wherein the at least one machine learning model includes mappings between simulated images generated from models of physical objects and real-world images of the physical objects. The technique also includes performing, by the at least one machine learning model, one or more operations on the first simulated image to generate a first augmented image of the first object. The technique further includes transmitting the first augmented image to a training pipeline for an additional machine learning model that controls a behavior of the physical process.

A numerical controller is equipped with a check drawing function for drawing an unmachined path based on a machining program and a machining drawing function for drawing a machining trajectory during machining control based on the machining program. The numerical controller calculates a drawing trajectory correction vector which represents an amount of shift in an axial position at which machining is actually performed from an axial position commanded by the machining program, and creates a corrected machining trajectory by correcting a drawing position of the machining trajectory drawn by the machining drawing function, based on the calculated drawing trajectory correction vector. Then, the corrected machining trajectory and the unmachined path are displayed on a same screen.

A display device and a display method to enable, by reducing the amount of data to be displayed, reduction of the time required for display even when the data to be dealt with is three-dimensional coordinate data are obtained.

A display device according to the invention includes a tool-movement-path calculation means 14 to calculate, on the basis of data of a machining program on which movement commands for a tool in a three-dimensional coordinate system are written, tool movement paths through which the tool moves in the three-dimensional coordinate system, a path-replacement-processing unit 19 to replace, on the basis of the tool movement paths calculated by the tool-movement-path calculation means 14 and a predetermined index, consecutive tool movement paths with a replacement path, and a display unit 20 to display the replacement path replaced by the path-replacement-processing unit 19.

A display device that displays an error between an instructed command position of a specific portion of a control target and a response position of the specific portion in a manner easily understandable to a user is described. The display device acquires a response position of the specific portion and calculates a difference in position of the command position and the response position. The display device displays a spatial trajectory based on the command position or a spatial trajectory based on the response position. The display device also displays each spatial trajectory in a mode where a portion of the spatial trajectory of the command position corresponding to the selected mark and a portion of the spatial trajectory of the response position corresponding to the relevant portion of the spatial trajectory of the command position are enlarged at a same magnification.