A method includes receiving, via at least one sensor of a robot, sensor data indicating one or more characteristics of an asset. The method includes detecting, based on the sensor data, an existing or imminent defect of the asset. The method includes fabricating a part suitable for use in correcting the defect. The structure of the part is derived using one or both of a digital representation of the asset generated using the sensor data or stored reference data related to the asset.

A method for controlling a robotic system includes determining a location and/or a pose of a power system component based on data received from one or more sensors, and determining a mapping of a location of a robotic system within a model of an external environment of the robotic system based on the data. The model of the external environment provides locations of objects external to the robotic system. A sequence of movements of components of the robotic system is determined to perform maintenance on the power system component based on the locations of the objects external to the robotic system and/or the location or pose of the power system component. One or more control signals are communicated to remotely control movement of the components of the robotic system based on the sequence or movements of the components to perform maintenance on the power system component.

A robot simulation device includes: an arrangement unit that arranges a robot model, a visual sensor model, and a workpiece model in a virtual space; a calculation unit that, by superimposing three-dimensional position information for a workpiece, acquired by a visual sensor in a workspace and based on a robot or the visual sensor, and shape characteristics of a workpiece model, calculates a position and orientation of the workpiece model based on a robot model or a visual sensor model in the virtual space; and a simulation unit that measures the workpiece model using the visual sensor model and executes a simulation operation in which work is performed on the workpiece model by the robot model. The arrangement unit arranges, in the virtual space, the workpiece model in the position and the orientation calculated by the calculation unit and based on the robot model or the visual sensor model.

Implementations disclosed herein relate to mitigating the reality gap through training a simulation-to-real machine learning model (Sim2Real model) using a vision-based robot task machine learning model. The vision-based robot task machine learning model can be, for example, a reinforcement learning (RL) neural network model (RL-network), such as an RL-network that represents a Q-function.

An autonomous system used for a production process includes a device configured to manipulate workpieces according to production process tasks. A device controller generates world model of the autonomous system to include data objects representing respective physical objects in the production process, such as workspace, workpieces, and the device. Semantic markers attached to the data objects include information related to a skill to accomplish a task objective. Semantic markers may be activated or deactivated depending on whether the physical object is currently available for a task performance. The device is controlled to perform tasks guided by the semantic markers while relying on an anticipation function with reasoning operations based on types of physical objects, types of skills, and configuration of the data objects.

A robot simulation device includes an image display unit configured to display a three-dimensional model of a robot system having a robot, a workpiece, and a peripheral device, as a pseudo three-dimensional object existing in a three-dimensional space, and a simulation execution unit configured to perform simulation operation for the three-dimensional model of the robot system displayed by the image display unit.

A trajectory planning apparatus including a joint axis classification unit for classifying a plurality of joint axes of a robot into axis groups, according to joint axis classification information for classifying into the axis groups including at least a path search axis group, a path search unit for searching for a path of an angle of the joint axis classified into the path search axis group that minimizes an evaluation function for evaluating a planed trajectory, based on trajectory start point information representing a posture of the robot at a start point of the planed trajectory and trajectory endpoint information representing a posture of the robot at an end point of the planned trajectory, and an axis group angle calculation unit for calculating an angle of the joint axis classified into each axis group other than the path search axis group during the search of the path.

A simulation device simulates a robot device including two two-dimensional cameras. The simulation device includes a setting point arrangement unit which arranges a plurality of setting points on a surface of a workpiece model, and a distance calculation unit which calculates distances from a three-dimensional sensor model to each of the setting points. The simulation device includes a three-dimensional information generating unit which generates three-dimensional information including positions of the setting points and distances from the three-dimensional sensor model to the setting points. The simulation device includes an exclusion unit which excludes the setting point that is not visible from the camera models. The simulation device changes a position and orientation of a robot model on the basis of the three-dimensional information.

A system for performing industrial tasks includes a robot and a computing device. The robot includes one or more sensors that collect data corresponding to the robot and an environment surrounding the robot. The computing device includes a user interface, a processor, and a memory. The memory includes instructions that, when executed by the processor, cause the processor to receive the collected data from the robot, generate a virtual recreation of the robot and the environment surrounding the robot, receive inputs from a human operator controlling the robot to demonstrate an industrial task. The system is configured to learn how to perform the industrial task based on the human operator's demonstration of the task, and perform, via the robot, the industrial task autonomously or semi-autonomously.

The present invention is to provide a robotic arm processing system, comprising: at least one robotic arm, at least one three-dimensional (3D) environment scanning device, and a processing device coupled between the robotic arm and the 3D environment scanning device. The robotic arm performs a processing procedure on at least one workpiece in a working area. The three-dimensional (3D) environment scanning device scans the working area to obtain 3D environment information of the working area. The processing device configures for generating a 3D model of the workpiece and a 3D model of the working area according to 3D environment information of the workpiece and the 3D environment information of the working area. Wherein the processing device generates a working path according to the 3D model of the workpiece and the 3D model of the working area and drives the robotic arm along the working path to perform a corresponding working procedure on the workpiece.