Training and/or using a recurrent neural network model for visual servoing of an end effector of a robot. In visual servoing, the model can be utilized to generate, at each of a plurality of time steps, an action prediction that represents a prediction of how the end effector should be moved to cause the end effector to move toward a target object. The model can be viewpoint invariant in that it can be utilized across a variety of robots having vision components at a variety of viewpoints and/or can be utilized for a single robot even when a viewpoint, of a vision component of the robot, is drastically altered. Moreover, the model can be trained based on a large quantity of simulated data that is based on simulator(s) performing simulated episode(s) in view of the model. One or more portions of the model can be further trained based on a relatively smaller quantity of real training data.

A computer-implemented method for quality inspection of a component of a manufacturing device includes obtaining operational data relating to operation of the manufacturing device. The operational data includes a time series of one or more physical properties of the manufacturing device. Status data relating to a component of the manufacturing device is obtained. The status data includes events relating to and/or characteristic properties relevant for utilization of the component within the manufacturing device. The computer-implemented method includes labelling one or more subsets of the operational data by associating one or more of the events and/or characteristic properties to the one or more subsets and providing the one or more subsets as labelled training data for training a machine learning model. The machine learning model serves for outputting a quality indicator based on the labelled training data input. The trained machine learning model is provided for quality inspection.

A robotic system is disclosed. The system includes a memory that stores a machine learning-based model to provide a scoring function value for a candidate item placement on a pallet on which are plurality of items are to be stacked given a current state value of the pallet and a set of zero or more items placed previously. The system includes one or more processors that use the model to determine a corresponding score for each of a plurality of candidate placements for a next item to be placed and the current state value associated with the current state of the pallet and a set of zero or more items placed previously, select a selected placement based at least in part on the respective scores, control a robotic arm to place the next item according to the selected placement.

According to an aspect, there is provided an apparatus comprising at least one processor and at least one memory connected to the at least one processor. The at least one memory stores program instructions that, when executed by the at least one processor, cause the apparatus to determine based on at least one indicator that a camera connected to the apparatus is in a dark environment, initiate a calibration sequence of the camera in response to determining based on the at least one indicator that the camera connected to the apparatus is in a dark environment, capture, during the calibration sequence, multiple images with the camera with different sets of shooting parameters, cause analysis of the captured images to obtain camera calibration data, and store the camera calibration data in a memory of the apparatus.

A nonverbal information generation apparatus includes a nonverbal information generation unit that generates nonverbal information that corresponds to feature quantities of voice or text on the basis of the feature quantities and a learned nonverbal information general model. The nonverbal information is information for controlling an expression unit that expresses behavior so that at least one of the number of times that the behavior is performed and the magnitude of the behavior correspond to the feature quantities.

A workpiece data processing method and apparatus are for accurately determining a relationship between production equipment processing parameters/ambient condition data and workpiece quality inspection results. A workpiece data method includes acquiring processing condition data, a quality attribute value and quality inspection result data of each of multiple workpieces processed by a piece of production equipment, the processing condition data of one workpiece including a processing parameter used by the production equipment when processing the workpiece and ambient condition data of the production equipment when processing the workpiece; determining a first relationship between the quality attribute value of the workpiece processed by the production equipment and the ambient condition data of the production equipment when processing the workpiece and the processing parameter of the production equipment; and determining a second relationship between the quality inspection result data and quality attribute value of the workpiece processed by the production equipment.

A positioning control device includes a position-command generation unit to generate a position command by which a shape of an acceleration in an accelerating section and a decelerating section is determined on the basis of a position command parameter, a drive control unit to drive a motor such that a detected position value of the motor or a control target follows the position command, an evaluation unit to calculate an evaluation value regarding positioning performance on the basis of a detected position value of the motor or the control target during execution of positioning control on the control target, and a learning unit to obtain a learning result by learning a relation between the position command parameter and the evaluation value when positioning control is executed plural times, while changing each of shapes of an acceleration in an accelerating section and a decelerating section independently.

A procedure to train an online scheduling system using Reinforcement Learning agents to process any kind of product variant and any kind of machine configuration is disclosed. The novel approach of scheduling jobs or products in a flexible manufacturing system is to train Deep Reinforcement Learning agents with generated training data. One agent may represent a product and may autonomously guide the product through the manufacturing system, including decisions regarding resource allocations (which module should process which operation) and transport decisions. Dependent on the mode to be trained, the identical job-specification for same, job-specifications from the same cluster for similar, and job-specifications from different clusters for different are chosen. This solution may handle any product variant to be produced within the considered system.

A computing device, including: a memory configured to store computer-readable instructions; and processing circuitry configured to execute the computer-readable instructions to cause the computing device to: generate an environmental condition model (ECM) based on collected environmental attribute data of a physical environment; deploy the ECM to estimate environmental risk for an autonomous agent based on the environmental attribute data and a position of the autonomous agent within the physical environment; and transmit information related to the estimated environmental risk to the autonomous agent to adapt its operation to reduce operational risk.

A control device of a wire electric discharge machine and a machine learning device are provided that can appropriately and readily determine a correction parameter. The control device, which optimizes the correction parameter for wire electrical discharge machining process, includes a machine learning device configured to learn the correction parameter for the wire electrical discharge machining process. The machine learning device includes a state observation unit configured to observe, as a state variable, condition data indicative of a condition for the wire electrical discharge machining process, a determination data acquisition unit configured to acquire determination data indicative of the correction parameter of the case where machining precision is favorable in the wire electrical discharge machining process, and a learning unit configured to learn the correction parameter in association with the condition for the wire electrical discharge machining process using the state variable and the determination data.