A numerical control device for controlling a plurality of drive shafts to drive a tool and cause the tool to cut a workpiece while vibrating the tool in a fixed vibrating direction regardless of a cutting direction, a comparison unit that compares a command value of a cutting depth with an actual value of the cutting depth based on a vibration amplitude of the drive shaft when the vibrating direction and the cutting direction are not the same as each other, the cutting depth being a difference between a position of a face to be machined of the workpiece before machining and a position of the machined face after machining; and an adjustment unit that adjusts a movement of the tool so that the actual value becomes smaller when the actual value is larger than the command value.

A method performed by a risk management node for autonomous devices. The risk management node may determine state parameters from a representation of an environment. The representation of the environment may include an object, an autonomous device, and a set of safety zones. The risk management node may determine a reward value based on evaluating a risk of a hazard with the object based on the determined state parameters and current location and speed of the autonomous device relative to a safety zone from the set of safety zones. The risk management node may determine a control parameter based on the determined reward value, and may initiate sending the control parameter to the autonomous device to control action of the autonomous device. The control parameter may be dynamically adapted to reduce the risk of hazard with the object based on reinforcement learning feedback from the reward value.

Implementations utilize deep reinforcement learning to train a policy neural network that parameterizes a policy for determining a robotic action based on a current state. Some of those implementations collect experience data from multiple robots that operate simultaneously. Each robot generates instances of experience data during iterative performance of episodes that are each explorations of performing a task, and that are each guided based on the policy network and the current policy parameters for the policy network during the episode. The collected experience data is generated during the episodes and is used to train the policy network by iteratively updating policy parameters of the policy network based on a batch of collected experience data. Further, prior to performance of each of a plurality of episodes performed by the robots, the current updated policy parameters can be provided (or retrieved) for utilization in performance of the episode.

An NC device, which is a numerical control device, includes: a program analyzing unit that analyzes a machining program to obtain a movement path along which to move a supply position of a material on a workpiece; a storage temperature extracting unit that extracts, from data on surface temperature of the workpiece, storage temperature in an area including the movement path on the workpiece; a layering volume calculating unit that calculates a volume of a layer forming an object on the basis of a relation between the storage temperature and a volume of the material that solidifies at the storage temperature in a given time; and a layering shape changing unit that changes a shape of the layer on the basis of the volume of the layer.

A diagnostic device for monitoring the operation of a technical plant with an automation system, wherein the diagnostic device includes a data memory in which at least one data set characterizing the operation of the plant with values of process variables can be stored, and an evaluation device, where the diagnostic device is characterized in that the evaluation device is configured to determine a diagnostic statement about the operation of the technical plant based on the data set and at least one self-organizing map and based on a program for controlling a sequence during the operation of the technical plant with repeatedly traversed step sequences via a Dynamic Time Warping method.

Apparatus and methods for training and controlling of, for instance, robotic devices. In one implementation, a robot may be trained by a user using supervised learning. The user may be unable to control all degrees of freedom of the robot simultaneously. The user may interface to the robot via a control apparatus configured to select and operate a subset of the robot's complement of actuators. The robot may comprise an adaptive controller comprising a neuron network. The adaptive controller may be configured to generate actuator control commands based on the user input and output of the learning process. Training of the adaptive controller may comprise partial set training. The user may train the adaptive controller to operate first actuator subset. Subsequent to learning to operate the first subset, the adaptive controller may be trained to operate another subset of degrees of freedom based on user input via the control apparatus.

A robot control device includes: a trained model built by being trained on work data; a control data acquisition section which acquires control data of the robot based on data from the trained model; base trained models built for each of a plurality of simple operations by being trained on work data; an operation label storage section which stores operation labels corresponding to the base trained models; a base trained model combination information acquisition section which acquires combination information when the trained model is represented by a combination of a plurality of the base trained models, by acquiring a similarity between the trained model and the respective base trained models; and an information output section which outputs the operation label corresponding to each of the base trained models which represent the trained model.

A technique is provided for control of a nonlinear dynamical system to an arbitrary trajectory. The technique does not require any knowledge of the dynamical system, and thus is completely model-free. When applied to a chaotic system, it is capable of stabilizing unstable periodic orbits (UPOs) and unstable steady states (USSs), controlling orbits that require non-vanishing control signal, synchronization to other chaotic systems, and so on. It is based on a type of recurrent neural network (RNN) known as a reservoir computer (RC), which, as shown, is capable of directly learning how to control an unknown system. Precise control to a desired trajectory is obtained by iteratively adding layers to the controller, forming a deep recurrent neural network.

A process control method for manufacturing semiconductor devices, including determining a quality metric of a production semiconductor wafer by comparing production scatterometric spectra of a production structure of the production wafer with reference scatterometric spectra of a reference structure of reference semiconductor wafers, the production structure corresponding to the reference structure, the reference spectra linked by machine learning to a reference measurement value of the reference structure, determining a process control parameter value (PCPV) of a wafer processing step, the PCPV determined based on measurement of the production wafer and whose contribution to the PCPV is weighted with a first predefined weight based on the quality metric, and based on a measurement of a different wafer and whose contribution to the PCPV is weighted with a second predefined weight based on the quality metric, and controlling, with the PCPV, the processing step during fabrication.

Apparatus and methods for training and controlling of e.g., robotic devices. In one implementation, a robot may be utilized to perform a target task characterized by a target trajectory. The robot may be trained by a user using supervised learning. The user may interface to the robot, such as via a control apparatus configured to provide a teaching signal to the robot. The robot may comprise an adaptive controller comprising a neuron network, which may be configured to generate actuator control commands based on the user input and output of the learning process. During one or more learning trials, the controller may be trained to navigate a portion of the target trajectory. Individual trajectory portions may be trained during separate training trials. Some portions may be associated with robot executing complex actions and may require additional training trials and/or more dense training input compared to simpler trajectory actions.