Robotic devices may be trained by a user guiding the robot along a target trajectory using a correction signal. A robotic device may comprise an adaptive controller configured to generate control commands based on one or more of the trainer input, sensory input, and/or performance measure. Training may comprise a plurality of trials. During an initial portion of a trial, the trainer may observe robot's operation and refrain from providing the training input to the robot. Upon observing a discrepancy between the target behavior and the actual behavior during the initial trial portion, the trainer may provide a teaching input (e.g., a correction signal) configured to affect robot's trajectory during subsequent trials. Upon completing a sufficient number of trials, the robot may be capable of navigating the trajectory in absence of the training input.

A machine tool includes an operation evaluation section that evaluates an operation thereof and a machine learning device that performs the machine learning of a movement amount of an axis thereof. The machine learning device calculates a reward based on state data including the output of the operation evaluation section, performs the machine learning of the determination of the movement amount of the axis, and determines the movement amount of the axis based on a machine learning result and outputs the determined movement amount. The machine learning device performs the machine learning of the determination of the movement amount of the axis based on the determined movement amount of the axis, the acquired state data, and the calculated reward.

A machine tool includes an operation evaluation section that evaluates an operation thereof and a machine learning device that performs the machine learning of a movement amount of an axis thereof. The machine learning device calculates a reward based on state data of the machine tool including output data from the operation evaluation section, performs the machine learning of the determination of the movement amount of the axis, and determines the movement amount of the axis based on a machine learning result and outputs the determined movement amount. The machine learning device performs the machine learning of the determination of the movement amount of the axis based on the determined movement amount of the axis, the acquired state data, and the calculated reward.

A numerical controller includes a machine learning device for performing machine learning of machining condition adjustment of a machine tool. The machine learning device calculates a reward based on acquired machining-state data on a workpiece, and determines an adjustment amount of machining condition based on a result of machine learning and machining-state data, and adjusts machining conditions based on the adjustment amount. Further, the machine learning of machining condition adjustment is performed based on the determined adjustment amount of machining condition, the machining-state data, and the reward.

Various aspects of methods, systems, and use cases include techniques for training or using a model to control a robot. A method may include identifying a set of action primitives applicable to a set of robots, receiving information corresponding to a task (e.g., a collaborative task), and determining at least one action primitive based on the received information. The method may include training a model to control operations of at least one robot of the set of robots using the received information and the at least one action primitive.

A machine learning device that learns an operation of a robot for picking up, by a hand unit, any of a plurality of workpieces placed in a random fashion, including a bulk-loaded state, includes a state variable observation unit that observes a state variable representing a state of the robot, including data output from a three-dimensional measuring device that obtains a three-dimensional map for each workpiece, an operation result obtaining unit that obtains a result of a picking operation of the robot for picking up the workpiece by the hand unit, and a learning unit that learns a manipulated variable including command data for commanding the robot to perform the picking operation of the workpiece, in association with the state variable of the robot and the result of the picking operation, upon receiving output from the state variable observation unit and output from the operation result obtaining unit.

A machining apparatus is provided with a machine learning device that performs machine learning. The machine learning device performs the machine learning by receiving the input of machining accuracy between a machining shape of a workpiece measured on-machine and design data on the workpiece and machining time of the workpiece measured by a measurement device. Based on a result of the machine learning, the machining apparatus changes machining conditions such that the machining accuracy increases and the machining time becomes as short as possible.

In variants, a method for industrial process control can include: determining an industrial system representation using a set of industrial system templates, wherein each template is associated with a control model and a set of attributes corresponding to control model features; determining associations between the attributes of the industrial system representation and data streams from the industrial system; and generating a set of control instructions for the industrial system based on the data streams associated with the attributes.

A computer-implemented method of determining actions for controlling a robot, in particular an assembly robot, includes (i) receiving a first and second input, wherein the first input is a sentence describing an action which should be carried out by the robot, wherein the second input is an image of a current state of an environment of the robot, (ii) feeding the first input into a first machine learning model and feeding the second input into a second machine learning model, wherein the first and second machine learning models are configured to determine tokens for their respective inputs, and (iv) feeding the tokens into a third machine learning model, wherein the third machine learning model outputs two outputs, wherein the first output is a switch for incorporating specialized skill networks and the second output are actions.

A simulation application container executes a simulation of a system in a simulation environment, through which an agent representing the system uses a reinforcement learning model to operate within the simulation environment. The simulation application container obtains data indicating how the agent performed in the simulation environment and transmits this data to a robot application container. The robot application container uses the data to update the reinforcement learning model and provides the updated reinforcement learning model to perform another iteration of the simulation and continue training the reinforcement learning model.