A method, according to the present invention, of adjusting control parameters used in a control apparatus of an electric motor includes the steps of: computing a first frequency characteristic (Step 1); computing a present speed-proportional gain range (Step 2); computing a present mechanical-system characteristic constant (Step 3); computing a present proportional gain range (Step 4); computing a secular characteristic (Step 5); computing a secular speed-proportional gain range (Step 6); computing a secular proportional gain range (Step 7); and selecting proportional gain values (Step 8).

Provided are a controller and a machine learning device that perform machine learning to optimize the servo gain of a machine inside a facility in accordance with action conditions, action environments, and a priority factor of the machine. Disclosed is a control system including: a state observation section that observes machine information on a machine as state data; a determination data acquisition section that acquires information on machining by a machine as determination data; a reward calculation section that calculates a reward based on the determination data and reward conditions; a learning section that performs the machine learning of the adjustment of the servo gain of the machine; a decision making section that determines an action of adjustment of the servo gain of the machine, based on the state data and a machine learning result of the adjustment of the servo gain of the machine; and a gain changing section that changes the servo gain of the machine, based on the action of adjustment of the determined servo gain.

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.

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 control parameter tuning device for tuning a control parameter stored in a control system that controls a controlled object on the basis of a control parameter, includes a model updating module configured to update a controlled-object model that represents the controlled object when tuning a control parameter using data acquired when the controlled object operates; a first search module configured to repeatedly run simulations using the updated controlled-object model to search for a control parameter within a first range, and output a candidate for an optimal value for the control parameter; and a second search module configured to repeatedly operate the controlled object and search for a control parameter within a second range narrower than the first range and determined by the candidate output by the first search module and acquire operation results for the controlled object.

A servo control system for controlling a plurality of axes of a machine tool, comprises: a plurality of servo control units for controlling the plurality of axes, respectively; a plurality of learning control units that are provided one each in the plurality of servo control units, and each configured to control a cyclic operation highly precisely; a common learning memory for storing correction data which at least a portion of the plurality of learning control units generates; a memory allocation unit for allocating at least a portion of a memory area in the learning memory to the axis that the learning control unit that generated the correction data controls; and a memory amount notifying unit for notifying the memory allocation unit as to the amount of memory that each of the plurality of learning control units of the respective axes requires.

A computer-supported manufacturing method for manufacturing at least one workpiece according to a manufacturing order using a processing device and for removing the workpiece from the processing device using a removal device having multiple suction elements is provided. The method includes determining a suction element status for the multiple suction elements, determining suction elements among the multiple suction elements that are capable of being used to remove the workpiece based on a workpiece geometry of the workpiece to be removed, predicting a chance of removal success for the workpiece according to the suction element status of the suction elements that are capable of being used for removal, and carrying out the manufacturing order by the processing device upon predicting a successful removal of the workpiece by the removal device.

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.

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.