A tandem control system for a machine tool, according to the present invention, comprises: a numerical control unit; a main operation unit; a PLC which executes a control command via communication with the numerical control unit or the main operation unit; a servo drive which includes a notch filter unit and executes the control command from the PLC; a servo motor unit which is driven under the control of the servo drive; and a power conversion unit which is electrically connected to the servo motor unit and the servo drive so as to apply current to the servo motor unit, wherein the servo drive suppresses resonance due to the operation of the servo motor unit by controlling the application state of current transferred to the power conversion unit according to changes of notch &; filter coefficients calculated in real time at the notch filter unit.

A method and robot controller configured to obtain an inertia-vibration model of the robot arm. The inertia-vibration model defines a relationship between the inertia of the robot arm and the vibrational properties of said robot arm and have been by setting the robot arm in a plurality of different physical configurations and for each of said physical configurations of said robot arm obtaining the vibrational properties and the inertia the robot arm. The inertia-vibration model makes it possible to in a simple and efficient way to obtain the vibrational properties of different physical configurations of the robot arm whereby the robot arm can be controlled according to the vibrational properties of the robot arm. This makes it possible to reduce the vibrations of the robot arm during movement of the robot arm.

A method and a robot controller for controlling a robot arm, where the robot arm comprises a plurality of robot joints connecting a robot base and a robot tool flange, where each of the robot joints comprises an output flange movable in relation to a robot joint body and a joint motor configured to move the output flange in relation to the robot joint body. The robot arm is controlled based on vibrational properties of at least one external object connected to the robot arm, where the vibrational properties are received via an external object installation interface by generating control signals for said robot arm based on a target motion and the received vibrational properties of the at least one external object, the control signal comprises control parameters for said joint motor.

A control device includes a second-control-signal generating section configured to reduce a predetermined frequency component from a first control signal for performing operation for moving a movable section of the robot to generate a second control signal and a storing section having stored therein reference information including information concerning combinations of ranges of positions of a control point of the robot and frequencies. The second-control-signal generating section determines, based on a position of the control point of the robot in the operation, with reference to the reference information, a frequency component to be reduced from the first control signal.

A learning method for training an obfuscation network capable of obfuscating original data for privacy, including steps of: (a) inputting training data into the obfuscation network to filter frequency information of the training data and thus generate obfuscated data; and (b) (i) inputting the obfuscated data into a learning network to generate characteristic information by performing learning operation on the obfuscated data, (ii) generating at least one task loss by referring to (ii-1) the characteristic information and its corresponding ground truth or (ii-2) a task-specific output, generated by using the characteristic information, and its corresponding ground truth, and (iii) training at least one of the learning network and the obfuscation network through a backpropagation of the task loss.

A conveying apparatus that facilitates setting of an operation mode and setting of appropriate conditions during teaching is provided. An input determination section determines whether or not a combination of a conveyable weight and an operation mode input from an input portion is appropriate. A motor parameter determination section determines one or more motor parameters of at least one servoamplifier for one or more servomotors based on the operation mode and the conveyable weight determined as appropriate by the input determination section. The one or more motor parameters include a maximum speed and a maximum acceleration of the one or more servomotors. A parameter change section allows a speed and an acceleration of the one or more servomotors to be changed up to the maximum speed and the maximum acceleration, respectively.

An abnormality detection method for detecting an abnormality of an encoder provided for a robot includes: obtaining corrected position information according to commanded position information output from a controller that designates the rotational position of a motor and an output signal output from the encoder; and, determining, after comparing the corrected position information with the detected position information according to the output signal output from the encoder, the abnormality of the encoder, if there is a difference greater than or equal to a predetermined value between the corrected position information and the detected position information. The controller removes a vibration component of the robot corresponding to the weight of an attachment load from the commanded position information and compensates for a time delay to obtain the corrected position information.

A robot system includes: a learning control unit configured to perform learning for calculating a learning correction amount for bringing a position of a control target portion toward a target position; a robot control unit configured to control the operation of the robot mechanism unit; a power spectrum calculating unit configured to calculate a power spectrum of a vibration data of the control target portion; a comparison unit configured to compare each power spectrum between at the time of the current learning and at the time of the immediately preceding learning; and a learning correction amount updating unit configured to adjust at least one of a phase and a gain of the learning correction amount used at the time of the current learning to set the adjusted learning correction amount as a new learning correction amount used at the time of next learning.

A learning method for training an obfuscation network capable of obfuscating original data for privacy, including steps of: (a) inputting training data into the obfuscation network to filter frequency information of the training data and thus generate obfuscated data; and (b) (i) inputting the obfuscated data into a learning network to generate characteristic information by performing learning operation on the obfuscated data, (ii) generating at least one task loss by referring to (ii-1) the characteristic information and its corresponding ground truth or (ii-2) a task-specific output, generated by using the characteristic information, and its corresponding ground truth, and (iii) training at least one of the learning network and the obfuscation network through a backpropagation of the task loss.

A control device includes: a processor wherein the processor is configured to generate one or more second control signals obtained by reducing at least one frequency component from a first control signal, output one control signal among the first control signal and the one or more second control signals, receive an instruction indicating execution of a reduction in the frequency component, generate a driving signal for driving a robot based on the control signal output from the processor and output the driving signal, output the first control signal when a first condition including non-input of the instruction indicating the execution of the reduction in the frequency component is satisfied, and output the second control signal when a second condition including input of the instruction indicating the execution of the reduction in the frequency component is satisfied.