A teaching apparatus is provided with an arm-side position sensor attached to arms, a dummy wafer placed on a stage, a dummy-wafer-side position sensor attached to the dummy wafer, and a signal receiver configured to receive a position signal from the arm-side position sensor to determine a position coordinate of the arm-side position sensor, and receive a position signal from the dummy-wafer-side position sensor to determine a position coordinate of the dummy-wafer-side position sensor. A control part, based on the position coordinate of the dummy-wafer-side position sensor, calculates a position coordinate of the arm-side position sensor when the arms hold the wafer, and moves the arms such that the arm-side position sensor moves to the calculated position coordinate.

Examples of a method for teaching a transportation position includes correcting the position of an alignment jig having a plurality of sloping surfaces relative to a susceptor pin projecting upwards from an upper surface of a susceptor by lowering a robot hand to bring one of the sloping surfaces into contact with the susceptor pin and causing the susceptor pin to slide on the sloping surfaces by virtue of an own weight of the aliment jig, detecting a position of the alignment jig before and after the positional correction of the alignment jig, and correcting a movement destination information by an amount corresponding to a difference between an initial position and a corrected position of the alignment jig.

A teaching apparatus is provided with an arm-side position sensor attached to arms, a dummy wafer placed on a stage, a dummy-wafer-side position sensor attached to the dummy wafer, and a signal receiver configured to receive a position signal from the arm-side position sensor to determine a position coordinate of the arm-side position sensor, and receive a position signal from the dummy-wafer-side position sensor to determine a position coordinate of the dummy-wafer-side position sensor. A control part, based on the position coordinate of the dummy-wafer-side position sensor, calculates a position coordinate of the arm-side position sensor when the arms hold the wafer, and moves the arms such that the arm-side position sensor moves to the calculated position coordinate.

Examples of a method for teaching a transportation position includes correcting the position of an alignment jig having a plurality of sloping surfaces relative to a susceptor pin projecting upwards from an upper surface of a susceptor by lowering a robot hand to bring one of the sloping surfaces into contact with the susceptor pin and causing the susceptor pin to slide on the sloping surfaces by virtue of an own weight of the aliment jig, detecting a position of the alignment jig before and after the positional correction of the alignment jig, and correcting a movement destination information by an amount corresponding to a difference between an initial position and a corrected position of the alignment jig.

A numerical controller including an automatic display unit of a teach program includes a manual movement axis monitor unit for monitoring whether there is an axis moved by manual feed, a teach target program selection and determination unit for selecting and determining a teach program controlling the axis, and a teach block selection and determination unit for selecting and determining a teach point from a movement direction of the axis, and selecting and determining, as a teach block, a block in the teach program in which the teach point is an end point.

A machine learning apparatus that learns a condition associated with a gain of a magnetic flux controller and a time constant of a magnetic flux estimator in a motor control apparatus includes: a state observation unit that observes a state variable defined by at least one of data relating to an acceleration of a motor, data relating to a jerk of the motor, and data relating to an acceleration time of the motor; and a learning unit that learns the condition associated with the gain of the magnetic flux controller and the time constant of the magnetic flux estimator in accordance with a training data set defined by the state variable.

A machine learning apparatus that learns a condition associated with a gain of a magnetic flux controller and a time constant of a magnetic flux estimator in a motor control apparatus includes: a state observation unit that observes a state variable defined by at least one of data relating to an acceleration of a motor, data relating to a jerk of the motor, and data relating to an acceleration time of the motor; and a learning unit that learns the condition associated with the gain of the magnetic flux controller and the time constant of the magnetic flux estimator in accordance with a training data set defined by the state variable.