Abstract: A neural network machine learning method includes a first arrangement step of arranging a stationary first obstacle and a moving second obstacle in a virtual space, a second arrangement step of arranging a current position and a destination of a mobile robot in the virtual space, a movement step of making the second obstacle move in accordance with a predetermined condition, and a reception step of receiving, from a user, a designation of a moving path for the mobile robot to go to the destination from the current position while avoiding the stationary first obstacle and the moving second obstacle. Learning is performed using teaching data accumulated by repeatedly executing the above steps.

Abstract: Surface image data relating to an upper cover rubber is continuously and successively captured by a surface camera device and input to a computation device. Each piece of surface image data is stored in a database in association with data on the circumferential position of that surface image data on a conveyor belt and data on the time at which that surface image data was captured. An input unit is used to display any piece of surface image data on a monitor, register surface image data in which a predetermined defect is present on the surface of the upper cover rubber in the database as data to be monitored, and automatically register in the database surface image data having the same circumferential position data as the data to be monitored as related data to be monitored. Such monitoring system determines the state of damage of a cover rubber surface.

Abstract: A machine learning method includes: a first learning step which is performed in a phase before a neural network is installed in a mobile robot and in which a stationary first obstacle is placed in a set space and the first obstacle is placed at different positions using simulation so that the neural network repeatedly learns a path from a starting point to the destination which avoids the first obstacle; and a second learning step which is performed in a phase after the neural network is installed in the mobile robot and in which, when the mobile robot recognizes a second obstacle that operates around the mobile robot in a space where the mobile robot moves, the neural network repeatedly learns a path to the destination which avoids the second obstacle every time the mobile robot recognizes the second obstacle.

Abstract: The arithmetic device configured to perform a calculation for controlling a motion of a grasping apparatus that performs work involving a motion of sliding a grasped object includes: an acquisition unit configured to acquire a state variable indicating a state of the grasping apparatus during the work; a storage unit storing a learned neural network that has been learned by receiving a plurality of training data sets composed of a combination of the state variable acquired in advance and correct answer data corresponding to the state variable; an arithmetic unit configured to calculate a target value of each of various actuators related to the work of the grasping apparatus by inputting the state variable to the learned neural network read from the storage unit; and an output unit configured to output the target value of each of the various actuators to the grasping apparatus.

Abstract: An end point detection method is provided for detecting and end point based on a drive current supplied to a drive unit that rotates and drives one of a polishing table and a holding unit. The end point detection method includes: a step (S102) of determining whether a polishing condition of a polishing process to be executed coincides with a preset specific polishing condition; a step (S103) of adjusting a current control parameter in a drive control unit that controls the drive current, the current control parameter related to a change in the drive current with respect to a change in a driving load of the drive unit, if it is determined that the polishing condition coincides with the specific polishing condition; and a step (S105) of detecting the drive current supplied to the drive unit based on the adjusted current control parameter.

Abstract: An end point detection method is provided for detecting an end point based on a drive current supplied to a drive unit that rotates and drives one of a polishing table and a holding unit. The end point detection method includes: a step (S102) of determining whether a polishing condition of a polishing process to be executed coincides with a preset specific polishing condition; a step (S103) of adjusting a current control parameter in a drive control unit that controls the drive current, the current control parameter related to a change in the drive current with respect to a change in a driving load of the drive unit, if it is determined that the polishing condition coincides with the specific polishing condition; and a step (S105) of detecting the drive current supplied to the drive unit based on the adjusted current control parameter.

Abstract: A first and a second substrate polishing apparatus and are provided with a film thickness sensor for measuring a film thickness of layer to be polished and polish the layer by pressing the substrate against a polishing pad. The first substrate polishing apparatus outputs difference between output value of the film thickness sensor when an underlayer is exposed and output value of the film thickness sensor when the substrate is not present, as a first offset value. The second substrate polishing apparatus has a storage unit that stores information of the first offset value, an output correction unit that corrects the output value from the film thickness sensor based on the first offset value, and an end point detection unit that outputs control signal indicating end point of substrate polishing when measured value of the film thickness of the layer calculated based on the corrected output value reaches target value.

Abstract: In a scheme in which a top ring is held to an end portion of a swing arm, the present invention improves accuracy of polishing end point detection. A polishing apparatus for polishing between a polishing pad 10 and a semiconductor wafer 16 disposed opposed to the polishing pad 10 includes a polishing table 30A for holding the polishing pad 10 and a top ring 31A for holding the semiconductor wafer 16. A swing shaft motor 14 swings a swing arm 110 for holding the top ring 31A. The arm torque detection section 26 detects arm torque applied to the swing arm 110. An end point detection section 28 detects a polishing end point indicating an end of polishing based on the detected arm torque.

Abstract: A control apparatus of the motor according to one aspect includes: a first feedforward calculator configured to calculate a first motor output torque value so that a torque value indicated by a torque command signal can be generated in a joint part of a robot based on a model of a motor, a decelerator, or a link and the number of rotations of the motor, a second feedforward calculator configured to calculate a second motor output torque value based on the torque value indicated by the torque command signal without depending on the number of rotations of the motor; and a comparator configured to add the first motor output torque value, the second motor output torque value, and a third motor output torque value calculated based on the torque value detected by a sensor and the torque value indicated by the torque command signal.

Abstract: A polishing apparatus 100 includes a first electric motor 14 that rotationally drives a polishing table 12, and a second electric motor 22 that rotationally drives a top ring 20 that holds a semiconductor wafer 18. The polishing apparatus 100 includes: a current detection portion 24; an accumulation portion 110 that accumulates, for a prescribed interval, current values of three phases that are detected by the current detection portion 24; a difference portion 112 that determines a difference between a detected current value and the accumulated value, where the detected current value is detected in an interval that is different than the prescribed interval; and an endpoint detection portion 29 that detects a polishing endpoint that indicates the end of polishing of the surface of the semiconductor wafer 18, based on a change in the difference that the difference portion 112 outputs.

Abstract: The object of the present invention is to provide a small-sized metal detection sensor for detecting fine metal contaminants, using an electromagnetic induction detection technique. A metal detection sensor for 20 detecting metal 14 contained in an object under inspection moving through a passageway 18 comprises: magnets 24, 26 generating static magnetic field; and a coil 30 for detecting a magnetic field 28 generated by the metal 14. The magnets 24, 26 are located outside of the coil 30 along its axial direction, and the coil 30 is located outside of the magnets 24, 26 along the axial direction connecting the N poles and the S poles of the magnets 24, 26. The magnets 24, 26 are opposed to the coil 30.

Abstract: In a scheme in which a top ring is held to an end portion of a swing arm, the present invention improves accuracy of polishing end point detection. A polishing apparatus for polishing between a polishing pad 10 and a semiconductor wafer 16 disposed opposed to the polishing pad 10 includes a polishing table 30A for holding the polishing pad 10 and a top ring 31A for holding the semiconductor wafer 16. A swing shaft motor 14 swings a swing arm 110 for holding the top ring 31A. The arm torque detection section 26 detects arm torque applied to the swing arm 110. An end point detection section 28 detects a polishing end point indicating an end of polishing based on the detected arm torque.

Abstract: Surface image data relating to an upper cover rubber is continuously and successively captured by a surface camera device and input to a computation device. Each piece of surface image data is stored in a database in association with data on the circumferential position of that surface image data on a conveyor belt and data on the time at which that surface image data was captured. An input unit is used to display any piece of surface image data on a monitor, register surface image data in which a predetermined defect is present on the surface of the upper cover rubber in the database as data to be monitored, and automatically register in the database surface image data having the same circumferential position data as the data to be monitored as related data to be monitored. Such monitoring system determines the state of damage of a cover rubber surface.

Abstract: An eddy current detection device configured to form a stronger magnetic field in a polishing target and a polishing apparatus employing the same eddy current detection device are provided. An eddy current detection device that can be disposed near a semiconductor wafer on which a conductive film is formed includes a plurality of eddy current sensors. The plurality of eddy current sensors are disposed near to one another. Each of the plurality of eddy current sensors includes a pot core, an exciting coil disposed in the pot core and configured to form an eddy current in the conductive film, and a detection coil disposed in the pot core and configured to detect the eddy current formed in the conductive film.

Abstract: A control system according to an embodiment includes a motor configured to drive a link, a first sensor configured to detect information about the driving by the motor or information about a relation between the driving means and the load member as first sensor information, a second sensor configured to detect information about a displacement of the link as second sensor information, and a control unit configured to perform feedback control of the driving means so as to follow a command value in a two-inertial system model including an inertial system on a load side and an inertial system on a driving side. The control unit includes a disturbance observer configured to estimate a disturbance, and a filter configured to convert an estimated value of the disturbance into a driving force of the motor.

Abstract: A polishing apparatus of the present disclosure polishes a polishing target by pressing the polishing target against a polishing pad. An eddy current sensor measures an impedance that is changeable according to a change of a film thickness of the polishing target, at a plurality of positions of the polishing target, and outputs measurement signals. A difference calculator generates data corresponding to a film thickness based on a measurement signal. The difference calculator calculates a difference between data at different times based on measurement signals output by the eddy current sensor at different times at a center of the polishing target. An end point detector detects a polishing end point indicating the end of polishing based on the difference calculated by the difference calculator.

Abstract: A polishing apparatus 100 includes a first electric motor 14 that rotationally drives a polishing table 12, and a second electric motor 22 that rotationally drives a top ring 20 that holds a semiconductor wafer 18. The polishing apparatus 100 includes: a current detection portion 24; an accumulation portion 110 that accumulates, for a prescribed interval, current values of three phases that are detected by the current detection portion 24; a difference portion 112 that determines a difference between a detected current value in an interval that is different to the prescribed interval and the accumulated current value; and an endpoint detection portion 29 that detects a polishing endpoint that indicates the end of polishing of the surface of the semiconductor wafer 18, based on a change in the difference that the difference portion 112 outputs.

Abstract: A pneumatic fender monitoring system is provided. Image data captured by using at least one of a front view imaging device that successively images an external shape in a front view of a pneumatic fender used disposed between a vessel and a vessel or a side view imaging device that successively images the external shape in a side view of the pneumatic fender is successively input into a control unit and successively displayed on a monitor, and the control unit determines, on the basis of the image data, whether an amount of deformation of the external shape of the pneumatic fender is within a preset tolerance range or outside of a preset tolerance range.

Abstract: A conveyor belt monitoring system includes an imaging device which sequentially images a longitudinal predetermined range of a conveyor belt in running from above the conveyor belt. Image data captured by the imaging device is displayed in a monitor, and then is sequentially input into a control unit as detection data. The control unit causes a meander suppressing device to reduce a meander width of the conveyor belt on the basis of the image data.

Abstract: A motor control system includes a motor, a rotational angle sensor that detects a rotational angle of a motor shaft of the motor, a torque sensor that detects shaft torsion torque between the motor shaft, and an output shaft fixed to a load member driven by the motor, and a motor controller that controls the motor. The motor controller estimates a rotational angle of the output shaft, based on the rotational angle of the motor shaft, the shaft torsion torque, and torsional rigidity obtained in advance with respect to a region between the motor shaft and the output shaft, and controls the motor, using the estimated rotational angle of the output shaft.