Fanuc Corporation

Preferred Networks, Inc.

Shun Suyama

Kazutaka Nakayama

Hiroshi Nakagawa

Daisuke Okanohara

Eiichi Matsumoto

Ryosuke Okuta

Hidetoshi Kumiya

Keigo Kawaai

Takumi Oyama

Takashi Yamazaki

Yuuki Kimoto

Shinya Chikara

Hangjie Jiang

Tsuneyoshi Nakashima

A drive mechanism of a transfer tool configured to drive a swing axis and tilts the workpiece includes: a motor; a speed reducer including an output shaft arranged in parallel to the swing axis and configured to reduce speed of rotation of the motor; and a link mechanism configured to couple the swing axis with the output shaft, in which the link mechanism includes a first link portion fixed to the output shaft at a middle portion in a length direction thereof; a second link portion fixed to the swing axis at a middle portion in a length direction thereof; a third link portion that couples one end portions of the first link portion and the second link portion with each other in a rotatable manner; and a fourth link portion that couples other end portions of the first link portion and the second link portion with each other in a rotatable manner, in which the first link portion and the second link portion are arranged in parallel to each other, and in which the third link portion and the fourth link portion are arranged in parallel to a line segment linking a central axis of the output shaft with a central axis of the swing axis.

Drive mechanism for transfer tool

A machine learning device that learns an operation of a robot for picking up, by a hand unit, any of a plurality of objects 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 object, an operation result obtaining unit that obtains a result of a picking operation of the robot for picking up the object 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 object, 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.

Machine learning device, robot system, and machine learning method for learning object picking operation

A lifetime estimation device for a robot including a linear-motion mechanism including a guide member and at least one slider moving along the guide member includes: a load calculation unit that calculates, at predetermined time intervals, a load acting on each slider on a basis of a program for operating the robot and geometric parameters of the robot and a load mounted on the robot; a travel-distance calculation unit that calculates travel distances of the slider at the time intervals; a lifetime calculation unit that calculates a lifetime of the linear-motion mechanism on a basis of the loads calculated by the load calculation unit and the travel distances calculated by the travel-distance calculation unit; and a display unit that displays the calculated lifetime.

Lifetime estimation device for robot

Provided is an arm fixing device that includes: a bracket having close-contact surfaces that are brought into close contact with a mounting surface provided in a supporting member, and a mounting surface provided in an arm or a link for transmitting drive force to an arm, also having one of a screw hole or a through hole that is formed to penetrate each of the close-contact surfaces at a position corresponding to a position of the other of a screw hole or a through hole provided in each of the mounting surfaces, and bridged over the mounting surfaces such that each of the close-contact surfaces is brought into close contact with a corresponding one of the mounting surfaces; and a fastener that penetrates the through hole and is fastened to the screw hole.

Arm fixing device and reducer replacement method

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.

Machine learning device, robot system, and machine learning method for learning workpiece picking operation

A transfer tool includes a substantially strip-shaped frame; a wrist-side slider provided on one side of the frame in a thickness direction in a manner capable of moving along a longitudinal direction of the frame; a workpiece-side slider provided on another side of the frame in the thickness direction in a manner capable of moving along the longitudinal direction; and a distal-end swing shaft attached to the workpiece-side slider. The shaft includes a support section supported by the workpiece-side slider in a manner capable of swinging around an axis line extending in a width direction of the frame and supporting a workpiece, and an actuator attached to the workpiece-side slider and causing the support section to swing. The actuator includes a motor, and a pair of gears that transmits driving force of the motor to the support section. At least one of the gears is formed into a fan shape.

Growing community of inventors

Yamanashi, Japan

Shun Suyama