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.

A grasping error correction method includes a position information acquisition step of acquiring position information of a plurality of areas of a lower component 2, a grasping error value calculation step of calculating a grasping error value based on the position information at the time of the reproduction and the position information of the plurality of areas of the lower component 2 at the time of teaching, and an arm control step of controlling an operation of a multi-axis articulated arm 11a so as to correct the grasping error value. Further, in the grasping error value calculation step, the grasping error value is calculated so that a grasping error in a processing nearby area, which is one of the plurality of areas of the lower component 2 that is closest to the processing area, is preferentially eliminated over those in the other areas of the lower component 2.

An apparatus including a combination possibility calculation unit to calculate a stable orientation in which, from three-dimensional shape data of a part, the part is stabilized on a flat surface, to calculate a grasping method for grasping the part with a hand, and to calculate a combination in which the hand does not interfere from system configuration data including information on a connection destination of the hand and a combination group of the grasping method and the stable orientation; a regrasping path calculation unit to calculate a regrasping path of the part by using the calculated combination; a path group calculation unit to calculate a path having the minimum number of teaching points from the regrasping path as a path group based on orientation data for designating an input orientation and an alignment orientation of the part; and a program generation unit to generate a program of a robot based on the path group.

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.

A sortation system is disclosed that includes a programmable motion device including an end effector, a perception system for recognizing any of the identity, location, and orientation of an object presented in a plurality of objects, a grasp selection system for selecting a grasp location on the object, the grasp location being chosen to provide a secure grasp of the object by the end effector to permit the object to be moved from the plurality of objects to one of a plurality of destination locations, and a motion planning system for providing a motion path for the transport of the object when grasped by the end effector from the plurality of objects to the one of the plurality of destination locations, wherein the motion path is chosen to provide a path from the plurality of objects to the one of the plurality of destination locations.

A sortation system is disclosed for providing processing of homogenous and non-homogenous objects in both structured and cluttered environments. The sortation system includes a programmable motion device including an end effector, a perception system for recognizing any of the identity, location, and orientation of an object presented in a plurality of objects, a grasp selection system for selecting a grasp location on the object, the grasp location being chosen to provide a secure grasp of the object by the end effector to permit the object to be moved from the plurality of objects to one of a plurality of destination locations, and a motion planning system for providing a motion path for the transport of the object when grasped by the end effector from the plurality of objects to the one of the plurality of destination locations, wherein the motion path is chosen to provide a path from the plurality of objects to the one of the plurality of destination locations.

A grasp management system and corresponding methods are described. In some examples, information about a set of grasps of a robotic manipulator is accessed. The information is used by the robotic manipulator to attempt to grasp an item using the set of grasps associated with a first grasping orientation. An orientation of the robotic manipulator can be adjusted into a second grasping orientation and the robotic manipulator can attempt to grasp the item using the set of grasps associated with the second grasping orientation. Information about the attempts can be recorded and used to determine a richness measure that may represent a richness of the set of grasps for the item.

Provided is an article retrieval system including: a sensor that measures the states of articles stored in a storage container; an article detection part for detecting the articles on the basis of the states of the articles measured by the sensor; handling part for retrieving the articles or changing the positions and/or orientations of the articles detected by the article detection part; and a controller that controls the sensor, the article detection part, and the handling part. The controller includes: a space dividing part for dividing the space in which the articles exist according to the states of the articles measured by the sensor; and a switching part for switching at least one of a method of measurement with the sensor, a method of detection with the article detection part, and a method of retrieval with the handling part in each of the spaces divided by the space dividing part.

A measuring apparatus comprises an image sensor configured to image an object; and a processor configured to obtain information of a position, posture or both thereof of a first object, and a contact between the first object and a second object different from the first object based on an output of the image sensor, and perform evaluation of the information based on the contact.

A robot system includes workpiece phase detection units that detects a phase of a workpiece around an axis in a substantially vertical direction; a robot including a hand that holds the workpiece, and a wrist capable of rotating the hand around a rotation axis in the substantially vertical direction; and a control unit that controls the robot, wherein the control unit controls the robot based on the phase of the workpiece detected by the workpiece phase detection units, in such a way that the workpiece is held and picked by the hand in a reference phase, among a plurality of predetermined reference phases, closest to a current relative phase of the hand and the workpiece and the phase of the workpiece is aligned with a predetermined target phase by rotation of the wrist.