A transfer system includes a first station at which a workpiece is placed, a second station which receives the workpiece from the first station, a robot including a holder for holding the workpiece and for transferring the workpiece from the first station to the second station, an image capturing unit for capturing an image of the workpiece that reflects a position of the workpiece in the first station, a first memory unit that stores intended placement position information indicating an intended placement position of the workpiece in the first station, and a deviation calculator that calculates a deviation of the position of the workpiece in the first station relative to the intended placement position. The deviation calculator calculates the deviation based on the image of the workpiece and the intended placement position information.

Device (100) for achieving a temporary connection between two objects (101,102) which are movable relative to each other, comprising respective connecting means (114,154), being brought together in order to jointly establish said connection, a movable robot (110), arranged to continuously displace the first connecting means relative to the first object, a control means (120), arranged to control the movements of the robot relative to the first object, as well as a sensor means (130), arranged to continuously read a relative position between the first connecting means and the second connecting means while the said objects move relative to each other. The invention is characterised in that the control means is arranged to, while the objects move relative to each other, continuously control the robot so that the first connecting means is displaced, relative to the first object and up to the second connecting means, and there connects to the second connecting means. The invention also relates to a method.

A machine learning device and a machine learning method are provided. A controller, which serves as the machine learning device and the machine learning method, is provided to perform machine learning of algorithms for arranging a flexible wire-like workpiece to a predetermined state using an industrial robot. In an embodiment, the machine learning device includes: an acquisition unit that acquires, as state variables, a state of the workpiece before arrangement starts and a state of the workpiece during arrangement; and a learning unit that performs machine learning of an algorithm for arranging the workpiece based on the state variables acquired by the acquisition unit.