A machine learning device, which detects an operator, communicates with a database registering information concerning the operator, and learns display of an operation menu based on the information concerning the operator, includes a state observation unit which observes an operation history of the operation menu; and a learning unit which learns the display of the operation menu on the basis of the operation history of the operation menu observed by the state observation unit.

A system for visual state identification including: a visual display system including a plurality of light displays, each of the light displays provided to different physical locations on an automation system; an execution device operatively connected to the visual display system, including: an input device configured to receive data from the automation system; and computer readable instructions which, if executed by a processor, cause the processor to: receive input data; determine the state of the automation system based on the input data, wherein the state may include an area of interest related to one of the different physical locations; communicate with the visual display system to selectively light a portion of one or more of the plurality of light displays to display the state of the automation system and the physical location of the area of interest.

A system and method comprising a noninvasive framework utilizing electroencephalography (EEG) to achieve the neural control of a robotic device for continuous random target tracking.

A machine learning device includes: a state observation unit that acquires a state vector sequence as a group of state vectors corresponding to a transition of operation screens responsive to a series of operations or change in a machine state; a training data acquisition unit that acquires training data containing input data and label data; and a learning unit that performs supervised machine learning using the training data to generate a learned model for predicting screen type data to be used next or on an occasion after the next by a user.

A machine learning device includes: a state observation unit that acquires a state vector sequence as a group of state vectors corresponding to a transition of operation screens responsive to a series of operations or change in a machine state; a training data acquisition unit that acquires training data containing input data and label data; and a learning unit that performs supervised machine learning using the training data to generate a learned model for predicting screen type data to be used next or on an occasion after the next by a user.

An operating system for a container handling machine, including an operating device for the container handling machine having a screen and a data transmitter for transmitting information and at least one separate additional screen having a data receiver for receiving information, with the operating device designed for selecting the information and the additional screen designed for displaying the selected information.

Provided is an input device of a machine tool and a machine tool that can eliminate the need for separately securing an installation location of a non-contact reader on a machine surface, thereby allowing for fewer restrictions in the machine configuration, machine structure, and machine design. Disclosed is an input device of a machine tool or machine tool that includes a non-contact reader therein. The input device includes an operation panel unit that includes: a substrate to which a key is mounted; a substrate mounting member that includes a key hole into which the key is to be inserted and disposed to be laminated on a front face side of the substrate; and a covering member that is disposed to be laminated on a front face side of the substrate mounting member so as to cover a surface of the substrate mounting member and the key, in which the non-contact reader is mounted on the substrate.

A robot off-line programming method. The method includes: respectively obtaining a first data representing positions and orientations of the plurality of targets on at least one work piece, a second data representing position of the at least one work piece, a third data representing geometry of a tool, and a fourth data representing the tool position and orientation with respect to an end of the robot; obtaining the robot path for which the tool tip passes through the plurality of the targets on the at least one work piece; using a function of an inverse kinematics for the robot model in consideration of the first data, the second data, the third data and the fourth data, calculating how many of the targets on the obtained robot path are reachable to the tool in relation to various rotation angle of the tool around the tool axis within a predetermined range so as to comply with optimization criteria. With the automatic calculation and intuitive preview, users could get to know directly about how many targets can be processed actually on a robot path. If the reachability is unsatisfied, the users could also have chances to modify the settings to obtain a more reasonable and precise path. An apparatus for implementing the method is also disclosed.

The invention relates to a smartwatch having a transmitter/receiver unit and a display unit, wherein the smartwatch is configured for receiving diagnosis notifications of a plurality of automation technology field devices by means of the transmitter/receiver unit, for analysing the received diagnosis notifications and classifying same in predefined device statuses, in particular in device statuses according to the NAMUR recommendation, as well as for displaying the classified device statuses of the field devices by means of the display unit. The invention also relates to a method for maintaining an automation technology system, in which a plurality of field devices are integrated, by means of a smartwatch according to the invention.

A method is, inter alia, disclosed, which comprises the following: obtaining and/or holding available production parameter information of a packaging system, wherein the production parameter information for one or a plurality of predefined production parameters of the packaging system in each case represents a course recorded for a predefined previous time period; determining at least for each of the predefined production parameters a respective course expected for a predefined future time period at least partially based on the production parameter information; displaying or causing to display a production parameter course view as part of a graphic user surface, wherein a first section of the production parameter course view graphically represents the courses of the predefined production parameters recorded for the predefined previous time period and wherein a second section of the production parameter course view following the first section graphically represents the courses of the predefined production parameters expected for the predefined future time period.