A robot system includes a robot, a teach pendant having an operator interface, and a robot controller with a computer and associated hardware and software containing a virtual representation of the robot and the environment. The system employs a method for avoiding collisions including moving a manipulator arm along an actual path in an environment containing objects constituting collision geometry. Operator input is entered into the teach pendant, whereby the operator is able to directly control motion of the robot along the actual path. A recent history of the motion of the robot is recorded, and a predicted path of the robot is developed based on the input entered into the teach pendant and the recent history of the motion of the robot. Real-time collision checking between the predicted path and the collision geometry is performed while the operator manually controls the robot using the teach pendant.

A method includes receiving sensor data for an environment about the robot. The sensor data is captured by one or more sensors of the robot. The method includes detecting one or more objects in the environment using the received sensor data. For each detected object, the method includes authoring an interaction behavior indicating a behavior that the robot is capable of performing with respect to the corresponding detected object. The method also includes augmenting a localization map of the environment to reflect the respective interaction behavior of each detected object.

A machine learning device, which learns shocks to a teaching device, includes a state observation unit which observes data based on an inclination of the teaching device or a present position of the teaching device; a label obtaining unit which obtains a label based on a shock received by the teaching device; and a learning unit which generates a learning model based on an output of the state observation unit and an output of the label obtaining unit.

A teach pendant includes an input unit and allowing teaching of operation of a robot by an input to the input unit, the teach pendant further includes a measurement reference surface which comes into surface contact with a measured surface of the robot, a tilt sensor whose position is fixed with respect to the measurement reference surface, and an output means which outputs a detection value of the tilt sensor to a control device of the robot in a state where the measurement reference surface is in surface contact with the measured surface and when a predetermined input operation is performed on the input unit or a contact detection sensor for detecting surface contact between the measurement reference surface and the measured surface detects the surface contact.

A method of handling safety of an industrial robot of a robot system, the method including providing at least one virtual safety border defined in relation to the industrial robot, where each virtual safety border is associated with a condition to be fulfilled by the industrial robot; for each virtual safety border, performing an indication operation by the robot system, where the indication operation indicates a position of the virtual safety border in a physical workspace of the industrial robot; and for each indication operation, receiving a verification input from a user. A control system and a robot system are also provided.

A control device includes a motion controller configured to control operation of a mechanical apparatus according to an operational command, a correction controller configured to correct the operation of the mechanical apparatus according to manipulational information outputted from a manipulating device, a memory part configured to store first operational information indicative of the operation of the mechanical apparatus, and correctional information indicative of the correction made by the correction controller, and a learning part configured to carry out machine learning using the first operational information and the correctional information corresponding to the first operational information. The motion controller controls the operation of the mechanical apparatus according to the operational command based on the command of the learning part, and the manipulating device outputs the manipulational information based on second operational information indicative of motion of the manipulating device.

A system and method for teaching a painting robot using wireless signals. The system includes a robot teaching assembly having a teaching tablet and a cradle to which the tablet is mounted, where the tablet includes a screen and a tablet Wi-Fi radio. The system also includes a robot controller assembly having a robot controller and a controller Wi-Fi radio, where the tablet radio and the controller radio are in wireless communication with each other to transmit signals to teach the robot. The cradle includes an emergency stop button for stopping the robot and an enable switch that must be closed to allow the robot to operate. The emergency stop button and enable switch are electrically coupled to the robot controller assembly by a safety signal cable. The cradle and the teaching tablet are not electrically coupled.

The invention relates to a hand-held operating device for operating an industrial robot, the device including a graphical operator interface having a touch-sensitive display for displaying at least one virtual operating element, which represents a function for operating the robot, and which can be operated by touching the operating element with a finger of an operating person or a pen, a control unit for controlling the graphical operator interface and for communicating with a robot controller, a haptic mark associated with at least one virtual operating element and designed as a guide, which haptic mark is arranged in a display frame; that surrounds the touch-sensitive display at least in some areas and/or is arranged in frame segments of the display frame and by means of which haptic mark the finger of an operating person or the pin can be guided in the direction of the at least one operating element.

A robotic navigation system includes a handheld navigation unit associated with a frame of reference. The handheld navigation unit is moveable with respect to a plurality of axes and is configured to send movement signals based on movement of the handheld navigation unit. A controller is configured to receive the movement signals from the handheld navigation unit and determine control signals for the robot. The control signals are configured to incrementally move the robot with respect to a point of interest removed from the robot. The point of interest is removed from a fixed point on the robot as defined by assigned coordinates. The controller is further configured to reassign the assigned coordinates following each incremental movement of the robot.

The present invention relates to a robot teach pendant unit (2) coupled to a programmable robot controller (1), the teach pendant comprising a graphical screen (6), and a native user interface program (9) which creates a graphical user interface and displays the user interface on the graphical screen. The robot teach pendant further comprises a processing component (10) capable of receiving an application including one or more animated graphical objects, instructions for displaying the animated objects on the graphical screen, information on the behavior of the animated graphical objects, and instructions on how the user can interact with the animated graphical objects, and the processing component is configured to display the animated graphical objects on the screen and to set up a sandbox providing an isolation mechanism for safely running the application without disturbing the execution of normal teach pendant operations, and said user interface program is programmed to host directly the processing component and instructing it to load and display the application containing the animated graphical objects.