A skill transfer mechanical apparatus includes an operating part, a controller, a motion information detector and an operation apparatus. The controller includes a basic motion instructing module, a learning module, a motion correcting instruction generator, a motion correcting instruction, and a motion information storing module. The learning module carries out machine learning of the motion correcting instruction stored in the motion correcting instruction storing module by using the motion information stored in the motion information storing module, and after the machine learning is finished, accepts an input of the motion information during the operation of the operating part, and outputs the automatic motion correcting instruction. The operating part moves the working part according to an automatic motion instruction based on the basic motion instruction and the automatic motion correcting instruction, and the manual motion correction.

A device for robotic direct lead-through teaching includes a robot, a replacing member and a lead-through teaching member. The robot has an operation member coupled with the replacing member. The lead-through teaching member mounted replaceably at the replacing member has a force sensor. The force sensor has six-axis load information. A path teaching is executed manually upon the operation member of the robot so as to store coordinate information. In additional, a method for robotic direct lead-through teaching is also provided.

Provided is a robot system including a robot including at least one sensor that detects an applied external force and a controller that controls the robot. The controller changes an operation mode of the robot when performing lead-through teaching in accordance with a position and a pattern of the external force detected by the sensor.

The present invention relates to a robotic system having at least one robotic arm, a control unit for controlling the robotic arm and a robotic arm sensor system, wherein the controller and robotic arm sensor system are designed to respond to predetermined haptic gestures of the user acting on the robotic arm in such a way that the robotic system performs at least one predetermined operation associated with the haptic gesture.

A robot and method for controlling an industrial robot, which has a first robot arm, a second robot arm, a joint defining a kinematic pair between the first and second robot arms, an actuator for generating relative movement between the first and second robot arms, and a robot controller for controlling the movements of the actuator. The method includes the steps of: determining a presence of a first torque indication at the actuator to be interpreted as a first command to the robot controller; repeatedly obtaining an external torque value (.sub.ext) to obtain an external torque behavior; comparing the external torque behavior with the first torque indication; and executing a robot function corresponding to the first command upon detecting that the external torque behavior corresponds to the first torque indication. The obtained external torque behavior depends on a reference torque value (.sub.ref) obtained from a dynamic model of the robot.

An industrial robot having high operability for a user is provided. An industrial robot includes a manipulator, a controller which controls an operation of the manipulator, and a detection device attached to the manipulator and detecting a gesture input. The controller executes a process corresponding to the detected gesture input.

Robotic devices may be trained by a trainer guiding the robot along a target trajectory using physical contact with the robot. The robot may comprise an adaptive controller configured to generate control commands based on one or more of the trainer input, sensory input, and/or performance measure. The trainer may observe task execution by the robot. Responsive to observing a discrepancy between the target behavior and the actual behavior, the trainer may provide a teaching input via a haptic action. The robot may execute the action based on a combination of the internal control signal produced by a learning process of the robot and the training input. The robot may infer the teaching input based on a comparison of a predicted state and actual state of the robot. The robot's learning process may be adjusted in accordance with the teaching input so as to reduce the discrepancy during a subsequent trial.

A method for automatically ascertaining an input command for a robot, wherein the input command is entered by manually exerting an external force onto the robot. The input command is ascertained on the basis of the joint force component attempting to cause a movement of the robot in only one robot joint coordinate sub-space which is specific to the input command. The joint forces are imprinted with the external force.

A document processing device including a touchscreen type operation panel and configured to be capable of communicating with a terminal device, a position of the terminal device being likely to move in accordance with operation by a user includes: a communication unit configured to transmit and receive a radio wave to and from the terminal device to perform communication; a communication intensity detection unit configured to detect communication intensity of the terminal device received at the communication unit; an operation information detection unit configured to detect operation information of input operation when the input operation for the operation panel is performed; and a data transfer amount control unit configured to control a data transfer amount in the communication between the terminal device and the communication unit based on the communication intensity detected by the communication intensity detection unit and the operation information detected by the operation information detection unit.

A robot and method for controlling an industrial robot, which has a first robot arm, a second robot arm, a joint defining a kinematic pair between the first and second robot arms, an actuator for generating relative movement between the first and second robot arms, and a robot controller for controlling the movements of the actuator. The method includes the steps of: determining a presence of a first torque indication at the actuator to be interpreted as a first command to the robot controller; repeatedly obtaining an external torque value (.sub.ext) to obtain an external torque behaviour; comparing the external torque behaviour with the first torque indication; and executing a robot function corresponding to the first command upon detecting that the external torque behaviour corresponds to the first torque indication. The obtained external torque behaviour depends on a reference torque value (.sub.ref) obtained from a dynamic model of the robot