A teaching method for detecting external force applied to a robot arm, driving the robot arm with force control based on the external force, and teaching a position and a posture of the robot arm, the teaching method including gradually relaxing, according to an elapsed time from when operation of the robot arm is started or a movement amount of the robot arm from when the operation of the robot arm is started, a restrictive condition for restricting the driving of the robot arm.

An apparatus for recording positions in a control program of a manipulator, which includes a manipulator, a controller having a control program, and a manual control device, wherein the controller can actuate the manipulator 10 in a compliance control, in which the manipulator is allowed to occupy an actual position different to the nominal position, wherein the controller, when recording the current position of the manipulator in the control program, carries over into the control program in a situation-based manner the nominal position, the actual position or a hybrid position comprising nominal and actual components of the current position. In addition, a corresponding method is also disclosed.

An industrial robot including a movable robot arm for supporting a tool, and a control unit configured to control the movement of the robot. The control unit is provided with an alignment function for aligning the tool with at least one specified axis. The control unit is configured to supervise the movement of the robot, and to automatically adjust the orientation of the tool so that the tool is aligned with the specified axis upon detecting that the movement of the robot has been stopped and the alignment function is activated. Also disclosed is a method for controlling the industrial robot, and to the use of the method for teaching a robot a path including a plurality of target points by lead-through programming.

A teaching method for detecting external force applied to a robot arm, driving the robot arm with force control based on the external force, and teaching a position and a posture of the robot arm, the teaching method including gradually relaxing, according to an elapsed time from when operation of the robot arm is started or a movement amount of the robot arm from when the operation of the robot arm is started, a restrictive condition for restricting the driving of the robot arm.

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.

In a workpiece loader device, a loader mechanism is configured to move a loader hand directly held by operator's hands to a desired position. A loader mechanism control part stores position coordinates as workpiece receiving position coordinates when the loader hand is moved by operator's hands to the workpiece receiving position and a completion of moving is confirmed.

An industrial robot including a movable robot arm for supporting a tool, and a control unit configured to control the movement of the robot. The control unit is provided with an alignment function for aligning the tool with at least one specified axis. The control unit is configured to supervise the movement of the robot, and to automatically adjust the orientation of the tool so that the tool is aligned with the specified axis upon detecting that the movement of the robot has been stopped and the alignment function is activated. Also disclosed is a method for controlling the industrial robot, and to the use of the method for teaching a robot a path including a plurality of target points by lead-through programming.

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.

In a workpiece loader device, a loader mechanism is configured to move a loader hand directly held by operator's hands to a desired position. A loader mechanism control part stores position coordinates as workpiece receiving position coordinates when the loader hand is moved by operator's hands to the workpiece receiving position and a completion of moving is confirmed.

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.