A control device includes a robot control section that controls a robot including a hand and a force detecting section; and a operation-mode switching section that switches, when storing a position and a posture of the robot, a first mode for moving the robot by the robot control section until an external force applied to the hand satisfies a predetermined condition and a second mode for moving the robot by the robot control section on the basis of an external force applied to a first part included in the robot.

A robot hand guide device includes a first connection flange configured to connect the robot hand guide device to a tool flange of a robot arm, a second connection flange configured to fasten a tool to be handled by the robot arm to the robot hand guide device, and a transfer apparatus configured to transfer forces and torques between the first connection flange and the second connection flange. A sensor device attached to the transfer apparatus is configured to detect forces and torques transferred via the transfer apparatus. The robot hand guide device further includes at least a first connection element connected to the first connection flange and configured for detachably connecting a guide handle of the robot hand guide device to the first connection flange.

Learning to effectively imitate human teleoperators, even in unseen, dynamic environments is a promising path to greater autonomy, enabling robots to steadily acquire complex skills from supervision. Various motion generation techniques are described herein that are rooted in contraction theory and sum-of-squares programming for learning a dynamical systems control policy in the form of a polynomial vector field from a given set of demonstrations. Notably, this vector field is provably optimal for the problem of minimizing imitation loss while providing certain continuous-time guarantees on the induced imitation behavior. Techniques herein generalize to new initial and goal poses of the robot and can adapt in real time to dynamic obstacles during execution, with convergence to teleoperator behavior within a well-defined safety tube.

A specifying data generating apparatus configured to generate specifying data for causing a robot to reproduce a motion of a target object including a generating unit configured to generate, based on manual data indicative of a motion of a target object manually operated, specifying data for specifying, in association with a time, a position and a posture of an end effector of a robot configured to imitate the motion of the target object, and a correcting unit configured, when a period during which a motion of the end effector operated according to the specifying data generated by the generating unit deviates from a predetermined tolerance has occurred, to correct, through extension in a time direction, the specifying data of at least the period during which there is the deviation from the tolerance.

A specifying data generating apparatus configured to generate specifying data for causing a robot to reproduce a motion of a target object including a generating unit configured to generate, based on manual data indicative of a motion of a target object manually operated, specifying data for specifying, in association with a time, a position and a posture of an end effector of a robot configured to imitate the motion of the target object, and a correcting unit configured, when a period during which a motion of the end effector operated according to the specifying data generated by the generating unit deviates from a predetermined tolerance has occurred, to correct, through extension in a time direction, the specifying data of at least the period during which there is the deviation from the tolerance.

A device for and method of operating a machine. The method includes providing a sequence of skills of the machine for executing a task, selecting a sequence of states from a plurality of sequences of states, depending on a likelihood, wherein the likelihood is determined depending on a transition probability from a final state of a first sub-sequence of states of the sequence of states for a first skill in the sequence of skills to an initial state of a second sub-sequence of states of the sequence of states for a second skill in the sequence of skills.

A setting-up arrangement and a method for setting up a mobile automaton includes at least the steps of a) coupling a movable element of the mobile automaton to a movable guide element of a guide device, b) exerting a force on the movable element via the movable guide element by operating the guide device, by which the movable element is moved in a guided manner along a predetermined movement profile via the guide element, c) acquiring a setup dataset characterizing the movement profile and, as a result, setting up the mobile automaton.

In accordance with one embodiment, an automated probe system includes a probe configured to be reversibly inserted into a live body part, a robotic arm attached to the probe and configured to manipulate the probe, a first sensor configured to track movement of the probe during an insertion and a reinsertion of the probe in the live body part, a second sensor configured to track movement of the live body part, and a controller configured to calculate an insertion path of the probe in the live body part based on the tracked movement of the probe during the insertion, and calculate a reinsertion path of the probe based on the calculated insertion path while compensating for the tracked movement of the live body part, and send control commands to the robotic arm to reinsert the probe in the live body part according to the calculated reinsertion path.

A 3D position and orientation calculation and robotic application structure using an inertial measuring unit and string—encoder positions sensors.

An industrial robot having a manipulator and a robot controller configured to control the motions of the manipulator. The robot controller is configured during lead-through programming of the robot to compare a robot position or a robot orientation (TCP) with at least one virtual position or virtual orientation defined in space, and to actively control the motions of the robot in relation to the at least one virtual position or virtual orientation when the difference between the robot position or robot orientation and the least one virtual position or virtual orientation is smaller than an offset value.