A method for generating a control program for a laboratory automation device includes: receiving video data displaying a work area of a laboratory assistant, the work area containing a hand-held pipette and containers for receiving a liquid; detecting openings of the containers in the video data and determining positions of the openings; detecting a pipette tip of the hand-held pipette in the video data and determining a movement of the tip; and generating the control program for the laboratory automation device from the movement of the pipette tip with respect to the positions of the openings, wherein the control program is adapted for moving a pipetting arm with a robot pipette of the laboratory automation device with respect to containers of the laboratory automation device accordingly to the movement of the hand-held pipette in the work area.

A robot controller comprising a processor that is configured to execute computer-executable instructions so as to controls a robot including an arm capable of moving at least one of a target object and a discharger capable of discharging a discharge object to the target object, wherein the processor is configured to use a first position based on a jig removably attached to the discharger to generate teaching information on a position of the arm.

A robot controller comprising a processor that is configured to execute computer-executable instructions so as to controls a robot including an arm capable of moving at least one of a target object and a discharger capable of discharging a discharge object to the target object, wherein the processor is configured to use a first position based on a jig removably attached to the discharger to generate teaching information on a position of the arm.

A robotic system includes a base with a manipulator is attached to the base. At least one sensor is associated with the manipulator. The at least one sensor detects a trajectory of an external disturbance on the manipulator or an external cue from a user. A controller is provided that converts the trajectory detected by the at least one sensor to an input signal or the external cue detected by the at least one sensor to an input signal. A drive system receives the input signal, and in response to the input signal powers the base or to power the base in a trajectory corresponding to the external cue. A method for intuitive motion control of the robotic system is also provided.

A robotic system includes a base with a manipulator is attached to the base. At least one sensor is associated with the manipulator. The at least one sensor detects a trajectory of an external disturbance on the manipulator or an external cue from a user. A controller is provided that converts the trajectory detected by the at least one sensor to an input signal or the external cue detected by the at least one sensor to an input signal. A drive system receives the input signal, and in response to the input signal powers the base or to power the base in a trajectory corresponding to the external cue. A method for intuitive motion control of the robotic system is also provided.

The systems and methods provide an action recognition and analytics tool for use in manufacturing, health care services, shipping, retailing, restaurants and other similar contexts. Machine learning action recognition can be utilized to determine cycles, processes, actions, sequences, objects and or the like in one or more sensor streams. The sensor streams can include, but are not limited to, one or more video sensor frames, thermal sensor frames, infrared sensor frames, and or three-dimensional depth frames. The analytics tool can provide for establishing traceability.

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 robot system characterized by an elongate robot arm formed of multiple joint modules for selectively positioning an end effector carried by the arm's distal end and a computer based control system capable of being programmed by physical manipulation of the arm by a human operator.

A medical observation device includes an imaging unit configured to photograph an image of an operation site, and a holding unit configured to be connected with the imaging unit and have rotary shafts which are operable with at least six degrees of freedom. Among the rotary shafts, at least two shafts are active shafts whose driving is controlled based on states of the rotary shafts, and at least one shaft is a passive shaft which is rotated according to direct external manipulation accompanying contact.

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.