This robot system includes a robot on which a driver bit for rotating a screw is mountable, and a robot controller that controls the robot. The robot controller gives a command to the robot to insert a teaching jig into a screw hole which is to be threaded with the screw in a state where the teaching jig is mounted instead of the driver bit, and determines a direction in which the driver bit is inserted by adjusting a direction in which the teaching jig is inserted so as not to cause a load due to interference between the teaching jig and the screw hole.

A surface of a workpiece has a smooth region, and a stepped region including a step. A three-dimensional object printing method includes first print operation of ejecting liquid from a head onto the smooth region, and second print operation, antecedent to or subsequent to the first print operation, of ejecting liquid from the head onto the stepped region. The amount of change in an angle of ejection, which is angle formed by a first normal line and a second normal line, during execution of the second print operation is larger than the amount of change in the angle of ejection during execution of the first print operation. The first normal line is a line normal to the ejection face. The second normal line is a line normal to the surface of the workpiece at a point of intersection with the first normal line.

A method of deriving autonomous control information involves receiving one or more sets of associated environment sensor information and device control instructions. Each set of associated environment sensor information and device control instructions includes environment sensor information representing an environment associated with an operator controllable device and associated device control instructions configured to cause the operator controllable device to simulate at least one action taken by at least one operator experiencing a representation of the environment generated from the environment sensor information. The method also involves deriving autonomous control information from the one or more sets of associated environment sensor information and device control instructions, the autonomous control information configured to facilitate generating autonomous device control signals from autonomous environment sensor information representing an environment associated with an autonomous device, the autonomous device control signals configured to cause the autonomous device to take at least one autonomous action.

A method of deriving autonomous control information involves receiving one or more sets of associated environment sensor information and device control instructions. Each set of associated environment sensor information and device control instructions includes environment sensor information representing an environment associated with an operator controllable device and associated device control instructions configured to cause the operator controllable device to simulate at least one action taken by at least one operator experiencing a representation of the environment generated from the environment sensor information. The method also involves deriving autonomous control information from the one or more sets of associated environment sensor information and device control instructions, the autonomous control information configured to facilitate generating autonomous device control signals from autonomous environment sensor information representing an environment associated with an autonomous device, the autonomous device control signals configured to cause the autonomous device to take at least one autonomous action.

An automated kitchen assistant system inspects a food preparation area in the kitchen environment using a novel sensor combination. The combination of sensors includes an Infrared (IR) camera that generates IR image data and at least one secondary sensor that generates secondary image data. The IR image data and secondary image data are processed to obtain combined image data. A trained convolutional neural network is employed to automatically compute an output based on the combined image data. The output includes information about the identity and the location of the food item. The output may further be utilized to command a robotic arm, kitchen worker, or otherwise assist in food preparation. Related methods are also described.

An automated kitchen assistant system inspects a food preparation area in the kitchen environment using a novel sensor combination. The combination of sensors includes an Infrared (IR) camera that generates IR image data and at least one secondary sensor that generates secondary image data. The IR image data and secondary image data are processed to obtain combined image data. A trained convolutional neural network is employed to automatically compute an output based on the combined image data. The output includes information about the identity and the location of the food item. The output may further be utilized to command a robotic arm, kitchen worker, or otherwise assist in food preparation. Related methods are also described.

A robot teaching system includes: a photographing unit that photographs an image including a welding target and a marker installed on an industrial robot; a camera coordinate system setting unit that sets a camera coordinate system on a basis of the marker included in the image; an operation path setting unit that sets an operation path of the industrial robot on a basis of a welding position of the welding target included in the image in the camera coordinate system; and a program generation unit that generates a working program, while converting the set operation path from the camera coordinate system into a robot coordinate system set in a robot control apparatus on a basis of a position of the marker installed on the industrial robot. The robot teaching system generates a working program allowing appropriate welding at a welding position.

A system that uses 3D scanning and a process agnostic pointing device that is used in conjunction with user input to create a robot program.

This patent defines a method for making robot programming more intuitive for tasks such as welding. The method further is an enhancement of manual guiding methods of robot positioning and can improve situations in which finer resolution or control of the robot end-effector is required. A motion sensor is mounted in series with the n−1 joint and in parallel with the n.sup.th joint, where n is the number of degrees of freedom or number of joints of the serial manipulator. The motion sensor is further mounted directly in-line with the n.sup.th joint and becomes part the opposing portion of the n.sup.th joint. The motion sensor further is uniquely adapted to apply to non-spherical wrist robots. The motion sensor senses input movements by a robot operator and controls the output tool motion in a controlled manner with resolution defined by user input at the motion sensor.

In one aspect, an example method includes (i) while a media playback device of a vehicle is playing back content received on a first channel, generating, by the media playback device, a query fingerprint using second content received on a second channel; (ii) sending, by the media playback device, the query fingerprint to a server that maintains a reference database containing a plurality of reference fingerprints; (iii) receiving, by the media playback device from the server, identifying information corresponding to a reference fingerprint of the plurality of reference fingerprints that matches the query fingerprint; and (iv) while the media playback device is playing back the first content received on the first channel, providing, by the media playback device for display, at least a portion of the identifying information.