The invention relates to a method for handling products (17) using an automation system and to an automation system (10), the products being captured by means of an imaging sensor (18) of a control device (12) of the automation system and being handled by means of a handling mechanism (13) of a handling device (11) of the automation system, the control device processing sensor image data from the imaging sensor and controlling the handling device as specified by training data sets contained in a data memory (21) of the control device, the training data sets comprising training image data and/or geometric data and control instructions associated therewith, the training data sets being generated, as a statistical model, exclusively from geometric data contained in the training image data of products, by means of a computer using a computer program product executed thereon, the training data sets being transmitted to the control device.

The purpose of the present invention is to provide a workpiece unloading device that can stabilize cycle time even when work for reversing a workpiece is involved. A workpiece unloading system comprises a workpiece unloading device for unloading a workpiece, and a control device for setting workpiece unloading order. The control device comprises: a storage unit that stores a set posture representing a posture of a workpiece when the workpiece is set on a jig; a current posture detection unit that detects a current posture representing the current posture of the workpiece; a change amount calculation unit that calculates a change amount between the set posture and the current posture; an unloading candidate identification unit that compares the change amount with a threshold value, and identifies, on the basis of the comparison result, a workpiece as an unloading candidate with priority; and an unload instruction unit that outputs, to the workpiece unloading device, a first instruction to unload the workpiece as the unloading candidate with priority.

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for controlling an agent interacting with an environment to perform a task. In one aspect, one of the methods comprises receiving an observation; processing the observation using an a recurrent encoder neural network configured to receive as input the observation and to generate as output an encoder representation of the observation that comprises a respective feature vector for each of a plurality of spatially distinct portions of the observation, wherein each respective feature vector has a plurality of dimensions; for each of a plurality of subschema recurrent neural networks: generating a respective attention weight for each of the plurality of dimensions, generating an attended encoder representation, and updating the subschema hidden state using at least the attended encoder representation; and selecting an action using the updated subschema hidden states of the plurality of subschema recurrent neural networks.

A prewashing system includes a dish recognizing unit that recognizes a dish that is an object of prewashing executed prior to main washing, a first prewashing unit that performs prewashing of the dish that is the object of prewashing by a flow of water, a second prewashing unit that performs prewashing of the dish that is the object of prewashing by a washing tool, a prewashing method deciding unit that decides a prewashing method using at least one of the first prewashing unit and the second prewashing unit, on the basis of a form of the dish that is the object of prewashing, which is recognized by the dish recognizing unit, and a prewashing executing unit that executes prewashing of the dish that is the object of prewashing, by the prewashing method decided by the prewashing method deciding unit.

A learning device and other techniques allow accurate diagnosis of a production facility. A learning device (10) includes a data acquirer that acquires data for learning, and a model generator that generates a learning model for inferring a condition of a workpiece (3) handled in a production facility (2) on the basis of the data for learning. The data for learning includes setting data indicating a setting of the production facility (2), image data indicating an image of the production facility (2) captured by a camera (4), temperature data indicating a surface temperature of the production facility (2) measured by a temperature sensor (5), distance data indicating a distance from a range sensor (6) to the production facility (2) measured by the range sensor (6), and condition data indicating the condition of the workpiece (3) handled in the production facility (2).

According to one embodiment, a picking system includes a picking robot and a control device. The picking robot transfers an object from a first space to a second space by using a robot hand. The control device controls the picking robot. When a first measurement result related to a shape of the object in the first space when viewed along a first direction is acquired, the control device performs a first calculation of calculating a position candidate for placing the object in the second space based on the first measurement result. When a second measurement result related to a shape of the object when viewed along a second direction is acquired, the control device performs a second calculation of calculating a position of the robot hand when placing the object in the second space based on the second measurement result and the position candidate.

Method for controlling the operation of an industrial robot configured in particular to carry out pick-and-place or singulation tasks.

A robot system is provided with a three-dimensional sensor which acquires three-dimensional information of an object, and a robot which includes a gripping device for gripping an object. The robot system uses first three-dimensional information which relates to a state before an object is taken out and second three-dimensional information which relates to a state after an object is taken out as the basis to acquire three-dimensional shape information of an object, and uses the three-dimensional shape information of the object as the basis to calculate a position and posture of the robot when an object is placed at a target site.

A method can include: receiving imaging data; identifying containers using an object detector; scheduling insertion based on the identified containers; and optionally performing an action based on a scheduled insertion. However, the method can additionally or alternatively include any other suitable elements. The method functions to schedule insertion for a robotic system (e.g., ingredient insertion of a robotic foodstuff assembly module). Additionally or alternatively, the method can function to facilitate execution of a dynamic insertion strategy; and/or facilitate independent operation of a plurality of robotic assembly modules along a conveyor line.

The present invention relates to a robot teaching system based on image segmentation and surface electromyography and robot teaching method thereof, comprising a RGB-D camera, a surface electromyography sensor, a robot and a computer, wherein the RGB-D camera collects video information of robot teaching scenes and sends to the computer; the surface electromyography sensor acquires surface electromyography signals and inertial acceleration signals of the robot teacher, and sends to the computer; the computer recognizes a articulated arm and a human joint, detects a contact position between the articulated arm and the human joint, and further calculates strength and direction of forces rendered from a human contact position after the human joint contacts the articulated arm, and sends a signal controlling the contacted articulated arm to move along with such a strength and direction of forces and robot teaching is done.