A control device 1X mainly includes an operation sequence generation means 16X, a first robot control means 171X, a switching determination means 18X, and a second robot control means 172X. The operation sequence generation means 16X is configured to generate an operation sequence of a robot. The first robot control means 171X is configured to perform a first robot control that is a control of the robot based on the operation sequence. The switching determination means 18X is configured, during execution of the first robot control, to determine, based on the operation sequence, whether or not to switch to a second robot control, which is a control of the robot based on an external input. The second robot control means 172X is configured, if it is determined by the switching determination means 18X that the switching is required, to perform the second robot control.

A device and method for controlling a robotic device. The method includes: training a control model, which includes a parameter model and an object model, including: providing for each initial state-target state pair of a plurality of initial state-target state pairs a control state sequence, including states and transition states, each transition state being assigned a set of task parameters; ascertaining a set of state transition-state-state transition triples, and for each: adapting the parameter model so that the parameter model ascertains a probability distribution for each task parameter from the set of task parameters, which is assigned to the state transition following the state, adapting the object model so that the object model ascertains for each object a probability distribution for the state of the object; and controlling the robotic device with the control model using the trained parameter model and the trained object model.

The present invention relates to a user friendly method for programming a robot, where the method comprises placing the robot at a given position P0 in the surroundings and using a portion or point P of the robot (for instance the point to which a tool is attached during use of the robot) to define one or more geometrical features relative to the surroundings of the robot and establishing a relationship between the geometrical features and first coordinates of a robot-related coordinate system, whereby the robot can subsequently be instructed to carry out movements of specified portions of the robot relative to said surroundings by reference to said one or more geometrical features. By these means it becomes easy for users that are not experts in robot programming to program and use the robot. The geometrical features can according to the invention be stored in storage means and used subsequently also in other settings than the specific setting in which the programming took place.

Disclosed herein is a computing device that includes a memory and a processor. The memory stores processor executable for a robotic process engine. The robotic process engine accesses a distributed packaged robotic process to procure code and generate a local robotic process. The code includes parameters, while local robotic process includes input fields in accordance with the parameters. The robotic process engine receives input arguments via the input fields of the local robotic process to generate a configuration and executes the local robotic process utilizing the configuration. The execution of the local robotic process mirrors an execution of the distributed packaged robotic process without changing the distributed packaged robotic process.

A teaching method of teaching a position of a control point on a working route through which the control point set on a robot arm passes when the robot arm performs work and a posture of the robot arm using three-dimensional data of a working object, includes a first step of setting a predetermined first work point on the working route based on the three-dimensional data, and a second step of associating a first coordinate system set for the first work point with a second coordinate system set for the robot arm when the control point is located at the first work point, wherein, at the second step, one is selected from a plurality of candidates of the first coordinate system at the first work point, and the selected coordinate system is set as a first correction coordinate system for the first work point.

Robots, methods, and computer program products for training and operating (semi-) autonomous robots to complete multiple different work objectives are described. A robot accesses a library of reusable work primitives from a catalog of libraries of reusable work primitives, each reusable work primitive corresponding to a respective basic sub-task or sub-action that the robot is operative to autonomously perform. A work objective is analyzed to determine a sequence (i.e., a combination and/or permutation) of reusable work primitives that, when executed by the robot, will complete the work objective. The robot executes the sequence of reusable work primitives to complete the work objective. A robot can be deployed with an appropriate stored library (or access to an appropriate library) of reusable work primitives, based on what the robot is expected to do, or what service category or role the robot will operate in.

Robots, methods, and computer program products for training and operating (semi-) autonomous robots to complete multiple different work objectives are described. A robot accesses a library of reusable work primitives from a catalog of libraries of reusable work primitives, each reusable work primitive corresponding to a respective basic sub-task or sub-action that the robot is operative to autonomously perform. A work objective is analyzed to determine a sequence (i.e., a combination and/or permutation) of reusable work primitives that, when executed by the robot, will complete the work objective. The robot executes the sequence of reusable work primitives to complete the work objective. A robot can be deployed with an appropriate stored library (or access to an appropriate library) of reusable work primitives, based on what the robot is expected to do, or what service category or role the robot will operate in.

A system for selection and configuration of a robotic process includes a data input module to receive a stream of inputs relating to a user engaged in a task of interest, an input analysis module to analyze the stream of inputs and provide a series of timestamped actions and associated action parameters, and a component selection module to select a component of an AI solution for use in an automated robotic process, based on, at least in part, an action of the series of actions, the associated action parameters, or the components ability to simulate one or more of the actions in the series of actions.

A system control device includes: a first interface connected communicatively to a terminal device; a second interface connected communicatively to at least one robot controller controlling at least one robot; and a control unit. The control unit acquires job information generated based on input information. The job information is used for identifying a library in accordance with work to be executed by the robot and is capable of compensating for an undefined portion. The control unit outputs a work command to the at least one robot controller based on the job information.

A method for selection and configuration of an automated robotic process includes receiving a temporal biometric measurement of a worker performing a task, receiving a spatial-temporal environmental input provided to the worker, identifying a type of reasoning used when performing the task partially based on the temporal biometric measurement of the worker, selecting a component of an AI solution to replicate the type of reasoning, and configuring the component of the AI solution based on the spatial-temporal environmental input. The temporal biometric measurement includes a set of spatial-temporal imaging data of a brain of the worker and identifying the type of reasoning includes identifying a set of spatial-temporal neocortical activity patterns of the worker, identifying an active area of a neocortex of the worker; and selecting the component of the AI solution partially based on the identified active area of the neocortex.