A method includes determining motion imitation information for causing a system to imitate a physical task using a first machine learning model that is trained using motion information that represents a performance of the physical task, determining a predicted correction based on the motion information and a current state from the system using a second machine learning model that is trained using the motion information, determining an action to be performed by the system based on the motion imitation information and the predicted correction; and controlling motion of the system in accordance with the action.

In order to be able to automatically eliminate discrepancies, arising in the course of the configuration of a robot-object system environment, between the reality of the robot-object system environment and its digital representation as a CAD model, without manual on-site commissioning of the robot-object system environment with adaptation of the CAD model to the reality, the following is proposed for configuring a robot-object system environment having at least one object and having a robot for object manipulation and object sensing: synchronizing a digital robot twin, which digitally represents the robot-object system environment and controls the robot for the object manipulation on the basis of a control program, for expedient use of the robot in the robot-object system environment during the object manipulation, appropriately and, in this regard, in one or two stages.

In one aspect, there is provided a computer-implemented method that includes receiving a request to generate workcell data representing physical dimensions of a workcell having a physical robot arm, executing a calibration program that causes the physical robot arm to move within the workcell and record locations within the workcell at which the robot arm made contact with an object, generating, from the locations within the workcell at which one or more sensors of the robot arm recorded a resistance above a threshold, a representation of physical boundaries in the workcell, obtaining an initial virtual representation of the workcell, and updating the initial virtual representation of the workcell according to the representation of physical boundaries generated from executing the calibration program.

A control device includes: a storage unit storing a work program of a robot; a display control unit displaying a virtual robot formed by virtualizing the robot and a teaching point in a simulator screen at a display unit, based on the work program stored in the storage unit; and an accepting unit accepting a selection of the teaching point displayed in the simulator screen. The display control unit displays, in the simulator screen, a first window including a first command corresponding to the selected teaching point, when the accepting unit accepts the selection of the teaching point.

Computerized engineering tool and methodology to develop neural skills for computerized autonomous systems, such as a robotics system (50), are provided. A disclosed computerized engineering tool (10) may involve an integrated arrangement of respective modular functionalities arranged in a closed loop, such as may include a physics engine (14), a neural data editor (16), an experiment editor (18), a neural skills editor (20), and a machine learning environment (22). Disclosed embodiments are conducive to cost-effectively simplifying development efforts involving neural skills, such as by reducing the time involved to develop the neural skills involved in any given robotics system and by reducing the level of expertise involved to develop neural skills.

A differentiable simulator for simulating the cutting of soft materials by a cutting instrument is provided. In accordance with one aspect of the disclosure, a method for simulating a cutting operation includes: receiving a mesh for an object, modifying the mesh to add virtual nodes associated with a predefined cutting plane, optimizing a set of parameters associated with a simulator based on ground-truth data, and running a simulation via the simulator to generate outputs that include trajectories associated with a cutting instrument. Optimizing the set of parameters can include performing inference based on a set of ground-truth trajectories captured using sensors to measure real-world cutting operations. The inference techniques can employ stochastic gradient descent, stochastic gradient Langevin dynamics, or a Bayesian approach. In an embodiment, the simulator can be utilized to generate control signals for a robot based on the simulated trajectories.

A switchgear or controlgear with unmanned operation and maintenance includes: an equipment safety system that includes a steering and control system for calculating a action radius of a robot system. An acting area in an internal space of the switchgear or controlgear is divided into virtual zones. Each action in each virtual zone is precalculated predictively as a micro simulation in which actual sensor data are considered before an intended action is triggered.

A method of evaluating safety of a robot includes a step of obtaining a three-dimensional image or three-dimensional model of a test robot comprising shape information of a real robot, a step of setting a movement time and movement path of the test robot by inputting profile information comprising movement time information and movement path information of the test robot, a step of calculating a collision pressure and collision force applied to a collision object in consideration of a shape, effective mass, movement speed, and direction of an injury-causing dangerous portion of the test robot, and a step of evaluating safety of the robot by determining whether magnitudes of the calculated collision pressure and collision force fall within magnitudes of a predetermined maximum collision pressure and predetermined maximum collision force.

Methods and systems according to one or more examples are provided for testing an automated platform, such as a robot. In one example, a system comprises a first robot configured to perform one or more processing operations on a workpiece. The system further comprises a second robot configured to simulate one or more parameters of the workpiece and an associated processing operation to provide one or more test conditions corresponding to each of the one or more processing operations the first robot would perform on the workpiece to test the first robot.

A robotic programming apparatus, while using a robot equipped with a spraying device to move the spraying device, for creating an operation program of an application operation for applying a sprayed material sprayed from a nozzle of a spraying device to a member, that includes an operation pattern storage section configured to store a plurality of types of operation patterns each indicating operation of the spraying device that are operation patterns each formed of a continuous trajectory including periodic iteration of a constant pattern, and a pitch interval determination section configured to determine, for one operation pattern of the plurality of types of operation patterns stored in the operation pattern storage section, a pitch interval of the periodic iteration of the constant pattern in the one operation pattern based on a spray parameter representing a spray characteristic of the sprayed material by the nozzle of the spraying device.