A control device includes a processor. The processor displays a first image of a robot, first input/output images representing a robot input/output, a second image of a peripheral device, second input/output images representing a device input/output, and an input/output edit screen accepting an input/output relationship between the robot output and a peripheral device input on a display. Each of the robot output and the peripheral device input causes the robot and the peripheral device to perform a synchronous operation or an asynchronous operation that is synchronously or asynchronously performed between the robot and the peripheral device, respectively. When one of the first input/output images corresponds to the synchronous operation, one of the second input/output images corresponds to only the synchronous operation. When another of the first input/output images corresponds to the asynchronous operation, another of the second input/output images corresponds to only the asynchronous operation.

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for integrating sensor streams for robotic demonstration learning. One of the methods includes selecting, by a learning system for a robot, a base update rate for combining multiple sensor streams into a task state representation. The learning system repeatedly generates the task state representation at the base update rate, including combining, during each time period defined by the update rate, the task state representation from most recently updated sensor data processed by the plurality of neural networks. The learning system repeatedly uses the task state representations to generate commands for the robot at the base update rate.

A method for controlling and/or monitoring a machine arrangement having at least one machine, in particular at least one robot, with the aid of a processor arrangement having a plurality of processors each with at least one core. The method includes selecting, in particular temporarily selecting, a first available and at least one further available core on the proviso that these cores are implemented, in particular arranged, on different processors of the processor arrangement, in particular during operation of the machine arrangement and/or on the basis of an updated directory and/or on the basis, in particular as a result, of an ascertained need for redundant processing of process signals; processing process signals redundantly with the aid of these selected cores; and controlling and/or monitoring the machine arrangement on the basis of this processing.

Proposed is a capturing apparatus. The capturing apparatus may include a setting unit configured to set environment information of a robot equipped with a camera; and a pattern unit configured to set a capturing pattern of the robot based on the environment information.

Method for determining a grasping hand model suitable for grasping an object by receiving an image including at least one object; obtaining an object model estimating a pose and shape of the object from the image of the object; selecting a grasp class from a set of grasp classes by means of a neural network, with a cross entropy loss, thus, obtaining a set of parameters defining a coarse grasping hand model; refining the coarse grasping hand model, by minimizing loss functions referring to the parameters of the hand model for obtaining an operable grasping hand model while minimizing the distance between the finger of the hand model and the surface of the object and preventing interpenetration; and obtaining a mesh of the hand represented by the enhanced set of parameters.

One embodiment can provide a robotic system. The system can include a machine-vision module, a robotic arm comprising an end-effector, a robotic controller configured to control movements of the robotic arm, and an error-compensation module configured to compensate for pose errors of the robotic arm by determining a controller-desired pose corresponding to a camera-instructed pose of the end-effector such that, when the robotic controller controls the movements of the robotic arm based on the controller-desired pose, the end-effector achieves, as observed by the machine-vision module, the camera-instructed pose. The error-compensation module can include a machine learning model configured to output an error matrix that correlates the camera-instructed pose to the controller-desired pose.

The present invention provides a method for robot action imitation learning in a three-dimensional space and a system thereof, relates to the technical fields of artificial intelligence and robots. A method based on a series-parallel multi-layer backpropagation (BP) neural network is designed for robot action imitation learning in a three-dimensional space, which applies an imitation learning mechanism to a robot learning system, under the framework of the imitation learning mechanism, to train and learn by transmitting demonstrative information generated from a mechanical arm to the series-parallel multi-layer BP neural network representing a motion strategy. The correspondence between a state characteristic matrix set of the motion and an action characteristic matrix set of the motion is learned, to reproduce the demonstrative action, and generalize the actions and behaviors, so that when facing different tasks, the method does not need to carry out action planning separately, thereby achieving high intelligence.

A method for redundant control in a distributed automation system, preferably a real-time automation system, for operating a client device of the distributed automation system is discussed. The method includes using the client device to monitor for the occurrence of a fault in communication between the client device and a first computing infrastructure that is part of the distributed automation system and operates the client device. The method may also include using the client device, once the fault occurs, to instruct a second computing infrastructure of the distributed automation system to operate the client device.

A computer-implemented method for performing few-shot imitation is disclosed. The method comprises obtaining at least one set of training data, wherein each set of training data is associated with a task and comprises (i) one of samples of rewards and a reward function, (ii) one of samples of state transitions and a transition distribution, and (iii) a set of first demonstrations, training a policy network embodied in an agent using reinforcement learning by inputting at least one set of first demonstrations of the at least one set of training data into the policy network, and by maximizing a risk measure or an average return over the at least one set of first demonstrations of the at least one set of training data based on respective one or more reward functions or respective samples of rewards, obtaining a set of second demonstrations associated with a new task, and inputting the set of second demonstrations and an observation of a state into the trained policy network for performing the new task.

A method for efficiently ascertaining output signals of a sequence of output signals with the aid of a sequence of layers of a machine learning system, in particular a neural network, from a sequence of input signals. The neural network is supplied in succession with the input signals of the sequence of input signals in a sequence of discrete time increments. At the discrete time increments, signals present in the network are in each case further propagated through a layer of the sequence of layers.