Provided is a teaching device including a grouping unit which divides machining points into machining point groups so that a machining head can sequentially machine each machining point for a machining time and so that a non-machining time can be minimized, a machining path determination unit which determines a machining path on which an in-group movement time of a robot is shortest for each machining point group, a teaching process adjustment unit which adjusts a machining order of the machining points and an operation order of the machining point groups so as to minimize a distance between groups and which optimizes the grouping so as to minimize a total movement time for completing machining, and a teaching data output unit which outputs, as teaching data, machining execution positions on the machining path obtained as a result of processing of the teaching process adjustment.

Apparatus and methods for training and operating of robotic devices. Robotic controller may comprise a predictor apparatus configured to generate motor control output. The predictor may be operable in accordance with a learning process based on a teaching signal comprising the control output. An adaptive controller block may provide control output that may be combined with the predicted control output. The predictor learning process may be configured to learn the combined control signal. Predictor training may comprise a plurality of trials. During initial trial, the control output may be capable of causing a robot to perform a task. During intermediate trials, individual contributions from the controller block and the predictor may be inadequate for the task. Upon learning, the control knowledge may be transferred to the predictor so as to enable task execution in absence of subsequent inputs from the controller. Control output and/or predictor output may comprise multi-channel signals.

Apparatus and methods for training and controlling of e.g., robotic devices. In one implementation, a robot may be utilized to perform a target task characterized by a target trajectory. The robot may be trained by a user using supervised learning. The user may interface to the robot, such as via a control apparatus configured to provide a teaching signal to the robot. The robot may comprise an adaptive controller comprising a neuron network, which may be configured to generate actuator control commands based on the user input and output of the learning process. During one or more learning trials, the controller may be trained to navigate a portion of the target trajectory. Individual trajectory portions may be trained during separate training trials. Some portions may be associated with robot executing complex actions and may require additional training trials and/or more dense training input compared to simpler trajectory actions.

A device and a method for controlling a robotic device, including a control model. The control model includes a robot trajectory model, which for the pickup includes a hidden semi-Markov model with one or multiple initial states, a precondition model, which for each initial state of the robot trajectory model includes a probability distribution of robot configurations before the pickup is carried out, and an object pickup model, which for a depth image outputs a plurality of pickup robot configurations having a respective associated probability of success.

A training system for a robot includes: a model having a transformer architecture and configured to determine how to actuate at least one of arms and an end effector of the robot; a training dataset including sets of demonstrations for the robot to perform training tasks, respectively; and a training module configured to: meta-train a policy of the model using first ones of the sets of demonstrations for first ones of the training tasks, respectively; and optimize the policy of the model using second ones of the sets of demonstrations for second ones of the training tasks, respectively, where the sets of demonstrations for the training tasks each include more than one demonstration and less than a first predetermined number of demonstrations.

Methods and apparatus related to training and/or utilizing a convolutional neural network to generate grasping parameters for an object. The grasping parameters can be used by a robot control system to enable the robot control system to position a robot grasping end effector to grasp the object. The trained convolutional neural network provides a direct regression from image data to grasping parameters. For example, the convolutional neural network may be trained to enable generation of grasping parameters in a single regression through the convolutional neural network. In some implementations, the grasping parameters may define at least: a “reference point” for positioning the grasping end effector for the grasp; and an orientation of the grasping end effector for the grasp.

A method for controlling a robotic device, in which a composite robot trajectory model made up of robot trajectory models of the movement skills is generated for a sequence plan for a task to be carried out by the robot including a sequence of movement skills and primitive actions to be carried out, and the robot is controlled, if after one movement skill according to the sequence plan one or multiple primitive action(s) is/are to be executed before the next movement skill, by interrupting the control of the robot according to the composite robot trajectory model after carrying out the movement skill, and by executing the one or multiple primitive action(s) and then resuming the control of the robot according to the composite robot trajectory model.

Deep machine learning methods and apparatus related to semantic robotic grasping are provided. Some implementations relate to training a training a grasp neural network, a semantic neural network, and a joint neural network of a semantic grasping model. In some of those implementations, the joint network is a deep neural network and can be trained based on both: grasp losses generated based on grasp predictions generated over a grasp neural network, and semantic losses generated based on semantic predictions generated over the semantic neural network. Some implementations are directed to utilization of the trained semantic grasping model to servo, or control, a grasping end effector of a robot to achieve a successful grasp of an object having desired semantic feature(s).

Methods, systems, and apparatus, including computer programs encoded on computer storage media, of training a global policy neural network. One of the methods includes initializing an instance of the robotic task for multiple local workers, generating a trajectory of state-action pairs by selecting actions to be performed by the robotic agent while performing the instance of the robotic task, optimizing a local policy controller on the trajectory, generating an optimized trajectory using the optimized local controller, and storing the optimized trajectory in a replay memory associated with the local worker. The method includes sampling, for multiple global workers, an optimized trajectory from one of one or more replay memories associated with the global worker, and training the replica of the global policy neural network maintained by the global worker on the sampled optimized trajectory to determine delta values for the parameters of the global policy neural network.

Systems and a method for predicting motion-outcome data of a robot moving between a given pair of robotic locations. Data on a given pair of robotic locations are received as input data. A function trained by a machine learning algorithm is applied to the input data, wherein a related robotic motion-outcome data is generated as output data. The robotic motion-outcome data is provided as output data.