Disclosed techniques for decreasing teach times of robot systems may obtain a first set of parameters of a first trained robot-control model of a first robot trained to perform a task and determine, based on the first set of parameters, a second set of parameters of a second robot-control model of a second robot before the second robot is trained to perform the task. In some cases, a plurality of sets of parameters from trained robot-control models of respective robots trained to perform a task may be obtained. Thus, for example, a convergence of values of those parameters on a value, or range of potential values, may be determined. Embodiments may determine values for parameters of the control model of the (e.g., second) robot to be trained within a range, or a threshold, based on values of corresponding parameters of the trained robot(s).

A system for trajectories imitation for robotic manipulators is provided. The system includes an interface configured to receive a plurality of task descriptions, wherein the interface is configured to communicate with a real-world robot, a memory to store computer-executable programs including a robot simulator, a training module and a transfer module, and a processor, in connection with the memory. The processor is configured to perform training using the training module, for the task descriptions on the robot simulator, to produce a plurality of source policy with subgoals for the task descriptions. The processor performs training using the training module, for the task descriptions on the real-world robot, to produce a plurality of target policy with subgoals for the task descriptions, and update the parameters of the transfer module from corresponding trajectories with the subgoals for the robot simulator and real-world robot.

Systems and methods for intelligent tool detection are described. One embodiment includes placing a tool in a tool tray, and detecting a presence of the tool. Information associated with the presence of the tool is communicated to a processing system communicatively coupled to the tool tray. The tool is removed from the tool tray, and the removal is detected. Communication associated with the removal of the tool is communicated to the processing system. A distinction between information associated with the tool being present in the tool tray and information associated with the tool being removed from the tool tray is learned.

A machine learning device includes a state observation unit for observing, as state variables, an image of a workpiece captured by a vision sensor, and a movement amount of an arm end portion from an arbitrary position, the movement amount being calculated so as to bring the image close to a target image; a determination data retrieval unit for retrieving the target image as determination data; and a learning unit for learning the movement amount to move the arm end portion or the workpiece from the arbitrary position to a target position. The target position is a position in which the vision sensor and the workpiece have a predetermined relative positional relationship. The target image is an image of the workpiece captured by the vision sensor when the arm end portion or the workpiece is disposed in the target position.

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.

A robot device (10) acquires object information related to an object to be gripped by the robot device including a grip unit (32) that grips an object. The robot device (10) then determines, based on operation contents executed by the robot device with the object gripped and the object information, a constraint condition when the operation contents are executed.

A method for optimizing autonomous driving includes applying different autonomous driving parameters to a plurality of robot agents in a simulation through an automatic setting by means of the system or a direct setting by means of a manager, so that the robot agents learn robot autonomous driving; and optimizing the autonomous driving parameters by using preference data for the autonomous driving parameters.

A robot that includes an RL agent that is configured to learn a policy to maximize the cumulative reward of a task, to determine one or more features that are minimally correlated with each other. The features are then used as pseudo-rewards, called feature rewards, where each feature reward corresponds to an option policy, or skill, the RL agent learns to maximize. In an example, the RL agent is configured to select the most relevant features to learn respective option policies from. The RL agent is configured to, for each of the selected features, learn the respective option policy that maximizes the respective feature reward. Using the learned option policies, the RL agent is configured to learn a new (second) policy for a new (second) task that can choose from any of the learned option policies or actions available to the RL agent.

The invention relates to a field off artificial intelligence (AI) technologies, and discloses a method and an apparatus for high-order iterative self-learning control for a robotic fish, and a storage medium; the control method performs preferential iterative calculation on control gain elements in the control gain set to obtain a target control gain set; and performs high-order iterative calculation according to the target control gains, the first control input thrust and the first tracking error to obtain a target control input thrust, and then controls a robotic fish to swing according to the target control input thrust to obtain an expected speed. In this way, complete tracking and rapid convergence of a swim speed of a robotic fish in the whole operation space may be achieved.

Methods, systems, apparatus and computer program products for implementing machine learning within control systems are disclosed. An industrial facility setting slate can be received from a machine learning system and a determination can be made as to whether to adopt the settings in the industrial facility setting slate. The machine learning model can be a neural network, e.g., a deep neural network, that has been trained, e.g., using reinforcement learning to predict a data setting slate that is predicted to optimize an efficiency of a data center.