An artificial intelligence device is disclosed. In an embodiment, the artificial intelligence device includes a sensor configured to acquire an output value according to control of a control system, and an artificial intelligence unit comprising one or more processors configured to obtain one or more updated parameters of a control function of the control system based on the output value using reinforcement learning, and update the control function for providing a control value to the control system with the one or more updated parameters.

Methods, apparatuses, and systems associated with anomaly detection and resolution are described. Examples can include detecting, via a sensor of a robot, an object in a path of the robot while the robot is performing a task in an environment and classifying the object as an anomaly or a non-anomaly and the environment as anomalous or non-anomalous using a machine learning model. Examples can include proceeding with the task responsive to classification of the object as a non-anomaly and the environment as non-anomalous and resolving the anomaly or the anomalous environment and proceeding with the task responsive to classification of the object as an anomaly or the environment as anomalous.

A position control method for a servo, includes: receiving, from a control terminal, a motion control command that comprises a motion planning parameter about position of an output shaft of the servo; acquiring speed information or time information indicated by the motion planning parameter, and determining a constant parameter control duration according to the speed information or time information; determining a control parameter corresponding to a constant parameter control stage according to the constant parameter control duration and a preset constant parameter; performing a transient adjustment to the servo when the constant parameter control stage ends, and changing the control parameter to an adaptive operation parameter when the transient adjustment ends; and controlling a rotation angle of the output shaft of the servo to perform a position control of the servo, based on duration values and control parameters corresponding to each of a plurality of control stages.

A method and system for reinforcement learning can involve applying a finite-difference approach to a controller, and tuning the controller in response to applying the finite-difference approach by taking a state as an entirety of a closed-loop step response. The disclosed finite-different approach is based on a random search to tuning the controller, which operates on the entire closed-loop step-response of the system and iteratively improves the gains towards a desired closed-loop response. This allows for prescribing stability requirement into the reward function without any modeling procedures.

A control device of a wire electric discharge machine and a machine learning device are provided that can appropriately and readily determine a correction parameter. The control device, which optimizes the correction parameter for wire electrical discharge machining process, includes a machine learning device configured to learn the correction parameter for the wire electrical discharge machining process. The machine learning device includes a state observation unit configured to observe, as a state variable, condition data indicative of a condition for the wire electrical discharge machining process, a determination data acquisition unit configured to acquire determination data indicative of the correction parameter of the case where machining precision is favorable in the wire electrical discharge machining process, and a learning unit configured to learn the correction parameter in association with the condition for the wire electrical discharge machining process using the state variable and the determination data.

A method and system for reinforcement learning can involve applying a finite-difference approach to a controller, and tuning the controller in response to applying the finite-difference approach by taking a state as an entirety of a closed-loop step response. The disclosed finite-different approach is based on a random search to tuning the controller, which operates on the entire closed-loop step-response of the system and iteratively improves the gains towards a desired closed-loop response. This allows for prescribing stability requirement into the reward function without any modeling procedures.

An objective of the present invention is to provide a control device, control system, control method, and computer-readable storage medium, for enabling verification of the reliability of operation machine control. Provided is a control device comprising: a control part comprising a controller for outputting output data with regard to input data, said control part serving to control an operation machine using the controller; an acquisition part for acquiring attribute information including statistics of previously obtained input data and output data; and an evaluation part for, on the basis of a comparison of the attribute information with new input data being newly inputted into the controller and/or new output data being newly outputted from the controller with regard to the new input data, evaluating to what extent the new input data and/or the new output data deviate from the statistics.

A position control method for a servo, includes: receiving, from a control terminal, a motion control command that comprises a motion planning parameter about position of an output shaft of the servo; acquiring speed information or time information indicated by the motion planning parameter, and determining a constant parameter control duration according to the speed information or time information; determining a control parameter corresponding to a constant parameter control stage according to the constant parameter control duration and a preset constant parameter; performing a transient adjustment to the servo when the constant parameter control stage ends, and changing the control parameter to an adaptive operation parameter when the transient adjustment ends; and controlling a rotation angle of the output shaft of the servo to perform a position control of the servo, based on duration values and control parameters corresponding to each of a plurality of control stages.

A machine learning includes a state observation unit that observes, as state variables representing a current state of an environment, PID control parameter data indicating the a parameter of the PID control during machining, machining condition data indicating a machining condition of the machining, and machining environment data relating to a machining environment of the machining, a determination data acquisition unit that acquires, as determination data, tool life determination data indicating an appropriateness determination result relating to depletion of the life of a tool during the machining, and cycle time determination data indicating an appropriateness determination result relating to the cycle time of the machining, and a learning unit that learns the machining condition and the machining environment of the machining, and the parameter of the PID control in association with each other.

A method for devising an optimum control policy of a controller for controlling a system includes optimizing at least one parameter that characterizes the control policy. A Gaussian process model is used to model expected dynamics of the system. The optimization optimizes a cost function which depends on the control policy and the Gaussian process model with respect to the at least one parameter. The optimization is carried out by evaluating at least one gradient of the cost function with respect to the at least one parameter. For an evaluation of the cost function a temporal evolution of a state of the system is computed using the control policy and the Gaussian process model. The cost function depends on an evaluation of an expectation value of a cost function under a probability density of an augmented state at time steps.