In order to control a technical system using a control model, a transformation function is provided for reducing and/or obfuscating operating data of the technical system so as to obtain transformed operating data. In addition, the control model is generated by a model generator according to a first set of operating data of the technical system. In an access domain separated from the control model, a second set of operating data of the technical system is recorded and transformed by the transformation function into a transformed second set of operating data which is received by a model execution system. The control model is then executed by the model execution system, by supplying the transformed second set of operating data in an access domain separated from the second set of operating data, control data being derived from the transformed second set of operating data.

According to one embodiment, a data collection system includes an event data collector, a state machine generator, a state machine list, and a state machine driver. The event data collector collects sense signals respectively as a plurality of event data. The state machine generator generates a state machine as a model corresponding to the workpiece. One of the sense signals is acquired when the workpiece is fed into the processing system. The state machine generator generates the state machine and generates an ID for the state machine when the event data collector collects one of the plurality of event data corresponding to the one of the sense signals. The state machine driver drives the state machine retained in the state machine list by sending, to the state machine retained in the state machine list, an event corresponding to another one of the sense signals.

The present technology addresses the problem of quickly and safely improving policies in online reinforcement learning domains. As its solution, an exploration strategy comprising diverse exploration (DE) is employed, which learns and deploys a diverse set of safe policies to explore the environment. DE theory explains why diversity in behavior policies enables effective exploration without sacrificing exploitation. An empirical study shows that an online policy improvement algorithm framework implementing the DE strategy can achieve both fast policy improvement and safe online performance.

Provided is a system and method for training and validating models in a machine learning pipeline for failure mode analytics. The machine learning pipeline may include an unsupervised training phase, a validation phase and a supervised training and scoring phase. In one example, the method may include receiving a request to create a machine learning model for failure mode detection associated with an asset, retrieving historical notification data of the asset, generating an unsupervised machine learning model via unsupervised learning on the historical notification data, wherein the unsupervised learning comprises identifying failure topics from text included in the historical notification data and mapping the identified failure topics to a plurality of predefined failure modes for the asset, and storing the generated unsupervised machine learning model via a storage device.

Systems and methods described herein can involve management of a system having a plurality of sensors, the plurality of sensors observing a plurality of process steps, which can involve selecting a subset of the plurality of sensors for observation; executing anomaly detection from data provided from the subset of the plurality of sensors; for a detection of an anomaly from a sensor from the subset of sensors, selecting ones of the plurality of process steps based on the detected anomaly; estimating a probability of anomaly occurrence for the selected ones of the plurality of process steps; and for the estimated probability of anomaly occurrence meeting a predetermined criteria, selecting ones of the plurality of sensors associated with the selected ones of the plurality of process steps for observation.

A program identification method is for identifying an application program that is stored in a terminal device coupled to a robot system and that is used for teaching work on an operation of a robot provided in the robot system. The method includes: acquiring program information corresponding to the application program from the terminal device; and comparing the program information with first information stored in the robot system and thus identifying whether the application program is a first application program corresponding to the first information or not.

Systems, methods, and instrumentalities are disclosed for switching a control scheme to control a set of system modules and/or modular devices of a surgical hub. A surgical hub may determine a first control scheme that is configured to control a set of system modules and/or modular devices. The surgical hub may receive an input from one of the set of modules or a device located in an OR. The surgical hub may make a determination that at least one of a safety status level or an overload status level of the surgical hub is higher than its threshold value. Based on at least the received input and the determination, the surgical hub may determine a second control scheme to be used to control the set of system modules. The surgical hub may send a control program indicating the second control scheme to one or more system modules and/or modular devices.

A task optimization method and a task optimization device in a mobile robot are provided. The task optimization method includes: obtaining at least one task type in a mobile robot and usage information when all users use a task corresponding to each task type; separately performing machine learning on the usage information of all the users corresponding to each task type to obtain at least one piece of user's usage habit information corresponding to each task type and usage probability thereof, thereby performing machine learning on usage information when all users use the task corresponding to the task type; based on the at least one piece of usage habit information corresponding to each task type, the usage probability thereof and the real-time usage information, optimizing the task corresponding to the task type used by the user in real time.

One application of deep learning methods and labelled data is for industrial production or work applications. For such applications implemented with machine learning applications, massive amounts of data are required to train, validate, and/or tune models for better fitting the requirements. However, obtaining such data has typically be costly and difficult. Embodiments provide adaptable processes that provide data labelling methods for work settings. Embodiments take advantage of the work or production processes to label and collect data, which save time and money and improves accuracy. Embodiments prevent or reduce the need for worker training costs and human mistake-triggered data labelling problems. Embodiments also improve data labelling quality and speed-up of the development cycle.

The present technology pertains to obtaining sensor data and processed sensor data related to a base world scenario encountered by an AV entity. The sensor data and processed sensor data may be assessed to determine an importance value for the base world scenario. When the importance value is above a threshold, a closed course staging system may stage a re-creation of the base world scenario in a closed course environment (i.e., a closed course scenario). An AV may then interact with the closed course scenario. Sensor data and processed sensor data from the AV’s interaction with the closed course scenario may then be added to training data used to train ML models for AVs.