An automated control of a system having a plurality of cooperating components involving controlled elements and sensors uses a simulator configured to simulate operation of the components. The simulator stores data representing states of the components and modifies the states over time in accordance with simulated operation of the system. An input module receives data from at least the sensors and updates in the simulator the data representing states of the components. An output module reads from the simulator the data representing states of the components and generates at least controlled element control signals for the controlled elements of the components. The simulator contains a virtual state machine representing the system, and automation of the system is achieved without state machine logic representing the system within the input module and the output module.

Provided is a system including a planning section that generates a production plan for a production site, using a planning model; a simulating section that simulates operation of at least a portion of the production site, based on a simulation model of the at least a portion of the production site; a monitoring section that monitors actual operation of the at least a portion of the production site; a calibrating section that calibrates the simulation model, based on a difference between the simulated operation and the actual operation; and a control section that controls the at least a portion of the production site, based on a simulation result obtained by simulating the operation of the at least a portion of the production site in accordance with the production plan, using the simulation model that has been calibrated.

Embodiments are directed to a computer-based tool that can identify an anomalous state of a component in a real-world environment, even if the component experiences gradual and/or seasonal trends. The tool receives data from sensors monitoring a component. The tool uses a trained machine learning model to calculate a predicted behavior of the monitored component. Actual behavior of the component, captured by current sensor readings, is compared to the predicted behavior of the component, calculated by the machine learning model, to compute a divergence. The computed divergence is used by a statistical learning method to determine if the component in the real-world environment is in an anomalous state.

Embodiments are directed to a computer-based tool that can identify an anomalous state of a component in a real-world environment, even if the component experiences gradual and/or seasonal trends. The tool receives data from sensors monitoring a component. The tool uses a trained machine learning model to calculate a predicted behavior of the monitored component. Actual behavior of the component, captured by current sensor readings, is compared to the predicted behavior of the component, calculated by the machine learning model, to compute a divergence. The computed divergence is used by a statistical learning method to determine if the component in the real-world environment is in an anomalous state.

Active utilization of a robotic simulator in control of one or more real world robots. A simulated environment of the robotic simulator can be configured to reflect a real world environment in which a real robot is currently disposed, or will be disposed. The robotic simulator can then be used to determine a sequence of robotic actions for use by the real world robot(s) in performing at least part of a robotic task. The sequence of robotic actions can be applied, to a simulated robot of the robotic simulator, to generate a sequence of anticipated simulated state data instances. The real robot can be controlled to implement the sequence of robotic actions. The implementation of one or more of the robotic actions can be contingent on a real state data instance having at least a threshold degree of similarity to a corresponding one of the anticipated simulated state data instances.