A computer-implemented method of adaptively controlling an autonomous operation of a vehicle is provided. The method includes steps of (a) in a critic network in a computing system configured to autonomously control the vehicle, determining, using samples of passively collected data and a state cost, an estimated average cost, and an approximated cost-to-go function that produces a minimum value for a cost-to-go of the vehicle when applied by an actor network; and (b) in an actor network in the computing system and operatively coupled to the critic network, determining a control input to apply to the vehicle that produces the minimum value for the cost-to-go, wherein the actor network is configured to determine the control input by estimating a noise level using the average cost, a cost-to-go determined from the approximated cost-to-go function, a control dynamics for a current state of the vehicle, and the passively collected data.

The training of a learning agent to provide real-time control of an object is disclosed. Training of the learning agent and training of a corresponding pioneer agent are iteratively alternated. The training of the learning and pioneer agents is under the supervision of a supervisor agent. The training of the learning agent provides feedback for subsequent training of the pioneer agent. The training of the pioneer agent provides feedback for subsequent training of the learning agent. During the training, a supervisor coefficient modulates the influence of the supervisor agent. As agents are trained, the influence of the supervisor agent is decayed. The training of the learning agent, under a first level of supervisor influence, includes real-time control of the object. The subsequent training of the pioneer agent, under a reduced level of supervisor influence, includes replay of training data accumulated during the real-time control of the object.

Aspects of the disclosed technology encompass the use of a deep-learning controller for monitoring and improving a manufacturing process. In some aspects, a method of the disclosed technology includes steps for: receiving control values associated with a process station in a manufacturing process, predicting an expected value for an article of manufacture output from the process station, and determining if the deep-learning controller can control the manufacturing process based on the expected value. Systems and computer-readable media are also provided.

Methods for implementing power delivery transactions between a buyer and a seller of electrical energy supplied to an electrical grid by an integrated renewable energy source (RES) and energy storage system (ESS) of a RES-ESS facility are provided. Estimated total potential output of the RES is compared to a point of grid interconnect (POGI) limit to identify potential RES overgeneration, and the buyer is charged if potential RES overgeneration is less than potential overgeneration during one or more retrospective time windows. The method provides a basis for the RES-ESS facility owner to be paid for an estimated amount of energy that did not get stored as a result of a grid operator not fully discharging an ESS prior to the start of a new day.

A heating, ventilation, and air conditioning (HVAC) control device is configured to record a plurality of actual occupancy statuses, to determine a plurality of corresponding predicted occupancy statuses, and to compare the plurality of predicted occupancy statuses to the plurality of actual occupancy statuses. The device is further configured to identify conflicting occupancy statuses based on the comparison. A conflicting occupancy status indicates a difference between an actual occupancy status and a corresponding predicted occupancy status. The device is further configured to identify timestamps corresponding with the conflicting occupancy statuses, to identify historical occupancy statuses corresponding with the identified timestamps, and to update the conflicting occupancy statuses in the predicted occupancy schedule with the historical occupancy statuses.

A computer-Implemented method, system, and computer program product for optimizing production of an industrial facility. The industrial facility is designed to produce a predefinable quantity of at least one product. A model trained by machine learning is provided at a first time and the trained model is executed at a second time following the first time to generate a rolling forecast for a predefinable time interval. The predefinable time interval begins after the second time and the rolling forecast forecasts for any time within the time interval a quantity of the at least one product to be produced at this time. The rolling forecast is further processed by means of a further model to calculate a reforecast on the basis of the rolling forecast.

A method and computing device for inferring an airflow of a controlled appliance operating in an area of a building. The computing device stores a predictive model. The computing device determines a measured airflow of the controlled appliance and a plurality of consecutive temperature measurements in the area. The computing device executes a neural network inference engine using the predictive model for inferring an inferred airflow based on inputs. The inputs comprise the measured airflow and the plurality of consecutive temperature measurements. The inputs may further include at least one of a plurality of consecutive humidity level measurements in the area and a plurality of consecutive carbon dioxide (CO2) level measurements in the area. For instance, the controlled appliance is a Variable Air Volume (VAV) appliance and a K factor of the VAV appliance is calculated based on the inferred airflow.

A method for optimizing production of sheet-metal parts, the production comprising cutting out and singularizing the sheet-metal parts and bending the sheet-metal parts, wherein the method includes: (A) training a neural network, which is executed on a Monte Carlo tree search framework, by means of supervised learning and self-play with reinforcement learning; (B) recording constraints for the sheet-metal parts, the constraints comprising geometric data of the sheet-metal parts; (C) creating an optimized production schedule by way of the neural network; and (D) outputting the production schedule.

Disclosed herein are a sound sleep assistance apparatus, a sound sleep assistance method, and a sound sleep assistance system. According to an embodiment, there is provided a sound sleep assistance apparatus for assisting the sound sleep of a user by communicating with a sleep pad, the sound sleep assistance apparatus including: a communication interface configured to communicate with the sleep pad that acquires the physiological index information of the user while the user lies down; and a controller configured to determine the sleep stage of the user based on the physiological index information, and to provide a sound source corresponding to the determined sleep stage.

This application addresses an integrated smart system to control the variables involved in the process for melting mineral concentrates. Specifically, it addresses an integrated smart system that allows the whole melting process operation to be controlled, measuring the mineralogical quality and quantity of the concentrate that is injected into the melting furnace, as well as variables such as the temperature, the level of the liquid phases and the percentage of copper within the furnace. In this manner, by reading said variables, it acts autonomously on manipulated variables, considering uncertainties, allowing a stable temperature to be maintained in the reactor, allowing products to be obtained at the required quality and controlling the liquid phases therein, among other controlled variables, to achieve efficient melting.