A sequential or cascading predictive control method is provided, including first solving a cost function and then a second cost function for two or more control objectives. The method includes separating the cost function into at least two or more cost functions, depending on the number of defined control objectives. The method additionally includes controlling a first variable with a unitary cost function, a single term or nature of the control objectives. The method also includes determining the possible states that minimize the cost of the first objective to be controlled. Considering only the options given through this determination, a second variable is controlled with a cost function that minimizes the cost function thereof.

The present application discloses a wide-field-of-view anti-shake high-dynamic bionic eye. A trajectory tracking method based on a bionic eye robot includes: establishing a linear model according to a bionic eye robot; establishing a full state feedback control system on the basis of the linear model; in the full state feedback control system, acquiring an angle and an angular acceleration required for a joint in a target tracking process of the bionic eye on the basis of a preset trajectory expectation value and a preset joint angle expectation value; the method further includes: adopting a linear quadratic regulator (LQR) to calculate a parameter K in the full state feedback control system, and minimizing energy consumption by establishing an energy function, so as to optimize the coordinated head-eye motion control of the linear bionic eye. The present application achieves the optimal control of the target tracking.

A method for monitoring a primary variable is carried out in a device having access to a set of sensors. The method includes the steps of receiving, from a network service, a series of forecasted values for the primary variable, each forecasted value being associated with one of a series of future time points; for at least one of the future time points, predicting a value for the primary variable using data of at least one secondary variable captured by a subset of the set of sensors, comparing the predicted value to the forecasted value associated with the future time point, and switching to a different subset of the set of sensors, if the predicted value deviates from the forecasted value with more than a specified threshold value.

Systems and methods for utilizing a spatial statistical model to maximize efficacy in performing trials on agronomic fields are disclosed herein. In an embodiment, a system receives first yield data for a first portion of an agronomic field, the first portion of the agronomic field having received a first treatment, and second yield data, for a second portion of the agronomic field, the second portion of the agronomic field having received a second treatment that is different than the first treatment. The system uses a spatial statistical model and the first yield data to compute a yield value for the second portion of the agronomic field, the yield value indicating an agronomic yield for the second portion of the agronomic field if the second portion of the agronomic field had received the first treatment instead of the second treatment. Based on the computed yield value and the second yield data, the system selects the second treatment. In an embodiment, in response to selecting the second treatment, the system generates a prescription map, the prescription map including the second treatment. The system may also generate one or more scripts which, when executed by an application controller, cause the application controller to control an operating parameter of an agricultural implement to apply the second treatment.

An apparatus, method and computer program is described comprising detecting a first object in a first image of a sequence of images using a neural network, wherein the means for detecting the first object provides an object area indicative of a first location of the first object; and tracking the first object, wherein the means for tracking the first object further comprises generating a predicted future location of the first object and generating an updated location of the first object using the neural network. The means for generating the predicted future location of the first object may, for example, receive said object area indicative of a first location of the first object and may receive said updated location information of the first object.

A method for automatically reducing the dimensionality of a mathematical representation of a controlled application system is provided. The method includes receiving, at a control system, data corresponding to control action and system state variables relating to the controlled application system, fitting a constrained reinforcement learning (CRL) model to the controlled application system based on the data, and automatically identifying a subset of the system state variables by selecting control action variables of interest and identifying system state variables that drive the CRL model to recommend each control action variable of interest. The method also includes automatically performing state space dimensionality reduction of the CRL model using the subset of system state variables, estimating a transition probability matrix for a constrained Markov decision process (CMDP) model of the controlled application system, and formulating the CMDP model as a linear programming (LP) problem using the transition probability matrix and several costs.

A method includes receiving a set of feature models, each feature model of the set of feature models corresponding to a respective feature associated with processing of a component, receiving a set of target properties for processing the component, where the set of target properties includes, for each feature, a respective target, determining, based on the set of feature models, one or more sets of predicted processing parameters in view of the set of target properties, generating one or more candidate process recipes each corresponding to a respective one of the one or more sets of predicted processing parameters, where the one or more candidate process recipes each correspond to a set of predicted properties including, for each feature, a respective predicted property value resulting from component processing, and selecting, from the one or more candidate process recipes, a process recipe for processing the component.

A heating, ventilation, or air conditioning (HVAC) system for a building includes HVAC equipment configured to provide heating or cooling to one or more building spaces and one or more controllers. The one or more controllers include one or more processing circuits configured to generate energy targets for the one or more building spaces using a thermal capacitance of the one or more building spaces to which the heating or cooling is provided by the HVAC equipment, generate setpoints for the HVAC equipment using the energy targets for the one or more building spaces to which the heating or cooling is provided by the HVAC equipment, and operate the HVAC equipment using the setpoints to provide the heating or cooling to the one or more building spaces.

It is an object of the present invention to provide a component management system or the like that can accurately predict component exhaustion in a component mounting device that performs work at a line. Specifying section updates the time table based on the arrival time point or the unloading time point in each of component mounting devices. Arrival predicting section predicts the arrival time point in each component mounting device based on the time table and updates a prediction table. Since component-exhaustion predicting section acquires the arrival time point of a circuit board for which a component will be exhausted from the prediction table and calculates a component exhaustion time point, it is possible to predict the component exhaustion time point with high accuracy. An operator can perform a replenishment work based on the component exhaustion time point.

Responding to grid events is provided. The system determines, based on an event, to modify an electrical load of a site. The system selects a parameter for the site to adjust to modify the electrical load. The system identifies a script constructed from previously processed interactions between a human-machine interface of the building management system to adjust the parameter for the site. The system establishes a communication session with a remote access agent executed by a computing device of the site to invoke the building management system of the site. The system generates a sequence of commands defined by the script to adjust the one or more parameters for the site. The system transmits the sequence of commands to cause the remote access agent to execute the sequence of commands on the human-machine interface of the building management system to modify the electrical load of the site.