Provided are an apparatus and method for a statistical memory network. The apparatus includes a stochastic memory, an uncertainty estimator configured to estimate uncertainty information of external input signals from the input signals and provide the uncertainty information of the input signals, a writing controller configured to generate parameters for writing in the stochastic memory using the external input signals and the uncertainty information and generate additional statistics by converting statistics of the external input signals, a writing probability calculator configured to calculate a probability of a writing position of the stochastic memory using the parameters for writing, and a statistic updater configured to update stochastic values composed of an average and a variance of signals in the stochastic memory using the probability of a writing position, the parameters for writing, and the additional statistics.

A system and method for identifying risk in warehouse environments includes video sensors configured to capture video streams and a central processing unit communicatively coupled to video sensors. The central processing unit is configured with an emerging risk discovery unit configured to detect a current risk subject in the obtained plurality of real time video frames. Further, the plurality of real time video frames are stored in a memory. A location of the current risk subject detected in the obtained plurality of real time video frames is detected. Further, physical characteristics of current risk subject for predicting one or more actions performed by the current risk subject are estimated, and actions and location of the current risk subject are processed to detect patterns or movements and activities undertaken by one or more risk subjects.

An apparatus for controlling a system includes a memory to store a model of the system including a motion model of the system subject to process noise and a measurement model of the system subject to measurement noise, such that one or combination of the process noise and the measurement noise forms an uncertainty of the model of the system with unknown probabilistic parameters, wherein the uncertainty of the model of the system causes a state uncertainty of the system with unknown probabilistic parameters. The apparatus also includes a sensor to measure a signal to produce a sequence of measurements indicative of a state of the system, a processor to estimate a Gaussian distribution representing the state uncertainty, and a controller to determine a control input to the system using the model of the system with state uncertainty represented by the Gaussian distribution and control the system according to the control input. The processor is configured to estimate, using at least one or combination of the motion model, the measurement model, and the measurements of the state of the system, a first Student-t distribution representing the uncertainties of the model and a second Student-t distribution representing the state uncertainty of the system, the estimation is performed iteratively until a termination condition is met, and fit a Gaussian distribution representing the state uncertainty into the second Student-t distribution.

Method for monitoring a stable convergence behaviour of a Kalman filter (KF), which estimates states and/or parameters of an energy storage system, in particular a battery cell (BZ), wherein a covariance behaviour—provided by the Kalman filter (KF)—in terms of at least one state and/or parameter of the energy storage system is compared with a corresponding desired covariance behaviour of the state and/or parameter, wherein the Kalman filter (KF) is automatically deactivated for each state and/or each parameter of the energy storage system, of which the covariance behaviour exceeds the corresponding desired covariance behaviour.

In order to at least approximately determine statistical properties of raw measured values, e.g., measurement noise and/or average errors, without knowledge of a filter applied to raw measured values and only with the aid of a useful signal obtained from the filtering, i.e., in order to make statements regarding measurement conditions by assuming a few frequently encountered boundary conditions, statistical properties of raw measured values are determined from the useful signal, which is composed of a temporal sequence of filter output values. A filter characteristic of the filter is ascertained from the temporal sequence of output values obtained under stable measurement conditions, the ascertained filter characteristic is inverted, raw measured values are reconstructed from the inverse of the filter characteristic and from the useful signal, and the statistical properties are ascertained from the reconstructed raw measured values and/or from the inverse of the filter characteristic and from the useful signal.

This application provides a multi-sensor-based state estimation method, an apparatus, and a terminal device. The method includes: in each cycle, extracting sensor messages and arranging the sensor messages into a queue; deleting a system state estimation value with a timestamp later than an initial timestamp; extracting the sensor messages from the queue; when prediction data is extracted, predicting a system state estimation value corresponding to the first timestamp according to a Kalman filter prediction algorithm; when the update data is extracted, obtaining the system state estimation value corresponding to the first timestamp, and updating the system state estimation value according to a Kalman filter update algorithm; after all the sensor messages in the queue are used, proceed to a next cycle; and detecting a system state estimation value with the latest timestamp in the state estimation queue, and outputting the system state estimation value.

Provided is a control module of a converter, in particular a power converter of a wind power installation, which is configured to control the converter in such a way that the converter emulates a behavior of a synchronous machine, comprising an, in particular internal, control loop which has an, in particular adjustable, virtual admittance by means of which the converter is controlled in order to emulate the behavior of the synchronous machine.

A method of controlling a device includes receiving data from a first sensor, encoding, via parameters of an encoder, the data to obtain a latent observation (w.sub.t) for the data and an uncertainty vector (σ.sub.wt) for the latent observation, processing the latent observation with a recurrent neural network to obtain a switching variable (s.sub.t) which determines weights (α.sub.t) of a locally linear Kalman filter, processing the latent observation and the uncertainty vector with said locally linear Kalman filter to obtain updated mean of latent representation (μ.sub.zt) and covariance of latent representation (Σ.sub.zt) of the Kalman filter, decoding the latent representation to obtain mean (μ.sub.xt) and covariance of a reconstruction of the data (Σ.sub.xt) and outputting the reconstruction at a time t.

A method for automatically determining and using noise statistics of noisy observation data provided by at least one sensor connected to a tracker, in order to improve tracking of a time-varying object across a scene using a Kalman algorithm. The Kalman algorithm allowing to get an estimation of dynamic parameters of the object and providing a precision of said estimation from said noisy observation data and from a corrected previous estimation. The method includes receiving reference data from a data source external to the Kalman algorithm and connected to the tracker, deriving, from said reference data, said noise statistics reflecting errors made by the sensor, and using said noise statistics as setting parameters of the Kalman algorithm.

In a general aspect, a method is presented for increasing the measurement precision of an optical instrument. The method includes determining, based on optical data and environmental data, a measured value of an optical property measured by the optical instrument. The optical instrument includes an optical path and a sensor configured to measure an environmental parameter. The method also includes determining a predicted value of the optical property based on a model representing time evolution of the optical instrument. The method additionally includes calculating an effective value of the optical property based on the measured value, the predicted value, and a Kalman gain. The Kalman gain is based on respective uncertainties in the measured and predicted values and defines a relative weighting of the measured and predicted values in the effective value.