Abstract: A robotic controller is provided for generating sequences of movement primitives for sequential tasks of a robot having a manipulator. The controller includes at least one control processor, and a memory circuitry storing a dictionary including the movement primitives, a pretrained learning module, and a graph-search based planning module having instructions stored thereon.

Abstract: A controller for controlling an operation of a robot to execute a task is provided. The controller comprises a memory configured to store a set of dynamic movement primitives (DMPs) associated with the task. The set of DMPs comprise a set of at least two dynamical systems: a function representing point attractor dynamics and a forcing function corresponding to a learned demonstration of the task. The controller comprises a processor configured to transform the set of DMPs to a set of constrained DMPs (CDMPs) by determining a perturbation function associated with the forcing function. The perturbation function is associated with a set of operational constraints. The processor is further configured to solve, a non-linear optimization problem for the set of CDMPs based on the set of operational constraints and generate, a control input for controlling the robot for executing the task, based on the solution.

Abstract: A computer-implemented method of training an autoencoder to recover missing data is provided. The autoencoder includes an encoder for encoding its inputs into a latent space and a decoder for decoding the encodings from the latent space. The method comprises creating a first training set including a valid data set of multiple dimensions, and training the encoder and the decoder in a first training stage using the first training set to reduce a difference between the valid data set provided to the encoder and a data set decoded by the decoder. The method further comprises creating a second training set comprising an invalid data set, and training the encoder in a second training stage using the second training set to reduce a difference between encodings of valid data instances and encodings of their corresponding invalid data instances.

Abstract: A controller for controlling an operation of a system is disclosed. The controller receives an input signal indicative of the operation of the system and rotates a test signal multiple times with different circular shifts to produce different rotations of the test signal forming a matrix data structure with the input signal. The input signal and the test signal are time-series data having values monotonically measured over time. The controller is further configured to apply a sliding three-dimensional (3D) window method to the matrix data structure to produce statistics of the input signal with respect to the rotations of the test signal. The sliding 3D window method iteratively moves window over the matrix data structure to compute a value of the statistics for a segment of the matrix data structure within the window. Furthermore, the controller controls the operation of the system according to the statistics of the input signal.

Abstract: A control system for controlling an operation of an elevator arranged to service different floors of a building, is disclosed. The control system comprises an input interface configured to receive a measurement of a distance metric to an object located at a service floor in a line-of-sight of a sensor; an output interface configured to cause a display device to display a floor value indicating a destination floor; and a processor configured to compare the received distance metric with a referenced distance metric to estimate a sign of the comparison and a value of the comparison; repeatedly update, until a termination condition is met, the floor value displayed on the display device in a direction of the elevator service indicated by the sign and with a frequency of the update indicated by the value; and cause the elevator to perform the service operation from the service floor to the destination floor.

Abstract: A multi-input call panel for controlling an operation of an elevator system, is disclosed. The multi-input call panel includes a touchable interface associated with a plurality of touchable inputs arranged at different locations on the multi-input call panel; a touchless interface including a processor configured to receive readings of a sensor detecting motion in proximity to the touchable interface and executing a probabilistic classifier trained to output a probability of correspondence of the received readings with an intention to touch one or multiple touchable inputs from the plurality of touchable inputs; and a controller configured to control the operation of the elevator system according to a control command associated with a touchable input of the plurality of touchable inputs when the touchable input is touched on the touchable interface, the classifier outputs the probability of the intention to touch the touchable input above a threshold or both.

Abstract: A computer-implemented method of training an autoencoder to recover missing data is provided. The autoencoder includes an encoder for encoding its inputs into a latent space and a decoder for decoding the encodings from the latent space. The method comprises creating a first training set including a valid data set of multiple dimensions, and training the encoder and the decoder in a first training stage using the first training set to reduce a difference between the valid data set provided to the encoder and a data set decoded by the decoder. The method further comprises creating a second training set comprising an invalid data set, and training the encoder in a second training stage using the second training set to reduce a difference between encodings of valid data instances and encodings of their corresponding invalid data instances.

Abstract: A controller for controlling an operation of a system is disclosed. The controller receives an input signal indicative of the operation of the system and rotates a test signal multiple times with different circular shifts to produce different rotations of the test signal forming a matrix data structure with the input signal. The input signal and the test signal are time-series data having values monotonically measured over time. The controller is further configured to apply a sliding three-dimensional (3D) window method to the matrix data structure to produce statistics of the input signal with respect to the rotations of the test signal. The sliding 3D window method iteratively moves window over the matrix data structure to compute a value of the statistics for a segment of the matrix data structure within the window. Furthermore, the controller controls the operation of the system according to the statistics of the input signal.

Abstract: A controller for controlling a system that includes a policy configured to control the system is provided. The controller includes an interface connected to the system, the interface being configured to acquire an action state and a measurement state via sensors measuring the system, a memory to store computer-executable program modules including a model learning module and a policy learning module, a processor configured to perform steps of the program modules. The steps include offline-modeling to generate offline-learning states based on the action state and measurement state using the model learning program, providing the offline states to the policy learning program to generate policy parameters, and updating the policy of the system to operate the system based on the policy parameters.

Abstract: A system for detecting an anomaly in an execution of an operation of a machine determines a local matrix profile (LMP) of a test signal with respect to the baseline signals. LMP is a time series of values, each LMP value for a time instance is determined for a segment of the test signal based on a minimum distance between the segment of the test signal with corresponding segments of the baseline signals, such that each LMP value is a value of a local dissimilarity of the execution of the operation of the machine with respect to the baseline executions of the operation of the machine. The system determines an accumulation of the LMP values above an LMP threshold and detects an anomaly when the accumulation above an anomaly detection threshold.

Abstract: A controller for controlling a heating, ventilating, and air-conditioning (HVAC) system arranged to condition an environment according to HVAC setpoints is provided. The controller is configured to accept target values of thermal states at predetermined locations in the conditioned environment, current values of the thermal states at the predetermined locations in the conditioned environment, and current values of the HVAC setpoints. The controller is further configured to determine, using a neural network, target HVAC setpoints such that a difference in an operation of the HVAC system according to the target HVAC points with respect to the operation of the HVAC system according to the current HVAC setpoints changes thermal states in the predetermined locations in the conditioned environment from the current values of the thermal state to the target values of the thermal state.

Abstract: A control system for controlling an operation of an elevator arranged to service different floors of a building, is disclosed. The control system comprises an input interface configured to receive a measurement of a distance metric to an object located at a service floor in a line-of-sight of a sensor; an output interface configured to cause a display device to display a floor value indicating a destination floor; and a processor configured to compare the received distance metric with a referenced distance metric to estimate a sign of the comparison and a value of the comparison; repeatedly update, until a termination condition is met, the floor value displayed on the display device in a direction of the elevator service indicated by the sign and with a frequency of the update indicated by the value; and cause the elevator to perform the service operation from the service floor to the destination floor.

Abstract: A system evaluates a plurality of faults in an operation of a machine at a set of future instances of time. The system uses a neural network including a first subnetwork sequentially connected with a sequence of second subnetworks for each of the future instance of time such that an output of one subnetwork is an input to a subsequent subnetwork. The first subnetwork accepts the current time-series data and the current setpoints of operation of the machine. Each of the second subnetworks accepts the output of a preceding subnetwork, an internal state of the preceding subnetwork, and a future setpoint for a corresponding future instance of time. Each of the second subnetworks outputs an individual prediction of each fault of a plurality of faults at the corresponding future instance of time.

Abstract: A system evaluates a plurality of faults in an operation of a machine at a set of future instances of time. The system uses a neural network including a first subnetwork sequentially connected with a sequence of second subnetworks for each of the future instance of time such that an output of one subnetwork is an input to a subsequent subnetwork. The first subnetwork accepts the current time-series data and the current setpoints of operation of the machine. Each of the second subnetworks accepts the output of a preceding subnetwork, an internal state of the preceding subnetwork, and a future setpoint for a corresponding future instance of time. Each of the second subnetworks outputs an individual prediction of each fault of a plurality of faults at the corresponding future instance of time.

Abstract: A system for detecting an anomaly in an execution of an operation of a machine determines a local matrix profile (LMP) of a test signal with respect to the baseline signals. LMP is a time series of values, each LMP value for a time instance is determined for a segment of the test signal based on a minimum distance between the segment of the test signal with corresponding segments of the baseline signals, such that each LMP value is a value of a local dissimilarity of the execution of the operation of the machine with respect to the baseline executions of the operation of the machine. The system determines an accumulation of the LMP values above an LMP threshold and detects an anomaly when the accumulation above an anomaly detection threshold.

Abstract: Future travel times of a target vehicle traveling on a route from a starting point to a destination are predicted by first acquiring, by a probe vehicle, real-time probe data to alternative links from the starting point to the destination. Then, the future travel time for each link is predicted using a set of regression functions.

Abstract: A method determines a run-curve of a motion of a vehicle as a function of at least a speed of the vehicle and a position of the vehicle in a continuous space. First, the method determines Markov decision process (MDP) with respect to a set of anchor states selected from the continuous space, such that a control moving the vehicle to a state transitions the MDP to an anchor state with a probability determined as a function of a distance between the anchor state and the state in the continuous space, and solves the MDP subject to constraints to determine an MDP policy optimizing a cost function representing a cost of the motion of the vehicle. Next, the method determines the run-curve based on the MDP policy.

Abstract: A method reduces the computation time for determining optimal run-curves for a specific travel time of a vehicle along a route between two locations. The computation is partitioned between pre-processing and real-time steps. A set of weights ? are generated, and run-curves for the weights are obtained and stored during the pre-processing. State transition matrices can also be determined and stored during the pre-processing. During real-time, a specific travel time is obtained. The travel time is used to interpolate the weight ? for the specific travel time from the stored weights. The memory can be updated for each solution for a specific travel time to dramatically reduce the time to optimize the run-curves.

Abstract: Future travel times of a target vehicle traveling on a route from a starting point to a destination are predicted by first acquiring, by a probe vehicle, real-time probe data to alternative links from the starting point to the destination. Then, the future travel time for each link is predicted using a set of regression functions.

Abstract: Future travel times along links are predicted using training and prediction phases. During training, seasonal intervals, a seasonal component of the training inflows are learned. The seasonal component is subtracted from the training inflows to obtain training deviations from the training inflows to yield statistics, which along with the seasonal components form a model of traffic flow on the link. During prediction, current travel times on the link are collected for current seasonal intervals to determine current inflows. A most recent travel time is subtracted from a most recent inflow to obtain a current deviation. For a future time, a predicted deviation is estimated using the statistics. The seasonal component is added to the predicted deviation to obtain a predicted inflow from which the future travel time is predicted.