Abstract: A controller is provided for performing dynamic grasping of a target object using visual sensory inputs. The controller includes a robotic interface connected to a robotic arm including links connected by joints having actuators and encoders, and a gripper of the end-effector of the robotic arm configured to grasp the target object in response to robot control signals, and a vision sensor configured to continuously provide visual observations for tracking poses of the target object in a workspace and compute grasp poses, wherein the vision sensor is mounted on a distal end of the robotic arm adjacent to the gripper. The controller trains the Eye-on-Hand reinforcement learner policy, tracks the poses of the target object, and generates robot control signals to follow the target object while keeping it in the field of view of the vision sensor and grasp the target object in the workspace.

Abstract: The present disclosure provides a system and a method for controlling a motion of a robot from a starting point to a target point within a bounded space with a floorplan including one or multiple obstacles. The method includes solving for an electric potential in a bounded virtual space formed by scaling the floorplan of the bounded space with the one or multiple obstacles and applying charge to at least one bound of the bounded virtual space while treating the scaled obstacles as metallic surfaces with a constant potential value, wherein the electric potential provides multiple equipotential curves within the bounded virtual space. The method further includes selecting an equipotential curve with a potential value different from a potential value of an obstacle equipotential curve, determining a motion path based on the selected equipotential curve, and controlling the motion of the robot based on the determined motion path.

Abstract: A photonic device for splitting optical beams includes an input port configured to receive an input beam having an input power, a power splitter including perturbation segments arranged in a first region and a second region of a guide material having a first refractive index, each segment having a second refractive index, wherein the first region is configured to split the input beam into a first beam and a second beam, wherein and the second region is configured to separately guide the first and second beams, wherein the first refractive index is greater than the second refractive index, and output ports including first and second output ports connected the power splitter to respectively receive and transmit the first and second beams.

Abstract: A robust machine learning system is provided for robust machine learning. The robust machine learning system includes a processor, and a memory storing a robust machine learning program and a Group Representation Network (GRepsNet), wherein the robust machine learning program runining on the processor. In this case the processor is configured to receive an input dataset represented by a first group representation via input layers connected to the GrepsNet, pass/transmit the input dataset through the GRepsNet configured to generate an output dataset represented by an output group representation from the input dataset, wherein the output group is equivalent to the first group, and generate the output dataset from output layers connected to the GRepsNet.

Abstract: The present disclosure provides an audio system, a method and a system for facilitating operation of a machine. The machine includes actuators assisting tools to perform tasks. In an example, the audio system is configured to receive an audio mixture of signals generated by audio sources including at least one of the tools performing the tasks, or the actuators. The audio sources forming the audio mixture are identified by a location relative to a location of each microphone of a microphone array measuring the audio mixture. The audio system is configured to extract an audio signal from the audio mixture generated by an identified audio source, based on a correlation of spectral features in a multi-channel spectrogram of the audio mixture with directional information indicative of the relative location of the identified audio source. The audio system outputs the extracted audio signal to facilitate the operation of the machine.

Abstract: A method of image reconstruction of a structure of a scene comprises collecting measurements of intensities of a wave over a period of time. The intensities of the wave are modified by propagation of the wave in the scene. The method also comprises collecting depth information indicative of the structure of the scene at different values of depth of the scene. The different values of depth correlate with different time segments forming the period of time. The method also comprises processing the measurements with a guided recurrent neural network to sequentially learn features of the structure of the scene using the depth information as a guidance and rendering one or multiple images indicative of the features of the structure learned by the recurrent neural network.

Abstract: The present disclosure provides a multiple-input multiple-output (MIMO) radar system and a method for detecting an object in a scene. The method comprises transmitting frequency modulated continuous wave (FMCW) in a radio frequency (RF) band, and collecting radar measurements of the scene sampled in a time-frequency domain within an intermediate frequency (IF) bandwidth. The method further comprises transforming the radar measurements into range-doppler space to produce measurements of different segments of the scene for different range-doppler bins formed by intersections of different range bins with different Doppler bins, classifying a presence of the hypothetical transmitter at different segments of the scene according to a signal model with an internal classification, combining the results of the classification to produce parameters of the object, and outputting the parameters of the object.

Abstract: The present disclosure discloses a controller and a method for controlling an electric motor. The controller comprises a feedback controller configured to generate a reference voltage vector, a hybrid flux observer configured to estimate a flux error vector based on a difference between a first stator flux linkage observed and a second stator flux linkage, and a position observer configured to estimate a position of a rotor of the electric motor based on a projection of the flux error vector in a direction orthogonal to a direction of a voltage error vector shifted with a phase of dynamics of the hybrid flux observer. The controller further comprises a state estimator configured to estimate a value of a state of operation of the electric motor based on the estimated position of the rotor, thereby closing a feedback control loop of the feedback controller.

Abstract: A cascaded controller for controlling a kinetic three-phase synchronous machine comprises a current control circuitry and an active power control circuitry operatively coupled with the current controller circuitry. The current control circuitry is configured to regulate a magnitude of inrush stator current for a stator of the kinetic three-phase synchronous machine by producing a first voltage control signal causing a flow of active power in the kinetic three-phase synchronous machine. The active power control circuitry is configured to produce a second voltage control signal to reduce the active power to zero, based on the first voltage control signal. The second voltage control signal controls a phase angle of the inrush stator current such that the stator current vector is oriented to align with a magnet axis of the rotor.

Abstract: A fault detection system is provided to extract fault signature from the time-domain stator current signal of a motor under varying load operations by solving a joint blind deconvolution-demodulation problem, where the stator current of a motor under varying operating conditions is modeled as a stator current of a steady operating condition influenced by the system response vector and a load modulation vector. A proximal alternating linearized minimization-type method is used to solve the joint blind deconvolution-demodulation problem, assuming that the spectrum of the sought-after signal is sparse. Motor fault detection is then performed using the recovered stator current of a steady operating condition.

Abstract: A controller is provided for operating a system under admissible states. The controller includes an interface configured to connect the system storing a set of measured system states, a set of reference inputs and a set of system parameters in a storage arranged inside or outside the system, a memory storing measured system states, admissible reference inputs and admissible parameter sets and computer-executable programs including a parameter estimator and an adaptive reference governor (ARG), a processor, in connection with the memory. The processor is configured to perform the ARG and the parameter estimator. The parameter estimator extracts a pair of a reference input and the system state and compute a system parameter estimate based on the reference input and system state.

Abstract: A camera is provided for reconstructing the surface of the object. The camera includes an optical module configured to spatially separate photons reflected from an object in a scene to form at least two focused and distinctly polarized images on a sensor, wherein the sensor is configured to receive the at least two polarized images on pixels the sensor and generate intensity values of the pixels, and a computing module including a processor and a memory having instructions stored thereon. According to the instructions, the processor computes depth values at points of a surface of the object based on a ratio of the intensity values of the pixels with respect to the at least two polarized images and reconstructs the surface of the object from the computed depth values.

Abstract: A computer-implemented method for detecting anomaly of an operation of a machine based on a signal indicative of the operation of the machine performing a task, comprises collecting hyperbolic embeddings of the signal indicative of the operation of the machine. The hyperbolic embeddings lie in a hyperbolic space. The method further comprises performing the detection of the anomaly of the operation of the machine based on the hyperbolic embeddings to determine an anomaly score and rendering the anomaly score. The machine operation is controlled based on the rendered anomaly score.

Abstract: A computer-implemented method for estimating a vital sign of a subject comprises receiving a sequence of imaging photoplethysmography (iPPG) signals measured from different regions of a skin of the subject and executing a cross-domain unrolling optimization iteratively minimizing a difference between the received iPPG signals and reconstructed iPPG signals followed by processing the reconstructed iPPG signals with an iPPG neural network trained in the frequency domain with machine learning to enforce a learned structure on the frequency coefficients of the reconstructed iPPG signals. The method further comprises determining the vital sign signal of the subject from the frequency coefficients of the reconstructed iPPG signals upon reaching a termination condition of the cross-domain unrolling optimization and outputting the vital sign signal corresponding to the reconstructed iPPG signals.

Abstract: A computer-implemented method is provided for performing energy disaggregation of a distribution system-level net-load measurements using continuous-point-on-wave (CPOW) measurement units.

Abstract: High-level synthesis (HLS) is a complex design flow that exploits the benefit of modern language features such as loops, inheritance, templates, etc. for rapid prototyping of hardware designs. Hardware engineers explore various design space parameters in a time-consuming trial-and-error approach to meet a target design specification. This invention provides a framework where machine learning methods are integrated with Bayesian optimization (BO) to accelerate hardware design in HLS. This tool is built around the context of HLS pragma exploration and kernel transformation. It can produce best set of pragma installments to determine parameters by optimizing on multi-objective functions, such as reduction of digital signal processor, flip-flop, look-up table, power consumption, and latency. The method uses classical deep neural network and quantum neural network for reinforcement meta learning to predict the synthesis characteristics and synthesizability under a given time budget.

Abstract: A motor assembly comprising a mover assembly and a stator. The mover assembly comprising a plurality of mover assembly units, each unit comprising: a non-ferromagnetic core with a profile of an outer surface having at least two flat sections lying on intersecting planes; at least two ferromagnetic laminated structures arranged on the at least two flat sections of the non-ferromagnetic core, each ferromagnetic laminated structure includes a stack of ferromagnetic plates, each plate is covered with a non-conductive coating. Each ferromagnetic laminated structure is arranged on a corresponding flat section of the at least two flat sections of the non-ferromagnetic core such that side of each ferromagnetic plate is adjacent to the non-ferromagnetic core thereby making the ferromagnetic plates of the at least two ferromagnetic laminated structures lie on intersecting planes.

Abstract: A controller is provided for generating carrier signals controlling a pulse width modulation (PWM) inverter driving an electric actuator.

Abstract: A radar system for tracking an object in a scene by transmitting frequency modulated continuous wave (FMCW) is provided. The radar system is configured to collect radar measurements of the scene sampled in a time-frequency domain within an intermediate frequency (IF) bandwidth to which reflection of the transmitted FMCW is shifted by mixing with a copy of the FMCW, where a frequency dimension of the time-frequency domain is quantized into multiple frequency bins forming the frequency bandwidth, where a time dimension of the time-frequency domain is quantized into multiple time instances forming a time interval corresponding to the PRI, count a number of amplitude peaks of the radar measurements for each frequency bin at different instances of time, identify a number of frequency bins with their counts of the number of peaks above a pre-determined threshold, and determine at least a distance to the object based on frequency analysis of the radar measurements.

Abstract: A control system for controlling motion of elevators of a bank of elevators uses a neural network trained for an extended destination prediction of a person based on a partial trajectory of the person to produce a multinomial of the extended destination prediction. The multinomial has at least two dimensions including a first dimension of destinations of the person and a second dimension of time intervals of the person arriving at the destinations of the first dimension. The control system optimizes a schedule of the bank of elevators based on the multinomial, and further controls the bank of elevators according to the schedule.