Mitsubishi Electric Research Laboratories, Inc.

Mitsubishi Electric Corporation

Toshiaki Koike-Akino

Keisuke Kojima

Philip Orlik

Kieran Parsons

David Millar

Pu Wang

Bingnan Wang

Milutin Pajovic

Satoshi Nishikawa

Ye Wang

Eiji Yagyu

Kyeong Jin Kim

Mitsunobu Gotoda

Stark C Draper

Rui Ma

Tobias Fehenberger

Koon Hoo Teo

Petros T Boufounos

Koichi Akiyama

Chunjie Duan

Yebin Wang

Qiuyao Zhu

Mohammad Tahersima

Tsuyoshi Yoshida

Jianlin Guo

Karl Berntorp

Hassan Mansour

Chungwei Lin

Yige Wang

Andrei Kniazev

Ramesh Annavajjala

Man-On Pun

Yacong Ding

Wei Liu

Kosuke Shinohara

Yuichiro Horiguchi

Yingheng Tang

Wangqing Yuan

Yehan Ma

Jianyuan Yu

Min Teng

Haoyu Fu

Maxim Goukhshtein

Manuela Felicetti

Jesper H Soerensen

Arindam Bose

Selman Ozbayat

Tiangao Gou

Cheng Liu

Yuxuan Xia

Muhammad Tahersima

Xiaoming Duan

Pavel Skvortcov

Okan Atalar

Mohammad Hossein Taher Sima

Andac Demir

Deniz Erdogmus

Provided herein is a method for controlling a manipulator, comprising accepting an initial pose of a load and a task for moving the load and retrieving using a mapping function, an identification trajectory corresponding to the initial pose of the load and controlling a plurality of actuators of the manipulator to move the load according to the retrieved identification trajectory and obtaining measured motion data and estimated motion data of the load each corresponding to motion of the load. The method further comprises estimating parameters of the load based on the measured motion data and the estimated motion data, obtaining a model of the manipulator having the load with the estimated parameters, and determining a performance trajectory to move the load according to the task based on the obtained model of the manipulator. The method further comprises controlling the actuators to move the load according to the performance trajectory.

Systems and methods for flexible robotic manipulation by fast online load estimation

A method for a target image reconstruction is provided. The method includes emitting stepped frequency waveforms having different constant frequencies at different periods of time, modulating the stepped frequency waveforms into frequency ranges each having a first frequency and a second frequency, wherein each of the stepped frequency waveforms are increased from the first frequency to the second frequency based on a range function, wherein the modulated stepped frequency waveforms are arranged with some sparsity factor. The method further includes transmitting the modulated stepped frequency waveforms to a target and accepting reflection of the modulated stepped frequency waveforms reflected from the target interfering the modulated stepped frequency waveforms and the reflection of the modulated stepped frequency waveforms to produce beat signals of interferences between the modulated stepped frequency waveforms and the reflection of the modulated stepped frequency waveforms, and reconstructing an image of the target from the beat signals.

Coherent optical sensor with sparse illumination

A system for automated construction of an artificial neural network architecture is provided. The system includes a set of interfaces and data links configured to receive and send signals, wherein the signals include datasets of training data, validation data and testing data, wherein the signals include a set of random number factors in multi-dimensional signals X, wherein part of the random number factors are associated with task labels Y to identify, and nuisance variations S. The system further includes a set of memory banks to store a set of reconfigurable deep neural network (DNN) blocks, hyperparameters, trainable variables, intermediate neuron signals, and temporary computation values including forward-pass signals and backward-pass gradients. The system further includes at least one processor, in connection with the interface and the memory banks, configured to submit the signals and the datasets into the reconfigurable DNN blocks, wherein the at least one processor is configured to execute a Bayesian graph exploration using the Bayes-Ball algorithm to reconfigure the DNN blocks such that redundant links are pruned to be compact by modifying the hyperparameters in the memory banks. The system realizes nuisance-robust variational Bayesian inference to be transferable to new datasets in semi-supervised settings.

Automated construction of neural network architecture with Bayesian graph exploration

A Bluetooth-enabled device is provided, the Bluetooth-enabled device being configured to control a radio frequency (RF) chain during a first period to receive at a single antenna selected from a plurality of antennas, a constant tone extension (CTE) signal of multiple frames transmitted by the Bluetooth-enabled transmitter over multiple frequencies. Further the RF chain is controlled during a second period to switch among the plurality of antennas to receive the CTE signal at each of the plurality of antennas. An initial time-of-flight (ToF) data of the CTE signal is determined from first samples of the CTE signal received during the first period. Further, the Bluetooth-enabled transmitter is localized with respect to a location of the Bluetooth-enabled device using a signal model connecting samples of the CTE signal with an unknown angle-of-arrival of the CTE signal received at specific times, an unknown ToF conditioned on the initial ToF data.

Bluetooth-based spatial-temporal localization

Data communications and storage systems require error control techniques and digital modulation schemes to be transferred efficiently and successfully. Constellation shaping based on probabilistic amplitude shaping (PAS) offers an energy-efficient transmission in particular for long shaping blocks. However, longer shaping blocks can cause burst errors and enhancement of bit error rates besides longer latency to complete distribution matcher and dematcher operations. Methods and systems are disclosed that provide a way to resolve the issues by introducing a dual concatenation of pre-shaping and post-shaping error correction codes to mitigate burst errors of shaping. This enables low-complexity, high-performance and parallel architecture with a balanced overhead of dual-concatenation codes for shaping systems.

Systems and methods for dual coding concatenation in probabilistic amplitude shaping

A system for flexible regularization and adaptable scaling of an artificial neural network is provided. The system includes a memory to store an artificial neural network and training data, a processor and interface to submit signals and training data into the neural network having a sequence of layers, each layer includes a set of neuron nodes, wherein a pair of nodes from neighboring layers are mutually connected with a plural of trainable parameters to pass the signals from the previous layer to next layer, a random number generator to modify the output signal of each neuron nodes for regularization in a stochastic manner following a multi-dimensional distribution across layer depth and node width directions of the neural network, wherein at least one layer has non-identical profile across neuron nodes, a training operator to update the neural network parameters by using the training data such that the output of neural network provides better values in a plural of objective functions; and an adaptive truncator to prune the output of neuron nodes at each layer in a compressed size of the neural network to reduce the computational complexity on the fly in downstream testing phase for any new incoming data.

Non-uniform regularization in artificial neural networks for adaptable scaling

A system and a method for tracking an expanded state of an object including a kinematic state indicative of a position of the object and an extended state indicative of one or combination of a dimension and an orientation of the object is provided herein. The system comprises at least one sensor configured to probe a scene including a moving object with one or multiple signal transmissions to produce one or multiple measurements of the object per the transmission, and a processor configured to execute a probabilistic filter tracking a joint probability of the expanded state of the object estimated by a motion model of the object and a measurement model of the object, wherein the measurement model includes a center-truncated distribution having truncation intervals. The system further comprises an output interface configured to output the expanded state of the object.

System and method for tracking expanded state of an object

Data communications and storage systems require error control techniques to be transferred successfully without failure. Polar coding has been used as a state-of-the-art forward error correction code for such an error control technique. However, the conventional decoding based on successive cancellation has a drawback in its poor performance and long latency to complete. Because the factor graph of polar codes has a lot of short cycles, a parallelizable belief propagation decoding also does not perform well. The method and system of the present invention provide a way to resolve the issues by introducing a protograph lifting expansion for a polar coding family so that highly parallelizable decoding is realized to achieve a high coding gain and high throughput without increasing the computational complexity and latency. The invention enables an iterative message passing to work properly by eliminating short cycles through a hill-climbing optimization of frozen bits allocation and permutation.

Protograph quasi-cyclic polar codes and related low-density generator matrix family

A system is provided for training a device design network. The system includes an interface configured to input data of a device, a memory to store the device design network including an encoder, a decoder, and an adversarial block, and a processor. The processor is, in connection with the memory, configured to update the encoder and the decoder based on a first loss function to reduce the difference between the input data and output data of the decoder, wherein the encoder is constructed by at least one convolutional layer followed by at least one parallel fully connected layer to extract features of a layout of the device, and update the adversarial block to construct by maximizing a second loss function.

Generative model for inverse design of materials, devices, and structures

A system for keyless entry applications using beamforming transmission in a millimeter wave spectrum in an environment. A memory with data including values indicative of link attributes associated with beam signal measurements with states of devices and states of environments. The states of the devices for each device including types of user behavior, locations and poses in each environment. Control circuitry performs beam training with a target device associated with at least one keyless entry application in the environment to measure beam signal values and environmental responses for different beams transmitted over the different beam angles. Selects, in response to the beam training, at least one dominant angle for a beamforming communication with the target device. Estimates, a state of the target device associated with the at least one keyless entry application or a state of the environment, corresponding to environmental responses for different beams estimated during the beam training.

Localization using millimeter wave beam attributes for keyless entry applications

A grating coupler having first and second ends for coupling a light beam to a waveguide of a chip includes a substrate configured to receive the light beam from the first end and transmit the light beam through the second end, the substrate having a first refractive index n1, a grating structure having curved grating lines arranged on the substrate, the grating structure having a second refractive index n1, wherein the curved grating lines have line width w and height d and are arranged by a pitch &#x39b;, wherein the second refractive index n2 is less than first refractive index n1, and a cladding layer configured to cover the grating structure, wherein the cladding layer has a third refractive index n3.

Integrated grating coupler

A communication system using beamforming transmission in a millimeter wave spectrum in an environment. A memory with data including values indicative of link attributes associated with beam signal measurements with states of devices and states of environments. The states of the devices for each device including types of user behavior, locations and poses in each environment. The states of the environments for each environment including, locations of physical objects and types of behavior of ambient users. Control circuitry performs beam training with a target device in environment to measure beam signal values and environmental responses for different beams transmitted over the different beam angles. Selects, in response to the beam training, at least one dominant angle for a beamforming communication with the target device. Estimates, one of a state of the target device or a state of the environment, corresponding to environmental responses for different beams estimated during the beam training.

Localization using millimeter wave beam attributes

An apparatus for processing a perturbation quantity received in a wireless network. The perturbation quantity including a non-linear effect from at least one transmitted signal of the wireless network. The apparatus including a Base Station (BS) configured to establish a link between the BS and a user equipment (UE). A processing circuit is configured to implement receiver-side decoders. Wherein a receiver-side decoder is configurable to provide a recovery of unknown symbols perturbed by the perturbation quantity, the recovery is at a receiver-side and the perturbation is at the transmitter-side. Provide receiver-side decoding for symbol detection of symbol-dependent transmit-side perturbations by imposing a hierarchical signal model on the transmitted symbol. Wherein the decoding that is provided by the receiver-side decoders is used to recover the unknown symbols perturbed by the perturbation quantity and to identify symbol dependent perturbations, to reduce decoding processing costs by either the UE or the BS.

Symbol detection of massive MIMO systems with unknown symbol-dependent transmit-side impairments

A scanner for image reconstruction of a structure of a target object uses a neural network trained to classify each segment of a sequence of segments of a modified wave into one or multiple classes. The sequence of segments corresponds to the sequence of layers of the target object, such that a segment of modified wave corresponds to a layer having the same index in the sequence of layers as an index of the segment in the sequence of segments. The scanner executes the neural network for each wave modified by penetration through the layers of the target object to produce the classes of segments of the modified waves. Next, the scanner selects the classes of segments of different modified waves corresponding to the same layer to produce an image of the layer of the target object with pixel values being functions of labels of the selected classes.

Learning-based see-through sensing suitable for factory automation

An optical waveguide interferometer that includes a first optical section, a second optical section, and a set of optical waveguides configured to connect the first and second optical sections, such that light propagating between the first optical section and the second optical section passes through each optical waveguide in the set, wherein the set of optical waveguides includes a first optical waveguide having a first length and a first width and a second optical waveguide having a second length and a second width, wherein the second length is greater than the first length, and the second width is greater than the first width.

Optical waveguide interferometer

Growing community of inventors

Belmont, MA, United States of America

Toshiaki Koike-Akino