Abstract: Provided are systems and methods for path-based navigation of tubular networks. In one aspect, the method includes receiving location data from at least one of a set of location sensors and a set of robot command inputs, the location data being indicative of a location of an instrument configured to be driven through a luminal network. The method also includes determining a first estimate of the location of the instrument at a first time based on the location data, determining a second estimate of the location of the instrument at the first time based on the path, and determining the location of the instrument at the first time based on the first estimate and the second estimate.

Abstract: Disclosed herein are system, method, and computer program product embodiments for providing a diversified cryptographic Root of Trust for application instances installed on different user devices. After installing an application, a client device transmits, to a cryptography server, (1) an application identification corresponding to a key from an operating system key store on the client device and (2) a device identification specific to an instance of the application on the client device. The cryptography server uses this data to generate and transmit a unique device fingerprint to the client device. The client device then diversifies a white-box cryptography (WBC) library using the application identification, the device identification, and the device fingerprint. The diversified WBC library protects the storage of cryptographic keys obtained from the cryptography server. These keys protect sensitive data on the client device and sensitive data sent to the cryptography server and other application servers.

Abstract: A method, comprising receiving at least one sound at an electronic device. The at least one sound is enhanced for the at least one user based on a compound metric. The compound metric is calculated using at least two sound metrics selected from an engineering metric, a perceptual metric, and a physiological metric. The engineering metric comprises a difference between an output signal and a desired signal. At least one of the perceptual metric and the physiological metric is based at least in part on input sensed from the at least one user in response to the received at least one sound.

Abstract: The present disclosure relates to systems, methods, and non-transitory computer-readable media that generates a digital data visualization from data of an analytics database. In particular, in some embodiments, the disclosed systems receive a digital text prompt that includes a target digital data visualization description. Furthermore, in some embodiments the disclosed systems generate visualization token predictions from the digital text prompt utilizing a language machine learning model. Moreover, in some embodiments the disclosed systems modify the visualization token predictions to generate refined visualization tokens and generates the digital data visualization based on the refined visualization tokens.

Abstract: A method, apparatus, non-transitory computer readable medium, apparatus, and system for image processing include obtaining a text prompt and an input image depicting a person, generating a latent code based on the text prompt and the input image, wherein the latent code is optimized by an identity preserving loss, and generating, using an image generator of a machine learning model, a synthetic image based on the latent code, wherein the synthetic image includes an element of the text prompt and preserves an identity of the person in the input image.

Abstract: A system comprises an ear-worn electronic device configured to be worn by a wearer. The ear-worn electronic device comprises a processor and memory coupled to the processor. The memory is configured to store an annoying sound dictionary representative of a plurality of annoying sounds pre-identified by the wearer. A microphone is coupled to the processor and configured to monitor an acoustic environment of the wearer. A speaker or a receiver is coupled to the processor. The processor is configured to identify different background noises present in the acoustic environment, determine which of the background noises correspond to one or more of the plurality of annoying sounds, and attenuate the one or more annoying sounds in an output signal provided to the speaker or receiver.

Abstract: A surface treatment of a printed trace improves electrical conductivity at a contact area defining an insertion or engagement of a circuit element. Mechanical and chemical treatment at a contact area of an extruded trace generated from 3-dimensional (3D) printing techniques mitigates resistance of the surface. A conductive trace may be extruded from a conductive filament material including conductive granules, flakes or powder. A solvent or etchant applied to the extruded surface at the contact point removes, dissolves or otherwise abrades the contact area. A mechanical drilling or incision may also be applied. Dissolution of the non-conductive material exposes the conductive material for improved contact with a conductive epoxy or paste applied to the contact area for receiving a conductive terminal (pin or pad) from a circuit element.

Abstract: A surgical robotic system automatically calibrates tubular and flexible surgical tools such as endoscopes. By compensating for unideal behavior of an endoscope, the surgical robotic system can accurately model motions of the endoscope and navigate the endoscope while performing a surgical procedure on a patient. During calibration, the surgical robotic system moves the endoscope to a target position and receives data describing an actual position and/or orientation of the endoscope. The surgical robotic system determines gain values based at least on the discrepancy between the target position and the actual position. The endoscope can include tubular components referred to as a sheath and leader. An instrument device manipulator of the surgical robotic system actuates pull wires coupled to the sheath and/or the leader, which causes the endoscope to articulate.

Abstract: Co-manipulation robotic systems are described herein that may be used for assisting with laparoscopic surgical procedures. The co-manipulation robotic systems allow a surgeon to use commercially-available surgical tools while providing benefits associated with surgical robotics. Advantageously, the surgical tools may be seamlessly coupled to the robot arms using a disposable coupler while the reusable portions of the robot arm remain in a sterile drape. Further, the co-manipulation robotic system may operate in multiple modes to enhance usability and safety, while allowing the surgeon to position the instrument directly with the instrument handle and further maintain the desired position of the instrument using the robot arm.

Abstract: The present application relates to generating adaptive protective relay event reports. In one embodiment, a system comprises a power system response subsystem to monitor electrical parameters in an electric power system and to receive a trigger signal from a trigger source based on identification of an event in an electric power system. An adaptive event report subsystem is configured to generate an adaptive report depending on the trigger related to the event and based on a pre-trigger start, a duration, and a sampling rate. The adaptive event report comprises at least one electrical parameter related to the event beginning at a time established by the pre-trigger start, covering an interval established by the duration, and recorded at the sampling rate.

Abstract: The present invention is related to data processing methods and systems thereof. According to an embodiment, the present invention provides a method of processing claim deduction documents using a machine learning model. The process begins by accessing data files and extracting information from them, which is subsequently stored. This document information, along with the machine learning model trained on various document formats, is used to classify the data files and generate tabular data. From this tabular data, data objects are created and included in an output data file. The information from the output file is then used to update the data of the machine learning model, optimizing it for improved future document processing. There are other embodiments as well.

Abstract: Real-time audio enhancement for a target speaker may be performed. An embedding of a sample of speaker audio is created using a trained neural network that performs voice identification. The embedding is then concatenated with the input features of a trained machine learning model for audio enhancement. The audio enhancement model can recognize and enhance a target speaker's speech in a real-time implementation, as the embedding is in the same feature space of the audio enhancement model.

Abstract: Examples herein provide an approach to enhance an audio mixture of a teleconference application by switching between noise suppression modes using a single model. Specifically, a machine learning (ML) model may be configured to, in response to receiving an audio mixture representation as input, suppress either a background noise of the audio mixture or suppress all noise of the audio mixture except a user's voice. In some examples, the ML model may be trained on speech and background noise training data during a training phase. In addition, the ML model may be trained on a user's voice during an enrollment phase. In addition, during an inference phase, the ML model may enhance the audio mixture by suppressing a portion of the audio mixture.

Abstract: Graphic visualizations, such as charts or graphs conveying data attribute values, can be generated based on natural language queries, i.e., natural language requests. To do so, a natural language request is parsed into n-grams, and from the n-grams, word embeddings are determined using a natural language model. Data attributes for the graphic visualization are discovered in the vector space from the word embeddings. The type of graphic visualization can be determined based on a request intent, which is determined using a trained intent classifier. The graphic visualization is generated to include the data attribute values of the discovered data attributes, and in accordance with the graphic visualization type.

Abstract: Embodiments are disclosed for performing content authentication. A method of content authentication may include dividing a query video into a plurality of chunks. A feature vector may be generated, using a fingerprinting model, for each chunk from the plurality of chunks. Similar video chunks are identified from a trusted chunk database based on the feature vectors using a multi-chunk search policy. One or more original videos corresponding to the query video are then returned.

Abstract: In aspects of event-based application interface transmission across mobile devices, a mobile device detects an event associated with a first application on the first mobile device; transmits an interface of a second application installed on the first mobile device to a second mobile device based on the event associated with the first application and a request to use the second application on the first mobile device; and receives, from the second mobile device, monitoring information associated with use of the second application on the second mobile device.

Abstract: Co-manipulation robotic systems are described herein that may be used for assisting with laparoscopic surgical procedures. The co-manipulation robotic systems allow a surgeon to use commercially-available surgical tools while providing benefits associated with surgical robotics. Advantageously, the surgical tools may be seamlessly coupled to the robot arms using a disposable coupler while the reusable portions of the robot arm remain in a sterile drape. Further, the co-manipulation robotic system may operate in multiple modes to enhance usability and safety, while allowing the surgeon to position the instrument directly with the instrument handle and further maintain the desired position of the instrument using the robot arm.

Abstract: Examples disclosed herein may involve a computing system configured to (i) after one or more sensor-equipped vehicles have traversed a real-world environment and captured sensor data that is representative of the real-world environment, perform an analysis of the sensor data; (ii) based on the analysis of the sensor data, derive a set of information about a traffic light within the real-world environment that includes one or more of (a) signal-face information that comprises an identification of each signal face of the traffic light or (b) traffic-rule information that comprises an indication of at least one traffic rule that is applicable to the traffic light; and (iii) encode the derived set of information about the traffic light into a map for the real-world environment.

Abstract: The present disclosure pertains to devices, systems, and methods for monitoring a generator. In one embodiment, the system may include a measurement subsystem to receive a plurality of split-phase measurements of branch currents associated with the at least one generator. A split-phase transverse differential monitoring subsystem may receive the plurality of split-phase measurements of branch currents associated with the at least one generator and may generate an offset value representing a standing split-phase current. A protective action subsystem may generate a first protective action based on the phasor operating current.

Abstract: Various disclosed embodiments are directed to using one or more algorithms or models to select a suitable or optimal variation, among multiple variations, of a given content item based on feedback. Such feedback guides the algorithm or model to arrive at suitable variation result such that the variation result is produced as the output for consumption by users. Further, various embodiments resolve tedious manual user input requirements and reduce computing resource consumption, among other things, as described in more detail below.