Robert Boschgmbh

Amazon Technologies, Inc.

Jonathan Jenner Macoskey

Samarjit Das

Ariya Rastrow

Grant Strimel

Soeren Wildemann

A method for self-diagnosing a data acquisition system for acquiring calibrated images of an area by a controller includes requesting a signal, from a sensor associated with a mobile platform in the area, removing from the signal, background noise associated with the mobile platform, thereby focusing the measurement to a foreground signal, wherein the background noise is removed from the foreground signal via a subspace approximation using singular value, requesting a previous-in-time signal indicative of a previous-in-time measurement of the parameter, wherein previous-in-time background noise is removed from a previous-in-time foreground signal via subspace approximation using singular value decomposition and in response to a change detection indicating a difference between a spectrogram of the background noise and a previous-in-time spectrogram of the previous-in-time background noise exceeding a predetermined threshold at a predetermined frequency, outputting a status signal indicative of a change in operating characteristics of the mobile platform.

Dynamic spatiotemporal beamforming self-diagonostic system

Techniques for using multiple machine learning (ML) models, with varying compute costs, for ASR processing is described. The system may include an arbitrator component configured to determine which ML model is to be used to process an audio frame from a sequence of audio frames representing a spoken natural language input. The arbitrator component may switch between the ML models, on a frame-by-frame basis, to reduce an overall compute cost for the entire spoken natural language input. The outputs of the different ML models may be combined to determine the final output for the entire spoken natural language input.

Speech processing techniques

A system for detecting vehicle body damage is disclosed. One or more ultrasonic transceivers are installed on a portion of the vehicle body and configured to transmit and receive ultrasonic sound waves. One or more controllers are coupled to the one or more ultrasonic transceivers. The one or more controllers are programmed to cause the ultrasonic transceiver to emit first ultrasonic sound waves and receive first reflected ultrasonic sound waves, store in memory first sound signature data relating to the first reflected ultrasonic sound waves, cause the ultrasonic transceiver to emit second ultrasonic sound waves and receive second ultrasonic sound waves, and determine a presence of damage on the portion of the vehicle body based on second sound signature data relating to the second reflected ultrasonic sound waves deviating from the first sound signature data.

Using sound to detect vehicle body anomalies

Some devices may perform processing using machine learning models trained at a centralized system and distributed to the device. The centralized system may update the machine learning model and distribute the update to the device (or devices). To reduce the size of an update, the centralized system may train a model update object, which may be smaller in size than the model itself and thus more suitable for sending to the device(s). A device may receive the model update object and use it to update the on-device machine learning model; for example, by changing some parameters of the model. Parameters left unchanged during the update may retain their previous value. Thus, using the model update object to update the on-device model may result in a more accurate updated model when compared to sending an updated model compressed to a size similar to that of the model update object.

Updating models with trained model update objects

A method for imaging a room by a controller includes requesting a signal, indicative of a measurement of a parameter, from a sensor associated with a position and direction of a mobile platform in the room, wherein the measurement from the sensor includes background noise, distortions, and a foreground signal of interest, in response to the mobile platform reaching a new position, requesting a second measurement of the parameter from the sensor associated with the new position of the mobile platform, spatially aggregating the signal from the sensor and associated position and direction to create an energy map via spatio-dynamic beamforming, wherein the background noise and distortions are reduced, by spatially averaging beamformed information acquired across multiple locations to synthesize signals indicative of the foreground signal of interest, analyzing the energy map to identify a state of an apparatus in the room, and outputting a foreground beamformed image.

Dynamic spatiotemporal beamforming

A mobile platform for calibrated data acquisition includes a transceiver within the mobile platform, a locomotion unit configured to move the mobile platform within an area, a sensor coupled with the locomotion unit and configured to output a signal, and a controller that is configured to request a measurement of a parameter from the sensor, remove from the measurement, background noise associated with the mobile platform, thereby focusing the measurement to foreground noise, in response to the mobile platform reaching a new position and direction, request a second measurement of the parameter from the sensor, remove from the second measurement, background noise associated with the mobile platform at the new position, aggregate the signal from the sensor and associated position and direction to create an energy map via spatio-dynamic beamforming, and analyzing the energy map to identify a state of an apparatus in the area.

Growing community of inventors

Pittsburgh, PA, United States of America

Jonathan Jenner Macoskey