Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training and deploying machine-learned compact representations of radio frequency (RF) signals. One of the methods includes: determining a first RF signal to be compressed; using an encoder machine-learning network to process the first RF signal and generate a compressed signal; calculating a measure of compression in the compressed signal; using a decoder machine-learning network to process the compressed signal and generate a second RF signal that represents a reconstruction of the first RF signal; calculating a measure of distance between the second RF signal and the first RF signal; and updating at least one of the encoder machine-learning network or the decoder machine-learning network based on (i) the measure of distance between the second RF signal and the first RF signal, and (ii) the measure of compression in the compressed signal.

Abstract: Methods and systems including computer programs encoded on computer storage media, for training and deploying machine-learned communication over RF channels.

Abstract: Methods and systems including computer programs encoded on computer storage media, for training and deploying machine-learned communication over radio frequency (RF) channels. One of the methods includes: determining first information; generating a first RF signal by processing using an encoder machine-learning network; determining a second RF signal that represents the first RF signal altered by transmission through a communication channel; determining a first property of the first signal or the second RF signal; calculating a first measure of distance between a target value of the first property and an actual value of the first or second RF signal; generating second information as a reconstruction of the first information using a decoder machine-learning network; calculating a second measure of distance between the first information and the second information; and updating at least one of the encoder machine-learning network or the decoder machine-learning network based on the first and second measures.

Abstract: A method includes obtaining signal information corresponding to a plurality of radio signals received at two or more sensing devices from a candidate location, determining a plurality of reconstructed signals based on the signal information, determining time-estimates and frequency-estimates based on a correlation between the plurality of radio signals and the plurality of reconstructed signals, determining metadata corresponding to the plurality of radio signals based on the signal information, the time-estimates, or the frequency-estimates, transmitting at least a portion of the metadata to an information combining node, obtaining the portion of the metadata from the information combining node, determining a relationship between the metadata, and determining the candidate location based on the metadata and the relationship between the metadata.

Abstract: The present invention is an adjustable door sweep that would be available as either 1.) an accessory attached to the bottom of an exterior door or 2.) an integrated component of a newly manufactured exterior door. Both embodiments would feature a ½? thick, loose bundle of 2.5? long nylon sweep bristles running the width of the door and protruding from a ½?? aperture on the bottom of the door or accessory. When deployed from the bottom of the door or accessory, they would conform perfectly to the exact surface of the threshold.

Abstract: A task scheduling system that can be used to improve task assignment for multiple satellites, and thereby improve resource allocation in the execution of a task. In some implementations, configuration data for one or more satellites is obtained. Multiple objectives corresponding to a task to be performed using the satellites, and resource parameters associated with executing the task to be performed using the satellites are identified. A score for each objective included in the multiple objectives is computed by the terrestrial scheduler based on the resource parameters and the configuration data for the one or more satellites. The multiple objectives are assigned to one or more of the satellites. Instructions are provided to the one or more satellites that cause the one or more satellites to execute the task according to the assignment of the objectives to the one or more satellites.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for radio frequency band segmentation, signal detection and labelling using machine learning. In some implementations, a sample of electromagnetic energy processed by one or more radio frequency (RF) communication receivers is received from the one or more receivers. The sample of electromagnetic energy is examined to detect one or more RF signals present in the sample. In response to detecting one or more RF signals present in the sample, the one or more RF signals are extracted from the sample, and time and frequency bounds are estimated for each of the one or more RF signals. For each of the one or more RF signals, at least one of a type of a signal present, or a likelihood of signal being present, in the sample is classified.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training and deploying machine-learned identification of radio frequency (RF) signals.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for correcting distortion of radio signals A transmit radio signal corresponding to an output of a transmitting radio signal processing system is obtained. A pre-distorted radio signal is then generated by processing the transmit radio signal using a nonlinear pre-distortion machine learning model. The nonlinear pre-distortion machine learning model includes model parameters and at least one nonlinear function to correct radio signal distortion or interference. A transmit output radio signal is obtained by processing the pre-distorted radio signal through the transmitting radio signal processing system. The transmit output radio signal is then transmitted to one or more radio receivers.

Abstract: First information is obtained from a sensing device at a first time. The first information corresponds to a radio signal received at the device from a candidate location. The device is at a first location at the first time. Second information is obtained from the device at a second time. The second information corresponds to a radio signal received at the device from the candidate location. The device is at a second location at the second time. A system determines that a pattern is in each of the first and second information and determines relationships between the candidate location and the device at each first and second location. The system obtains inverses of the relationships and determines estimates of the received radio signals based on the information and inverses. The system measures or estimates energy emitted from the candidate location based on the estimates.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training and deploying machine-learned compact representations of radio frequency (RF) signals. One of the methods includes: determining a first RF signal to be compressed; using an encoder machine-learning network to process the first RF signal and generate a compressed signal; calculating a measure of compression in the compressed signal; using a decoder machine-learning network to process the compressed signal and generate a second RF signal that represents a reconstruction of the first RF signal; calculating a measure of distance between the second RF signal and the first RF signal; and updating at least one of the encoder machine-learning network or the decoder machine-learning network based on (i) the measure of distance between the second RF signal and the first RF signal, and (ii) the measure of compression in the compressed signal.

Abstract: One or more processors control processing of radio frequency (RF) signals using a machine-learning network. The one or more processors receive as input, to a radio communications apparatus, a first representation of an RF signal, which is processed using one or more radio stages, providing a second representation of the RF signal. Observations about, and metrics of, the second representation of the RF signal are obtained. Past observations and metrics are accessed from storage. Using the observations, metrics and past observations and metrics, parameters of a machine-learning network, which implements policies to process RF signals, are adjusted by controlling the radio stages. In response to the adjustments, actions performed by one or more controllers of the radio stages are updated. A representation of a subsequent input RF signal is processed using the radio stages that are controlled based on actions including the updated one or more actions.

Abstract: Methods and systems including computer programs encoded on computer storage media, for training and deploying machine-learned communication over radio frequency (RF) channels. One of the methods includes: determining first information; generating a first RF signal by processing using an encoder machine-learning network; determining a second RF signal that represents the first RF signal altered by transmission through a communication channel; determining a first property of the first signal or the second RF signal; calculating a first measure of distance between a target value of the first property and an actual value of the first or second RF signal; generating second information as a reconstruction of the first information using a decoder machine-learning network; calculating a second measure of distance between the first information and the second information; and updating at least one of the encoder machine-learning network or the decoder machine-learning network based on the first and second measures.

Abstract: First information corresponding to a radio signal received at a first sensing device from a candidate location is obtained. Second information corresponding to a radio signal received at a second sensing device from the candidate location is obtained. A first relationship between the first sensing device and the candidate location and a second relationship between the second sensing device and the candidate location are determined. A first inverse and a second inverse of respectively the first and second relationships are obtained. A first estimate of the radio signal at the first sensing device is determined from the first information and the first inverse. A second estimate of the radio signal at the second sensing device is determined from the second information and the second inverse. Energy emitted from the candidate location is measured based on the first estimate and the second estimate.

Abstract: An unmanned aerial system (UAS) detection device includes a sensor having programmed instructions to cause the sensor to scan energy in an electromagnetic spectrum; process the energy in the electromagnetic spectrum into bursts; determine whether the bursts are valid UAS bursts based on burst criteria; and correlate the bursts into a single signal.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training and deploying machine-learned communication over multi-input-multi-output (MIMO) channels.

Abstract: A task scheduling system that can be used to improve task assignment for multiple satellites, and thereby improve resource allocation in the execution of a task. In some implementations, configuration data for one or more satellites is obtained. Multiple objectives corresponding to a task to be performed using the satellites, and resource parameters associated with executing the task to be performed using the satellites are identified. A score for each objective included in the multiple objectives is computed by the terrestrial scheduler based on the resource parameters and the configuration data for the one or more satellites. The multiple objectives are assigned to one or more of the satellites. Instructions are provided to the one or more satellites that cause the one or more satellites to execute the task according to the assignment of the objectives to the one or more satellites.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a storage medium, for processing radio signals. In once aspect, a system is disclosed that includes a processor and a storage device storing computer code that includes operations. The operations may include obtaining first output data generated by a first neural network based on the first neural network processing a received radio signal, receiving, by a signal transformer, a second set of input data that includes (i) the received radio signal and (ii) the first output data, generating, by the signal transformer, data representing a transformed radio signal by applying one or more transforms to the received radio signal, providing the data representing the transformed radio signal to a second neural network, obtaining second output data generated by the second neural network, and determining based on the second output data a set of information describing the received radio signal.

Abstract: First information is obtained from a sensing device at a first time. The first information corresponds to a radio signal received at the device from a candidate location. The device is at a first location at the first time. Second information is obtained from the device at a second time. The second information corresponds to a radio signal received at the device from the candidate location. The device is at a second location at the second time. A system determines that a pattern is in each of the first and second information and determines relationships between the candidate location and the device at each first and second location. The system obtains inverses of the relationships and determines estimates of the received radio signals based on the information and inverses. The system measures or estimates energy emitted from the candidate location based on the estimates.

Abstract: A method includes obtaining signal information corresponding to a plurality of radio signals received at two or more sensing devices from a candidate location, determining a plurality of reconstructed signals based on the signal information, determining time-estimates and frequency-estimates based on a correlation between the plurality of radio signals and the plurality of reconstructed signals, determining metadata corresponding to the plurality of radio signals based on the signal information, the time-estimates, or the frequency-estimates, transmitting at least a portion of the metadata to an information combining node, obtaining the portion of the metadata from the information combining node, determining a relationship between the metadata, and determining the candidate location based on the metadata and the relationship between the metadata.