Abstract: An example method of estimating the angular resolution of antenna array comprises: receiving a plurality of values of magnitude and phase of a radio frequency (RF) signal for each antenna element of a plurality of antenna elements comprised by an antenna array; performing, by a machine learning model, a feature extraction operation to transform the plurality of values of magnitude and phase into a plurality of data points in a reduced-dimension space; clustering, by the machine learning model, the plurality of data points into a plurality of clusters; and computing, based on the clustered data points, an angular resolution value for the antenna array.

Abstract: Systems and methods provide a first sample of audio data and detect speech onset in the first sample of the audio data. Responsive to detecting the speech onset, systems and methods switch from capturing second samples of the audio data at first intervals, to capturing the second samples of the audio data at second intervals. Systems and methods provide contiguous audio data using the second samples of the audio data captured at the first intervals and at least one captured portion of the second samples of the audio data captured at the second intervals.

Abstract: Techniques by a wireless to estimate the position of a remote device are disclosed. A main receiver of the wireless device may determine multiple first phase values of the RF signal received through a first antenna during multiple time intervals. An auxiliary receiver may determine multiple second phase values of the RF signal received through an array of auxiliary antennas during the multiple time intervals. Each of the second phase value may correspond to the RF signal received through one antenna of the array during one of the time interval. The wireless device may determine an oscillator offset between a local oscillator of the main transceiver and a local oscillator of the auxiliary receiver. The wireless device may estimate an angle of arrival (AoA) of the RF signal or a distance based on the multiple first phase values and the multiple second values by compensating for the oscillator phase offset.

Abstract: In an example embodiment, a device comprises one or more processors and a baseband controller. The one or more processors are configured to: determine, from a payload of at least one received packet, a channel identification (ID) of a notice window in a sequence of transmission windows; transmit, in the notice window, a notice packet that identifies a target window, the target window being later in the sequence of transmission windows than the notice window; generate a target packet that includes inverse whitened data; and transmit the target packet in the target window. The baseband controller is configured to execute signal whitening on the target packet, where the signal whitening of the inverse whitened data in the target packet results in a substantially sinusoidal signal when the target packet is transmitted by the device.

Abstract: A passive entry, passive start (PEPS) application is described, wherein a number of sensors are configured with wireless communication protocol information for wireless communication between a master device and a BLE hub. The sensors eavesdrop signals from the master device to the BLE hub while not in operative communication with the master device. Eavesdropped signals are processed to determine and calculate position-related information, such as phase and magnitude of the wireless signals received at multiple antennas of the sensors, angle-of-arrival (AoA), and distance or position of the master device relative to the sensors, individually or as a system. Power management techniques for a PEPS system are also described.

Abstract: An example method of operating a device includes using a switching circuitry to a first subset of antennas from an antenna cluster, using the first subset of antennas to receive a first Bluetooth signal, generating a first directional value of the first Bluetooth signal, using a processing element to evaluate at least one antenna of the antenna cluster based at least partly on the first directional value, selecting a second subset of antennas based on evaluation, using the second subset of antennas to receive a second Bluetooth signal, and generating a second directional value of the second Bluetooth signal. Other embodiments of the device and operations thereof are also disclosed.

Abstract: An example method of estimating the angular resolution of antenna array comprises: receiving a plurality of values of magnitude and phase of a radio frequency (RF) signal for each antenna element of a plurality of antenna elements comprised by an antenna array; performing, by a machine learning model, a feature extraction operation to transform the plurality of values of magnitude and phase into a plurality of data points in a reduced-dimension space; clustering, by the machine learning model, the plurality of data points into a plurality of clusters; and computing, based on the clustered data points, an angular resolution value for the antenna array.

Abstract: An example method for estimating the angle-of-arrival (AoA) and other parameters of radio frequency (RF) signals that are received by an antenna array comprises: receiving a plurality of radio frequency (RF) signal power measurements by a plurality of antenna elements at a plurality of RF channels; computing, by applying a machine learning model to the plurality of RF signal power measurements, an estimated RF signal parameter value; and outputting the RF signal parameter value.

Abstract: A system includes a transceiver configured to receive frequency dependent channel estimates or beamforming feedback in a multi-carrier, multi-antenna communication system, and a multi-layer perceptron feed forward neural network component, coupled with the transceiver, configured to estimate parameters of multipath reflections using representations of the channel estimates or beamforming feedback, and to generate transmission correction factors for the transceiver.

Abstract: A system includes a transceiver configured to receive frequency dependent channel estimates or beamforming feedback in a multi-carrier, multi-antenna communication system, and a multi-layer perceptron feed forward neural network component, coupled with the transceiver, configured to estimate parameters of multipath reflections using representations of the channel estimates or beamforming feedback, and to generate transmission correction factors for the transceiver.

Abstract: A phrase detection device includes a high latency pipeline to transmit a first portion of audio data from an audio data source to a processing unit, where the high latency pipeline includes a history buffer to store the first portion of the audio data, and a low latency pipeline to transmit a second portion of the audio data from the audio data source to the processing unit with a lower latency than the high latency pipeline. A sound onset detector coupled with the audio data source detects a sound onset event based on the audio data. A synchronization circuit coupled with the high latency pipeline and the low latency pipeline, in response to the sound onset event, synchronizes output to the processing unit of the first portion of the audio data stored in the history buffer and the second portion of the audio data via the low latency pipeline.

Abstract: A passive entry, passive start (PEPS) application is described, wherein a number of sensors are configured with wireless communication protocol information for wireless communication between a master device and a BLE hub. The sensors eavesdrop signals from the master device to the BLE hub while not in operative communication with the master device. Eavesdropped signals are processed to determine and calculate position-related information, such as phase and magnitude of the wireless signals received at multiple antennas of the sensors, angle-of-arrival (AoA), and distance or position of the master device relative to the sensors, individually or as a system. Power management techniques for a PEPS system are also described.

Abstract: An example method of operating a device includes using a switching circuitry to a first subset of antennas from an antenna cluster, using the first subset of antennas to receive a first Bluetooth signal, generating a first directional value of the first Bluetooth signal, using a processing element to evaluate at least one antenna of the antenna cluster based at least partly on the first directional value, selecting a second subset of antennas based on evaluation, using the second subset of antennas to receive a second Bluetooth signal, and generating a second directional value of the second Bluetooth signal. Other embodiments of the device and operations thereof are also disclosed.

Abstract: In an example embodiment, a device comprises one or more processors and a baseband controller. The one or more processors are configured to: determine, from a payload of at least one received packet, a channel identification (ID) of a notice window in a sequence of transmission windows; transmit, in the notice window, a notice packet that identifies a target window, the target window being later in the sequence of transmission windows than the notice window; generate a target packet that includes inverse whitened data; and transmit the target packet in the target window. The baseband controller is configured to execute signal whitening on the target packet, where the signal whitening of the inverse whitened data in the target packet results in a substantially sinusoidal signal when the target packet is transmitted by the device.

Abstract: An apparatus includes a wireless transceiver configured to communicate data with a network device. The apparatus also includes a processing device, operatively coupled with the wireless transceiver. The processing device is configured to determine whether a computing device coupled to the apparatus has data to transmit to the network device. The processing device is also configured to transmit a first message indicating that the computing device does not have data to transmit to the other device in response to determining that the computing device does not have data to transmit to the network device. The processing device is further configured to transition the apparatus to a reduced power state. The apparatus uses less power in the reduced power state than in an active state.

Abstract: An example method of a wireless device includes, determining a first attribute value of a first radio frequency (RF) signal received through a first antenna during a first period, determining a first attribute value of a second RF signal received through the first antenna during a second period, determining a second attribute value of the first RF signal received through a second antenna during the first period, and determining a second attribute value of the second RF signal received through a third antenna during the second period. The method further includes compensating for a determined difference between a first offset introduced by a first oscillator and a second offset introduced by a second oscillator and then estimating an angle of arrival associated with the first and second RF signals, based on attribute values of the first RF signal and the second RF signal.

Abstract: A method can include, by operation of a first device, generating sequence information for a plurality of sequential transmission windows, the sequence information including at least a channel identification (ID) corresponding to a base frequency for each window; generating payload data for a packet and wirelessly transmitting the packet in one of the windows, the payload data including sequence information for a window later in the sequence than the window in which the packet is transmitted. By operation of an application executed on a second device, a target packet can be composed that includes inverse whitened data; wherein the whitening of the inverse whitened data by the second device results in a substantially sinusoidal signal when the target packet is transmitted. The first device can determine a direction of the second device by processing the substantially sinusoidal signal. Devices for executing such a method are also disclosed.

Abstract: An example apparatus uses a transceiver to determine a first attribute value of a first RF signal received through a first antenna during a first period. An attribute estimator determines a second attribute value of the first RF signal received through a second antenna during the first period. Responsive to a control signal, the apparatus switches the attribute estimator from being coupled to the second antenna to being coupled to a third antenna. The apparatus then uses the transceiver to determine a first attribute of a second RF signal received through the first antenna during a second period and uses the attribute estimator determine a second attribute of the second RF signal received through the third antenna during the second period. The apparatus then can estimate an angle of arrival associated with the first and second RF signals based on the first and second attributes of the first RF signal and the first and second attributes of the second RF signal.

Abstract: Systems and methods provide a first sample of audio data and detect speech onset in the first sample of the audio data. Responsive to detecting the speech onset, systems and methods switch from capturing second samples of the audio data at first intervals, to capturing the second samples of the audio data at second intervals. Systems and methods provide contiguous audio data using the second samples of the audio data captured at the first intervals and at least one captured portion of the second samples of the audio data captured at the second intervals.

Abstract: Disclosed herein are systems, methods, and devices for time of arrival estimation in wireless systems and devices. Devices include a packet detector configured to identify a data packet included in a received signal having a symbol frequency. Devices also include a time stamping unit configured to generate an initial time stamp in response to the packet detector identifying the data packet. Devices further include an IQ capture unit configured to acquire a plurality of IQ samples representing phase features of the received signal. Devices additionally include a processing unit that includes one or more processors configured to generate an estimated time of arrival based on the initial time stamp and the plurality of IQ samples.