Techniques and apparatuses are described that enable full-duplex operation for radar sensing using a wireless communication chipset. A controller initializes or controls connections between one or more transceivers and antennas in the wireless communication chipset. This enables the wireless communication chipset to be used as a continuous-wave radar or a pulse-Doppler radar. By utilizing these techniques, the wireless communication chipset can be re-purposed or used for wireless communication or radar sensing.

Techniques and apparatuses are described that enable full-duplex operation for radar sensing using a wireless communication chipset. A controller initializes or controls connections between one or more transceivers and antennas in the wireless communication chipset. This enables the wireless communication chipset to be used as a continuous-wave radar or a pulse-Doppler radar. By utilizing these techniques, the wireless communication chipset can be re-purposed or used for wireless communication or radar sensing.

A method, apparatus and computer program product are provided to estimate the location of a vehicle based at least in part upon two or more road signs that are depicted by one or more images captured by one or more image capture devices onboard the vehicle. By relying at least in part upon the two or more road signs, the location of the vehicle may be refined or otherwise estimated with enhanced accuracy, such as in instances in which there is an inability to maintain a line-of-sight with the satellites of a satellite positioning system or otherwise in instances in which the location estimated based upon reliance on satellite or radio signals is considered insufficient. As a result, the vehicle may be navigated in a more informed and reliable manner and the relationship of the vehicle to other vehicles may be determined with greater confidence.

Techniques and apparatuses are described that implement a smart-device-based radar system capable of performing gesture recognition using a space time neural network. The space time neural network employs machine learning to recognize a user's gesture based on complex radar data. The space time neural network is implemented using a multi-stage machine-learning architecture, which enables the radar system to conserve power and recognize the user's gesture in real time (e.g., as the gesture is performed). The space time neural network is also adaptable and can be expanded to recognize multiple types of gestures, such as a swipe gesture and a reach gesture, without significantly increasing size, computational requirements, or latency.

Techniques and apparatuses are described that implement a smart-device-based radar system capable of performing gesture recognition using a space time neural network. The space time neural network employs machine learning to recognize a user's gesture based on complex radar data. The space time neural network is implemented using a multi-stage machine-learning architecture, which enables the radar system to conserve power and recognize the user's gesture in real time (e.g., as the gesture is performed). The space time neural network is also adaptable and can be expanded to recognize multiple types of gestures, such as a swipe gesture and a reach gesture, without significantly increasing size, computational requirements, or latency.

Systems, methods and circuitries are disclosed for compressing radar data. In one example, a radar sender unit includes adaptive compression circuitry configured to determine tuning data, wherein the tuning data is based on one or more operating conditions; compress radar data based on the tuning data; and transmit the compressed radar data to a radar control unit for further processing.

Systems, methods and circuitries are disclosed for compressing radar data. In one example, a radar sender unit includes adaptive compression circuitry configured to determine tuning data, wherein the tuning data is based on one or more operating conditions; compress radar data based on the tuning data; and transmit the compressed radar data to a radar control unit for further processing.

A computer assisted method for processing output from a mmWave sensor to derive a more reliable count of people in a room, zone or space being monitored by the sensor. In some examples, damping is applied to a varying “people count” signal from the sensor. The damping reduces volatility of the people count and avoids counting anomalous false positive detections. When the people count value decreases, damping may be applied more heavily to disregard intermittent false negatives where the sensor momentarily fails to detect an actual person. In some examples, the mmWave sensor provides point clouds representing the approximate shape and location of detected apparent objects, some of which may be people. Some example methods define digital targets corresponding to the point clouds. The targets are deemed to represent real people if the objects and their corresponding targets have sufficient lifespan and exhibit movement within a predetermined normal range.

A computer assisted method for processing output from a mmWave sensor to derive a more reliable count of people in a room, zone or space being monitored by the sensor. In some examples, damping is applied to a varying “people count” signal from the sensor. The damping reduces volatility of the people count and avoids counting anomalous false positive detections. When the people count value decreases, damping may be applied more heavily to disregard intermittent false negatives where the sensor momentarily fails to detect an actual person. In some examples, the mmWave sensor provides point clouds representing the approximate shape and location of detected apparent objects, some of which may be people. Some example methods define digital targets corresponding to the point clouds. The targets are deemed to represent real people if the objects and their corresponding targets have sufficient lifespan and exhibit movement within a predetermined normal range.

An apparatus comprising a processor configured to: receive an input dataset indicative of radar signals received at a plurality of antenna elements from a plurality of targets; define a matrix, Ã, of direction-of-arrival-angle vectors representing an expected response of the radar signals from the target and comprising a function of a direction of arrival angle relative to the antenna elements and including antenna-imperfection-factors that represent the angle dependent effect of antenna imperfections; define an objective function based on the input dataset and the matrix; search for a set of the direction of arrival angles for each of the plurality of targets by the repeated evaluation of the objective function for a plurality of candidate matrices based on matrix A, wherein said set is derived from one of the candidate matrices of the plurality of candidate matrices that provides a maximum or minimum evaluation of the objective function.