Abstract: A method for warning a wearer of a pacemaker against potential electromagnetic interference by a radar-aided mobile device is provided. The method includes obtaining sensor data from a sensor of an electronic device. The method includes detecting electromagnetic interference (EMI) risk based on the sensor data obtained. The method includes determining whether a condition for executing an EMI risk mitigation function is satisfied, based on the detected EMI risk. The method includes, in response to determining that the condition for executing the EMI risk mitigation function is satisfied, performing the EMI risk mitigation function. In some embodiments, performing the EMI risk mitigation function includes at least one of: adjusting a radio frequency (RF) transmit power; and outputting an alert that warns a user of the electronic device about a pacemaker in relation to the detected EMI risk.

Abstract: A method includes obtaining a stream of radar data into a sliding input data window composed of recent radar frames from the stream. Each radar frame within the data window includes features selected from a predefined feature set and at least one of time-velocity data or time angle data. The method includes, for each radar frame within the data window, receiving a binary prediction indicating whether the radar frame includes a gesture end. The method includes in response to the binary prediction indicating that the radar frame includes the gesture end, triggering an early stop (ES) checker to determine whether an ES condition is satisfied. Determining whether the ES condition is satisfied comprises determining whether a noise frames condition and a valid activity condition are satisfied. The method includes in response to a determination that the ES condition is satisfied, triggering a gesture classifier to predict a gesture type.

Abstract: A method includes obtaining a target distance and target velocity for each radar frame within a sliding input data window. Each radar frame within the data window includes extracted features. The method includes determining a dynamic threshold distance (dth) for a range of distances wherein performance of a gesture is valid. The method includes determining whether the target distance corresponding to a current radar frame satisfies a proximity condition based on the dth. The method includes in response to a determination the proximity condition is not satisfied, detecting a start of activity based on the extracted features. The method includes segmenting gesture frames from non-gesture frames in the data window, in response to at least one of: a determination the first proximity condition is satisfied, or a determination the current radar frame includes an end of the activity. The method includes discarding the non-gesture frames to modify the data window.

Abstract: A method includes, during operation of a proximity-detection module of an electronic device: determining a distance, velocity, and angle of a target relative to the electronic device based on radar data obtained from a radar transceiver of the electronic device; adjusting a configuration of the radar transceiver based on at least one of the distance, velocity, or angle of the target; and while at least one of the distance, velocity, or angle is greater than a respective threshold, repeating the determining and adjusting operations. The method also includes, in response to determining that each of the distance, velocity, and angle is less than its respective threshold, determining whether at least one wake-up trigger for gesture-based commands is detected. The method further includes, in response to determining that the at least one wake-up trigger for gesture-based commands is detected, triggering operation of a gesture-recognition module of the electronic device.

Abstract: A method for end-to-end dynamic gesture recognition using mmWave radar is provided. The method includes triggering an electronic device to activate a gesture recognition mode in response to detecting that a condition for activating the gesture recognition mode is satisfied. The method includes obtaining radar data while the gesture recognition mode is activated, wherein the radar data includes time-velocity data (TVD). The method includes detecting a start and an end of a gesture based on the TVD of the obtained radar data. To classify the gesture, the method includes determining a gesture, from among a set of gesture, that corresponds to a portion of the TVD between the start and the end of the gesture. The method includes outputting an event indicator indicating that a user of the electronic device performed the gesture classified.