System and method for synthesizing sensor readings

A system for synthesizing sensor data in a wearable device, the system comprising:

• a plurality of sensors arranged in a first predetermined pattern, with each of the plurality of sensors arranged at respective first locations on the wearable device;
• and
• one or more controllers communicatively coupled to the plurality of sensors, the one or more controllers configured to:
• obtain a corresponding plurality of sensor readings from the plurality of sensors;
• based on the plurality of sensor readings and a plurality of estimation weights, estimate a plurality of synthesized sensor readings for a corresponding plurality of synthesized sensors, the plurality of synthesized sensors arranged in a second predetermined pattern, wherein the second predetermined pattern maps each of the plurality of synthesized sensors to respective second locations on the wearable device, wherein the second predetermined pattern includes at least one interstitial location between adjacent sensors of the plurality of sensors arranged in the first predetermined pattern and at least one location external to the plurality of sensors arranged in the first predetermined pattern, wherein a number of the plurality of synthesized sensors is greater than a number of the plurality of sensors;
• and
• generate feedback to a user using the synthesized sensor readings, the feedback comprising at least one of a vibrotactile signal, an audio signal, a visual display, and an avatar;
• wherein the plurality of estimation weights are predetermined in a preprocessing phase that comprises:
• obtaining training data comprising training sensor readings measured at locations of both the first predetermined pattern and the second predetermined pattern;
• computing an input data set corresponding to the first predetermined pattern and a reference data set corresponding to the second predetermined pattern;
• and optimizing the estimation weights by gradient descent to reduce error between estimated sensor values and the reference data set.