What if Machine Learning could predict when, and how badly, we have to pee?

The Pee-ometer is a proposed device that predicts when a person has to pee, both as an object of utility and critique. While we are not necessarily advocating that there should be pee-ometers, the possibility of such a device, and working on a brief tied to an intimate and taboo topic such that of human bodily waste, simultaneously reveals and exasperates social tensions, relational frictions and interactional loops with smart technology. And by extending the technical practice of training into the design space it asks, what or who is being training?

This project is ongoing as a part of the Implicit Interaction project at KTH Royal Institute of Technology.

design research collage for the pee-ometer by Karey Helms