Probabilistic Home Automation
My recent addtion of multiple hypothesis tracking enables my home automation system to not only say how many people it thinks are home and which rooms are occupied but also to assign a probability to each of those numbers. That changes the way it will work as I replace boolean values with probability comparisons to see if it is, say 95% certain before it acts on a value. It also enableds exciting new scenarios that I’ll explore here.
More intelligent lighting control
In the past my home automation relied mostly on time-outs to decide when a room was no longer occupied. After a period of no activity on any of the sensors in the room (motion, strain-gauge, TV volume control, light switches, or telephones) it would start dimming the lights in that room and would turn off any audio playing. There were a couple of more complicated scenarios where it attempted to use logic to reason that someone was still in a room if that room could be closed off. And while my house does have a lot of sensors this approach really wasn’t that much smarter than a cheap PIR motion light switch.
The light state machine makes it seem smarter because it will leave a light on or off when a user wants to override this relatively dumb behavior and the gradual, imperceptible dim feature makes it a lot more forgiving (or rather ‘forgiven’ when it makes a mistake).
Now, however with a probabilistic model of the home based on ‘target tracking’ it can turn lights off much sooner as it can be almost certain that the one person in that room just moved to a neighboring room. This will allow it to save even more energy over my baseline from years ago before any home automation was installed.
Tue Feb 13 2018 17:14:00 GMT-0800 (Pacific Daylight Time)