I just got across Project A2 : Intelligently interacting light switches. Sounds really interesting.
I have a few questions:
The most naive approach I can think about it is this - When a motion detector sensor detects the presence of a person, the light turns on.
Now that we are adding intelligence - is it that basically we are trying to determine the path that a person might take and then turn on lights accordingly? Lets suppose that the particular person has an ID, and our devices have historical data about that person as well as of other people. So the path is determined by taking into context and giving apt weight to both forms of data - to predict a path.
If that is the case, I have a concern. As for any learning problem, we will be operating under probabilities. Given the nature of the problem in hand, there maybe multiple paths possible with high probability(Right?). For energy efficiency, we won’t really like the lighting system to turn on all the probable lights. That is the precise reasons for having sensors. So how does the intelligent lighting system help?
The hardware part looks simple. I guess that any micro-controller with a PIR motion sensor attachment and a bunch of LEDs should be good enough for prototyping. Although I think we can simulate the environment by laying down a graph of motion sensors and lights instead of setting up hardware. Does this make sense?
Looking forward to the comments!