Having got Helios one step closer to working (the bug is on Nick’s side now) the rest of the day was spent cleaning out the lab (it looks great now…we just need to configure the Hue Tap, and hide the gently decaying walls somehow) and reading up on Kamin Whitehouse‘s research group and their projects.
Whitehouse’s group had several interesting projects underway, and even though they weren’t using machine learning on end-user programming they had stumbled upon some powerful innovations. I want to talk about my favorite so far, the Marauder’s Map.
Using ultrasonic sensors at each door and hallway in a house, Whitehouse’s group is able to track who is in which room (using varying heights to uniquely identify people). The group also connected sensors to the electric and water mains allowing them to add appliance and water use in the map as well. With the map abstraction certain tasks become extremely simple. If no persons are in a room then the lights should be off (these are hard-coded rules as opposed to ML though), if no one is in the house the doors should be locked etc.
With this week’s focus on adding the mulitsensor and door sensor the group could easily replicate the Marauder’s map (uniquely identifying people will remain tricky). While this is still somewhat in the future, it might prove to be a useful metaphor, especially for a user-programming purpose.