[ogou]

The most useful indicator seems to be rapid leg movement combined with no change in position. That's not typical cat criteria. Rapid legs usually mean position change (running). I would use a very small accelerometer on a front paw connected to BLE enabled microcontroller on a collar. That's the easy part. Triangulating position is harder. GPS would be too heavy, but you could use BLE signal strength from 3 different receivers around the house. I imagine someone has solved that problem before.

Or, you could put Yuri in a closed area with camera monitoring. Train a YOLO5 model in Yuri vision and let it monitor the area. You would have to simulate a seizure though. You could make a fabric facsimile of the animal and place it in different areas on its side. The shape of an animal in a seizure is not the same as when it's sleeping. It would be up to you to determine the difference.

[robotsliketea]

Someone has indeed solved this problem before! Your comment reminded me that a project triangulating a cat via BLE was posted to HN a few years ago:

https://news.ycombinator.com/item?id=26024049 https://github.com/filipsPL/cat-localizer

[phi161]

> That's the easy part

Wait, I thought that's the _difficult_ part! What kind of accelerometer would that be? And is there a microcontroller small and light enough for a cat?

(and thanks for your answer of course!)