It's research, not a product. Even with that, framing it as a smart home sensor in the press release is a stretch.
1) 93.75% success rate in controlled conditions, 92.1% in a somewhat-realistic deployment scenario - too low for reliability. I wouldn't use something like that to trigger smart home automations.
2) Range hardcapped at ~1m due to how ultrasound works, you can't centralize detection. Their answer is to give everyone in the household a wearable receiver, which is eeeeeeeh idk, doesn't look consumer-friendly to me.
3) Paper suggests a mix of durable and consumable parts for the transmitter. Their numbers show that the 3d-printed PLA cantilever needs to be replaced every 900 cycles or so. Should work fine, but...
4) ...every transmitter pair needs to be tuned per-setup, every time. Not a plug&play in the consumer sense.
This is the big constraint:
> 2) Range hardcapped at ~1m due to how ultrasound works, you can't centralize detection. Their answer is to give everyone in the household a wearable receiver, which is eeeeeeeh idk, doesn't look consumer-friendly to me.
Sure yes if you could do this with an always-listening smartphone or smartwatch that would be workable, but even then it constrains it to an occupant-activity detector.
Fixing that would require in the best case prompting an app install when visitors arrive. And still it is deaf to any other changes such as a door closing in the wind.
All possible, but feels several technosocial cycles away. Interesting to think about anyway.
Could be more interesting for hard-to-reach underwater sensors. Water attenuates RF quite severely, but is good at conducting ultrasound. The response would have to be in ultrasound, too, of course.
5) These can be great if you want them to be monitored, but if I'm using my wife's toilet when I'm not supposed to, I'll simply hold the disk when I lift the seat.
From the artwork it looks like they're targeting industrial use. Seems like a low grade replacement for bar/qr code scanning. The "wearable" (more likely integrated into some other thing than worn IMO) receiver seems to point in that direction too.
Author probably has a specific use case in mind. Probably some application where EM emissions are undesirable or power is complicated that has thus far resisted automated industrial data entry. Investigating the use of something like ultrasound would align with constraints like that. Someone (department head? PR department?) said that was too niche and to make up some bullshit with mass market appeal.