Live data from Hacker News

Developing an underwater robot to save people from drowning

fraunhofer.de

21–28 of 28 posts

Re: Developing an underwater robot to save people from drowning

#21
I used to work for an underwater robotics company.

I fucked right off when they smelled military contract $$$ and pivoted to become an ISO 9000 compliant house of drudgery and boredom where one was more likely to work on Word documents speccing a hypothetical robot than build the damn robot.

This is the kind of application I would've pulled every string I could to work on while I was there.

Re: Developing an underwater robot to save people from drowning

#22
post #12

Earlier quoted context omitted.

> Does it really try to strap the person to a hospital bed, underwater...? It looks like it folds two barriers against the sides of casualty to pinch them in place. I imagine that if you are not completely incapacitated, you can dodge or wriggle out of it. I would also guess that, given that it's supposed to be clever enough to spot an incapacitated casualty to rescue, it might be clever enough to stop trying to resc…

I give it 7 seconds before the children start pretending to drown at the bottom of the pool to summon the rescuebot.

I can see the famous kissing scene from Squints in "The Sandlot" movie remade once again.

Re: Developing an underwater robot to save people from drowning

#23
This seems like an over-engineered and failure-prone solution. A cheaper, more robust solution might be human lifeguards + medic-alert necklace with GPS.

If you pull off your necklace, it emits a screeching alarm, and you instantly show up as an emergency red blip to rescue. A decent enough Android smartphone costs like $20 at the low end.

Surely a pool or beach could force guests to rent and wear these for a few bucks (or waive their rights to being saved).

Re: Developing an underwater robot to save people from drowning

#24
post #12

Earlier quoted context omitted.

> Does it really try to strap the person to a hospital bed, underwater...? It looks like it folds two barriers against the sides of casualty to pinch them in place. I imagine that if you are not completely incapacitated, you can dodge or wriggle out of it. I would also guess that, given that it's supposed to be clever enough to spot an incapacitated casualty to rescue, it might be clever enough to stop trying to resc…

> I would also guess that, given that it's supposed to be clever enough to spot an incapacitated casualty to rescue, it might be clever enough to stop trying to rescue you if you attempt to swim away. One would hope, but I wouldn't hazard a guess at that. It likely uses some type of ML/NN to spot an incapacitated person; there are a bazillion pretrained models that recognized people in images. I know of no models tha…

For decades, all sorts of devices with very simple processors have been able to detect when the force against an actuator exceeds a certain amount and reverses or disengages it.

Re: Developing an underwater robot to save people from drowning

#25
post #12

Earlier quoted context omitted.

> Does it really try to strap the person to a hospital bed, underwater...? It looks like it folds two barriers against the sides of casualty to pinch them in place. I imagine that if you are not completely incapacitated, you can dodge or wriggle out of it. I would also guess that, given that it's supposed to be clever enough to spot an incapacitated casualty to rescue, it might be clever enough to stop trying to resc…

I give it 7 seconds before the children start pretending to drown at the bottom of the pool to summon the rescuebot.

Yes, and that's the other thing.

To reliably distinguish between drowning and breath-holding, you need to wait (or have more context)

This device (which has to come out through a secret underwater hatch and propel itself amongst people) cannot be faster than a lifeguard who has spotted the questionable situation and put themselves close to it before making a decision.

Re: Developing an underwater robot to save people from drowning

#26
post #24

Earlier quoted context omitted.

> I would also guess that, given that it's supposed to be clever enough to spot an incapacitated casualty to rescue, it might be clever enough to stop trying to rescue you if you attempt to swim away. One would hope, but I wouldn't hazard a guess at that. It likely uses some type of ML/NN to spot an incapacitated person; there are a bazillion pretrained models that recognized people in images. I know of no models tha…

For decades, all sorts of devices with very simple processors have been able to detect when the force against an actuator exceeds a certain amount and reverses or disengages it.

Also, if it can spot an incapacitated person amongst all the other swimmers, then it must be able to recognise when people are not incapacitated, otherwise it would just be going around randomly grabbing swimmers.

Re: Developing an underwater robot to save people from drowning

#27
I would like to see an augmented reality computer vision device that allows lifeguards to spot drowning people faster. Maybe even have an alarm in case they are paying attention to something else. Also underwater cameras. Although I imagine after a while, alarm fatigue would get them in the end.

Another cool feature would be spotting people running on the pool deck and shining a projector on them or something then an annunciator telling them not to run.

What I like about this robot is that it could be used in pools that don't normally have a lifeguard. Residential pools are a big killer of kids.

Re: Developing an underwater robot to save people from drowning

#28
post #24

Earlier quoted context omitted.

> I would also guess that, given that it's supposed to be clever enough to spot an incapacitated casualty to rescue, it might be clever enough to stop trying to rescue you if you attempt to swim away. One would hope, but I wouldn't hazard a guess at that. It likely uses some type of ML/NN to spot an incapacitated person; there are a bazillion pretrained models that recognized people in images. I know of no models tha…

For decades, all sorts of devices with very simple processors have been able to detect when the force against an actuator exceeds a certain amount and reverses or disengages it.

Yes, but how do you infer intent from the force put against the actuator? There is no point in using this robot if it doesn't work if people are heavier than some arbitrary value, or if they get released because they bumped against something while being towed...
Post reply on HN