Researchers are experimenting with robots to help speed up the restoration of coral reefs.
…
Their researchers have been training an artificial intelligence to control collaborative robots (cobots), which work closely alongside humans.
“Some of these processes in coral propagation are just repetitive pick and place tasks, and they’re ideally suited to robotic automation,” says Ms Foster
A robotic arm can graft or glue coral fragments to the seed plugs. Another places them in the base, using vision systems to make decisions about how to grab it.
“Every piece of coral is different, even within the same species, so the robots need to recognise coral fragments and how to handle them,” says Nic Carey, senior principal research scientist at Autodesk.
“So far, they’re very good at handling the variability in coral shapes.”
Oh, man, I just realized the machine learning verbiage like saying “trained” instead of “programmed” is being embraced by tech companies in part to avoid responsibility for human choices.
Not that the coral reef robot scientists are doing that. They’re obviously using machine learning. I just found it odd to read they “trained” a non-living thing.
There’s a difference. When you program a machine it follows rigid logic. It’s predictable.
When you train a machine it does not. It can make its own inferences and operate outside of strict parameters. It can also make bad inferences, what we call AI hallucinations.
I don’t know that what you’re saying is wrong about avoiding responsibility, but programmed is not the right word for what’s basically a genie in a bottle. And we still hold accountable the member of the tribe that lets the genie out, or should anyway.
Reading the short VN South Scrimshaw really made me appreciate coral reefs.
This is the best summary I could come up with:
“It’s a really special part of the world,” says marine biologist Taryn Foster from the Abrolhos Islands, 40 miles from the coast of Western Australia.
“Climate change is the most significant threat to coral reefs around the world,” says Cathie Page from the Australian Institute of Marine Science’s (AIMS).
“Severe bleaching events caused by climate change can have very negative effects,” Ms Page continues, “and we don’t have good solutions yet”.
“Some of these processes in coral propagation are just repetitive pick and place tasks, and they’re ideally suited to robotic automation,” says Ms Foster
However the real world presents many challenges: wet, living coral needs to be handled delicately, possibly on a moving boat, and saltwater is potentially damaging to electronics.
“To stay ahead of the curve and enable coral reefs to survive a warming future requires a substantial investment of time, money, and human capital,” says AIMS scientist Cathie Page.
The original article contains 904 words, the summary contains 152 words. Saved 83%. I’m a bot and I’m open source!
Interesting idea. I wonder how this will work when the oceans are so acidic through the co2 in the air that every lime based creature will die. At least in the colder regions