AI-Driven Robot Installs Nearly 10,000 Solar Modules in Australia (cleantechnica.com) 30
Long-time Slashdot reader AmiMoJo shares an article from Renewables Now: Chinese tech company Leapting has successfully completed its first commercial deployment of photovoltaic (PV) modules with an AI-driven solar module mounting robot in Australia. The Chinese company was tasked with supporting the installation of French Neoen's (EPA:NEOEN) 350-MW/440-MWp Culcairn Solar Farm in New South Wales' Riverina region. Shanghai-based Leapting said this week that its intelligent robot has installed almost 10,000 modules at an "efficient, safe, and stable" pace that has "significantly" reduced the original construction timeline.
Litian Intelligent was deployed at the Australian project site in early February. The machine has a 2.5-metre-high robotic arm sitting on a self-guided, self-propelled crawler. Equipped with a navigation system, and visual recognition technology, it can lift and mount PV panels weighing up to 30 kilograms. By replacing labour-intensive manual operations, the robot shortens the module installation cycle by 25%, while the installation efficiency increases three to five times as compared to manual labour and is easily adapted to complex environments, Leapting says.
Or, as Clean Technica puts it, "Meet the robot replacing four workers at a time on solar projects." This is part of a broader industrial trend. In the United States, Rosendin Electric demonstrated its own semi-autonomous system in Texas that allowed a two-person team to install 350 to 400 modules per day, a clear step-change from traditional methods. AES Corporation has been developing a robot called Maximo that combines placement and fastening with computer vision. Trina Solar's Trinabot in China operates in a similar space, with prototype systems demonstrating 50-plus modules per hour... In an industry where time-to-energy is critical, shaving weeks off the construction schedule directly reduces costs and increases net revenue...
[T]he direction is clear. The future of solar construction will be faster, safer, and more precise — not because of human brawn, but because of robotic repetition. There will still be humans on-site, but their role shifts from lifting panels to managing throughput. Just as cranes and excavators changed civil construction, so too will robots like Leapting's define the next era of solar deployment.
Litian Intelligent was deployed at the Australian project site in early February. The machine has a 2.5-metre-high robotic arm sitting on a self-guided, self-propelled crawler. Equipped with a navigation system, and visual recognition technology, it can lift and mount PV panels weighing up to 30 kilograms. By replacing labour-intensive manual operations, the robot shortens the module installation cycle by 25%, while the installation efficiency increases three to five times as compared to manual labour and is easily adapted to complex environments, Leapting says.
Or, as Clean Technica puts it, "Meet the robot replacing four workers at a time on solar projects." This is part of a broader industrial trend. In the United States, Rosendin Electric demonstrated its own semi-autonomous system in Texas that allowed a two-person team to install 350 to 400 modules per day, a clear step-change from traditional methods. AES Corporation has been developing a robot called Maximo that combines placement and fastening with computer vision. Trina Solar's Trinabot in China operates in a similar space, with prototype systems demonstrating 50-plus modules per hour... In an industry where time-to-energy is critical, shaving weeks off the construction schedule directly reduces costs and increases net revenue...
[T]he direction is clear. The future of solar construction will be faster, safer, and more precise — not because of human brawn, but because of robotic repetition. There will still be humans on-site, but their role shifts from lifting panels to managing throughput. Just as cranes and excavators changed civil construction, so too will robots like Leapting's define the next era of solar deployment.
Cutting off one's nose to spite one's face (Score:1)
Re: (Score:3)
Could be a game changer for rapidly building solar farms anywhere with minimal manpower and skill needed.
Could also be useful for exploring the moon and Mars.
Re: (Score:2)
It's nothing we can't build ourselves (Score:1, Troll)
Re: (Score:2)
Did you copy and paste that all at once?
Re: (Score:2)
Imagine how many solar panels you could install for $1.9 trillion? Too bad that money was all wasted on reducing inflation. ...
In Australia (Score:2)
All installed upside-down, no doubt.
Re: (Score:2)
All installed upside-down, no doubt.
Possible responses: :-)
(a) Duh, the Sun is also upside down there.
(b) Do you mean oriented 180 degrees top-to-bottom or back-to-front - or both?
Not neural network based (Score:4, Informative)
Calling it AI-driven because buzzword bingo because the thing that everyone is now referring to as "AI" is based on neural networks, where it effectively guesses what to do based on previous situation. This on the other hand is appears to be entirely based your regular old logic that is programmed by humans. You could claim it's an expert system [wikipedia.org] but calling that an AI has been out of fashion for decades. Their own product page [leapting.com] never refers to it as AI but does say it is intelligent.
Is it autonomous? Yes but only within specified parameters. Is it AI? Sure, in so far that a paper-towel dispenser is an AI because it recognizes when a new paper-towel needs to be dispensed, just a like a human.
Re: (Score:3)
Here is another one that looks remarkably similar [youtube.com]. Also based primarily on standardization of components and repetition. Here is another one [youtu.be], which seems to have been funded by Amazon.
Re: (Score:2)
We had image recognition before the term "AI" was bandied about. We're coming up on fifteen years of facial recognition for unlocking phones, long before the tech companies were using the term as a marketing concept.
I could easily believe that the software taking camera input has been programmed to recognize the particular shapes germane to the job that it is doing and to use that input to vary what it's doing. I would hesitate to call that "AI". If that's AI, then those IC sorting robots that we've had
Re: (Score:2)
We had image recognition before the term "AI" was bandied about
Not exactly, AI is almost as old as computers. A* search is AI, even if it's not intelligent. The term "AI" has been exaggerated to mean many things, and this was true from the beginning.
I would hesitate to call that "AI". If that's AI,
It's not really worth arguing about though, because people use the terms they want. Say, "it's not general AI." Call it weak AI. Say it's just an algorithm. Say it's not more intelligent than a calculator. But if you try to say it's not AI, then people will be able to disagree by redefining the word.
Re: (Score:1)
What if any Joe Blow can use English to control the robot?
Re: (Score:1)
"the thing that everyone is now referring to as "AI" is based on neural networks"
Why did the Attention is all you need article, saying you don't need neural networks to do context sensitivity, produce the paradigm shift of a conversational AI that neural networks alone could never produce?
It Should Be Smart To Install Them Everywhere (Score:2)
That uses electricity or else this is all a PR stunt as usual.
Re: (Score:1)
You're a stunt.
It's in a paddock in the middle of a remote farming community. The robot saved the installer the cost of labor.
baseload? (Score:2)
Re: (Score:3)
Batteries are growing *very* fast. US is on pace to double it's install base this year alone.
Won't be grid scale tomorrow but in a decade a significant percentage of grid demand will be battery sourced.
CA is already flattening the duck curve with late afternoon battery storage https://energycentral.com/c/em... [energycentral.com]
Re: (Score:1)
Imagine a 5+ GW nuclear power plant like that at Brarakah. ( https://en.wikipedia.org/wiki/... [wikipedia.org] ) There are four reactors at the plant, each reactor needs some down time for refuel and maintenance, so assume at any time there's a reactor shutdown which means it is producing 75% of rated output 24/7. The capacity factor is likely better than that but for the moment assume 75%.
On the other hand you have solar power, which has a capacity factor of about 20%. While I'm sure some people will want to point out
Re: (Score:3)
more gish gallop.
The reason solar is eminently viable is the simple math of 8000:1 over supply. More solar energy hits the earth in an hour than the human race uses, in all forms, in an entire year. Haven't seen the numbers on wind but I'll assume it's at least 1/4 of that. Even at your 20% solar figure, that's 1500-2000x what we need. Utterly stupid not to see that as a primary source - add in no moving parts and just sits there, basically the minimum amount of maint needed. Nothing else even comes
Re: (Score:3)
Re: (Score:2)
Man, if only someone had invented a way to store electricity.
10,000 modules (Score:2)
THAT MANY modules?
Indeed, that robot is driven.