Farming Startup Unveils Self-Driving Robot That Uses AI To Zap Weeds (geekwire.com) 98
Carbon Robotics, a Seattle company led by Isilon Systems co-founder Paul Mikesell, is unveiling its self-driving robot that uses artificial intelligence to identify weeds growing in fields of vegetables, then zaps them with precision thermal bursts from lasers. GeekWire reports: [W]hat farmers need is less a revolution in farming methods than a revolutionary tool that fits into their current farming patterns, Mikesell said. Carbon worked closely with farmers in eastern Oregon and southern Idaho, he said. As a result, Carbon's robot system -- the Autonomous Weeder -- was built about the size of a medium tractor so it would fit in the furrows between rows of common crops like onions and sweet potatoes.
It can cover up to 16 acres of cropland a day, zapping as many as 100,000 weeds an hour, Mikesell said. And since it's self-driving, all a farmer has to do is take it to the field in the morning and turn it on. "We're really intent on not making farmers have to change how they're doing things," Mikesell said. "That's been a key to our success. We fit right into their operations."
Carbon has sold out all the robots it built for the 2021 planting season, and is looking for an industrial partner who could help it build more units for 2022, Mikesell said. The company is looking to get into the hundreds of units built and shipped for next year, he said. "There's a demand for a lot more than that, tens or hundreds of thousands of them."
It can cover up to 16 acres of cropland a day, zapping as many as 100,000 weeds an hour, Mikesell said. And since it's self-driving, all a farmer has to do is take it to the field in the morning and turn it on. "We're really intent on not making farmers have to change how they're doing things," Mikesell said. "That's been a key to our success. We fit right into their operations."
Carbon has sold out all the robots it built for the 2021 planting season, and is looking for an industrial partner who could help it build more units for 2022, Mikesell said. The company is looking to get into the hundreds of units built and shipped for next year, he said. "There's a demand for a lot more than that, tens or hundreds of thousands of them."
I want someone (Score:3)
to make one of these for a home garden.
Re:I want someone (Score:5, Interesting)
Re: (Score:3)
I want someone to make one of these for mosquitoes.
Mosquito Laser [youtube.com]
This mosquito laser has been working for 11 years but is owned by a patent troll [intellectualventures.com] more interested in lawsuits than in helping the 400,000 children who die from malaria every year.
Re: (Score:1)
Re: (Score:2)
Reductions in infant and child mortality are generally tied to reduced birth rates, not higher. High birth rates in poor countries are in large part (but not entirely) based on ensuring that some of them make it to adulthood. As infant and childhood survival rates go up, birth rates tend to go down.
Re: (Score:2)
Re: (Score:2)
You're not going to get to 2.1 overnight. Fertility rates in Africa peaked at about 6.7 from about 1960 to about 1973. It's down to about 4.25 now (about a 37% reduction) and the projected trend is to reach population replacement rate by the end of the century. Maybe it will go down faster as conditions improve, but until conditions improve, it's going to remain relatively high.
Re: (Score:2)
Thats bullshit, watch any tv show or clip of africa and the kids clearly outnumber the adults. Theres no way each mum only has 2 kids. Any doco on a town or village, clearly tells the story of a woman with at least 5 kids.
Re: (Score:2)
Welcome to the world, racist.
Re: (Score:1)
Re: (Score:2)
Re: (Score:2)
Re: (Score:2)
From what I remember the mosquito laser is not economically viable
Re: (Score:2)
Right, that's what patent trolls due for a living. They destroy real use of the technology, while sucking out legal fees far in excess of the legitimate profit justified by what the patent actually does.
This usually happens because manufacturing is hard, and most of the money to be made from an invention is usually the money made by successfully running a factory.
Re: (Score:2)
Due to the cost of the hardware alone
Re: (Score:2)
Re: (Score:2)
Right, Except there is a minimum cost, and the minimum is likely going to be more than 50$ (which a conservative minimum and is about the cost of a cell phone with a camera and a lidar both of which are produced at scale currently, I think a safer bet would be 200$, the reason for this being the need for precise optics and lenses for both camera and laser)
A mosquito net is ~3$ a can of deet is about that much. Right now the cost of the prototype mosquito fence looks to be at least 5k$
Re: (Score:2)
Have you ever even heard of laser engravers, or makers?
Re: (Score:2)
Intellectual Ventures isn't actually a patent troll. When he left Microsoft and was looking for something new to do Myrvold saw lots of interesting patents that were not being used, mostly because good inventors tend to be shitty managers. IV buys patents and then licenses them to companies to get them out in the world rather than letting them sit dormant. They don't just sit on them and sue anyone doing anything even vaguely similar like a typical patent troll.
Re: (Score:1)
" IV buys patents and then licenses them to companies to get them out in the world rather than letting them sit dormant."
If you speak from experience, I would like to talk to you. hkeithhenson at gmail.
When the Asian hornets started invading France, I tried to talk to them about licensing the mosquito laser. The idea was to upgrade it to kill hornets and install systems in bee yards.
No luck whatsoever.
Re: (Score:2)
My experience at IV was as a contracted security engineer setting up access control and security video at the headquarters and later the lab about a decade ago. (I think the lab has since moved to a different building.) The people that I worked with, administrative and management folks mostly, seemed quite proud of the organization they were associated with and the things that they were doing. My understanding is that they worked mostly with manufacturers, so a laser or farm equipment manufacturer would
Re: (Score:2)
"IV buys patents and then licenses them to companies"
This is what a patent troll does.
Re: (Score:2)
Typically what I think of patent trolls are IP holders who spend more time in court suing anyone doing anything vaguely like whatever they hold the IP of.
Re: (Score:2)
Well, then look up what the word means and figure out it isn't defined as, "companies who sue more than cusco likes," but is instead based on weather they sue people for a making the product when they don't even make it themselves.
Re: (Score:2)
https://www.investopedia.com/t... [investopedia.com]
While the practice of patent trolling is not illegal, a company that acts as a patent troll files patent claims without any intention of ever developing a product or service.
- - - - -
This doesn't describe IV, as their main source of revenue is companies to which they license the IP that they hold. Yes, they'll sue if the believe someone is infringing their (imaginary) property, but that's not their main line of business.
Re: (Score:1)
LOL, I'm not even going to read all your words. What I saw was that you chose to quote investopedia.
That's a great resource for learning about the stock market. But why would you think stock brokers would be the people defining words like this? Give me a break.
Maybe do a search at this website called "slashdot" and you can learn about what the word means in actual use.
Re: (Score:2)
Just picked one at random, the pretty much all say the same thing.
Re: (Score:3)
Actually the price for one of these lasers can provide thousands of free mosquito nets, which are more effective. Mervold donated the price of a couple of them to the Gates Foundation to do just that. The mosquito laser is a cool toy though, I watched it in their lab when I was there working on their security system. It targets only female mosquitoes of the species which can carry malaria and ignores the rest, since mosquitoes are an integral part of many ecosystems.
Re: (Score:2)
but zapping a mosquito is *so* much more satisfying than screening it out . . .
Re: (Score:2)
Re: I want someone (Score:2)
I want someone to make one . . .
. . . fot humans!
-- Zorlac of Baaal
Re: (Score:2)
Re:I want someone (Score:5, Funny)
to make one of these for a home garden.
It is way too big for a home garden.
This may be a better fit: Tertill Garden Weeding Robot [amazon.com].
I am skeptical if this is a cost-effective way of weeding a home garden.
I use teenaged forced labor: I unplug the router until the tomato patch is weed-free.
Re: (Score:2)
I just want a robot laser to zap weeds, I don't care if it's cost effective. I have killed many a weed in my day as there are many many weeds in my area.
Re: (Score:2)
"I use teenaged forced labor: I unplug the router until the tomato patch is weed-free."
My kingdom for a mod point. Bravo! If only I still had any, and my grandchild is still in diapers.
Re: I want someone (Score:2)
I though Fanta was the Mexican drink of choice...
Re: I want someone (Score:2)
Twist: Written by a Canadian, due to fleeing Muricans.
Re: (Score:2)
There were less than eleven thousand US immigrants to Canada in 2019. /yawn
Re: (Score:2)
Tertill Weeding Robot
https://www.kickstarter.com/pr... [kickstarter.com]
Re: (Score:2)
Well, there's the Tertill. I want one, but my wife won't let me pay $400 for a weeding robot. It's a cool concept, though.
https://tertill.com/collection... [tertill.com]
Cool Evil Bond weapon (Score:2)
No, Mr. PotatoHead, I expect you to die
100,000 weeds per hour? (Score:2)
That's almost 28 per second. Exactly what kind of Skynet predecessor is this, with that kind of array of independently aimed lasers?
Definitely the wave of the eventual future (Score:5, Interesting)
Even with proper use, you can't avoid herbicide resistance. Selection pressure is selection pressure. So efficient, mechanical means of destroying weeds will eventually be required, along with other practices like intercropping which greatly reduce the need for weed control.
Swarms of these robots will be required. Just to put the efficiency thing in perspective, I can spray herbicide on 120 acres in less than an hour (120' boom at 14 mph). In a day I can spray over a thousand. That's a lot of little robots to do the same job. The nice thing about mechanical (in this case fire!) destruction of weeds is that it's not possible for a plant to be selected for resistance. However there is a possibility for selection based on whatever parameters the AI decides it's looking for. I heard a story not that long about out of China if I recall, where they had a particularly problematic weed that had to be hand picked out of the crop. Eventually the only variants of the weed left looked very much like the crop at that early stage. So I guess even this kind of mechanical control still is problematic.
Anyway it's interesting, particularly how they focused on trying to work with what works for current farms. So many ideas are great, but it's hard to adapt them to the realities I work with, whether its financial, technical, or scale of economy.
Re:Definitely the wave of the eventual future (Score:5, Interesting)
Decades ago, before most of you were born, I was learning Tzeltal (a Mayan language of southern Mexico). One day I was out in the corn field with the village headman and his teenage son. The corn plants were a few inches tall, and there were grass blades growing up with them. We were chopping out the grass with machetes. (I know, that seems like using a sledge hammer to... but it's what we had.) I was using my machete to chop something out, when I suddenly realized it was corn instead--the two looked very similar at that stage, I think the grass leaves were slightly bluer. The teenager working next to me saw me almost chop out the corn. "Nopol la'aboj ixim", he said: "You almost cut the corn." It's funny how events like that get cemented in your brain--as I say, it's been decades now, and I've forgotten a lot of the language--but not that.
Anyway, wrt your comment: yes, the grass looked a lot like corn. Whether that was evolution, I don't know; maybe corn (or corn's predecessor, teosinte) and grass started out looking similar millennia ago.
Re:Definitely the wave of the eventual future (Score:4, Interesting)
"maize split off from teosinte grass [vox.com] some 9,000 years ago"
Re: (Score:2)
Yes, it won't cause genetic selection as do herbicides (well, maybe it won't, we'll see over time). It will certainly selectively kill some weeds and not others - some have underground stems (e.g. bermuda grass); this will not kill those. For other weeds, I imagine they will need to be careful to adjust the laser to go deep enough to kill the growing point, otherwise the process could select for deeply growing weeds that can recover.
Also, it would be difficult to kill the weeds growing right up against the
Re: (Score:2)
Selection pressure is selection pressure
With this new weed zapper, we're going to breed weeds that look exactly like crops.
Re: (Score:2)
Even with proper use, you can't avoid herbicide resistance. Selection pressure is selection pressure. So efficient, mechanical means of destroying weeds will eventually be required, [...]
Selection pressure is selection pressure, regardless of if it’s chemical, thermal, mechanical, or some other force.
The nice thing about mechanical (in this case fire!) destruction of weeds is that it's not possible for a plant to be selected for resistance.
Not true! If the roots go deep enough, the weed may survive, and pretty soon you will have selected for weeds that can survive attacks from lasers. Or perhaps a strain becomes particularly adept at incorporating silica into its structure in such a way that it diffuses the laser, limiting the damage it incurs. There are innumerable variations on this idea.
Re: (Score:2)
Re:Definitely the wave of the evea hrntual future (Score:2)
The nice thing about mechanical (in this case fire!) destruction of weeds is that it's not possible for a plant to be selected for resistance.
Do you want Doomsday [wikipedia.org]? Because that's how you get Doomsday.
Re: (Score:2)
Yep, like you say, selection pressure is selection pressure. Kill things that don't look like crops, and the only weeds that survive to pass on their genes will be those that look like crops, with the similarity increasing over time as you get better telling them apart.
As for the relative cost effectiveness of spraying - that could change rapidly if you had to pay for all the health and ecological damage those herbicides do both downstream and to consumers. Right now you're benefiting from exploiting t
Re: (Score:2)
Easy to say. Such a criticism of agriculture works both ways, however. You're eating food more cheaply than at any time in history precisely because herbicide use has proven to be relatively safe and effective over a long term, at feeding numbers of people thought impossible a few decades ago. Consequently this monetary cost you want to apply must go all the way back to the price you pay for your food. Are you willing to pay double? Triple? Are you aware of how current farm economics work? I seriously
Re: (Score:2)
I think the huge potential value is how this will make low till and no till farming even more productive, by preserving soil health. The robot cannot compete with you using heavy equipment in terms of acreage per hour. But if the robot means you buy zero herbicide, cut your fertilizer costs drastically, and you do not need to buy more expensive genetically modified seed, that is where you win economically. Hopefully, you could be grossing less per acre, and take home more profit.
Re: (Score:2)
>is that it's not possible for a plant to be selected for resistance.
maybe.
But small parabolic collections of reflecting metal exuded on the surface could be interesting . . . :)
"It's firing back!"
Just as long as the thing recognizes chihuahuas as weeds . . .
An autonomous mobile robot with zapping lasers (Score:2)
Re: (Score:2)
Define "weeds". (Score:2)
One man's weeds are another man's herbs, or helpful plants or symbionts with regard to the soil biome or pest prevention.
Also, the times of naked soil should be over by now. Dies out too quickly in warmer climates, can't keep heat in colder climates, loses nutrients too fast, can't keep a proper biome, ... naked soil is unnatural for a reason. (Loose straw is a good cover.)
Re:Define "weeds". (Score:4, Interesting)
It's quite simple, really. Weeds are any plant that has an economic cost to leave growing, and if it increases the seed bank in the soil. Some of my weeds could be incredibly costly to leave. Also, most of my weeds are actually volunteers from one type of previous crop.
With regards to your comments about naked soil, you are correct that soil does not naturally want to be uncovered, and weeds are part of nature's process to cover it up again. And yes naked soil does lose organic matter. However where I live soil that's covered takes 2-3 weeks longer to warm the soil to growing temperature than soil which was lightly tilled before winter. In fact right now the soil is strangely cold for this time of year, despite having above-average temperatures for much of the winter, and no snow cover (which probably is responsible for the cold soil). So for the mechanics of farming, and the timely establishment of crops, tillage still finds widespread use, but most farmers try to do it as little as possible. I have neighbors that have been no-till for many years, but they have an increased dependence on herbicides.
Re: (Score:3)
Here's an interesting observation regarding tillage. Most of our latest and greatest tillage machines in Canada these days come from Europe. High speed discs, rippers, mulchers, etc. Apparently tillage is widespread in Europe (I can attest to that as I've seed many, many tilled fields in the winter in Europe). Most of these fields have been heavily tilled, plowed even, for centuries. Yet their organic matter is pretty good and have been stable for decades. And their yields are very good, often double wh
Re: (Score:2)
Tilth is really not the problem, compaction is the problem. that was the advantage of historical tillage, which was done with animals. now it's done with machines that tend to compact the soil and create hardpan, which in turn holds water and creates anaerobic conditions that destroy soil diversity.
The other big problem of tilth is soil blowing away, but if you don't cut down all the trees between fields that's not a big problem.
The UK imports about ten times as much food as it exports. Is it really produci
Re: (Score:2)
Can have many reasons, crop rotation, by definition better soil, plowing the remains of the plants after harvest under the ground again, using mostly manure or sewage to fertilize, no idea :D
Re: (Score:2)
Yup. All of those things. Most of which are widely practiced in North America too. It's also interesting that in the 1600s and 1700s, farmland in the colonies was rich and fertile, cleared fields in the forest, much like Europe, and farmed using the same techniques. By the 1800s it had begun to be depleted, which led to some of the migrations west by farmers. By west I mean moving from New York to Ohio sort of thing.
I freely admit that no one, including soil scientists, understands the soil very well d
Re: (Score:2)
Weeds are the plants the farmer doesn't want growing on his field.
Do they support right to repair? (Score:2)
Re: (Score:2)
They support the Right to Reboot.
Isilon Systems co-founder Paul Mikesell (Score:2)
Oh, yeah, thanks for clarifying...
Who the heck is "Paul Mikesell" and what the heck is "Isilon Systems"?
Where's the residential variant? (Score:2)
I'd love a little robot that roamed my lawn, zapping dandelions and broad-leafed weeds before I notice them.
Re: (Score:1)
I'd love a little robot that roamed my lawn, zapping dandelions
Ok. So why are you destroying a valuable food crop?
Re: (Score:2)
Ok. So why are you destroying a valuable food crop?
Valuable to whom? How much would you be willing to pay for them? Would you pay more than the cost of harvesting, preparing, and shipping?
diesel hydraulic? (Score:1)
One of the videos on the website mentions a diesel hydraulic. Does that mean this thing is running of diesel? If so, how much fuel does it use to run?
Better or worse for biodiversity? (Score:5, Insightful)
I guess the more accurate the removal of weeds is, the less pesticide required, which is a good thing.
However, it is clear that this is not the be and end all of the picture, as the living soil is ... effectively, dying.
When you plant millions of acres of a monoculture and eliminate all other competing living organisms, you no longer have nature on your side and thus need to continually 'feed' the soil.
The soil under the crops, is, to all intents and purposes, mostly 'dead', in that there are little to no living organisms within it.
It is just a damn shame that the amount of money being put into efforts to create mono-cultures in order to increase yield, isn't being put toward experimenting with alternative methods, where the natural order of things is used to control pests or weeds.
At the very least, wide corridors of nature should be allowed to thrive - with all the benefits that could bring.
Sure, it can also bring problems - it's a delicate balance.
However, the very fact that bees have to be shipped around the country in order to provide pollination to many crops, is absolutely a sign that mono-cultures will eventually result in pretty much everything other living organism over vast swathes of land, being eliminated.
That can't be a good thing - and most certainly isn't.
Bees are suffering a double whammy - being killed of by pesticides (depending who you believe - I'm inclined to believe the biologists) and not having a natural environment full of biodiversity.
Re: (Score:2)
Shipping bees ought to be illegal. Literally. You should not be able to transport them across, say, county lines.
Why? Because doing this exposes the bees to infestations and infections, which are then transported by humans moving the hives.
Unfortunately not shipping bees is incompatible with our whole "rape the planet" plan. There's not enough for them to eat while they're not pollinating our crops, because we've destroyed too much wilderness.
Re: (Score:2)
The planet has been "raped" for 10s of thousands of years, we're just better at doing it now.
Re:Better or worse for biodiversity? (Score:4, Interesting)
There are farmers developing soil health oriented farming techniques. This is potentially a huge boon to the environment, including probably the cheapest way to bring a large amount of CO2 out of the atmosphere while doing something economically useful.
So Awesome! (Score:1)
To kill weeds with new technology that mimics what humans used to do - manually weed - rather than use chemicals - which come with very high unintended consequences - is just a giant leap forward.
I know, I know... the robots that can mimic precise human behavior also come with unintended consequences, but for food, I'd much rather have food that was robot-weeded rather than poisonously chemical-soaked any meal.
Idiots (Score:2)
Simple Question :
Zapping weeds will attract less pollinators at a time when insect number are on the decline -
True or False ?
As always the real probem is ignored (Score:1)
In other words. . . . (Score:2)
We're approaching a time like that scene in Runaway [imdb.com] where they have to capture and subdue a malfunctioning crop robot.
Hell yes (Score:2)
This tech sounds like the best thing... sounds like a huge huge huge reduction in toxic chemicals to treat plants, that'd normally be eaten in small doses, get washed into water/rivers/lakes/oceans, screw up local animals and blow over into neighboring farms (sorry Monsanto wind overspray kill your neighbor, have to buy your GMO to survive BS). THANK YOU!
Re: Hell yes (Score:1)
I am hoping that these gizmos are bought and used by local governments/states to keep ditches weed-free. Guess it's too much to ask humans not to throw their smoked butts out windows which then start fires.