Farming robot kills 100k weeds per hour with lasers
freethink.com
freethink.com
This is a super interesting problem because the confusion matrix (fp/fn/tp/tn) rate that makes this economical is going to be variable across both crops, and market demand.
If there suddenly there was a demand jump for peas, you could afford to use a model with less accuracy, because you are optimizing betwee a sunk labor cost and margin on your yield. You could literally tune your detection parameters based on futures price data, since if if prices were high, you could optimize compute on your model. Anyway, spoken as a total outsider, but what a cool and interesting set of problems.
I think lasers for killing large animals (including us) will be prohibitively expensive for a long time to come, fingers crossed.
1. https://www.brookings.edu/wp-content/uploads/2018/12/africas...
Although I keep thinking the movie Runaway (1984) is going to be a much truer representation of reality than I would like.
Both the drone and the ground robot would need milimiter precision geolocation to coordinate otherwise the laser can miss the weed.
Now for individual weeds you need precise aiming but that's only from a few feet away at max.
The overall geo location boils down to being able to track a row as you go down it and then go to the next row at the other end. The lasers don't care about the geo location at all.
A flying drone seems like the wrong way to solve the problem, though. For a drone close enough to the ground to reliably detect weeds, you'd likely need a multi-rotor, a slow flying fixed wing aircraft, or a blimp. A multirotor has a huge energy penalty, and a fixed wing aircraft or blimp loses the practical gains vs. just using a tractor of some sort.
If the camera sees the correct spectra for a known weed it can drop down and get a closer inspection then mark the spot or just burn the weeds with an attached laser.
I assume the crawler is necessary because--in order for the laser to work--the weeds need to be identified very early as they emerge from the ground. You might not be able to spot them at such an early stage from above without expensive optics.
Now there is opportunity to have one long wire that the tractor reels in/out as it makes passes. This isn't a flying drone, but that isn't really needed for anything other than cool.
You don't need wires to be that rigid for that.
I’m not sure why people are inventing more complicated solutions when this robot seems to handle the job quite well without them. It covers 20 acres in a day, you can likely keep 100+ acres weed free continuously without any other special gimmicks.
There are already solutions that use drone photogrammetry to map crop health, ground coverage and so on. It feels like a logical next step to use a drone to assist mapping the best route/find problem areas to target for the weed-roomba.
That's a ridiculous solution to a non-existent problem. The robot literally has no rush to go to the weeds. It can crawl along the field by itself 24/7. Throw in a solar panel charging station and you literally have free energy for it to piss away.
Instead you want to add complexity to the setup, increase maintenance costs and potentially shorten the lifespan of the system.
If it covers all your land in under a day, sure. If not, then route planning may mean you can have one rather than two or more of these very expensive machines.
It's not a drasticly complex addition, and mapping weeds with drones appears to be a use of them already.
This assumes weeding is a time sensitive task, which I find very doubtful. Realistically covering your land area in a week is probably enough, but maybe that's much higher.
If sending a 20 pound gas drone with a 2 TB solid-state drive and 60 FPS 4K camera on it up and down the field for one 100th of the fuel consumption once a week saves 500 hours a year off that beast, it’d probably be worth it.
This true of any modern farming equipment, which is why planting strategy is so critical--I kept messing up in my first year as I was going way too fast instead of taking my time and my planted rows were never straight, it was in a green house and we had an old diesel tractor so my lungs were hurting after the first hour and I just compromised on that aspect.
But then when I had to go back and weed, maintain and eventually harvest the oddly planted fields of salads and potatoes I made sure to follow the natural ebb and flow of the soil compaction, which was there even after it was tilled.
What I'm saying is that the compacted soil can help you in later seasons to maintain the direction of growth so it's not entirely a bad thing to have. And unless you farmed the same fields for several seasons/years you would overlook this as a net benefit. Eventually seasoned farm hands can do it while drinking and smoking and just listening to how the engine is struggling without even touching the steering wheel, they can even get out of the tractor and walk ahead of it as it's crawling forward to check if everything is fine. Where as for apprentices like myself who had no real experience in Ag it was a remarkable discovery that one shouldn't overlook.
Also, drones are already widely in use; they monitor temperature and moisture in real time and a offer other services right now [0]. Their is a company that I found that posted here on YC a few years ago that offers this as a service [1].
I was actually going to get my commercial drone's license a couple month's before I retired as a farm manager in Hawaii due to extensive injuries, but my fintech startup required saving and scraping all my pennies to afford getting it off the ground. I might consider getting it again as things start to be more widely deployed and the costs keep coming down and I still would like to be involved in some capacity in Ag.
Farms are designed to be serviced by farm vehicles. A vehicle makes a lot of sense.
Polyculture farming could become much more economically feasible if drones could weed out all non-whitelisted species.
Would also be a great boon to forestry: would be awesome to make a bunch of drones to fly through forests and zap any non-native invasive species it sees.
Sure, but the weedkiller isn't the only vehicle that needs to work on the farm. I don't think flying drones are going to be ploughing any time soon.
Given the climate change it could be the other way around. Zap some native saplings, which can no longer thrive.
Yes, let's put powerful lasers on drones flown by AI. What could happen? I just hope the human recognition model doesn't shoot more of one race than another.
I'm not sure that's a great idea either, but flying brings more problems than it solves in this problem space.
Well, there are some robots that travel on aerial lines, typically used for cable inspection. Here's a quick search result: https://spectrum.ieee.org/automaton/robotics/industrial-robo...
And, hey, with unmanned drones over rural fields you won't get any Hindenburg disasters.
But I think it might be possible to focus sunlight to generate energy to kill weeds, not through battery or generated electricity.
A spider-carriage walking robot which could step around the valuable plants, climb steeper hills, and wouldn't dictate a row-and-plow approach to agriculture, that could be pretty compelling. Less soil compaction, more flexibility, could work inside forested regions as well. It has potential.
Also: no more chemical weed killers.
Do this with bugs, and get rid of insecticides as well.
My second thought was, "Please nobody invent a drone that shoots lasers at 'not hotdog'".
I had a professor in college who was building self-driving tractors and would come in every other week complaining about John Deere this, or Case that, trying to steal his business with more expensive solutions. It turns out you can use GPS for a rough location and a fancy $200 gyroscope for millimeter precision. Then just plant the seeds on an exact grid and you know that anything not on the grid is a weed.
And actually, his suggestion was to use high-pressure water jets to cut the weeds instead of lasers. It would/could be less energy-intensive.
Lasers are not used because they’re expensive and dangerous. And Co2 lasers (as per the machine in the article) are powerful but super fragile.
Water shooting around at high pressure is in no way efficient or easy to handle.
Compressed light is the technology that’s actually going to be used for precision weeding. It has the speed, power and simplicity of lasers, without the cost and danger: https://www.linkedin.com/feed/update/activity:67899797724715...
The gimbal alone on your flying drone will cost more than the entire river.
That kind of sensor is expensive though, and while you could probably do it for cheap with something like a DLP wheel (edit: or an array of different light emitters) plus a B/W camera, ML might be more price-effective, though probably more error-prone, so it isn't a given if you want a high match rate.
Also, isn't this a fire hazard?
[1] https://en.wikipedia.org/wiki/Hyperspectral_imaging#Agricult...
...until they evolve to emit the same spectrum of light as the crops being harvested! Cuz you know that's going to happen.
Crops are planted in a specific pattern, at a specific time, grow at a specific rate, and have a unique shape. So you have a lot of information to work with.
The answer is to select according to a wide range of criteria, and not rely on a single one. That way, weeds cannot progressively acquire resistance, and need to check all the boxes at once, which makes it highly unlikely that they will pass on their "slightly better" genes.
And of course, the larger the scale you employ a single weeding system at, the more risky it gets. It would be great for supplementing herbicide (while lowering doses) at first, for instance.
Examples of this are Rye and Oats.
...that's exactly what CV needs to handle.
I can imagine discriminating species of a hundred leaves in a very high resolution images to be very challenging.
The leaves are 3-dimensional objects can be twisted, tangled, curled up, broken, half rotten, sunburnt...
A slightly more advanced sensor or lighting apparatus wouldn't cost much more, proportionately to the cost of the whole system.
Unlikely. Heating a plant to kill it is considerably lower power than heating a plant to combust it and turn it to ash. It would also be trivial to add a water sprayer as part of the process.
Bit of a pedantic note:
What other sensor could you use?
I'm grasping at straws (pun not intended) to figure out any other modality that could work as well in a giant field of psuedo-randomly mixed plants with the wind blowing chemical signatures all about.
With visible light, all you have to go on is small differences in shades of green and shape of the leaves. With other spectra you'd have more cues.
A spectrometer is a single pixel camera, I guess, but it isn't being used with imaging optics, and it isn't being used to stitch together a photograph.
In a general case you could embed some version of GFP instead of glyphosate resistance. Then you can set the system loose (within the field, lol) to actively interrogate plants, zapping intruders that fail their scans.
That's actually the "weed control at scale" developed in conjunction with the tractor.
I'm not a fan of modern conventional agriculture. The abuse done to topsoil is terrible, and we need better systems. But new systems need to keep their eye on the ball and the ball is a John Deere pulling a 40-foot cultivator across a field while the "operator" reads twitter ( or <verb>s Clubhouse ) only looking up to mind the turns.
Everything starts somewhere, but just because your tech has ML and Laserbeams doesn't mean it passes the tool/toy test.
After all, this is what we did with chemical weedkillers.
My high school summer job actually was helping with wheat harvest. You can only work when it's hot as you get better prices on the harvest.
There were certain kinds of weeds that really clog the combine (usually ragweed, not a huge problem in the early summer, but weird things happen) or cause damage to the cutting head (invasive brush/tree species). We walked the field and pulled anything really bad out.
Talk about a way to earn $25/day. You only finished when the equipment was put up for the night.
Most farms irrigate with a giant automated system that sweeps around the field in regular intervals. These weed death lasers could be integrated to the base of the system and ran from the same power that moves the pivot.
Since these things don't move all that fast, you could have a central track and move the killer box up and down the line.
Also seems odd to have it be something that is self-powered and autonomous rather than just something you pull behind a tractor on the three point hitch (where you could power off the PTO of the tractor). Seems excessively novel, given most farmers are already spending time going up and down the rows cultivating, etc. anyways. Adds to the cost, and complexity.
Meh. Worse case you could even have a wire.
74-hp Cummins diesel QSF2.8
4 hydraulic drive motors
75-gallon fuel capacity
Lasers are 150 watts, so a small fraction of the power draw.
Seems like getting the automation is key, replacing herbicides would require multiple passes over the same ground.
Lasers are notoriously inefficient, CO2 ones are in the 5-20% range.
So probably at least 1000W for the lasers, assuming 10% efficiency.
Salivating because that's a lot of power that you can use for experiments, much more than most laser technicians have ever seen.
Horrified because not only are you going to go instantly blind (as usual), but now the rest of your head will smolder too.
And before those 1500W get into the tube, they go through a high-voltage power supply, which is maybe 80% efficient if you're lucky. All-up power draw on a laser of that scale is somewhere north of 2KW from the wall.
(And before anyone asks: Yes this is very good efficiency for a laser, which is one reason why CO2 is so popular. YAG and fiber lasers tend to be in the low single-digit percents.)
Super interesting especially think of it as in its infancy. Also would be interested to see how the real world results are. I'm guessing it can laser all life but I would be curious to see how well the algorithm worked with protecting certain species.
(Video of an operating unit)
There is nothing particularly unbelievable about the device, and it seems, as such innovations tend to be, quite obvious.
It would be more interesting to see a video where they fire the lasers. Can it aim while moving? Can it aim while the engine is on and everything is vibrating?
Same with most fisheries.
If governments want these sectors to go green, that is going to be a very big and painful band-aid to peel off.
How is that different from any other business expense in any other industry.
It’s not some special loophole.
If you use $1000 of electricity to harvest your crops, that $1000 would be equally as deductible because it’s just a cost of production?
Each of these lumbering beasts goes 5 MPH, burning diesel the entire time. How many gallons of gas is going to be spent weeding a hundred acres of farmland?
For example, replacing a deforested area might sometimes be faster by introducing a non-native invasive species. From a carbon perspective it would be a net-good, from an ecosystem perspective it would be a net-bad. Which is more important?
That doesn't seem odd to me at all. The whole point of this thing is to let it run all day killing weeds while you do other stuff. The fact it only has a max of 5mph (and likely significantly slower when there are actual weeds to kill) means you would spend all day every day in the field trying to take care of weeds.
When they spray for weeds they're going significantly faster than that and cover a massive swath in one pass, and that's generally outsourced to someone other than the farmer himself. This looks like it's good for maybe 3 rows at a time.
There's a lot of automated tractors now
I noticed this thing uses hydraulic drive motors... I assume that was so they could run the engine as 'electrical first', but I also wonder if it gives them better start/stop control of the cart.
I'd imagine the end result would be more fuel and in the long run more expense.
I can see selling two models, one autonomous, one three point hitch / PTO. The advantage of the latter is clear to me.
But then the product starts to look a lot less sci-fi, doesn't it? We already have pull-behind weed burners that use propane torches and not lasers. The only "magic" would be in the AI recognition systems (which I have questions about.) Perhaps one could not get investment $$ for it then :-(
Also propane torches seem more efficient to me than converting diesel combustion to electricity to heat energy.
Fully agreed about the 3-point comment though. Why take on building an autonomous tractor AND a targeted weed-killer, rather than tackling the differentiating problem only? Seems like a hype train measure. Or the systems integration is very important, in which case a partnership would be the obvious route or white-labeling an autonomous tractor. Regardless, this strategy seems very weird to me too.
"Autonomous vehicles are hot and AI is hot, go with that."
Based on what? The cummins engine they're using is bulletproof and a rounding error in the cost of the unit. Hydraulic motors will run for 10s of thousands of hours without any maintenance beyond a fluid change.
People in this thread keep claiming tractors are fully autonomous, which model? If they aren't fully autonomous, what farmer is volunteering to spend hundreds to thousands of hours in their tractor doing nothing but putting along at 5mph stop-and-go while this thing zaps weeds?
https://thinkingagriculture.io/the-agriculture-unicorn-hidin...
No idea if this is something that modern tractors could accommodate already or whether it would need some annoying human-in-the-loop stop and go.
If you pull it behind a tractor, you need to hire someone to drive the tractor. This defeats the purpose of an autonomous weeding system.
This is certainly true for dry plants. If they're weeds, they're actively growing, so they are trapping a lot of moisture that could make it hard to burn. If the weeds are a problem, then they're going to be growing. Many weeds, too, will continue to grow, even if their leaves are damaged or removed.
A machine continually damaging cotyledons in emerging seedlings would go a long way. That's part of the advantage of a continually running weed killer.
Limiting usage to when the light will be strong enough to be focused would seriously limit the hours of usage
Maybe adding solar panels to harness solar energy to offset ICE emissions would be a consideration
Having this thing be autonomous makes it more expensive to acquire, yes, but way cheaper to operate because the labor cost of pulling this thing with a non-autonomous tractor is quite large (even if the tractor were autonomous, having two autonomous robots doing different things is better than having one doing two different things that might halve its availability for each kind of task). This is a very big deal. If labor were a non-issue we'd have people weeding manually and we'd not use herbicides. Everything in farming is about labor, which is why we've gone from being agrarian societies to industrial and post-industrial ones: by bringing economies of scale to agriculture in order to greatly reduce labor costs in agriculture.
Question about this tech is, does it really kill weeds, or just defoliate them? Like, is this laser strong enough to get down to the roots, which are often very deep with weeds?
If not, I’m wondering why lasers instead of something mechanical that can corkscrew down and tear up the entire root?
https://www.forestry-suppliers.com/product_pages/products.ph...
I use it for everything, from digging up plants, to leveraging boulders, to actually maintaining trails.
How long will weeds live if they continuously get their foiliage removed? How about when part of the root (closest to the surface) is damaged/burned as well?
I really don't know, but I imagine that if such a robot went out into the field many or most days, there wouldn't be much of an issue. The weeds would continually get weaker.
Fixing a blue steel corkscrew seems easier than debugging a laser.
Realistically, a farmer would swap out the part.
Any actual work on the laser is more likely to be done by a trained professional, if anything to cut down on accidental burns.
I thought weed was the cash crop. /s
Question from a non-farmer: if it were cost-effective to defoliate weeds once per day, would that be good enough? I.e., I would think that totally prevents the weeds from thriving.
But some weeds, like invasive blackberries here in the Pacific Northwest, are extremely resilient and will shrug off defoliation.
> But some weeds, like invasive blackberries here in the Pacific Northwest, are extremely resilient and will shrug off defoliation.
How does that work? I thought all plants (by definition?) need photosynthesis to stay alive in non-dormant states.
Do blackberry plants have some way of getting energy other than photosynthesis in their leaves?
There are parasitic plants that don't photosynthesize at all, like the Monotropoideae and Rafflesiaceae.
Among photosynthesizing plants, rhubarb can be "forced" (grown in complete darkness to reduce bitterness and get an earlier harvest), and potatoes can sprout if left in the pantry for too long.
They actually kill them because they cook the root. That's ALSO why it has to be autonomous - it can't be done at a run.
We worked on this when I was at MTD, but I think they abandoned the project after I left.
I do miss hardware though!
Here's a very (terribly) high level technology overview from the company we were working with: https://g-neighbor.com/gni-technology/
> The reason a plant is green is because it reflects green light and for photosynthesis a plant uses blue light. Overloading the blue frequency range disrupts the enzymes in the photosynthetic process, which cuts off the food supply to the plant and it dies. Some herbicides overload the metabolic system of the plant and makes the weed burn from the inside out. I thought that overloading the photosynthetic system would maybe do the same thing.
In other news: https://www.sciencemag.org/news/2021/04/pacific-northwest-s-...
So what is a more worthwhile use of high tech? Being someone in tech and having greatly economically benefited from it, I've recently been reframing what I know about software tech, startups, innovation with a regenerative paradigm. I am still making my way through Carol Sanford's work on regenerative paradigms and figuring out a lot of this stuff out. So far:
(1)
Christopher Alexander had introduced the idea of creating pattern languages for people living, working, and playing within building architecture so that they can modify and design their own living spaces. What we ended up with are cookie-cutter housing in suburbia. His work greatly influenced OOP and Human-Computer-Interface design (see his 1996 OOPSLA Keynote) ... and what we ended up with is the Gang of Four, Apple products, growth hacks, and "user engagement".
What we don't have are individuals, families, and communities having computer tech that can customized by the users for what works in their local environment. Smalltalk was designed with that intent in mind, but our legacy from Smalltalk is the Gang of Four and OOP "design patterns".
(2)
There was a recent article posted here. It was a fictional interview, the premise being someone from a parallel world where software design was elevated on par with science and art, and not merely engineering. They start with a "design brief" rather than engineering requirements. I lost track of that article.
Just some evolving thoughts.
I have this struggle often. Before software engineering, I was working on permaculture farms and apprenticed as a natural builder (cob mostly).
I still have no idea how to make a living from this though.
Despite growth in organics, 99% of farmland in the U.S. is still conventional. Anything that reduces chemical herbicide usage on that farmland is a good thing.
Example is the dandelion. Besides having culinary and medicinal value, it acts as a pioneer species for depleted soil. Killing it with more roundup or zapping it with a laser, and then contaminating the land with more fertilizer will just encourage more dandelion growth. The land and ecosystem is signaling a fertility issue, and our present practices work against it.
I say this even though the common mallow is the bane of my existence here in the lower Sanoren ;-)
Go start your own thing instead of lazily smashing others.
It seems like you are making an implied argument. Not stating your argument ensures it can't attacked. Not wanting your argument attacked suggests it is weak and won't stand up to scrutiny.
This time, I was adding a subtle sarcasm, which I knew a small minority of HN readers will pick up. They are already familiar with food forests, restoration agriculture, and some may even be familiar with regenerative paradigms.
But let me see if I can condense this into something explicit:
Rather than eliminating everything but the monocrop, there are alternative forms of agriculture that takes advantage of the synergies that come from companion planting, “guilds”. Specific combination of plants planted together can be put together to reduce ecological invasions, or create an ecosystem that can produce harvestable food items for most of the year. Some combinations can mutually resist pests and diseases. Others can be combined to take advantage of vertical spaces (canopy layers), or to effectively modify the local hardiness and heat zones, or modify wind conditions.
Designing such a thing can get very complex. Some designs, however, become so resilient, they continue producing human-harvestable food despite being abandoned for over 150 years.
The Pacific Northwest is not the only region where indigenous people have used these practices. There is quite a bit of anthropological evidence that this is a wide spread practice ... what is novel with that article is that ecologists are acknowledging that this had happened in the Pacific NW.
An alternative use of ML, CV, and robotics, might be something that can observe and identify all the participants in an ecosystem, such as food forest, and use ML to sketch out the possibility space in which viable cross species synergies can enhance an ecosystem. This could be used as an aid in designing a food forest.
One use of ML, accelerates ecological degeneration. A different use of ML accelerates ecological regeneration. I don’t think the latter involves a weed killing robot.
No one is suggesting this be done. Fanatical monocropists don't exist.
Your argument is based on a false dichotomy. We can make monocrop farming more efficient and environmentally friendly (eliminate pesticides) while also exploring other systems.
More efficient and environmentally friendly are contradictory in terms of monocrop
> Fanatical monocropists don't exist.
Uh what? What about the almost 100 million acres of corn in the US?
By “monocropping”, I am talking about planting a single cash crop on a plot of land. A farm may operate multiple crops, each on its own field. They might rotate crops with cover. Some might even interplant crops in rows, or even between plants (as cover). Each field is intended to grow and harvest a single cash crop. You don’t even want to different varieties of the same species close together because you want to ensure a consistent produce. Many restaurants demand consistency (easier to consistently produce dishes when ingredients are of consistent size and quality), and consumers have been conditioned to take a few varieties as representative. (Example: many consumers think of Roma tomatoes when they think of “tomato”).
The combines are designed to till, sow, and harvest in generally linear rows, for a single type of crop. The field is plowed in a way to be level, so that watering can be as uniform as possible. Soil amendments, such as fertilizer, is relatively simple to apply.
So as an example, an old Native American practice called the Three Sisters: corn, squash, and beans, can be planted together. These three crops, when planted together, includes a plant that will fix nitrogen (beans), as well as a ground cover (squash) that help retain moisture. The corn stalk functions as a trellise for the beans, and help shade it. Beans can be harvested early in the season, corn and squash later in the season, with squashes working well as a dense store of nutritional energy that will last through the winter. It also happens that there are lots of culinary dishes that also combines these three plants.
I know of no industrial farming practices or equipment that practices the Three Sister. Driving a harvesting tractor through there will destroy the squash, and probably the beans too.
There are other combinations such as, tomatoes and basil; strawberries and asparagus.
When I use companion planting in my garden, I noticed a few things. First, harvesting is more difficult. You have to be able to identify each plant. I had to look through the different canopy layers to see what is going on. But it was also my first attempt, and I think I can design it a lot better.
When done this way, yield are not as good for any single crop (if they don’t synergize on nitrogen fixing). But I also wonder if the total crop output across all harvestable plants are better.
That is just for annual crops. There is a similar practice that can done for perennial crops. This is what those “food gardens” mentioned in that article, though they are usually called “food forests” by enthusists.
One of the things about this method of farming is that it is intended to decentralize food production, letting the bulk of the food production be local, in order to reduce transportation. You can then grow varieties that taste better and are more nutritionally dense, instead of being bred for staying edible and transported by refrigeration. (I am looking at you, roma tomatoes and hothouse tomatoes).
During the years of international sanction, Cuba had to develop self-sufficiency with use of very little fertilizer (no oil imports), no gasoline driven farm equipment (no oil), and as little motorized transportation as possible. They used a variety of methods, some drawn from modern science and some drawn from older farming practices; but whatever it was, they could not simply use pesticides, fertilizers, or refrigeration.
https://www.architectural-review.com/essays/cubas-urban-farm...
https://www.smartcitiesdive.com/ex/sustainablecitiescollecti...
Is that what you mean or did you mean something else, like the machine could eliminate some non-monocrop plants but not others?
Rather than doing that, we can use companion planting, integrated pest management (chickens, ducks, etc) on smaller fields.
Smaller fields and multi-crops don’t have the same scale as the current farming operations. But the idea here isn’t to replace a large commercial monocropping farm with another large commercial polycropping farm. Instead, we are replacing large monocropping farms with many smaller farms using these methods, and locating them to population centers.
As far as the point you brought up about society eliminating non-monocropping methods ... I don’t think there is a need to have our society use laws to force monocroppers out of business. Instead, I think it is better as a grassroot effort with people practicing this, as a sort of ecological succession —- people starting up home gardens and neighorhood farms to supplement existing food supplies, with monocropping dying on its own.
It does not even have to happen in affluent places first. There are many urban food deserts where people can only get expensive, nutritionally-poor food from convenience stores. You get some small operations there, even hybrid methods, with community involvement and it can change a neighborhood. (Examples: Urban Farming Guys out in Kansas City, and Brad Lancaster out in Tuscon, AZ)
There are plenty of commercial farmers who want to get out of the debt trap they got into with cash cropping. Some even tried their hand at organic farming ... but some will bring their big farm monocropping mindset into it and fail. I think many farmers (and not the agricorps) love working the land and feeding their society. The ones that don’t have been leaving farming for easier work.
But I do think there are things our society does to keep agricorps going. If food decentralization reaches a certain point, I think those agricorps will fight back to retain control of their markets.
First, the evolution of the computational model is simply faster than biological evolution. The computation model is going to be inside biological evolution's (metaphorical) OODA loop. Humans are going to be helping, too, it's not like it's just going to be up to the deep learning algorithms on their own.
Second, for most weed plants, they aren't just a couple of genes away from mimicking corn... they're probably dozens or hundreds of genes away from mimicking corn. Evolution is OK at adapting current things to new uses, or doing a massively-parallel search on what you can do with just a tweak to a gene, but if the task can't be done with one of those things, it just loses and the organism dies. Or, to put it another way, it's good at climbing slopes one step at a time, but if you present it with a cliff it just fails.
It's essentially the same reason why nothing has evolved a resistance to a human gardener yanking them physically out of the ground and leaving them to die on the concrete... it's not just a matter of tweaking a couple of genes for that. This robot presents an exceedingly harsh selection landscape for a weed.
I think evolution over longer timespans is the algorithm that keeps giving. In a single run it created all life and current technology. Evolution is radically open-ended, and that's how it gets around deceptive search spaces.
Not the case. https://en.wikipedia.org/wiki/E._coli_long-term_evolution_ex... gives us a concrete example of this; the ability to metabolize citrate required two mutations, the first of which isn't useful on its own.
As long as a mutation isn't drastically harmful, it may persist in the population to be built upon later.
> It's essentially the same reason why nothing has evolved a resistance to a human gardener yanking them physically out of the ground and leaving them to die on the concrete...
They have evolved quite a few of these. Try and clear a lawn of dandelions and you'll discover they regenerate from their taproot if you leave any of it in. https://en.wikipedia.org/wiki/Vavilovian_mimicry indicates another, where false flax has evolved based on a human invention, winnowing machines, to evade them.
Rye grain evolved so effectively based on human activity that it went from weed to useful crop, even.
A few examples come to mind:
- "Clovers" fix nitrogen in the ground, other plants can take that nitrogen from the ground, some gardeners now intentionally keep this weed to benefit the plants they are growing for crops. I think the term is called "rotating cover crop".
- "Comfrey" has incredibly long tap root which mines minerals and stores those in the leaves. Gardners/farms can plant comfrey, chop the entire top off, the decaying leaves release the minerals into the surface soil for the surround crop plants to utilize. Without comfrey, those minerals would of been locked away from the main crop. After the comfrey is cut, it grows back the leaves again and the gardener/farmer can repeat this cycle.
- Some weeds attract beneficial insects to the garden/farm and thus benefit the main crop. Wise gardener/farmer would keep these around. For example, more bees means more insect pollinated fruit to be grown.
The pattern with highly competitive specifies results in either extinction of one of the species or a mutual beneficial evolution. For example:
- "Bull horn Acacia tree" - Ants and the tree have co-evolved that in the present they are highly depend on each other for survival. In the history, at one point when the ants and tree were introduced the ants brought a lot of acacia tree destruction followed by ant death because of loss of food source - but over time the trees that benefited the ants got selected along with the ants that were compatible with the trees.
If you'd like to learn more on the topic of coevolved species, I recommend this 30 min video on the topic https://youtu.be/hCAvBmY7ZgA
I don't know what this robot will do, the story is being currently written so we will see what happens!
And eventually the humans will too.
Typographic ML attacks work and are pretty funny.
Elsewhere on this thread is a great example of this in practice. https://en.wikipedia.org/wiki/Vavilovian_mimicry
> Seeds that are thrown the same distance as flax seeds have thus been selected for, making it near impossible to separate the seeds of these two species.
[1] https://www.agriculture.com/technology/robotics/the-future-o...
Translation: The wages we pay are crap and we're not going to pay them more.
But the market will always find the place where the work is unbearable and stop just shy of that.
You underestimate the percentage of the income some people spend on food. That's why agriculture is heavily subsidised.
That’s a collective action problem. You can’t get everyone to pay $1 more. If your strawberries (for example) cost $1 more per pint then your sales will drop accordingly. It doesn’t matter if all strawberry farms agree to pay more to their strawberry pickers. You aren’t only competing against other strawberry farms, you’re competing against all other food. If strawberries are too expensive, people will eat candy or potato chips instead.
In 2019, California agriculture produced about $50B in receipts, with almost $22B in exports. Our water goes with those exports too.
Now, that kind of nationalism is very uncalifornian.
My original point is that even though we produce a crazy amount of farmed goods in CA, we still import things that we grow here and export. Always seems odd to me to see produce from Ecuador in the grocery store when I can buy better quality down the road from a local farm stand.
But it's also incredibly fulfilling work, and it's a great example of a community-driven effort to accomplish something very important: providing food.
So I think it falls into a similar category of "college is over-emphasized and we have a dwindling supply of trades-workers". While in school in a rural farm town, I never once heard anyone say "what about farming?" when discussing future career choices. It's not marketed as an attractive option. Maybe it's as simple as "farmers have the work-life balance of an emergency room doctor while making ~1/6th" (source: Dad is the farmer, Brother-in-law is the doctor)
Anyway, it's a problem I think about a lot. I didn't get into farming, but in many ways I wish I had, because it's a highly undervalued skill with a very rewarding outcome: you feed communities. How do we change the narrative? Do we need policy changes? Continued technological advancement? A push to educate the next generation of farmers within schools? I'm not sure, but I don't think it's always as simple as saying "it doesn't pay enough". That _is_ an issue, but it's not the only issue.
If it pays as much as other jobs with shorter, less sporadic hours, it's underpaid.
I'd love to take a break from my job once in a while to do some other, probably more manual work.
I think everyone used to go back to the countryside to help with harvest during summer, bur I feel overspecialized these days. How about incentivizing companies to take more part-time workers (as in, do not make it difficult to do so)? Together with minimal wages, it could be quite interesting. I also think having a broader skillset (more people helping) would help quite a bit: If I worked part-time at a bakery, I could probably help them with their computer/electronics troubles, for instance.
But. I survived my early 20's on these kinds of jobs while I sorted my shit out. I'm grateful for the experience and the ability to support myself while I did that.
After Jurassic park, there was a huge uptick in paleontology, and everything else related, even Veterianism (!).
Most of the currents that kids get from movies are destructive to society IMO, but if it could be tapped into - it is a source of influence. Humans naturally copy what they see.
If a series of movies with the hero being an entomologist came out, it would do us good. If there were a bunch of farm boys that played with nature in a way that made it cool, we would harvest the benefits for generations.
What is that big unpainted aluminum box sticking out the front? Why is it sticking out the front? It makes the machine look like a prototype, not a production machine. Aren't they "for sale but sold out?"
The video section subtitled "The bedtop is scanned to detect weeds in realtime" https://youtu.be/vSPhhw-2ShI?t=58 is ...odd. The two camera shots on the left show just weeds (top) and just onions (bottom). One would expect the "before" camera to show both weeds and onions. The "after" camera shows only onions so the machine must be 100% effective. /s
In the same shot, the ground under the machine does not look like it has any onions and it looks like it has only a few weeds, many fewer than the "weeds" camera shows. You can see "sparks" where the machine is presumably lasering weeds, but there are many weeds under the machine that survive the "weeding".
The press release https://www.businesswire.com/news/home/20210413005415/en/Car... is oddly interesting too. Only one farmer is quoted. (Only one? I though the production machines were all sold out. Where are the other farmers who bought machines?) The quote is pretty specious and his qualifications to judge the machine is very vague "[he] has utilized Carbon Robotics’ technology on his farm." So he apparently does not own a production machine. "Utilized" is a very nebulous term - could mean he used it to weed his fields (mmmmm yeah) or the company used his field to run tests on the machine (seems more likely).
I love the summary quote of Mr. Johnson: "These robots work with a variety of crops, are autonomous and organic. The sky’s the limit.” Doe people actually talk that way? No farmer I know talks like that. Sounds to me like something a PR flak wrote.
Back to the original article... "Even farmers who can afford to buy the robot might not be able to get their hands on one for some time — Carbon Robotics has already sold out of the bots it had available for 2021 delivery." I'm guessing the number of bots it had available for 2021 delivery is zero, in which case the statement isn't quite a lie.
Why use lasers when we can genetically engineer goats to hate the taste of corn/sorghum/wheat and love the taste of weeds?
Grazing animals would eat the weeds and naturally fertilizer the land. No harm if they don’t totally kill the weed, more food to fatten them up.
Granted, that's just a billion dollar idea. The multi-billion dollar idea is, as you said, to modify the animal and the plant together. The goats hate some taste in the corn, and the corn produces the taste such that humans cannot taste it. Maybe it'll ripen after harvest and the taste will lessen. I dunno. This way you can double-dip and charge the farmers on the new plant varietals and the goats. Bonus points if you can modify the goats to produce milk that's got vitamin-D in it or something.
I've seen this set-up in Victoria and SA before. The goats eat the grasses/weeds that grow in-between the grapes of vineyards. I've no idea if the goats eat the grapes every once in a while. The wine grapes are pretty sour and bitter to us humans at least.
It would be very 'green' overall.
Contextual example: https://news.ycombinator.com/item?id=25749015
When I read people talk about how hard it is to find labor I think to myself "Well, maybe if you paid them more it would be easier to find laborers". I worked in manufacturing for a few years and plant managers were often stating the difficulty in finding laborers. I imagine offering higher wages would make it easier to find workers. No?
> "It's harder to find people to do that work every single year," vegetable farmer Shay Myers told the Seattle Times.
You can bet that a farm that saved money weeding with robots wouldn't drop the price of produce reflecting their lower costs. Like prices if everything, it's more what the market will bear rather than some geometric relationship to labor/production costs.
At some point, this kind of framing was probably easier for an average reader to understand... IDK when that stopped being the case, but it's not recent.
In any case, this kind of tech is potentially interesting. Weeds, pests and other agricultural issues can usually be solved biologically (eg weeds get eaten, outcompeted, etc.), chemically (eg roundup) or mechanically (someone pulls the weed). We've long been leaning on chemical way too heavily.
If/when robotic weeding is available, the economics may be pretty compelling. If it takes off, it will almost certainly open a lot of unexpected opportunities. Genuinely important agg-tech, IMO, can be approximated by how it affects a given farm. If you are still, broadly, farming the same types of crops in the same ways then it's incremental. Most commonly today, incremental advances mean growing slightly different cultivars paired with complimentary fertilizers & pesticides. AKA, the Monsanto Way. I don't think we're going to make much more progress this way. Also, advancing to "Modern Farming" this way is pretty tightly couples with corporate farming.
What's potentially interesting about robots like this (if/when they're good) is that it may scale down well.
Really cool product!
I think what this product may lack if anything, is some RGB LED lighting and a name with X or Z in it, eg "CarbonX LASER-Z". Especially now with eSports increasing popularity, perhaps we may find eFarmingSports finding a niche, where the most zapped weeds per time unit wins.
There's no sense letting it get rained on, so it needs some sort of cap (especially given that it's presumably electric high powered lasers).
It doesn't seem to move fast enough to care about wind resistance.
A cube is a nice easy shape to build... so why not a cube.
Elsewhere in this comment section someone pointed out that the generator on this supplies slightly more energy than the rated maximum of most houses. It only has a few sq m of solar space on it for solar panels... that doesn't seem like it will even be a dent.
Like usual, you're better of putting solar panels on the ground somewhere. If this thing ever becomes electric I think it will have to either be by a wire, or by using electricity to convert CO2 back into fuel. Maybe if batteries improve a bit by battery, but right now it sounds like it would need to spend a large portion of it's time recharging (just comparing to electric vehicles).
On the flip side - this might be a great candidate for these guys carbon capture technology: https://news.ycombinator.com/item?id=26412624
Not all of the *cides could be replaced with these, but certainly you could identify undesired plants and insects that way, and destroy them. Insects may be fast enough to require lasers, but who knows? Non-desired plants could simply get snipped and fall to the ground. Fungi ... could at least be identified and marked on a map for later spraying.
I think all of this is do-able (and a lot better place to start for self-driving AI than the lofty goal of cars, given the restricted domain, lower speed, reduced danger ...), but the real question is: can these robots price out lower than the *cides they might replace?
Yes, I'm sure their customers will buy expensive machines that don't work. Haha, farmers are dumb, am I right?
Ugh.
It does this well.
Unfortunately, the hot dog is the only thing that it can positively identify. Everything else is "Not A Hot Dog."
https://medium.com/@timanglade/how-hbos-silicon-valley-built...
Once they get small enough, homes will one day have insect-sized robots in the walls preventing termite and other insect infestations. But maybe without lasers.
Burning leaves doesn’t reliably kill plants, if you don’t pull it out by the roots you’ll be getting those same weeds back in short order.
Certainly progress towards something, but a very expensive impractical step for most.
I suppose they probably use galvanometers for aiming the laser? Galvos are very fast but they tend not to be terribly accurate. This device isn't for precision machining so it's probably good enough. I'd also expect the vibration and jostling of the machine to be a problem, but maybe it stops momentarily whenever it does a laser sweep.
I'd think that they really ought to have some kind of shroud draped around it during regular operation to prevent eye damage if someone is too close (especially if there's a risk of shiny metal objects lying on the ground). CO2 laser light is invisible; generally, you just see a white flash when it burns things because that's the light given off by the heated material.
There'd also be an obvious fire hazard, though in practice a well-focused high power beam can often just vaporize a thing before it catches on fire. Cutting paper and cardboard in a laser cutter is usually fine; it's wood that tends to burn. (Especially oily wood.) At any rate they'd probably be restricted to using the machine when fire risk is low.
I wonder how well it copes with weeds that are growing right next to desirable plants? As the crop plants get bigger, it must get harder to get the right angle to burn the weed without hitting the plant.
I also wonder how effective it is at actually killing weeds. Maybe if it can get them when they're small, it can linger the laser over the site of the weed long enough to cook the root.
I'm hoping this sort of thing catches on and becomes more advanced. Near where I live we have a huge park that's being overtaken by English ivy. It's very hilly and forested, so any ivy-killing robot would probably have to be something like a hexapod, and lasers are kind of questionable in a forest setting except maybe on wet days.
When Ford hired workers to deal with the pests, the pests evolved to hide from the workers under the leaves below knee level.
I hope this technology also gets applied to pests like the invasive Popillia japonic.
We could probably use high-tech robots to identify the different plans and harvest one without damaging the other. Something that is currently not possible in large scale farming and thus wont allow us to plant different things in the same space.
Then we "fix" it by adding whats missing aka we use tons of fossil fertilizer.
Big money machine: Myers expects the farming robot to pay for itself in two to three years, but it does come with a hefty price tag: Carbon Robotics' CEO Paul Mikesell told the Seattle Times it costs hundreds of thousands of dollars (he declined to provide an exact price).
Agtech is a fascinating business.
Have they mentioned its safety around animals? Presumably a neural network would identify most mammals properly, but what about an insect? Could a praying mantis be lumped in as a weed?
This seems to be a risk with the use of high power lasers, meant to burn the weeds.
I grant solid state is more reliable, but when it fails it's often a replace not repair situation, which could be more expensive.
And the lasers will still have moving parts right? They have to aim themselves at the weeds.
Distance. The laser and aiming mirrors can all be up in the body, while the beam reaches the dirty work.
Energy efficiency. It might be that the total energy to bring a motor up to speed and swing the arm at the weed may be greater than a brief zap with a laser, even if the instantaneous power of the laser is much higher.
Certainty. A string trimmer takes a certain amount of nuance to start gently so you don't bog down the string, advance through the weed, and understand when it's done. A laser can just run at a fixed power and scan speed, and almost certainly produce the desired results.
Frickin' lasers. There's PR value to that.
This diminishes farmers' dependence on patented "Roundup-ready" seeds, and on the Roundup herbicide itself. That can only be good for everybody except Monsanto.
You better believe they're trying _something_ to preserve their market, it's just more underhanded than that.
Also it's the autonomous element that allows it run continuously (day and night) to accomplish its goal
Satisfying slowmo killshots near end :)
Wonder if it would be possible to do a simplified 2D version in a window frame or something. Should also reduce the risk of burning someone's eyes out.
Is killing weeds generally used in unsustainable agriculture or are there weeds that truly needs to be killed?
Is that typical?
In some cases the tradeoff can simply be between the quantity vs quality of the crop, but it’s not always intuitive which strategy results in improved quality.
Like most whiz bang farming tech it seems too clever (expensive) by half.
It’s not as big of an issue if you have grazing animals, because many (such as sheep and goats) will often go after the “weeds” first. Pigs will happily take it straight down to the earth.
I was in my last year of apprenticeship in Switzerland when New Holland was testing their autopilot planting system, something John Deere had already deployed, and it pretty much had to be corrected every few meteres. But the overall sentiment was that this tech is great, but is still a long way from becoming a reality. Having been in tech and from CA I knew that was partly true but that you cannot dismiss the rate of progress if bright minds and resources are coupled with determined and skilled workers.
I had access to one of those John Deere, it had a realtively comfortable cabin with a radio and seat warmers etc... but after seeing the sticker shock (500k CHF) I saw how they were closed sourced and had to be serviced by appointment only--the brother in law owned the nearby JD dealership in town. I never bothered to use them more than one or twice when the older manual tranmission and for more spartan Renault, Masey-Fugerson, Case, Fiat tractors weren't available or had to haul much larger cargo (100s of tons of potatos to the fulfillment depot, or take 20 cows out of pasture into the barn under 15 mins) due to snow storms.
With that said, this has unit has seemingly limited applications: as you can see this was done in the early phases of growth (looks like very early germination/sprouting) and while you can do this in later stages for things like greens and possibly tubers and other lower growth crops with spaces in between this won't work for things that like grains and corn which are much taller, more densely sowed and have thicker canopies and are what accounts of the most mono-crop and pesticide use outside of cotton.
It's amazing, and I hope we see more of this instead of smart phone 'innovation' but this is why I think rather than shoot for full autonomy in Ag we should just have equipment that can focus on the more menial and labor intesive things like weeding, planting, harvesting because the farmer will always need to be on sight for things like pH test, irrigation, nutrient fluctuations, changes in weather (hail, frost) etc... And have the farm manager be paid well, like 70K+ and that they get trained from an early stage in their careers to rely and use this kind of technology wherever possible and have direct feedback with technologists to direct them to other uses.
I advocated for this as much as I did for sustainability and renewable Ag when I was farming, and it was looked down on in the Biodyanmic community that relies on lots of 'woo' to mask that it's a back breaking, manual labor intensive job that is necessary to create a superior product and justify the +30% mark up in price.
This alone would free up so much more Human capital and allow one to do more of their time that can help sustain the business and help in creating auxiliary business models to support the core instead of focusing on weeding and lower yields due drops is soil fertility due to overuse of fertilizers and pesticides and a direct result due to lack of labor, which other than the ongoing water crisis, and climate change is the biggest issue for farmers in the Western/developed World.
It was only a matter of time. A doom of our own making.
Err... that's probably not what you wanted to hear, though.
No way. Computer image recognition is nowhere close to human recognition in real-world contexts. Still full of errors and bugs.
We can not solve our problems with the same level of thinking that created them. - Einstein
There are some promising reports of enhanced agricultural outcomes from reduced inputs based on alternative strategies such as seedballs, dense intercropping, crop inter-rotation, less intense land use and higher biodiversity. Major issues with such approaches seem to be homogeneity (required by large scale distributors) and difficulties with autonomous harvesting or increased labour (increased yields are no good if you can't harvest them efficiently).
for more: https://blogs.lse.ac.uk/businessreview/2020/09/18/the-great-...
In theory our economic system has been set up in a way that structural unemployment is impossible in the long term term. Automation increases the excess savings rate by cutting labor costs, the excess money is then invested into more automation which only causes excess savings to grow. The unemployment caused by automation goes hand in hand with deflationary pressure as automation decreases the cost of goods. The Fed will respond to a fall in the inflation rate by lowering the interest rates, which encourages borrowers to invest their money and create more jobs. If borrowers fail to invest and the excess savings keep accumulating the interest rates will drop until they hit 0% at which point people will switch to treasury bonds and if those fall to 0% they will withdraw their money as cash. As treasury yields drop to 0% this forces the US government to increase the total investment rate of the economy on behalf of the buyers of the treasury bonds. If the government doesn't increase its deficit the economy will have to respond by reducing the total savings rate, which effectively means unemployment because someone must consume more than they earn. If all of the above fails, the government can send stimulus checks to its citizens. This will increase the inflation rate which will eat away at uninvested savings. In theory the Fed could the same thing but it would be called helicopter money with the crucial difference that there would be nothing on the Fed's balance sheet to counteract inflation exceeding expectations.
Of course all of this is in theory, in practice there is zero political will power. Just look at Trump, he could have done the infrastructure bill, but he didn't. It wouldn't surprise me if Biden fails to push it through and we have to come up with increasingly extreme options that nobody wants. Ideas like Keynesian gold digging only exist because the political environment has "collapsed" to the point where no good ideas are left.
Also mulching and growing cover crops alongside and in succession with our crops [3] prevents weeds without as much labor as traditional wedding. For example planting clover around crops, which stays short and fixes nitrogen while competing with weeds.
I wish we would spend more time rethinking our industrial farming practices, rather than try to prop them up with diesel burning robots.
[1] https://www.researchgate.net/publication/236942635_Grazing_A... [2] https://web-japan.org/trends01/article/021022sci_r.html [3] https://eorganic.org/node/2535
[2]: Again, great, but very crop-specific.
[3]: I've seen/used mulching on permaculture farms, and it seems like a fairly effective method. Also has the benefits of reducing the need for water, and regenerating topsoil via decomposition. But labor-intensive. The clover idea is very interesting and new to me.
> I wish we would spend more time rethinking our industrial farming practices, rather than try to prop them up with diesel burning robots.
Agree wholeheartedly! And if the answer is that more labor is required to farm sustainably, then I'm personally all for that. But I'm also pragmatic, and if we could improve the economics of sustainable farming by automating some of the manual labor, I think that would be great. I'm not sure this specific robot addresses that - it seems designed for industrial monoculture farms - but it's an interesting idea to me.
All farming is "going against nature", by definition.
Take a 100m by 100m field and let it go "with nature" for 10 years. Do you think it'll magically sprout tons of wheat? It'll be great for plants and animals, that's for sure, but we can't eat what will be growing there.