RoboCrop: Teaching robots how to pick tomatoes
99 points
1 day ago
| 9 comments
| phys.org
| HN
HanClinto
23 hours ago
[-]
"Tomatoes typically bear fruit in clusters, requiring robots to pick the ripe ones while leaving the rest on the vine, demanding advanced decision-making and control capabilities."

At what point do we begin to grow tomatoes specifically for their harvestability (in addition / as opposed to other attributes)?

This sort of thing happened years ago with farmers producing product specifically for things like "durability in shipping" -- I'm thinking of "machine-pickable" as the natural next step for growers to aim for.

Is this already being done? I'd love to hear about how this sort of thing is already in place.

Whether this means mechanically manipulating flower + fruit locations (specifically growing vines in a way that produces fruit in a controlled manner), or possibly even breeding cultivars that specifically have more robot-friendly fruit clustering, I wonder what these sorts of efforts might look like in the future?

reply
mcguirep
21 hours ago
[-]
> I'm thinking of "machine-pickable" as the natural next step for growers to aim for.

> Is this already being done?

This is, indeed, already something that is done. As I understand it, for tomatoes it's typically for canning varieties, but they're called determinate cultivars[1]. Even with those, I know in processing you still have to discard the occasional fruit that isn't ripe.

I imagine this kind of technological solution would also be more useful when picking tomatoes for use as the fresh fruit.

[1] https://en.wikipedia.org/wiki/Determinate_cultivar

reply
liamzebedee
10 hours ago
[-]
They are doing this now actually for plant breeding! "Engineering crop flower morphology facilitates robotization of cross-pollination and speed breeding" covers one example by breeding flowers to be more easily pickable by robotics.

[1] https://www.cell.com/cell/abstract/S0092-8674(25)00840-2

reply
ac29
22 hours ago
[-]
The way greenhouse tomatoes are grown is already pretty robot friendly.

See below for a couple examples:

https://www.denso.com/global/en/news/newsroom/2024/20240513-...

https://tta-iso.com/innovations/harvai

reply
Hasz
21 hours ago
[-]
It is done for entire species.

There is plenty of fruits (Pawpaw, loquat, soursop come to mind) that are really not grown at-scale commercially in the US due to spoilage, easy to bruise, or other similar issues.

If you like interesting fruit, I highly recommend https://www.youtube.com/@WeirdExplorer/

for many fruits you will have never seen before.

reply
fellowniusmonk
20 hours ago
[-]
Loquat cardamom jam is pure sex on a buttered english muffin. Probably the most satisfying flavor I've ever consumed, certainly there is no more satisfying flavor. Sadly just as my tree started producing bumper crops a historic freeze killed it.
reply
asdff
19 hours ago
[-]
People grow it all over socal but it has the weather for it.
reply
tdeck
14 hours ago
[-]
Berkeley is full of Loquat trees too. There is one in the Safeway parking lot :).
reply
phito
11 hours ago
[-]
Will they manage to make mass produced tomatoes when worse than they are now? Seriously they're so bad, they're not even worth purchasing in my opinion.
reply
inemesitaffia
2 hours ago
[-]
Most of the issues are from lack of ripeness at plucking.

If you wait till they are about to spoil on the vine, even the one's you really don't like will have taste

reply
amitport
9 hours ago
[-]
I bet you live in the US. What you describe is not a universal issue.
reply
phito
8 hours ago
[-]
No, I'm from Belgium and we get awful tasteless tomatoes from the Netherlands.
reply
techsystems
5 hours ago
[-]
Dutch products in general are low quality. So glad I got out.
reply
graemep
7 hours ago
[-]
In the UK we mostly grow our own tasteless tomatoes.
reply
stuaxo
9 hours ago
[-]
We already did this for durability, resulting in tomatoes that didn't taste of very much.

Now, the supermarkets that sold those have solved it by breeding ones that are incredibly sweet.

reply
iancmceachern
10 hours ago
[-]
"At what point do we begin to grow tomatoes specifically for their harvestability"

This has been happening for hundreds of years already with every food crop.

reply
anothernewdude
10 hours ago
[-]
Keeping them on the vine is far better for the consumer, who can have a range of tomatoes that ripen as you eat them.
reply
wingchen
22 minutes ago
[-]
related company when it comes to agriculture robotics: https://www.beagle-tech.com/
reply
asymmetric
1 day ago
[-]
Tangentially related: https://farm.bot/
reply
GiorgioG
1 day ago
[-]
$5,000-7,000...that's crazy.
reply
daemonologist
19 hours ago
[-]
What's crazy is that it only does the easy stuff (planting and watering). What we need is a robot to do the hard stuff (in my home-gamer opinion: pest control and weeding; maybe picking is most relevant for commercial agriculture).
reply
lukan
11 hours ago
[-]
Not sure if it comes out of the box, but it can also do simple pest control and weeding. Mechancical stomping plants at the wrong position or spraying with chemicals.

Harvesting would be fine for me to do by hand, because that is indeed he really hard part, especially with mixed crops.

reply
dekhn
1 day ago
[-]
I understand the desire of academics to help agriculture, but they really need to check in with the field before coming up with prototypes like this, because they are duplicating existing things (ag companies already do this), making hardware that would never survive the field (ag companies already solved this), and obscenely expensive (ag companies come up with better cheaper solutions).
reply
9rx
1 day ago
[-]
> I understand the desire of academics to help agriculture, but they really need to check in with the field before coming up with prototypes like this

Do they? Academia is about the individual. It is not about others. Sometimes what an academic comes up with ends up being applicable to a larger audience, but that's not the goal. Industry is where people try to do things for others.

reply
esafak
23 hours ago
[-]
This is the Engineering- not Literature department. People expect it to be useful.
reply
dekhn
23 hours ago
[-]
I mean, if you're an academic and you don't care if anybody uses your technology, that's fine, I guess, but the folks publishing these papers want the industry to use their ideas: "In the agricultural sector, labor shortages are increasing the need for automated harvesting using robots." is the very first sentence.
reply
9rx
23 hours ago
[-]
That's a product of coming up through a school system that emphasizes writing engaging content to please teachers. "Oh no, the farmers can't find help" sounds alarming and draws you in. But as you point out, it ends there. Beyond that, the academic goes off and does whatever is interesting to him personally without concern for what anyone else might actually need. And fair enough. He'd be working in industry if he were trying to please others.

And a farmer myself, I can tell you there is no "labor shortage". Quite the opposite. I can't find enough farm work to do! I could easily grow my operation tenfold without breaking a sweat. But there are so many other farmers who want that work as well. It is hard to compete.

reply
averageRoyalty
21 hours ago
[-]
> And a farmer myself, I can tell you there is no "labor shortage".

Are you a Japanese farmer? The context of the paper was Japanese, and there is absolutely a labour shortage. Your section of the world is a timy percentage, and whilst I'm glad you don't have a shortage, your experience is not the worlds.

reply
9rx
21 hours ago
[-]
> Your section of the world is a timy percentage

That's fair, but the same thing is said here too. It's a common trope that gets repeated because it sounds catchy, not because it is true.

> and there is absolutely a labour shortage.

Is there? Everything I can find suggests that Japan is no different than here: That farmers want to do more, but struggle to grow their operations under to the intense competition of every other farmer wanting to do the same.

What you find here, and seemingly also in Japan, is some farms that have gotten too big for their britches that cry "labor shortage" instead of "you know, maybe I should downsize and let someone else have a turn". That's not a labor shortage. If you can bleed them dry selling them your technology, good on ya! You absolutely should. But there is no need to worry about them. Letting them fail solves the problem just the same.

But if what you say is true, please point me to where I can find all this unutilized farmland that cannot be managed because there isn't anyone to do it. I am quite interested in becoming the one to take it over. I may not be a Japanese farmer today, but life is not static.

reply
qiqitori
14 hours ago
[-]
Determining whether there is an actual labor shortage is pretty difficult. In many cases:

* Doing the work in a completely different way would eliminate the need for more people doing the labor. In the case of Japan, there is a lot of small farmland. In the case of the US, farmland tends to be huge. I guess smaller farmland is more labor-intensive. Consolidating smaller strips of farmland into a larger piece of farmland may improve labor intensity. But that means that one person gets to do the farming for a higher margin and everybody else loses their profession.

* Lots of farmland is being worked by elderly people. At some point you can't do it anymore. Somebody not working in agriculture would have to give up their current job and go into agriculture. It's difficult to predict whether that will happen.

* Labor shortage often means "we can't find anybody who is willing to do it for 1000 yen per hour so there must be a labor shortage".

BTW, there are a lot of abandoned houses in Japan; many of them will come with some amount of farmland that could be used, but isn't used.

reply
dragonwriter
13 hours ago
[-]
> Determining whether there is an actual labor shortage is pretty difficult.

The only hard part is nailing down what people mean by “labor shortage”; resolving whether one exists under either the normal economic definition or the one people are actually using is pretty easy, but since the whole point of using the term is to mask that the actual complaint is about wages being too high, its really difficult to get people to admit what they are talking about.

reply
reeredfdfdf
11 hours ago
[-]
Yep, almost always in rich world "labor shortage" = I can't / don't want to pay a livable wage.

Over here in Europe my country has a sky high unemployment, yet picking tomatoes is mostly done by immigrants from Southeast Asia. The pay for that hard work is so bad that most natives won't bother, but it's okay if your plan is to save for a few years with absolute minimum budget, and then return to somewhere with much lower cost of living. I guess it's just the same with Latin American migrants in America.

Japan has historically been pretty anti-immigration, so they might prefer robots over this arrangement.

reply
9rx
13 hours ago
[-]
> Determining whether there is an actual labor shortage is pretty difficult.

Using the technical definition, it's actually pretty easy. There is also a colloquial definition. But under the colloquial definition it is not just pretty difficult, its is actually impossible as it isn't real thing.

> But that means that one person gets to do the farming for a higher margin and everybody else loses their profession.

Here's what happens here: One large farmer captures most of the market and then relies on farm workers to get the job done, while small farmers are left under-utilized. It seems the same is true in Japan. After all, we're talking about farm laborers, not famers. The small-plot farmer who is also doing all the work doesn't need legions of employees.

Which is all well and good, but when the larger farmer reaches the limits of how many people they can hire, the solution is simple: Cut back. The under-utilized farmers will happily step in to fill the gap.

> It's difficult to predict whether that will happen.

It might not happen, but if it doesn't happen, it wasn't ever needed. Do you see a reason for farmers to farm for no reason? I don't mean no reason like overproducing to ensure there is still food in the event of a catastrophe. That is actually a valid reason, even if it doesn't always seem like it. I mean like produce it and then immediately turn it back into the ground.

reply
dekhn
23 hours ago
[-]
I mean, many of us in academia (I was previously) have made things for industry only to learn that we ignored something important and obvious that was already known. I wish I could find the nice article that gave a bunch of examples of papers and concluded "John Deere already sells this product and it's being used at scale today; if you want to do better, at least be aware of what's going on in the field"
reply
Animats
22 hours ago
[-]
Here's the video "Fanuc already sells this product and it's being used at scale today."[1] This works in a very orderly greenhouse, one of the largest in Europe.

[1] https://www.youtube.com/watch?v=9nOdiwKDXYM

reply
9rx
23 hours ago
[-]
I'll grant you that people who don't understand the difference between academia and industry might mistakenly push themselves towards academia when they really want to be in industry, but we shouldn't take that as an understanding that academia and industry serve the same function. They have different names exactly because they are expected to be different. Academia is where one goes to explore oneself in pursuit of one's interests. Industry is where one goes to explore others in pursuit of serving their needs.
reply
lukan
11 hours ago
[-]
"Academia is where one goes to explore oneself in pursuit of one's interests. Industry is where one goes to explore others in pursuit of serving their needs."

Unfortunately, also in academia you cannot just do what interests you, unless you got unlimited funding somehow. Because also academia requires money. For you to live and to fund your research. And this does not get handed out freely, you got to apply for it - and you only get it, if your needs match the needs of those giving out the grants. Now yes, there is more possibility to do research not bound by a concrete practical application, but the framing is really not correct. You cannot just research what you want (Source, I left academia to do my independent research of what I want, what I could not do there)

reply
9rx
34 seconds ago
[-]
> Unfortunately, also in academia you cannot just do what interests you, unless you got unlimited funding somehow.

You cannot be both in academia and accepting someone else's funding to work on their problems at the same time. Once you accept the latter, you've moved into industry.

That's not to say academia becomes off-limits. You can also spend time out of your date working on your own pursuits. But when your time is focused on someone else's interests, you are no in academia. You are in industry.

reply
dekhn
22 hours ago
[-]
I disagree.

For example, I work for a company called Genentech that was founded by an academic. They discovered something important (how to clone genes) and shortly after, found medical applications (human growth hormone and insulin) that transformed treatment,

We carry out open-ended research on human biology, have many visitors from academia, along with dual appointments (person is both a professor and a scientist at the company), publish in the same journals as academics, etc...

And this is highly incentivized by the government: Bayh-Dole act makes universities want to patent tech that gets licensed by industry.

reply
9rx
21 hours ago
[-]
Where do you disagree? You point out that individuals are not statues and can shift between spending time in industry and in academia. You also point out that industry and academia are not confined by who owns the building that the people are occupying. But nobody was ever thinking that wasn't the case.

This is the first time anyone has even considered that someone could be forever stuck an academic or industry operative, or that industry can't take place in universities and academics in private businesses. Good on you for coming up with hypothetical alternatives suitable for a sci-fi thriller. You've clearly got a creative mind! But since they are only hypothetical, it is not clear what purpose they serve here or how it even could begin to relate to anything being discussed.

reply
graemep
7 hours ago
[-]
> In the agricultural sector, labor shortages are increasing the need for automated harvesting using robots

Making things sound useful might help with funding? It does for some people and in some places.

reply
zipy124
21 hours ago
[-]
That sentence is because in engineering journals you often need to state some problem you are solving. Proving the problem exists isn't necessary, just enough to convince the editor. Most academics don't care if someone uses the technology, just like most software engineers don't care about the user of their product.
reply
dekhn
21 hours ago
[-]
Yes it's the same reason in grad school they taught us to write grant proposals that cure diseases of senators and congresspeople, while actually working on fundamental research problems that have no direct applicability.
reply
asdff
19 hours ago
[-]
Every single STEM paper there is will have sentences like that putting the work into context and perspective.
reply
MisterTea
20 hours ago
[-]
> making hardware that would never survive the field

What I saw in the article was a prototype and see no reason for it to be "field ready."

reply
asdff
19 hours ago
[-]
It might not survive the field but seems fine for greenhouse setting. And a great way to line up a good computer vision engineering job with an ag firm after.
reply
ramy_d
1 day ago
[-]
I'm looking at something like this https://www.youtube.com/watch?v=l4Dc6QNWiIs and I feel like they are doing totally different things. Both harvest tomatoes, but these are totally different approaches.
reply
ruslan
23 hours ago
[-]
Did you see tamatoes harvested that way ? They are suitable only for producing sauce.
reply
reachableceo
1 day ago
[-]
Really? Can you link to those solutions please ?
reply
sbfeibish
6 hours ago
[-]
In my neck of the woods we use deers. And they work at night too.
reply
ge96
19 hours ago
[-]
I'm wanting to do this for dead leaves/pruning

Or if it makes more sense to just let them fall, identify and pick up the leaves from the floor/plant pot

reply
metalman
6 hours ago
[-]
"Robots will automatically harvest tomatoes that are easy to pick, while humans will handle the more challenging fruits." this is EXACTLY the oposite of the way it is supposed to work, and brings to mind agricultural sayings concerning greed and taking unfair advantage, "taking the low hanging fruit", and "cherry picking" with the blame of "inefficiency" going to fall on the plants, and a bigger push to breed "robot friendly" crops or no doubt "cant we just print this shit?"
reply
tguvot
19 hours ago
[-]
reply
zzzeek
1 day ago
[-]
> In the agricultural sector, labor shortages are increasing the need for automated harvesting using robots.

This is about Japan, but like the US, Japan has a restrictive immigration policy and an aging, not-replaced population that's at the core of this issue. Japan has been toying with expanding immigration in the area of health care workers [1] recently, but like in the US, there really isn't a labor shortage issue if immigration policy is liberalized.

So this is like so many other things a complex and mediocre technological solution to what's actually a political issue.

[1] https://www.bpb.de/themen/migration-integration/regionalprof...

reply
standardUser
19 hours ago
[-]
I agree about immigration, but the world has a large amount of very fertile land in places with very high costs of living. Bringing in large numbers of new immigrants at ultra low pay will have big consequences in most high-cost countries. It's worked well in the US, but that's because of our (former) identity as a nation of immigrants and the massive overlap between US and Latin American culture. In other nations, the outcome could very well be a racially/culturally incompatible underclass working the lowest paying and least consistent jobs, with little-to-no chance of fully integrating.
reply
tracker1
19 minutes ago
[-]
Some of this is showing in a lot of places already. Cultural adoption as part of migration is important and you can only bring in so many migrants while maintaining anything resembling a national identity. Not to mention secondary effects of bringing a literal under-class of migrant workers into a society already facing the aftermath of heavy inflation combined with wage stagnation.
reply
graemep
6 hours ago
[-]
I can understand culturally incompatible, but what on earth is "racially incompatible"?

> working the lowest paying and least consistent jobs, with little-to-no chance of fully integrating.

It depends who the immigrants are. If your immigration laws favour highly skilled immigrants that is not going to happen.

In the UK people who live in ethnically mixed areas tend to integrate. In fact, I think most people integrate but the minority who do not are just more noticeable and used politically (not by just one side either).

reply
zzzeek
17 hours ago
[-]
but Japan is actually relaxing immigration rules due to the need for younger workers. I bet they can pay them pretty well for less than the R&D, maintenance, and loss of productivity of the robots costs
reply
tracker1
15 minutes ago
[-]
Long term.. not sure that I agree. The cost of creating robots is going to go down. It's already relatively cheap to produce most of the robot, it's more down to the software development itself at this point. Also, even if a robot costs 2x what you would pay a person in a year at half the speed of a person, that robot can work effectively 4x as many hours a week as a person can.

My bigger concern to me is a conglomerate like ConAgra for robot farming comes in and only leases access to these machines instead of being able to buy/maintain/adapt them on the farms themselves. Leading to one more point of pressure against smaller farms in favor of larger conglomerates squeezing every bit of value from the middle out.

reply