Given where ML and CV are today, I'd bet on open source models trained on weeds within 3-5 years. This company can scale, but their unit price is going to plummet. Also, it sounds like they're using cameras, where it's concievable that other future sensors could be more efficient. An iteration of this with higher resolution cameras and small flying drones seems like an intuitive next step. This is a super interesting…
Drones do not seem like a logical step for me. I'm not a laser expert, but seems like the energy storage needed to kill hundreds to thousands of something with light is heavier than flying would realistically allow. Wheels and tracks are what farming is built around, no need to literally reinvent the wheel here.
Farming robot kills 100k weeds per hour with lasers
101–110 of 483 posts
Re: Farming robot kills 100k weeds per hour with lasers
#102There is a reckoning coming when agricultural robots will overtake manual labor. This is going to lead to a giant calamity of agricultural workers, specifically migrant workers, who are suddenly going to be without a job. I love the robots, I think it’s great, but we should be prepared for a human concern that WILL come.
Farming is already heavily industrialized and automated and uses a fraction of the labor it did a century ago. This is more a matter of using non toxic ways of dealing with weeds.
Re: Farming robot kills 100k weeds per hour with lasers
#103Earlier quoted context omitted.
Done: https://news.ycombinator.com/item?id=26376376
MS & Intellectual Ventures (2010) https://www.ted.com/talks/nathan_myhrvold_could_this_laser_z... Satisfying slowmo killshots near end :)
Re: Farming robot kills 100k weeds per hour with lasers
#104Re: Farming robot kills 100k weeds per hour with lasers
#105I have a feeling that the creators might be wrongly assuming that we could evolve plants to thrive in extreme monocultures (no other plant or animal life). I suspect these efforts will be met with diminishing returns of a) seeing lower yields because plants don't need to compete for resources b) really hard to go beyond 99% of desired plant because of energy consumption c) weeds adapting to fool the AI and resemble d…
How is this different from people pulling the weeds? They could have evolved to fool us already. I don’t see a huge difference since image recognition is something computers can do on par with humans.
No way. Computer image recognition is nowhere close to human recognition in real-world contexts. Still full of errors and bugs.
Re: Farming robot kills 100k weeds per hour with lasers
#106Re: Farming robot kills 100k weeds per hour with lasers
#107Earlier quoted context omitted.
Commodity drown with high powered laser for killing things based on image recognition sounds like sci-fi dystopia.
Yeah, I imagine massive overuse on "pest" species. Mosquito eradication will be a high priority for such technology, but there will be people who modify it to eradicate everything that flies or crawls. Everything smaller than a cat, if they could. I think lasers for killing large animals (including us) will be prohibitively expensive for a long time to come, fingers crossed.
Re: Farming robot kills 100k weeds per hour with lasers
#108"It's harder to find people to do that work every single year" Translation: The wages we pay are crap and we're not going to pay them more.
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.
Re: Farming robot kills 100k weeds per hour with lasers
#109"It's harder to find people to do that work every single year" Translation: The wages we pay are crap and we're not going to pay them more.
Raise the wages -> food prices rise. Rinse and repeat.