Japanese Robot Picks Only the Ripest Strawberries 202
kkleiner writes "The Institute of Agricultural Machinery at Japan's National Agriculture and Food Research Organization, along with SI Seiko, has developed a robot that can select and harvest strawberries based on their color. Ripened berries are detected using the robot's stereoscopic cameras, and analyzed to measure how red they appear. When the fruit is ready to come off the vine, the robot quickly locates it in 3D space and cuts it free. From observation to collection, the harvesting process takes about 9 seconds per berry. Creators estimate that it will be able to cut down harvesting time by 40%."
Reducing illegal immigration? (Score:5, Interesting)
Get the price of such robots down enough and there'll be little incentive to pay sub-par wages to migrant field workers. (Regardless of immigration status, but illegals are more exploitable.)
Conversely it could be because we've long had a source of cheap field labor that the US agricultural machinery business hasn't made such advances in robotics. Pity, really -- many of the issues a robotic strawberry picker has to deal with are common to the activity of a whole range of other robots. Build a general purpose agricultural field worker robot and have alternate software loads (and perhaps interchangeable picker mechanisms) for blueberries, tomatoes, whatever.
(Such picker robots, with appropriate sensors, could also be adapted to tasks like minefield clearing. Although that might lead to a scenario like that in the TV adaptation of Heinlein's "Jerry Was a Man".)
Re:Lot of track? (Score:4, Interesting)
Locomotion and selection are two distinct problems. Presumably the selection/picking components could be added to a suitable chassis designed for navigation real fields (which could support a host of other picking and crop-tending apps).
If not, then they still don't need a track for each row, just a track that can be moved from one row to another. Perhaps make the fields circular with a radial track, like some irrigation systems.
No Thank You (Score:4, Interesting)
Seriously.
Re:Goodbye Mexicans! (Score:4, Interesting)
While "Goodbye Mexicans" is a bit flamey, automating the jobs locals will never willingly do has always been a logical goal.
When we reduce manual labor, remove some jobs that draw poor people to the US, increase profits and make our farms more competitive we win.
We don't scrap massive combine harvesters in favor of horse-drawn equipment because they enormously increase productivity. Harvesting is dull, dirty, and sometime dangerous, ideal for robots.
Re:Reducing illegal immigration? (Score:5, Interesting)
Picking grapes by machine would be very interesting. If you drive around the south of France, you see fields of grapes for miles, all of which need to be harvested by hand to make wine. There's often quite a short period between the grapes being read to harvest and being overripe for wine making, and harvesting them at exactly the right point can make a big difference to the quality of the final product. If you could make robots that would travel up and down the fields quickly, revisiting each vine each day over a week or so and picking the grapes at exactly the right time (rather than, as humans do, when the majority are at the right level of ripeness), then I can imagine that you'd have some customers who would be very happy to pay a premium for the machine.
I doubt the situation is the same for strawberries. They aren't exactly luxury goods and so cost is the most important factor.