Yes, trying to lift large boxes with narrow sticks seems iffy.
It's a rather bulky machine for what it does.
Here's a commercially successful robot for the same job.[1][2] Universal Robots has some nice machinery. They've succeeded where Rod Brooks' Rethink Robotics failed. No cute display with facial expressions, but better mechanical engineering and short payback times. Also, UR's machines are safe around humans. The chopstick robot looks too dangerous to run outside a cage.
While AI for controlling robots in unstructured situations still isn't that great, the mechanical and electrical parts work much better. Motors and motor controllers are great and not too expensive. Sensors are widely available and pretty good. Compensation for flexing under load has made much progress, and robots no longer need to be as rigid as a milling machine. A decade or two ago, if you tried to do anything with robots, you spent most of your effort on those issues. (Been there, done that.) We're now past that.
Vision is far enough along that semi-structured jobs work pretty well. Pick up known object from bin, place in machine, get out of the way while machine does its thing, remove object from machine, put in output bin - that covers a lot of factory work. Especially with vision systems smart enough to notice that something is gone wrong, stop, and call for help.
Even better (or worse): trying to lift heavy boxes with narrow sticks by holding the box from the sides - no idea what force has to be exerted by the robot to keep the box from slipping...
The problem even not in creating sufficient force but that a heavy cardboard box will be broken if you will try to hold it by sides (instead of supporting bottom of the box)
Key point here: there's a cube/square scaling law problem. Mass and weight go up with the cube of the linear dimensions. Contact friction forces only go up with the contact area, which goes up as the square of the linear dimensions.
> no idea what force has to be exerted by the robot to keep the box from slipping...
I would assume that if it's anything like real chopsticks then the answer would be relatively little.
If you use chopsticks correctly, you can can use surprisingly little force to pick up realistically heavy objects. I believe the physics explanation of this ability is based around the concept of levers.
there are slick/slippery food pieces that can be extremely difficult to pick up with chopsticks. better/more stable chopstick skills (like this robot has) definitely help, but still a part of the problem is caused by the indirectly applied force on the two thin sticks. 3 or 4 chopsticks would be improvements.
hmm, just realized, I've been on a kick to learn to do things left-handed so if I lose by abilities with my right hand I'll be ready. Or just becuase it's annoying to asymmetrical. So, I just realized if I learn to use chopsticks with my left hand, I will have 4 chopsticks at my disposal. I will be a force at the dinner table with the ha cheung.
> there are slick/slippery food pieces that can be extremely difficult to pick up with chopsticks. better/more stable chopstick skills
As you say, slick/slippery being difficult comes down to chopstick skills.
The ultimate skills test is whether you can pick up something slick/slippery with Korean chopsticks.
Why Korean? Korean chopsticks are both thin and generally manufactured in polished stainless steel. Which makes them a greater dexterity challenge than the Chinese or Japanese formats.
I have seen a few life long chopsticks Chinese users make a mess of themselves eating food with chopsticks.
I now assume that at some point you're going to lose your food with them and more regularly than a fork
westerner here, i once read a story (that could very well be apocryphal, but the moral is true nonetheless) that the ancient east asians had invented metal spoons and such, but with ancient metallurgy the metals would impart a taste in your mouth. So, chopsticks were invented to allow the food to be placed in the mouth without any "foreign object" contact. That tremendously increased my enjoyment of eating with chopsticks, and made me not care about the inconvenience.
I have a speaks-chinese assistant, and when we have asian lunches I always use use chopsticks and she uses spoons, and also thinks I'm crazy. By coincidence I just told her this story last week (because I didn't want her to think I'm an effete weebo or something) and afterward she mockingly bowed to me and said "thank you round eye for teaching me the old ways"
Food has texture and a bottom to leverage, so unless the robots are also able to scoot under and object to lift it, using only the sides can require enough force to crush some boxes,
Why not use flat paddles instead? For better friction hold and less crushing. Also single arm/paddle support like an open hand for light boxes? Closest I could find: https://m.youtube.com/watch?v=-DQ9c1cFmNg
In the second video of the article the first box picked is crushed by the chopsticks.
“In the second video of the article the first box picked is crushed by the chopsticks.”
Addressed a bit farther into the article, which I was thankful for because I had the same initial reaction:
“ You may have noticed that the boxes in the videos are pretty beat up. That’s because the robot has been practicing with those boxes for months, but Dextrous is mindful of the fact that care is necessary, says Drumwright. ‘One of the things that we were worried about from the very beginning was, how do we do this in a gentle way? But our newest version of the robot has the sensitivity to be very gentle with the boxes.’”
I'm still looking for a good existing example of horizontal paddles with rotating wrist that competes with the chopstick idea. Most examples are restricted to known geometry, but I still think the chopsticks would be beaten by a pair of paddles every time (presuming similar control software).
Here's another palletizing arm and grippers combo:
I mean - imagine tying those chopsticks to your forearms and trying to manipulate boxes - it would be hard enough for a human. Much easier if tied two rubberised rackets to forearms?!
I wonder if this might be more useful if it were to use the 'chopsticks' to pull the boxes onto a centrally mounted tray that slides back so that the boxes can then be pushed off the other side - thereby keeping boxes upright.
I was thinking something similar. Have a conveyor below the gantries that you can drop boxes onto/into, and that conveyor moves the box to the desired location behind the picker.
This doesn't really work when there is no conveyor to drop boxes onto, though.
Yeah, I was surprised that it was flipping all of them. Certainly that gives you more reach for cheaper, but it feels like a moving conveyor that it just backs onto might pay for itself in better speed and versatility...
But eh. Selling both is probably an obvious choice.
Fantastic! So long as you are moving empty boxes and don't care about stabbing people to death every 42.7 days. I am sure OSHA will love it.
What really bothers me is the million dollar grant they got. Complete and utter waste of taxpayer money. Unbelievable. Most of us have to make real products to earn that kind of money.
Garbage trucks have long been a marvel to me. I used to wince every time I heard the dumpster outside my office get emptied. Every single time the operator would lift and tilt the dumpster, then smash it at least six times to make sure everything shook out. The dumpsters and the trucks had to withstand this beating over and over. The truck especially amazed me. Hundreds of pounds hanging on a cantilevered arm smashing down repeatedly--then moving onto the next dumpster!
You just have to take whatever crazy spec you were given for the mechanical parts and then multiply that by 100 to engineer anything that could survive a single day.
we use to have those but now there are underground containers. My card can open the one in my street and 2 around the corner. If one is full sooner than planned there is a phone number and they usually come pull it out of the ground in an hour, sometimes after 2 days. Happens every 2 year or so. Wonderful system, no garbage around the house.
I think that automation is great, but we will definitely need some enlightened form of socialism to run along with it if we want a minimally decent society.
Yes, trying to lift large boxes with narrow sticks seems iffy. It's a rather bulky machine for what it does.
Here's a commercially successful robot for the same job.[1][2] Universal Robots has some nice machinery. They've succeeded where Rod Brooks' Rethink Robotics failed. No cute display with facial expressions, but better mechanical engineering and short payback times. Also, UR's machines are safe around humans. The chopstick robot looks too dangerous to run outside a cage.
While AI for controlling robots in unstructured situations still isn't that great, the mechanical and electrical parts work much better. Motors and motor controllers are great and not too expensive. Sensors are widely available and pretty good. Compensation for flexing under load has made much progress, and robots no longer need to be as rigid as a milling machine. A decade or two ago, if you tried to do anything with robots, you spent most of your effort on those issues. (Been there, done that.) We're now past that.
Vision is far enough along that semi-structured jobs work pretty well. Pick up known object from bin, place in machine, get out of the way while machine does its thing, remove object from machine, put in output bin - that covers a lot of factory work. Especially with vision systems smart enough to notice that something is gone wrong, stop, and call for help.
[1] https://www.youtube.com/watch?v=6QuPJnDUFi8
[2] https://www.universal-robots.com/
Even better (or worse): trying to lift heavy boxes with narrow sticks by holding the box from the sides - no idea what force has to be exerted by the robot to keep the box from slipping...
The problem even not in creating sufficient force but that a heavy cardboard box will be broken if you will try to hold it by sides (instead of supporting bottom of the box)
Key point here: there's a cube/square scaling law problem. Mass and weight go up with the cube of the linear dimensions. Contact friction forces only go up with the contact area, which goes up as the square of the linear dimensions.
> no idea what force has to be exerted by the robot to keep the box from slipping...
I would assume that if it's anything like real chopsticks then the answer would be relatively little.
If you use chopsticks correctly, you can can use surprisingly little force to pick up realistically heavy objects. I believe the physics explanation of this ability is based around the concept of levers.
there are slick/slippery food pieces that can be extremely difficult to pick up with chopsticks. better/more stable chopstick skills (like this robot has) definitely help, but still a part of the problem is caused by the indirectly applied force on the two thin sticks. 3 or 4 chopsticks would be improvements.
hmm, just realized, I've been on a kick to learn to do things left-handed so if I lose by abilities with my right hand I'll be ready. Or just becuase it's annoying to asymmetrical. So, I just realized if I learn to use chopsticks with my left hand, I will have 4 chopsticks at my disposal. I will be a force at the dinner table with the ha cheung.
> there are slick/slippery food pieces that can be extremely difficult to pick up with chopsticks. better/more stable chopstick skills
As you say, slick/slippery being difficult comes down to chopstick skills.
The ultimate skills test is whether you can pick up something slick/slippery with Korean chopsticks.
Why Korean? Korean chopsticks are both thin and generally manufactured in polished stainless steel. Which makes them a greater dexterity challenge than the Chinese or Japanese formats.
I have seen a few life long chopsticks Chinese users make a mess of themselves eating food with chopsticks. I now assume that at some point you're going to lose your food with them and more regularly than a fork
westerner here, i once read a story (that could very well be apocryphal, but the moral is true nonetheless) that the ancient east asians had invented metal spoons and such, but with ancient metallurgy the metals would impart a taste in your mouth. So, chopsticks were invented to allow the food to be placed in the mouth without any "foreign object" contact. That tremendously increased my enjoyment of eating with chopsticks, and made me not care about the inconvenience.
I have a speaks-chinese assistant, and when we have asian lunches I always use use chopsticks and she uses spoons, and also thinks I'm crazy. By coincidence I just told her this story last week (because I didn't want her to think I'm an effete weebo or something) and afterward she mockingly bowed to me and said "thank you round eye for teaching me the old ways"
Food has texture and a bottom to leverage, so unless the robots are also able to scoot under and object to lift it, using only the sides can require enough force to crush some boxes,
Looks nice and it's impressive, but 1700 boxes in one day seems far less efficient though?
That's the price of working in the same envelope as humans. Can't build up too much kinetic energy.
Why not use flat paddles instead? For better friction hold and less crushing. Also single arm/paddle support like an open hand for light boxes? Closest I could find: https://m.youtube.com/watch?v=-DQ9c1cFmNg
In the second video of the article the first box picked is crushed by the chopsticks.
“In the second video of the article the first box picked is crushed by the chopsticks.”
Addressed a bit farther into the article, which I was thankful for because I had the same initial reaction:
“ You may have noticed that the boxes in the videos are pretty beat up. That’s because the robot has been practicing with those boxes for months, but Dextrous is mindful of the fact that care is necessary, says Drumwright. ‘One of the things that we were worried about from the very beginning was, how do we do this in a gentle way? But our newest version of the robot has the sensitivity to be very gentle with the boxes.’”
i was more confused by the tiny box not fitting on the conveyor. Lots of smart choices to choose from besides from cutting the recording???
Better example of paddles:
https://youtu.be/XPfWvqlEJ48?t=0m48s
https://www.universal-robots.com/plus/products/onrobot/2fgp2... The same paddle head can connect to multiple different arms and has suckers for sheets too.
I'm still looking for a good existing example of horizontal paddles with rotating wrist that competes with the chopstick idea. Most examples are restricted to known geometry, but I still think the chopsticks would be beaten by a pair of paddles every time (presuming similar control software).
Here's another palletizing arm and grippers combo:
https://youtu.be/goivYfJ9DE8
I mean - imagine tying those chopsticks to your forearms and trying to manipulate boxes - it would be hard enough for a human. Much easier if tied two rubberised rackets to forearms?!
Ah, "Chopstick robot handle(s) boxes with ease."
That was hard to parse. I was wondering how a "robot handle" would box with ease.
I definitely wouldn't want to box with a chopstick-fisted robot; that's like coming with bare hands to a sabre fight.
I wonder if this might be more useful if it were to use the 'chopsticks' to pull the boxes onto a centrally mounted tray that slides back so that the boxes can then be pushed off the other side - thereby keeping boxes upright.
I was thinking something similar. Have a conveyor below the gantries that you can drop boxes onto/into, and that conveyor moves the box to the desired location behind the picker.
This doesn't really work when there is no conveyor to drop boxes onto, though.
Great until it encounters the fabled "This Side Up" box.
Yeah, I was surprised that it was flipping all of them. Certainly that gives you more reach for cheaper, but it feels like a moving conveyor that it just backs onto might pay for itself in better speed and versatility...
But eh. Selling both is probably an obvious choice.
It's not like your UPS/FedEx/Amazon driver cares either though
Came here to say this. I found it a bit jarring to look at actually...
Looks like a high school science fair project (with a budget)…
I like this shankbot aka Mr. Stabby.
With complete disregard on right side up of packages.
waiting for the ai to figure out it can just stab and move, lol
"We prompted the AI to 'Take care of the customers', but didn't realize it had been trained on Twilight Zone re-runs."
Fantastic! So long as you are moving empty boxes and don't care about stabbing people to death every 42.7 days. I am sure OSHA will love it.
What really bothers me is the million dollar grant they got. Complete and utter waste of taxpayer money. Unbelievable. Most of us have to make real products to earn that kind of money.
I can see smaller versions of these mounted on the side or back of garbage trucks someday.
Garbage trucks have long been a marvel to me. I used to wince every time I heard the dumpster outside my office get emptied. Every single time the operator would lift and tilt the dumpster, then smash it at least six times to make sure everything shook out. The dumpsters and the trucks had to withstand this beating over and over. The truck especially amazed me. Hundreds of pounds hanging on a cantilevered arm smashing down repeatedly--then moving onto the next dumpster!
You just have to take whatever crazy spec you were given for the mechanical parts and then multiply that by 100 to engineer anything that could survive a single day.
Hydraulics are extraordinary.
Our local trash service already has pneumatic arms that grab and dump the trash cans. [0] is one of many offerings.
[0] https://www.heil.com/bodies/liberty-automated-sideload-garba...
we use to have those but now there are underground containers. My card can open the one in my street and 2 around the corner. If one is full sooner than planned there is a phone number and they usually come pull it out of the ground in an hour, sometimes after 2 days. Happens every 2 year or so. Wonderful system, no garbage around the house.
Pretty cool as long as you're okay with your boxes being flipped upside down.
I think any of the standard services will place your boxes in whatever orientation they want.
a couple of minimum wage teenagers could do it faster, better, cheaper, and safer.
Interesting, would adding a 3rd stick actual make this more viable?
As long as you don't call it a claw/gripper. /s
I think that automation is great, but we will definitely need some enlightened form of socialism to run along with it if we want a minimally decent society.