Boston Dynamics' Stretch Can Move 800 Heavy Boxes Per Hour (ieee.org) 91
Stretch is a new robot from Boston Dynamics that can move approximately 800 heavy boxes per hour. As IEEE Spectrum reports, it's part of "a new generation of robots with the intelligence and flexibility to handle the kind of variation that people take in stride." From the report: Stretch's design is somewhat of a departure from the humanoid and quadrupedal robots that Boston Dynamics is best known for, such as Atlas and Spot. With its single massive arm, a gripper packed with sensors and an array of suction cups, and an omnidirectional mobile base, Stretch can transfer boxes that weigh as much as 50 pounds (23 kilograms) from the back of a truck to a conveyor belt at a rate of 800 boxes per hour. An experienced human worker can move boxes at a similar rate, but not all day long, whereas Stretch can go for 16 hours before recharging. And this kind of work is punishing on the human body, especially when heavy boxes have to be moved from near a trailer's ceiling or floor.
"Truck unloading is one of the hardest jobs in a warehouse, and that's one of the reasons we're starting there with Stretch," says Kevin Blankespoor, senior vice president of warehouse robotics at Boston Dynamics. Blankespoor explains that Stretch isn't meant to replace people entirely; the idea is that multiple Stretch robots could make a human worker an order of magnitude more efficient. "Typically, you'll have two people unloading each truck. Where we want to get with Stretch is to have one person unloading four or five trucks at the same time, using Stretches as tools." All Stretch needs is to be shown the back of a trailer packed with boxes, and it'll autonomously go to work, placing each box on a conveyor belt one by one until the trailer is empty. People are still there to make sure that everything goes smoothly, and they can step in if Stretch runs into something that it can't handle, but their full-time job becomes robot supervision instead of lifting heavy boxes all day.
Stretch is optimized for moving boxes, a task that's required throughout a warehouse. Boston Dynamics hopes that over the longer term the robot will be flexible enough to put its box-moving expertise to use wherever it's needed. In addition to unloading trucks, Stretch has the potential to unload boxes from pallets, put boxes on shelves, build orders out of multiple boxes from different places in a warehouse, and ultimately load boxes onto trucks, a much more difficult problem than unloading due to the planning and precision required. [...] Boston Dynamics spent much of 2021 turning Stretch from a prototype, built largely from pieces designed for Atlas and Spot, into a production-ready system that will begin shipping to a select group of customers in 2022, with broader sales expected in 2023. For Blankespoor, that milestone will represent just the beginning. He feels that such robots are poised to have an enormous impact on the logistics industry.
"Truck unloading is one of the hardest jobs in a warehouse, and that's one of the reasons we're starting there with Stretch," says Kevin Blankespoor, senior vice president of warehouse robotics at Boston Dynamics. Blankespoor explains that Stretch isn't meant to replace people entirely; the idea is that multiple Stretch robots could make a human worker an order of magnitude more efficient. "Typically, you'll have two people unloading each truck. Where we want to get with Stretch is to have one person unloading four or five trucks at the same time, using Stretches as tools." All Stretch needs is to be shown the back of a trailer packed with boxes, and it'll autonomously go to work, placing each box on a conveyor belt one by one until the trailer is empty. People are still there to make sure that everything goes smoothly, and they can step in if Stretch runs into something that it can't handle, but their full-time job becomes robot supervision instead of lifting heavy boxes all day.
Stretch is optimized for moving boxes, a task that's required throughout a warehouse. Boston Dynamics hopes that over the longer term the robot will be flexible enough to put its box-moving expertise to use wherever it's needed. In addition to unloading trucks, Stretch has the potential to unload boxes from pallets, put boxes on shelves, build orders out of multiple boxes from different places in a warehouse, and ultimately load boxes onto trucks, a much more difficult problem than unloading due to the planning and precision required. [...] Boston Dynamics spent much of 2021 turning Stretch from a prototype, built largely from pieces designed for Atlas and Spot, into a production-ready system that will begin shipping to a select group of customers in 2022, with broader sales expected in 2023. For Blankespoor, that milestone will represent just the beginning. He feels that such robots are poised to have an enormous impact on the logistics industry.
Re: (Score:2)
Re: (Score:2)
I think the time constraints on this situation will basically prevent it from being interesting. The trucks impose a schedule and so you will basically have fixed lot sizes. Knapsack problems become interesting when you get to optimize for the number of knapsacks, but that's unlikely to apply here. Main complication I would predict is that last-mile deliveries will be dominated by packing the packages in reverse-delivery order. Last packages to be delivered must go into the truck first. (However, this could
Re: (Score:2)
[Anybody smell a brain fart?]
The knapsack problem and the traveling salesman problem were two of the biggies at the research lab. However, given the small size of the problem in this case, I'm pretty sure it isn't an interesting application. At least not for the mathematicians amongst us.
However, I think it's a good thing to give to robots. Having done the work briefly a few times, I don't envy any human being who's doing it.
No, the knapsack problem is on topic.
Do not trust the top of a box (Score:5, Insightful)
Re: Do not trust the top of a box (Score:1)
Better candidate for FP, possibly coming from someone who's actually done the work. But you have to tip the box carefully to get underneath it, and I'm having a bit of trouble understanding how to apply that with only one arm. Now if the robot had a bunch of tentacles...
Cue the Japanese pron.
Re:Do not trust the top of a box (Score:5, Interesting)
What straps? This thing relies on suction to pick up the box. I've received a half-dozen boxes - just at my house, within the last month - where the box had enough damage (even just creases/folds) that a suction cup would likely be worthless.
So basically this takes "the worst job in the warehouse", has the robot deal with the easy boxes, and human workers will have to deal with the problematic ones - all while working around the robots and with fewer humans available. Quite a step forward there for warehouse workers.
human workers working around the robots? (Score:2)
800 heavy boxes an hour is one every 4.5 seconds.
I wouldn't want to be in the way.
Re: (Score:2)
Re: human workers working around the robots? (Score:2)
Re: (Score:2)
Stretch is a boring robot for Boston Dynamics (Score:2)
Looks like something any robot company could build.
What happened to the two wheeled emu thing. Let alone dancing Atlas. We expect amazing (and probably useless) things from Boston Dynamics!
How about something with several arms that can pick up boxes properly without relying on suction? Or stack a few small ones up and move them like a human would? Or work with different size boxes?
Boring.
Also, if you want to unstack a truck quickly, put the boxes on pallets and use a fork lift.
Re: (Score:2)
Also, if you want to unstack a truck quickly, put the boxes on pallets and use a fork lift.
E-fucking-xactly.
Re: (Score:2)
Re: (Score:2)
Just put every cardboard box in a reusable, standard-sized plastic shipping bin
That is more work than just manually unloading the truck.
Re: (Score:2)
Re:Do not trust the top of a box (Score:5, Interesting)
Boxes shipped to distribution centers from vendors are likely far more uniform and less abused than those that have gone through the UPS, USPS, Amazon, DHL etc. crushing process.
The picture in the article* shows a truck with fairly large "identical" boxes - rather like what may show up from a manufacturer to another manufacturer or distribution site. Perhaps that is the market, at least initially, for this.
___
* I didn't read the article as I didn't want to have to turn in my /. card, but as far as I know there's no prohibition on looking at the pictures. This is rather the inverse of decades ago when people claimed to get Playboy to "read the articles".
Re: (Score:2)
If there are many identical boxes, they would normally be on a pallet.
So a forklift or worker with a pallet jack can move a dozen boxes at a time.
Re: (Score:2)
Re: (Score:1)
Does not look good for warehouse workers... (Score:2)
Sure, some will keep their job, supervising 10 robots. But the rest will find themselves unemployed. What was that again bout "technology always creates more jobs than it destroys"?
Re: (Score:2)
Re: (Score:2)
Because something has happened in the past, the future will just be more of the same
Yes, it will, unless there is some reason to believe that "This time is different."
But there is nothing different here. This robot is just another step in the automation and productivity that is the reason for our prosperity. If you want to see the alternative to an automated society, go live in Somalia.
Re: (Score:2)
I would suggest you look up Somaliland and ask yourself why is the UN so hesitant in recognizing them as a country, they have been able to get themselves halfway out of the whole that Somalia was and if recognized could start getting investments in a better future.
Re: (Score:2)
Imagine, for a second, that the low wage people with no skills who currently take boxes out of a truck and place them somewhere else don't have the knowledge, skills or ability to a) "MAKE these robots", b) don't live anywhere near the robots are made, and c) are unable to afford to move themselves and their families to where the robots are made - just to find out that they don't have the skills needed to work in a robot manufacturing factory.
Just because there are 'more jobs' doesn't mean that those jobs a
Re: (Score:3)
Yet wages are rising fastest for unskilled entry-level workers.
Reality is the exact opposite of your scenario.
Re: (Score:2)
Your statement does not appear to address the relocation issue. Would you care to expand on it?
Re: (Score:2)
Your statement does not appear to address the relocation issue. Would you care to expand on it?
First provide some evidence that "relocation" is an actual issue other than in coal mining towns.
Re: (Score:2)
Is the fact that it's an issue in coal mining towns not sufficient reason to address it?
Re: (Score:2)
Coal mining jobs aren't disappearing because of robots.
Re: (Score:1)
Coal mining jobs aren't disappearing because of robots.
Indeed. Coal mining jobs are disappearing BECAUSE of the same liberal cunts who lament the jobs disappearing.
Re: (Score:2)
Coal mining jobs are disappearing BECAUSE of the same liberal ...
Coal mining jobs are disappearing because of economics. Coal can't compete with either gas or wind.
Coal's demise was predicted decades ago. I have little sympathy for those who chose to stay and make their careers in coal mining.
Re: (Score:2)
"Coal can't compete with either gas or wind."
You forgot solar. Which isn't a big thing in West Virginia, so I've read, but it is a very big thing in Australia and quite a few other countries.
And yes, the sun doesn't shine at night so that's why batteries (of all sorts) are a thing now.
Re: (Score:1)
Coal mining jobs are disappearing because of economics. Coal can't compete with either gas or wind.
Coal's demise was predicted decades ago. I have little sympathy for those who chose to stay and make their careers in coal mining.
It can't compete because the liberal government is funneling huge amounts of money into gas and wind. You rig the game and then act like it's not rigged. Gas would probably do okay on its own. Wind, on the other hand, would collapse tomorrow if the subsidies went away. Wind is absolutely unreliable and those giant MOVING windmills require a metric ton of maintenance.
Re: Does not look good for warehouse workers... (Score:2)
No.. we who are in favor of automation actually have more empathy than you people who want humans doing repetitive back-breaking soul-less work. We are saying tax the robots, and provide that as universal basic income. A robot can do earn the salary for 10 humans, increase profits for investors and retirement plans, all while reducing the cost of the product it is producing.
Re: (Score:1)
No.. we who are in favor of automation actually have more empathy than you people who want humans doing repetitive back-breaking soul-less work. We are saying tax the robots, and provide that as universal basic income. A robot can do earn the salary for 10 humans, increase profits for investors and retirement plans, all while reducing the cost of the product it is producing.
Careful. You'll confuse them with logic. The racist liberals WANT there to be a Chinese woman hand-washing laundry for minimum wage. They're fine with her living a life of drudgery. Hey she's got a job... Who cares if it's mind-numbing..
Re: (Score:2)
Uh, it seems my comment is being misunderstood.
Perhaps I shouldn't post after sipping so much bourbon?
I'm not a writer, so I just type a bit of stream of consciousness stuff that makes sense to me. Then hit preview and after checking for the obvious spelling errors, submit it.
Basically, I agree with you that those workers whose jobs are replaced by automation should be looked after.
But who should look after them?
The point I was trying to make is that claims that "jobs destroyed are replaced by better jobs"
Re: Does not look good for warehouse workers... (Score:2)
Hmm ok. I skimmed over what you wrote and it seems acceptable for a bourbon infused rant. I will have a couple myself and re-read it.
Re: (Score:2)
Also, the economics do not pan out at all. Need to replace 1000 people with robots? Sure, 100 to supervise the robots, 10 to make and program them. Oops, 890 people out of a job. And in the end most of those 100 jobs supervising robots will go away as well.
Re: (Score:1)
Imagine, for a second, that the low wage people with no skills who currently take boxes out of a truck and place them somewhere else don't have the knowledge, skills or ability to a) "MAKE these robots", b) don't live anywhere near the robots are made, and c) are unable to afford to move themselves and their families to where the robots are made - just to find out that they don't have the skills needed to work in a robot manufacturing factory.
Just because there are 'more jobs' doesn't mean that those jobs are located anywhere near the newly unemployed live or can commute to.
The empathy vacuum in that comment is outstanding... :(
Translation: Keep old dead jobs around and halt all innovation because some fuckers are too stupid or lazy to learn a new skill. Fuck you and everyone like you.
You're a lazy, sniggling, cunt. You want to keep these jobs? Then build a fucking warehouse and employ these people.
Didn't see you trying to save the jobs of all those mall-workers when the malls started disappearing.
You liberal cunts are all the same. You demand EVERYONE ELSE does something.
Jobs go away when something better comes along.
Re: (Score:2)
Wow, harsh much, random angry person?
Malls are not disappearing in my country.
Maybe your country has some deeper issues that you might want to investigate?
And "Keep old dead jobs around and halt all innovation" is a big stretch from what I typed. I'm asking people/employers to consider what happens to those workers who are suddenly out of a job, and you decide that this means I want blacksmiths, milkmen and photocopier repairers to continue to be supported?
I have to give you credit for the appropriate use o
Re: (Score:2)
Sure, some will keep their job, supervising 10 robots. But the rest will find themselves unemployed. What was that again bout "technology always creates more jobs than it destroys"?
Oh look, another mouth-breather. More jobs now than at any other time in the history of the world and no blacksmiths or buggy makers to be seen anywhere. How many times do you idiots have to be proven wrong before you shut the fuck up? Somebody has to MAKE these robots. That's going to be an entire damn industry. You people are pathetic.
Well, it is clear you are deeply afraid of this and hence attack anybody that points out the facts. You probably do not understand that dumb aggression does not make facts go away.
Re: (Score:1)
Well, it is clear you are deeply afraid of this and hence attack anybody that points out the facts. You probably do not understand that dumb aggression does not make facts go away.
What facts? The ones I just gave your stupid ass about there being more jobs now than at any point in history (larger world population)? Those facts? Jobs go away. The fearful ones are the idiots like you who lament the passing of the blacksmith, whip maker, buggy builder, and slave auctioneer. All dead and gone jobs.
Afraid? Ha. Not even close. I actually upgrade my education constantly. 20 years ago it was avionics, today it's fixed wireless, tomorrow it'll be fingering your Mom.
Your retorts suck
A thought-experiment for Luddites (Score:5, Insightful)
Suppose, some genius discovers a drug — or a medical procedure — that eliminates all illness... It is reasonably easy to produce and costs, say, only $1000 per person.
Would you really object to its wide roll-out on account of all the doctors, nurses, and pharmacists losing their jobs?
Re: (Score:2)
Nope.
Illness is only one reason people end up in hospital.
Injuries are another rather big reason people arrive in ambulances.
Re: (Score:1)
Nope.
Illness is only one reason people end up in hospital.
Injuries are another rather big reason people arrive in ambulances.
I think you're missing the point here
Re: (Score:2)
As I was drunk when I responded, it's very likely indeed, yes.
But, my basic answer remains the same, I'd not object to a great benefit being granted to the entirety of humanity, not at all. Even if it means the medical profession are out of work.
Though I fear some nations may not benefit quite as swiftly as some others, sadly. Then again, if it's $1,000, various charitable foundations would obviously leap at the chance to provide it to the less wealthy nations, I'm, cough, sure.
Re: Does not look good for warehouse workers... (Score:5, Insightful)
Seriously? Your evidence that technology will not create more jobs than it destroys is a micro-example? That is like saying replacing horse carriages will result in job losses for inn keepers because people will require less stops en route to destinations. It is a narrow minded tunnel vision way of thinking. Yeah that particular job may be lost, but there might be a different job such as marketing, budget mansion building, or product design that opens up. Not to mention the price of the items will drop due to robot efficiency and ensuing competition because of reduce labor shortage.
Anyway, even if what you are saying were true it can be solved with taxation and Universal Basic Income. What is the point of a human breaking their back doing that task? It is better he spends time with family or reviews Netflix, or tries to gets educated in some talent.
Re: (Score:2)
Seriously? Your evidence that technology will not create more jobs than it destroys is a micro-example?
Obviously not. Are you stupid? Because expecting a whole trail of evidence in a /. posting would be stupid.
Really dislike the intended application (Score:3)
There are a number of things that really seem odd about this approach to a solution. For starters you have the whole “two-hand carry” rules when lifting heavier packages, done not just to protect workers’ backs, but also to ensure a stable and balanced grip and limit damage. Then you get into the whole conveyor thing; it would seem like a setup that tugs packages onto a conveyor would be so much easier to scale for the specific application.
I’m sure it is a cool project and all, but it hardly seems like it is hitting the right groove.
Re: Oh boy.. 50 lbs. (Score:2)
How many 50 lb reps can they do?
Re: (Score:1)
How many 50 lb reps can they do?
Does it matter? Why the hell would the limit be 50 lbs? Why not 200 pounds? I mean... wtf?
Unloading trucks sucks (Score:5, Informative)
As someone who has unloaded trucks for Target during over night stocking, I can say I would have loved one of these. It's never a certainty that the people who loaded the truck properly loaded it from bottom to top, heavy to light. So there was always the possibility something was going to fuck up your night and the rest of your shift. Less worker injuries is also awesome. They don't get the best and brightest to unload these trucks, so poor lifting habits got to people over time. Good stuff.
the top (Score:2)
Re: (Score:2)
A better way would be to have a second arm that has a plate/shelf for the box to slide onto. Then the first arm just slides the box on to the shelf. Can suction the side or top
Re: (Score:2)
Better for this application for sure but better as a general solution maybe not.
But, for this application something much more like a continuous mining machine would be much more interesting. Light weight arms pulling boxes onto a conveyor seems to make much more sense, as they should be able to operate at a rate closer to 3,000 boxes per hour with dramatically less complexity.
Re: (Score:2)
In the videos it grabs the top boxes from the side, pulls and then tilts them down.
Really? (Score:2)
"An experienced human worker can move boxes at a similar rate, but not all day long, whereas Stretch can go for 16 hours before recharging. "
Perhaps somebody should teach the robot to move a box of full batteries into himself.
Re: (Score:1)