[HN Gopher] Boston Dynamics robot Atlas goes hands on [video]
___________________________________________________________________
Boston Dynamics robot Atlas goes hands on [video]
Author : PotatoNinja
Score : 98 points
Date : 2024-10-30 14:46 UTC (3 days ago)
(HTM) web link (www.youtube.com)
(TXT) w3m dump (www.youtube.com)
| billconan wrote:
| do they really have this kind of jobs of moving parts from one
| shelf to another in a real factory?
|
| I think a more impressive demo would be last-mile package
| delivery, since it can climb stairs and operate elevators.
| enragedcacti wrote:
| Yes they definitely do, see very similar numbered organizers in
| the background of this video [1]. In auto mfg they need to
| reliably build dozens of configurations on one line while
| maintaining impeccable part tracking for auditing and triage
| purposes. Each shelf on the left could be a different version
| of the engine cover for a different trim and the shelf on the
| right will be brought to a station where workers will pick from
| it based on the number the computer tells them for the exact
| vehicle in front of them.
|
| This helps make sure the customer gets what they purchased and
| helps for QC and recalls. If one batch is bad then this system
| allows them to pinpoint down to the exact VINs that were
| affected.
|
| [1] https://www.youtube.com/watch?v=T8Jlod53BCU&t=60s
| Ancalagon wrote:
| Cool but this is kind of uncanny
| anshumankmr wrote:
| Awesome and terrifying
| krunck wrote:
| While humanoid robots are neat, if not uncanny, I would love to
| see robots with forms optimized for their work. A large octopus
| with legs would be ideal for this sort of parts handling job.
| slau wrote:
| I think the exact point they're trying to make is that a
| humanoid robot can pick up one shift exactly where a human left
| off. No custom robotics, no workplace changes, etc.
|
| This is _huge_ for the industry. Smarter Every Day visited a
| frisbee factory and they had automated a bunch of things.
| However, every automation point was extremely protected (fenced
| off) so that a bumbling human couldn't walk somewhere and get a
| limb ripped off. If I remember correctly they joked that it was
| OSHA or something, which it turned out to be.
| ethbr1 wrote:
| This ^
|
| The effort required to change a process shouldn't be
| underestimated.
|
| Especially considered that industrial environments are
| already (a) automated for lowest-hanging fruit things (e.g.
| moving stuff around at human height) & (b) optimized around
| human capabilities for the remaining things. Substituting a
| not-humanlike robot would require reconfiguring a lot of
| existing automation around it.
|
| If you have "like a human, but costs less" that can be
| plugged into any existing still-human process? You can
| literally swap them in.
|
| Eventually we'll get to hyperoptimized machines, but an
| easier sales story to say "We automate your existing human
| processes."
| Dilettante_ wrote:
| Imagine you're working your 35-hour shift at the
| Fulfillment(tm) Center and all around you there's robotic
| eldritch horrors scurrying through the two-storey high shelves
| nwah1 wrote:
| Factory robots that move in general are kind of gimmicks,
| except for those roomba things for Amazon warehouses.
|
| An assembly line with robotic arms has been standard for a
| long time now. And having many such arms working at the same
| time is normal. And each robotic arm will be doing one
| extremely narrowly defined task.
|
| Anything involving autonomous judgment and mobility
| introduces uncertainty.
| Dilettante_ wrote:
| Neuralink-equipped wageslaves mind-projecting into robo-
| octopuses, traversing the storehouse-grid with the aid of
| their many-suckered appendages. Navigating via implicitly
| interfacing with the warehouse's AI overseer.
| Log_out_ wrote:
| sudo Ph'nglui mglw'nafh Cthulhu R'lyeh wgah'nagl fhtagn
| moffkalast wrote:
| Ah yes, man made horrors on the edge of my comprehension.
| sfjailbird wrote:
| The legs do seem like a huge overcomplication. I can't think of
| many situations where they would be worth the added
| cost/complexity (compared to simple wheels). Sure they can walk
| stairs, but a place that employs freaking robots could easily
| make it robot accessible too, it would seem.
| robswc wrote:
| Totally agree here... but I have no robotics experience to
| back it up.
|
| Seems at the very least it could have little quad wheel
| things so it doesn't have to worry about balance as much.
| rad_gruchalski wrote:
| Did you see previous Atlas videos where this things jumps,
| does backflips and runs up stairs? The whole point is to make
| it operate in spaces designed for humans.
| DonnyV wrote:
| Optimization isn't efficient on the grand scale of things.
| Think of these robots more as exchangeable worker units. Lets
| say the warehouse isn't accepting many packages that day. So
| you don't need as many robots at the loading dock. But we have
| a lot of product that needs to be inventoried or shelved. Send
| a couple over and have them start doing it right away.
|
| You actually end up running a warehouse with less robots
| because they can easily be repurposed for other duties.
| mempko wrote:
| Compare this to the human controlled puppets Tesla demonstrated.
| Tesla made a big show of something Disney could do years ago.
| While Boston Dynamics is quietly building the real thing and
| showing us footage of it actually working.
| letmevoteplease wrote:
| Tesla has footage of Optimus working autonomously. Not bad
| progress for something that has been under development for two
| years.
|
| https://x.com/Tesla_Optimus/status/1846797392521167223
| kvark wrote:
| You are comparing a live demo with many bots interacting with
| humans, versus a recording of a single bot in a factory by
| itself.
| nofunsir wrote:
| But, Space man bad!
| bottlepalm wrote:
| The difference is Disney doesn't have any factories. I'd bet
| good money Tesla has Optimus doing real work in their
| factories, at scale, long before anyone else.
| threeseed wrote:
| Boston Dynamics has been deploying Spot at scale for years
| now:
|
| https://bostondynamics.com/industry/manufacturing
|
| And it's one thing to have a cute demo showcased under ideal
| scenarios and another to have it deployed in mission critical
| environments around real people.
| fragmede wrote:
| A mobile camera that can open doors is quite useful, but
| that's not on the same level as robot auto worker that
| could stamp out parts on a press.
| threeseed wrote:
| This statement makes no sense.
|
| We have had robots stamping parts for years. There is no
| need for a humanoid style configuration. Meanwhile what
| is needed and far more complex are robots that can
| interact with unpredictable people in unpredictable
| environments.
|
| Boston Dynamics has already demonstrated they can do
| this.
| fragmede wrote:
| I'm not sure what part doesn't make sense. Can you
| clarify where you got confused?
|
| Machine presses still have human operators somewhere,
| even though theres machines and robot arms involved. eg
| the end of that figure one video.
|
| Sure, a dog sized object autonomously not running into
| objects, some of which can move is an achievement, but
| it's still just a remote control camera.
| worik wrote:
| > I'd bet good money Tesla has Optimus doing real work in
| their factories, at scale, long before anyone else.
|
| On what do you base that?
|
| Tesla is so far behind BD, who are behind the Chinese
|
| My money is on the Chinese
| meindnoch wrote:
| See, this is a real video. Compare it with the obvious cgi fake
| that was put out a few months ago by Figure:
| https://www.youtube.com/watch?v=Sq1QZB5baNw I still can't believe
| how noone has called them out on that one.
| owenpalmer wrote:
| How do you know the figure 1 demo was fake?
| wg0 wrote:
| Well, anything could be fake these days even the Boston
| Dynamic's video could be fake in this day and age but...
|
| I tend to believe both videos probably are not fake. With
| speech recognition, text to speech AGI and the advancements in
| machine learning as applied to robotics, it is not impossible
| for many or any committed enough group of engineers with
| financial means to make some notable progress on that front.
|
| So it is not just skills but money too.
| nofunsir wrote:
| I often call out the cgi "enhancements" that I notice on Boston
| Dynamics videos. This one doesn't seem to have any that I can
| tell. On others, however, when I point them out, I get
| borderline religious vitriol pushback.
|
| From what I've observed, (so preface the following with "It
| seems to me that:") BD obviously has a well-honed "playback"
| tool. They have the ability to command the robot to operate in
| a new environment, record its own movements to sub-millimeter
| accuracy, and record the environment (it has a live 3d point
| map after all.). Then, they load in the recorded
| environment+motion data, and play it back as a 3D scene.
| Naturally, this would be needed to analyze the performance and
| make software and hardware iterations. However, this data is
| likely also used to re-create a digital scene for the purposes
| of cgi enhancement of a performance that's intended to be
| recorded and released to Youtube. Similar to how Favreau uses a
| giant screen to approximate the lighting on the chroma-keyed
| subjects[1] as they perform, this data -- a giant shiny
| rectangle goes here, a window and a flashing blue light bulb
| there, these steps over here -- combined with accurate camera
| motion data, is then used to create a digital model with the
| exact shadows that one would need to create a more realistic
| "fake video" in the first place. The trick is that Boston
| Dynamics then takes the original take (or iterations of takes
| of it running the exact same sequence), and iterate a cgi-
| enhanced version of their "cool dance video" that the marketing
| team then signs off on. "Ohh yeah, that's what our vision is.
| We don't want them to see shaky appendages, or micro-stutters.
| Add in some extra scuff marks, too! Perfect. Upload it."
|
| [1] https://illumin.usc.edu/the-volume-how-the-mandalorian-
| revol....
| threeseed wrote:
| > I get borderline religious vitriol pushback
|
| I can see that. Because you're posting incoherent scenarios
| with no evidence.
|
| Meanwhile we have Spot being deployed in Australian mines for
| surveillance where the environment is constantly changing.
| Not sure how they would accomplish this if everything they do
| is CGI.
| SirMaster wrote:
| But can it do a backflip?
| Miniminix wrote:
| Could it look less like the T800 from Terminator ?
| jamala1 wrote:
| Chinese Unitree's demos are better by now imo.
|
| https://www.youtube.com/watch?v=8dFTc4W8wm0
| hobofan wrote:
| What? The humanoid robot in the video is walking on the most
| even surface possible. Boston Dynamics has a more impressive
| walking video from 11 years ago (obviously restricted by the
| hardware at the time):
| https://www.youtube.com/watch?v=SD6Okylclb8
|
| Yes, human-looking gait is nice, but it isn't worth anything if
| it can't translate to real-world settings.
| modeless wrote:
| Unitree is catching up to Boston Dynamics in locomotion, but
| has not surpassed them yet I think. Unitree's real advantage is
| the much lower cost of their hardware and their ability to mass
| produce their robots.
|
| But IMO manipulation is harder than locomotion, both in
| hardware and software, and neither company is convincingly
| ahead there. I think the uncut laundry demo from Physical
| Intelligence a few days ago is better than anything shown by
| Unitree or BD for manipulation. https://www.physicalintelligenc
| e.company/blog/pi0#:~:text=Af....
| jemmyw wrote:
| I don't really want a robot wandering around doing laundry. I
| think what most people want is a box you dump clothes in and
| they come out folded, an extra machine next to the dryer.
| That would be a genuine time saver. I hate scaling Mount
| Foldmore.
| golol wrote:
| Well the robot is that machine....and much more.
| modeless wrote:
| I don't want more machines taking up space in my home. I
| don't want a bunch of special purpose "smart" devices with
| buggy software and dedicated apps requiring logins and
| firmware updates to plug security holes. I want one robot
| that can do it all. I'd get rid of my security system,
| cameras, smart thermostat, dishwasher, clothes washer,
| stand mixer, toaster, etc etc.
| 9dev wrote:
| The horror!
| emchammer wrote:
| LMAO Boston Dynamics used to have a guy randomly coming into
| the frame and giving the robot a kick and show it could
| recover, Unitree goes all-out kung fu on them.
| toxik wrote:
| Unitree products feel like oversized toys, not serious research
| platforms.
| noncoml wrote:
| How is its situational awareness? While walking with its elbow
| out carousing the item, would it avoid an object that would be
| out of its view by the time it was about to collide with its
| extended elbow?
| coldcode wrote:
| The video is impressive, but how does it learn? How long does it
| take before it can do something new? I realize this is still very
| much a research project, but I'd love to understand how it works.
| 101008 wrote:
| In which aspect is this better than a human?* It's slower,
| energy-wise more expensive (a human with just a sandwich can work
| for hours), less preciss and error-prone. As a Manager, I would
| prefer a person that I can blame (corporative and legally) if
| something goes wrong, that being responsible (legally, mainly!)
| if this robot makes a huge mistake.
|
| * From a business point of view. This is an incredible techinal
| achievement, I don't want to sound like this is not impressive.
| But it seems that every new development seems to focus on how
| they can replace humans or be better at or do things that we
| usually do.
| nuancebydefault wrote:
| From a business pov it's obviously better than a human because
| it does not need to feed its family.
| downboots wrote:
| Yet
| fragmede wrote:
| Selling one product and using the profits from that to
| create a second product is how businesses work. So if/when
| Tesla/anybody is selling their humanoid robot and those
| profits pay for going to feed the NVIDIA supercomputer that
| they're using to train models to run on robots, and to fund
| development of robot 2.0, that's exactly where we'll be.
| kyriakos wrote:
| the robot can work 24/7 7 days a week, and if you consider
| paying the human employee at the end of the month and not just
| providing a sandwich per shift then the energy costs are not
| that high.
| 101008 wrote:
| How much time the robot can work without recharging /
| maintenance? What's the throughput for the tasks? In the demo
| it only carried one object and it took it several seconds to
| move it. A person could do that faster, better, etc. It's
| real nice, but if you can convince a factory owner to replace
| people with this you are the best salesman in the world.
| fragmede wrote:
| I'm not a salesman but I imagine if you're trying to sell
| them to a factory owner, you'd play up the problems with
| the worst humans. Humans come in hungover, still drunk, or
| not at all. And don't call in. They complain about every.
| little. thing. "Why do I have to do it this way?" "I don't
| want to do it like that".
|
| They take long bathroom breaks (and think you don't notice,
| because they think you're stupid.) They steal. They fight
| with each other and need managing aka children's therapist
| for their bullshit. Which never stops. You can stop wasting
| your time dealing with the "human touch" and get back to
| what you really want - making more widgets so you can sell
| more widgets so you can make enough money for that kitchen
| remodel/winter/summer home/yacht/European vacation/jet.
|
| Fire them and replace them with RobotWorker. It doesn't get
| drunk and cause fights or HR incidents because it can't
| keep it in it's pants. They'll work all through the night
| and through every holiday, without the same trouble of
| having a second and third shift. You don't need to follow
| OSHA with these things, though you still don't want to
| damage them - there's a support contract but that's
| unnecessary downtime for you, and you don't want that.
| Still, you can just replace a robot's arm. Just imagine the
| lawsuits when that happens to a human employee.
|
| blahblahblah. I'm sure you can come up with more.
| quickthrowman wrote:
| One immediate use I can see for this robot is racking and
| energizing circuit breakers in electrical switchgear, which is
| one of the most dangerous things an electrician does. Arc flashes
| are very bad for humans, robots can be replaced easily.
|
| Racking 480V three-phase breakers: https://youtu.be/Rytjdqj_Img
| chollida1 wrote:
| Kind of shows just how far behind Telsa is with their "robot"
| wg0 wrote:
| Impressive. The machine learning application in these domains is
| the real game changer.
|
| PS: Isn't that the Lord of the Lithium, the Guardian of the
| Tunnels has the robot prototypes that not only serve drinks but
| do the small talk with full self driving AGI already?
| fakedang wrote:
| AGI - A Guy in India
| opless wrote:
| Or Indonesia
| karussell wrote:
| Is the noise coming from the robot? I thought they retired the
| hydraulics version?
| the__alchemist wrote:
| I think whenever I see humanoid robots like this: What is the
| battery life? I imagine this will be a critical limitation on
| these, until further notice.
| drooby wrote:
| The battery life of a human is 6-8 hours. Those pesky humans
| also want "rights". Takes a long time to make a new human too.
|
| So that's the competition.
| exe34 wrote:
| you can also swap out batteries for the robots
| fragmede wrote:
| this robot has arms and legs and apparently some measure of
| autonomy now as well. It can change it's own batteries!
|
| Which, humans do at least once a day, among tending to
| other biological needs as well. So the question is what's a
| useful run time if there's a bank of swappable batteries it
| can run back to refill from? Even if it had to go and swap
| batteries every two hours, for a factory robot that
| wouldn't be insurmountable.
| recursive wrote:
| > The battery life of a human is 6-8 hours. So that's the
| competition.
|
| How many naps are you taking? Normal uptime is at least 16
| hours. In special circumstances, much more is possible.
|
| I'd be amazed if the robots are more than 2. Slightly
| surprised if they're over 1.
|
| It's not exactly comparable.
| criley2 wrote:
| Humans have an uptime of 16 hours, but generally speaking
| can only operate professionally for an 8 hour span. The
| other 8 hours are spent mostly doing personal maintenance
| and refueling their physical and mental capabilities.
|
| Oh, and humans have traditionally banded together to punish
| those who ask for more than 8 hours a day or 5 days a week,
| and have even historically gotten very murdery over the
| subject. Buyer beware!
| the__alchemist wrote:
| I do not think you'll get anything close to that with these
| robots.
| mrshadowgoose wrote:
| Yup, it's a real shame that batteries can't be swapped.
| Retric wrote:
| Swapping batteries is often suggested, but rarely actually
| used in practice due to a wide range of logistical issues
| like thermal management, cost, etc.
| lvl155 wrote:
| Still find it comical that Masayoshi sold it to Hyundai instead
| of Tesla. BD was the perfect fit for Tesla at the time.
|
| Now not so much and I am glad BD isn't under Tesla umbrella.
| artninja1988 wrote:
| Why does it jump so awkwardly when the part doesn't fit and it
| has to readjust?
___________________________________________________________________
(page generated 2024-11-02 23:00 UTC)