Boston Dynamics' new Atlas robot doing work.

[BrianHG]

Finally, something you know isn't being puppeteered  by a human or following a prerecorded script.



All we need next is a video of Atlas making more Atlas....

[nctnico]

I find this impressive. Having been around for quite some decades already, I recall the first attempts of making robots like these but they never managed to impress. Bonus points for the developer who had the brilliant idea that the head and torso can rotate freely.

Elon Musk just ordered hundreds of these to replace those pesky factory workers so they have time to vote for his favorite idiot promising more jobs. 

[BrianHG]

I found the effortless really deep squat down at 1:03 while picking up an item in front of Atlas, not below, truly an impressive balancing act.
It's the first time Ive seen an automaton perform such a feat.

[pcprogrammer]

I find this impressive. Having been around for quite some decades already, I recall the first attempts of making robots like these but they never managed to impress. Bonus points for the developer who had the brilliant idea that the head and torso can rotate freely.

Indeed impressive, but watching it rotate like that feels weird.

Have to say that a human would outperform doing this task, but boredom will strike for the human, something a robot does not care about.

I wonder how the robot was instructed to perform this task and how it decided to do it in a seemingly random way. A human worker would be told to fetch the items from the racks and place them in the other container, and go ahead with the job.

As a side note, this is something the "realistic humanoid robot" on this forum will never be able to do. 

[SiliconWizard]

That's impressive robotics, and otherwise nice marketing, but adapting the task and work environment for simpler and much cheaper robots is much more effective usually. So for work? Yeah. Sure. If you want to sell "leaders" the idea of directly replacing human workers without having to make any change to the work environment and kind of tasks. That's odd or very short-term.

There are areas where they can be a benefit though, like in risky areas with nasty chemicals, radiation, etc, when a human body is otherwise well adapted.
But this probably sounds much too "niche" to be good marketing.

As to the robots not caring about being bored. They may eventually get more rights than mere humans in the great industry 5.0 world.

[ebastler]

Finally, something you know isn't being puppeteered  by a human

How do we know that? I would definitely assume that the robot autonomously coordinates its movements to bend forward, squat down etc. But is it doing all the image recognition, action and motion planning etc. on its own, or might there be a human somewhere across the room with a camera feed and some custom controllers?

[AndyC_772]

The tech looks very impressive, but it's still very apparent that the actual job it's doing is an absurdly simple one, like the kind of thing the player might have to do in a 1st person puzzle game. It's at that level of complexity - stand near collectable item, 'take', stand near target area, 'drop'.

I'm sure I've done something very similar in a VR game, and it still feels a million miles away from the kinds of work that humans perform in reality.

Does it have anywhere near the detailed object recognition and fine motor skills to, say, assemble a PCB into a housing and plug in the wiring loom? Or pack a shopping bag? Feed the cat?

[mikeselectricstuff]

I find this impressive. Having been around for quite some decades already, I recall the first attempts of making robots like these but they never managed to impress. Bonus points for the developer who had the brilliant idea that the head and torso can rotate freely.

Elon Musk just ordered hundreds of these to replace those pesky factory workers so they have time to vote for his favorite idiot promising more jobs. 

Why would he when he has Optimus - I'm waiting for the video of an Atlas vs.Optimus cage-fight

[squadchannel]

“Fully Autonomous” in the lower right corner is not enough evidence, but it is great.
In terms of managing the factory, it cannot be completely standalone, so it must be communicating in some way.
but if Atlas itself is doing all the image processing and motion control, this is great.

I would have liked to have seen it demonstrated with a jammer. I think can prove that it is standalone.

It is truly amazing to see more and more robots like this.

[guenthert]

The tech looks very impressive, but it's still very apparent that the actual job it's doing is an absurdly simple one, like the kind of thing the player might have to do in a 1st person puzzle game. It's at that level of complexity - stand near collectable item, 'take', stand near target area, 'drop'.

I'm sure I've done something very similar in a VR game, and it still feels a million miles away from the kinds of work that humans perform in reality.
[..]

   Does it?  In the eighties school made me visit a factory where they made pots for plants from clay.  I still starkly remember one work place where a woman took a workpiece from one shelf on the left, placed it under the press, pressed two buttons (you know why), turned and put the now pot-shaped workpiece on a shelf to her right.  Again and again and again.  I was so shocked, I couldn't move for several minutes.  I henceforth put decidedly more effort into my education (arguably objective of the school trip achieved).   
   Perhaps that has been fully automatized in the past forty years, as robots became cheaper than even unskilled labor and that poor soul has been freed of her servitude, but I'm sure there are still millions who toil like that five or (soon again in Greece) six days a week.

[xrunner]

   Does it?  In the eighties school made me visit a factory where they made pots for plants from clay.  I still starkly remember one work place where a woman took a workpiece from one shelf on the left, placed it under the press, pressed two buttons (you know why), turned and put the now pot-shaped workpiece on a shelf to her right.  Again and again and again.  I was so shocked, I couldn't move for several minutes.  I henceforth put decidedly more effort into my education (arguably objective of the school trip achieved).   
   Perhaps that has been fully automatized in the past forty years, as robots became cheaper than even unskilled labor and that poor soul has been freed of her servitude, but I'm sure there are still millions who toil like that five or (soon again in Greece) six days a week.

Look at the work people do in countries like Pakistan - it's all easily found on YT. If anyone wants to be shocked at what people do all day for a meager wage watch a few of them. Untold numbers of these jobs could be taken over with robots like that.

And of course that leads to the other question what happens to all the jobs like that when these robots take them over - and they will. A worry for another day I suppose.

[ebastler]

Look at the work people do in countries like Pakistan - it's all easily found on YT. If anyone wants to be shocked at what people do all day for a meager wage watch a few of them. Untold numbers of these jobs could be taken over with robots like that.

But for tasks of the limited complexity shown in the video, there is no reason at all to use humanoid robots with all their complexity, stability challenges etc. One can easily envision a small family of generic, much simpler robots which can be programmed to handle many tasks of this type. The following should cover most of it:

- Just a 6 DOF robotic arm, stationary
- Robotic arm on wheel base
- Pair of robotic arms, stationary
- Pair of arms on wheel base

[xrunner]

Robots don't get sick and don't need to be paid and can work in areas where the need to have environmental conditions acceptable for humans can be removed (i.e. air conditioning and removal of toxic air). They will last as long as you have spare parts and won't revolt or complain or steal or do poor quality work do to exhaustion. So yes I do believe it will happen in poor countries because there are the rich there too.

To paraphrase a quote from the Oracle in The Matrix: "What to people with a lot of money want? More money".

This can be argued all day long but let's see what happens. I believe I will be correct but time will tell.

[tom66]

Robots don't get sick and don't need to be paid and can work in areas where the need to have environmental conditions acceptable for humans can be removed (i.e. air conditioning and removal of toxic air). They will last as long as you have spare parts and won't revolt or complain or steal or do poor quality work do to exhaustion. So yes I do believe it will happen in poor countries because there are the rich there too.

To paraphrase a quote from the Oracle in The Matrix: "What to people with a lot of money want? More money".

This can be argued all day long but let's see what happens. I believe I will be correct but time will tell.

The problem is a robot like this will cost, say $100,000, right now.  If it has a 10 year useful life then the minimum wage worker in China is safe for now.    If however the prices fall (as most technology costs do), then it will be a problem.

To a lesser extent this is already being seen by chatbots replacing low level tech support.  These bots may eventually replace voice calling, which will devastate the services economies in India, Philippines, Indonesia etc. 

We are going to have to get rid of the idea of full employment being an achievable goal.  That creates major headaches for capitalism which relies on consumption to survive.

[tszaboo]

The problem is a robot like this will cost, say $100,000, right now.  If it has a 10 year useful life then the minimum wage worker in China is safe for now.    If however the prices fall (as most technology costs do), then it will be a problem.

To a lesser extent this is already being seen by chatbots replacing low level tech support.  These bots may eventually replace voice calling, which will devastate the services economies in India, Philippines, Indonesia etc. 

We are going to have to get rid of the idea of full employment being an achievable goal.  That creates major headaches for capitalism which relies on consumption to survive.

100K is quite cheap to replace a human in a production environment. At some point my home country was trying to get manufacturers to open factories there. They always told the amount invested and the number of jobs created, and I just divided them. In my estimation it was always around half a million EUR or USD to create one such job. That of course includes the cost of the building and the production line, but still, it's money spent vs job created.

That being said, in accordance with EU law, you cannot have moving parts such as this shared with other workers in the same area. So for example right now I don't replace a worker with a Kuka robot arm, because all the paperwork, compliance, rules and everything I would need to go through. Plus I'm not a production engineer. But for a dedicated factory floor with said robot arms and moving parts, the paperwork is actually less.

[xrunner]

The problem is a robot like this will cost, say $100,000, right now.  If it has a 10 year useful life then the minimum wage worker in China is safe for now.    If however the prices fall (as most technology costs do), then it will be a problem.

Yes agree. We don't know many things at the moment, we'll just have to see how it plays out. All I'm saying is if it does play out that inexpensive robotics (it doesn't have to be robots that look like people either) take over many menial jobs, the world is going to have a grave problem to solve with employing all the people left behind.

[SteveThackery]

I agree - the "work" in this case is contrived and trivially simple. But the video is intended to be a showcase for the robot behaving in a human-like way, with its highly sophisticated movements, balance, and so on. The "work" also seems to showcase some fairly basic object recognition, along with a degree of planning which is required for the robot to move to the right place, in the right position, to deposit the object.

In reality you would never use a humanoid robot for a basic pick-and-place role. It's just a demo, and a very impressive one.

[themadhippy]

wonder how many miles of fishing line and how many thumb tacks are in that thing

[CatalinaWOW]

Obviously a humanoid robot is the wrong answer for an assembly line that will be doing the same task for months or years.  But there is opportunity in short run production.  Also fabulously more difficulty.  Humans are probably safe in that arena for decades.

[tom66]

What I want to know is how easy is this thing to train.  Did they say "move the engine covers from here to there", or did they say "move item that looks like (deep learned engine cover) from location 2A to location 2B, iterate until 8 covers have moved, incrementing the counts as we go, 2A is marked like this, 2B is marked like that"?

I think this distinction is crucial because if you ask a human to move the engine covers from one area to another they will "solve" the rest of the problem themselves.  Even the dumbest person can do that without further instruction.  If you have to supervise and carefully instruct this thing, it'll take more resources than it saves, even if the motions to implement the actions themselves are fully autonomous. 

[nctnico]

I think this distinction is crucial because if you ask a human to move the engine covers from one area to another they will "solve" the rest of the problem themselves.  Even the dumbest person can do that without further instruction.

Don't be so sure about that. In order to keep things organised, you'll need to give people very detailed instructions and monitor whether they follow those instructions. You'd be surprised how many people can't do the simplest jobs and / or have a different idea compared to your own idea.

[globoy]

Probably this version of Atlas won't enter the work force in large numbers...

But I see it like the very early personal computers, and early personal computer software.  These machines weren't ever going to be adopted in large numbers, but they were a necessary stepping stone to the point where the personal computer was ubiquitous and deeply embedded in society a number of years later.

Think about the rate of change in bipedal robots over the last 10-15 years, from Honda's Asimov series to this.  Now think about what's going to happen over the next 10-15 years given the rate of change in the AI world and the amount of investment currently into the marriage of AI and robotics.  One might argue that the bipedal form isn't always the best for functional robots but it certainly is one that captures the imagination of humanity and is getting significant effort.  I'd bet that some of us will have robot caretakers in our dotage.

[HuronKing]

" We designed Atlas to be capable, intelligent, and robust, so even when a pesky pickle moves a dolly, the robot can autonomously recognize its new position and complete its task."

[ebastler]

That motion at 0:51 makes me slightly nervous... You wouldn't want to annoy that thing to the point where it gets impatient with you. 

[SteveThackery]

I think this distinction is crucial because if you ask a human to move the engine covers from one area to another they will "solve" the rest of the problem themselves.  Even the dumbest person can do that without further instruction.  If you have to supervise and carefully instruct this thing, it'll take more resources than it saves, even if the motions to implement the actions themselves are fully autonomous.

In a way, that's a slightly separate issue. The USP of Boston Dynamic's work is in the name: dynamics. They've made a bipedal, humanoid robot that can walk over rough - even loose - terrain, dance, jump, run, get up from the floor, stay balanced when someone tries to push it over..... it is magnificent, world-leading work and they have transformed the world of robotics.

The stuff you describe, which is really about machine intelligence, is something BD are working on, but don't seem to be the class leaders as far as I can make out. I think many, many commercial and academic organisations are working hard on it.  I think we would agree that if you wanted a robot to move items from one rack to another, you'd be nuts to invest in something as versatile as Atlas.  A box on wheels with one arm would be far more practical. And as you say, the "intelligence" of the machine - which would apply equally to Atlas and the one-armed box - is important but not obvious from the demonstration video.

[jonovid]

if the robot drops something? can it find the lost component on the floor and recover from the random deviation from its workflow, all without needing human intervention?
or will it system crash.

[SteveThackery]

if the robot drops something? can it find the lost component on the floor and recover from the random deviation from its workflow, all without needing human intervention?
or will it system crash.

We obviously don't know, because we're all looking at the same video. What is your point?

[xrunner]

if the robot drops something? can it find the lost component on the floor and recover from the random deviation from its workflow, all without needing human intervention?
or will it system crash.

I don't know, but I can safely say this. This is the worst that these robots will be able to perform. It will only improve.

[jonovid]

if the robot drops something? can it find the lost component on the floor and recover from the random deviation from its workflow, all without needing human intervention?
or will it system crash.

We obviously don't know, because we're all looking at the same video. What is your point?

my point I would to see this complex self balancing humanoid robot do more then just follow a basic set sequence like a car manufacturing robot , jukebox disc loading mechanism or a cam following 1800s automaton.  IMO complex multitasking is the essence of a humanoid robot.

[lokin4areason]

can see the military and the police having a go with this along with the manufacturing/ construction sector in eliminating manual labor aspect

[tom66]

Even if 10 robots need one handler to sort out the odd issue, it's a major reduction in workforce requirements, with all the associated social upheaval.

I suspect a 100% automated factory is decades off. There are some limited examples of this, but only very specific work that lends itself to automation.  General automation by autonomous robots is a very hard problem to solve.

[Bud]

can see the military and the police having a go with this along with the manufacturing/ construction sector in eliminating manual labor aspect

A walking robot is a niche use case. It is much more effective if it rolls, especially in controlled environments like factory floors.

[SteveThackery]

my point I would to see this complex self balancing humanoid robot do more then just follow a basic set sequence like a car manufacturing robot , jukebox disc loading mechanism or a cam following 1800s automaton.  IMO complex multitasking is the essence of a humanoid robot.

Why do you require "complex multitasking" from a humanoid robot in particular, rather than from all robots?  Surely there will be applications which require complex multitasking, and others which don't. The shape of the robot (box on wheels, or humanoid) shouldn't affect how much multitasking is required.

I'm just saying that those questions you ask are totally legitimate, but are questions that apply to the whole field of robotics, not specifically to Atlas.

[BrianHG]

Atlas doing exercise/pushups.  Also, his face plate is off revealing a bit underneath.

https://www.youtube.com/shorts/asHc4a55JX4

[SteveThackery]

Atlas's walk still isn't quite right. It seems never to lock out its knees, which most humans do briefly when walking at a moderate pace. Its permanently bent knee walk undermines its overall - astonishingly good - performance.

[eutectique]

As a side note, this is something the "realistic humanoid robot" on this forum will never be able to do. 

Just give it some time.

[pcprogrammer]

As a side note, this is something the "realistic humanoid robot" on this forum will never be able to do. 

Just give it some time.

Doubt it, but he does have the lord on his side. 

Atlas's walk still isn't quite right. It seems never to lock out its knees, which most humans do briefly when walking at a moderate pace. Its permanently bent knee walk undermines its overall - astonishingly good - performance.

It is also loud. Must be the flat feet Atlas has. But certainly impressive how it goes out and in from to standing position to do the push up work out. They should try weight lifting, also a balancing act.

[Siwastaja]

There is something to Boston Dynamics which makes them appear more credible than nearly anyone else:

1) They have chosen to build robots with really challenging mechanical... dynamics. The balancing actions they show cannot be faked with remote controls. They have to be truly autonomous features.
2) They are not just limited to stability of simple movements. Instead, they use their... dynamics very creatively in complex patterns. Again, can't be faked with remote controls (well, maybe except to give very high-level guidance, "do trick X now").
3) They demonstrated all of the above more than 5 years ago. From the current demonstrations the dynamics have not improved much, which is clearly because they were so impressive years ago already there is not much to improve. That very likely means they have been using their same engineering skills for something new, at a different level.

Besides, the demonstration they show in the video posted is not that impressive. I mean, if it was faked, they would have aimed higher. It is just right level of impression to be plausible.

There is a lot of "fake it until you make it" in robotics, and as such a lot of distorted expectations what can be and cannot be done. Having worked in a failed (seriously under-resourced and ran by... let's say unconventional opportunists) robotics startup some 5 years ago, I saw this pretty closely. Now when I see "autonomous projects" like delivery robots I'm nearly 100% sure they are at least assisted if not completely remote-controlled from some Indian call-center type cheap labor operation. It's not surprising Elon Musk does the same.

But I do believe that Boston Dynamics is one of the few who really fakes order of magnitude less than industry median. Possibly even near-zero faking.

[Njk]

Sorry for a low-tech question, but how it supposed to be powered?

Early the same company demoed a robotic donkey that can carry various payload, e.g. ammunition for a squad of soldiers. What was funny is that the donkey was noisy like a motorcycle because it used an ICE for electricity generation.

This device is not created for heavy lifting, but it's very agile so it also requires lot of energy. No problem to keep it powered for five minutes of shooting, but what's next? Even a living thing can't work forever, it need a considerable time to rest and to recover their energy by digesting the food. No way to beat them on efficiency, they're created by a billion years of evolution.

Any man-made machine is much less energy efficient. So if one is going to build an army of that robots, that army will require much more energy than a human army. Where to source it? Simply because of that it's obvious a devastating effect from the robot's population will be much more serious than that from a human population of equal amount. Although it's interesting business for someone.

[SiliconWizard]

Well, interesting question. I'd be really curious to know what the average and peak power consumption of these robots is.

[CatalinaWOW]

Energy consumption of robots isn't so clear cut as that.  I'll stipulate that joules/motion might be better for humans, but humans consume a lot of energy just heating the body to operating temp.  Robots do have to do some temperature control, but have a huge advantage in this part of the power budget.

[Siwastaja]

Any man-made machine is much less energy efficient.

I don't know, these could be surprisingly energy efficient. Like, the motors turning the joints regenerating to stop. Muscles can't do that, they dissipate into heat when "braking".

Amount of physical work done in the opening video is near-zero; it's not working at speeds where aerodynamics are a big issue. Assuming the joints have good bearings (and why wouldn't they), and any electric motors and gears are in modern >80% efficiency, I see no reason a 2-3kWh li-ion pack would not enable it to work for a long shift.

[Njk]

Energy consumption of robots isn't so clear cut as that.  I'll stipulate that joules/motion might be better for humans, but humans consume a lot of energy just heating the body to operating temp.  Robots do have to do some temperature control, but have a huge advantage in this part of the power budget.

The whole point of having a robot is to let it to do more work, increasing the duty cycle to maximize ROI. So the robot will have a cooling problem, not a heating problem.
But what's more important, from the environmental perspective, such autonomous robots seem like a plague worse than cars (unless the mass production is banned, which is unlikely). A way to hell

[Siwastaja]

The whole point of having a robot is to let it to do more work, increasing the duty cycle to maximize ROI

Maximization of duty cycle cannot be the whole point of having a robot. Maximization of ROI is, fair enough, but is not the same as maximization of duty cycle at all. For example, if you can reduce the duty cycle by 30% and halve the cost of the robot, then it makes more sense to do so, and have two robots instead.

Duty cycle is just a linear coefficient for availability. Four robots working at 25% duty cycle each could be well acceptable for most purposes, all that matters is cost effectiveness of the whole (how much work they do for the total cost).

From battery charging and discharging viewpoint, I would expect reaching 50% duty cycle is trivial and even 75% not difficult. Compare that to roughly 25% of a human being (6 hours of actual productive work per 24hrs).

[bdunham7]

From battery charging and discharging viewpoint, I would expect reaching 50% duty cycle is trivial and even 75% not difficult. Compare that to roughly 25% of a human being (6 hours of actual productive work per 24hrs).

Surely just having swappable battery packs is a simple solution to get near 100% duty cycle.  There are electric power tools now that are replacing gas-engine models even in high-demand applications like concrete saws, chainsaws, etc.  For example, the Milwaukee MX Fuel 12.0AH (72V) has about 1.3kWh of energy and can charge in about an hour.  With one or two spares cooking on a charger and a robot that can change its own battery, there's no reason it can't work all day even at a pretty high pace.

[Njk]

Duty cycle is just a linear coefficient for availability. Four robots working at 25% duty cycle each could be well acceptable for most purposes, all that matters is cost effectiveness of the whole (how much work they do for the total cost).

Sure, and that will make the robot sellers happy. For all the others, it seems less than ideal because it not only quadruples the required garage space. It's not a computer game, where you can replicate an object by the mouse click. Production of every robot implies the use of manufacturing space, energy, raw materials, etc., and the required efforts may not be always measured monetarily (it's not a hard unit anyway). For instance, it can be suddenly found that the most suitable materials belong to the rare-earth category. They're hard to find. Many people will object against the plans to undermine their houses for that materials, and for a good reason.

From battery charging and discharging viewpoint, I would expect reaching 50% duty cycle is trivial and even 75% not difficult. Compare that to roughly 25% of a human being (6 hours of actual productive work per 24hrs).

The energy density makes huge difference in possible applications. Different minimal density is required for different machine types. A wind-powered floating machines are known from the ancient times. A battery-powered rolling machines are in big fashion now. A battery-powered toy flying machines are known, but a battery-powered commercial airliner does not exist. It remains to be seen if it's feasible. It seems the walking machines are sitting somewhere in-between. Everyone knows about the batteries, but remember, the robotic donkey was powered by ICE.

[CatalinaWOW]

My point about the human consumption of energy was not pointing to a duty cycle issue in robots.  I see no obvious reason why they would be thermally limited to less than a 100% duty cycle.  Radiators aren't that hard to add if required. 

Sorry about the use of non metric units, but here in the US calories are THE unit of choice for evaluating human energy consumption.  Basal metabolism (just operating the body with no physical activity (keeping it warm, pumping blood and air and thinking) consumes something on the order of 2000-2300 calories per day for the average size male.  Heavy physical activity can roughly double that, indicating that at best the human body is 50% efficient in generating physical work.  The actual number is surely lower because there is almost no recovery of energy except for the spring action in the legs during walking and running and there is friction everywhere.  Cold weather makes it worse, with up to an additional 2000 calories a day to stay warm in extreme conditions.

[jonovid]

must have slip rings in its waist and hip sub-assembly. impressive engineering 

[SiliconWizard]

But can it play Doom?

[BrianHG]

But can it play Doom?

You bet the military would like that!

[pcprogrammer]

My point about the human consumption of energy was not pointing to a duty cycle issue in robots.  I see no obvious reason why they would be thermally limited to less than a 100% duty cycle.  Radiators aren't that hard to add if required. 

Sorry about the use of non metric units, but here in the US calories are THE unit of choice for evaluating human energy consumption.  Basal metabolism (just operating the body with no physical activity (keeping it warm, pumping blood and air and thinking) consumes something on the order of 2000-2300 calories per day for the average size male.  Heavy physical activity can roughly double that, indicating that at best the human body is 50% efficient in generating physical work.  The actual number is surely lower because there is almost no recovery of energy except for the spring action in the legs during walking and running and there is friction everywhere.  Cold weather makes it worse, with up to an additional 2000 calories a day to stay warm in extreme conditions.

You most likely mean 2000-3000 kilocalories for and adult male. https://www.nhs.uk/live-well/healthy-weight/managing-your-weight/understanding-calories/

A single calorie is not a lot of energy. https://www.britannica.com/science/calorie

The use of the term calorie instead of kilocalorie seems to be quite common on the internet, and even in daily live. My wife makes that mistake too.

[SiliconWizard]

Yes, in familiar terms we often erroneously use "calories" instead of "kilocalories" when dealing with our food intake.

To get an idea, 2500 kcal = 10.46 MJ => in one day (86400 s), that's an average of 121 W.
That sounds pretty economical to me.

[Siwastaja]

Surely just having swappable battery packs is a simple solution to get near 100% duty cycle.  There are electric power tools now that are replacing gas-engine models even in high-demand applications like concrete saws, chainsaws, etc.  For example, the Milwaukee MX Fuel 12.0AH (72V) has about 1.3kWh of energy and can charge in about an hour.  With one or two spares cooking on a charger and a robot that can change its own battery, there's no reason it can't work all day even at a pretty high pace.

Yeah. I understand well why battery swapping was not the right solution for EV industry, but for a freaking robot company making the robots swap their own battery packs, putting the used ones in chargers, etc., should be business as usual.

[Siwastaja]

To get an idea, 2500 kcal = 10.46 MJ => in one day (86400 s), that's an average of 121 W.

Yeah. That's basically the idle power to keep the pile of meat at +37degC, somewhat insulated with a layer of fat, further somewhat insulated with clothes, sitting in a room at +20degC. Doing some very random occasional work with higher peak power, but mostly moving their fingers posting crap like this post on the internets.

I'm sure a robot does better energy-wise. Unless it's some kind of ROS hiring 200 trainees to create a distributed system consisting of four Intel Xeon servers where the CPUs run red hot message-passing every coordinate to a separate coordinate transform server for a small 3x3 matrix operation which the CPU would have done in less than a nanosecond in its registers. And then get more money by remote-controlling the robot with standard RC stuff and forgetting to disclose it.

[CatalinaWOW]

Yes, in familiar terms we often erroneously use "calories" instead of "kilocalories" when dealing with our food intake.

To get an idea, 2500 kcal = 10.46 MJ => in one day (86400 s), that's an average of 121 W.
That sounds pretty economical to me.

The diet industry in the US loves the appearance of science, using lots of "sciency" sounding words with impossibly twisted logic tying them together.  But using the vernacular units or the correct locals the ratios remain the same.  About a third to a half of the possible energy input is not used to generate lifting or moving output.  Means muscle driven motion has to be incredibly efficient to be better than the motor driven efficiency of the robot.

Another comment comparing human to robotic workers.  Humans definitely have a duty cycle.  Even highly trained athletes cannot sustain continuous output 24 hours a day.  The human powered flight pilots are really straining to keep up their efforts for an hour.  Cyclists in the Tour de France and other such events manage.somewhere between 25% and 35% over a two week period that requires a long period of lower effort before the next race.

[Njk]

Also, the living creatures have very high redundancy and adaptation capabilities. I recalled myself working at formally 50% duty cycle (6 hours on-duty, 6 hours off-duty), actually higher than that, for many months. I presume even greater percentage can be achieved with enough pressure, perhaps at the cost of reduced service life. But you can't push a machine beyond its design limits.

[BrianHG]

But you can't push a machine beyond its design limits.

Funny thing about design limits.  Take a look as the Mars rover Spirit for example.  It was designed to last 90 days, or 3 months.  But, it went pass its designed limit to last over 6 years.  If there was a repair shop on Mars, it could have done another 6.

[Siwastaja]

But you can't push a machine beyond its design limits.

Machines are pushed beyond their design limits everywhere all the freaking time. Machines also fail similarly to humans in the sense that there is usually no sudden limit and you can't know in advance how much exactly design limits can be exceeded. Sometimes there is a sudden failure but at a point which is hard to predict closer to maybe +/- 20%. And sometimes the lifetime just decreases as the machine slowly stresses out.

Maybe the most clear difference is that in humans, unit-to-unit variation of design limits is much larger than on machinery, requiring careful hand-picking and monitoring of suitable personnel.

[Njk]

But you can't push a machine beyond its design limits.

Funny thing about design limits.  Take a look as the Mars rover Spirit for example.  It was designed to last 90 days, or 3 months.  But, it went pass its designed limit to last over 6 years.  If there was a repair shop on Mars, it could have done another 6.

Yes, but it's a rare special case. It was a research project where the requirements were not exactly known and more important, the bean counters were not allowed to exerсise their full power. When that public is kept on a tight leash, the things can be made really good.

I do remember my first job in the electronics industry in mid-seventies, right after the college. It was at a small manufacturing facility of the R&D center. The plant manufactured a precision on-board time keeping devices for the first satnav system (something like US' Transit). All the boards were assembled manually by the large teams of girls. And there were a guys like me, who were measuring and tuning the boards for required performance characteristics. As a freshman, I was assigned to a simple work, the 5 MHz buffer amplifier board. I had to measure the parameters like output amplitude, clear factor, power consumption, etc. in the range of power voltage and ambient temperature. There were no pots and the tuning method was to change the values of res and caps. For the temperature testing, I had to roll a huge temp chamber to my workbench and put the board inside. Some of that chambers were automated, while in others, the temperature controller was broken or missing so it was necessary to change the temperature manually, as appropriate. On the top of every chamber, a device was located that recorded the temperature profile on the paper roll, which was later archived with the other paperwork for that particular amplifier board. Funny, the board was for placement inside the vacuum glass vessel next to the oscillator board so it was for working at a constant temperature. Nevertheless, I had to measure all the parameters in the temp range from -60 to +70 C. Then, I had to submit the board to the soldering lady to install the tuned components professionally. The first document, with a signature of both sides. Then the vibration testing, one more form, that specified the G number, the waveform type and the time interval. Then the form for conformal coating (the coating type and the number of layers). Then go to the visual inspector, who had to officially make sure that every soldering joint is good, there is the space grade marking on every component, and the coating is OK. Then the form for overmolding the board with foam (the foam type, the outer dimensions). Then I'd to perform the measurements all over again, to finish the paperwork and to declare the work done. No wonder that in the end the paperwork overweighted the board itself. I think it's not much different in the other facilities in the world where that sort of equipment is manufacturing. Not a commercial application.