Humanoid Robots for Moon and Mars

[catdlr]

Specialty built robots are AWESOME! Legs, wheels, tracks or any other motive combination.

This serves as an exemplary illustration: the transition to reverse direction occurs so swiftly, along with the added flexibility of the arms and fingers, surpassing belief.  See this video.

https://twitter.com/CultureCrave/status/2008456094763676143

Culture Crave 🍿
@CultureCrave
New look at Boston Dynamics' Atlas robot 🤖

• Can lift up to 110 lbs

• Google's DeepMind’s AI models are being integrated

• They plan to scale production to ~30K units by 2028

[Twark_Main]

That’s like selling a forklift without tines.

If the tines cost as much as the entire rest of the forklift, and there were other cheaper attachments that you might use instead, then they would definitely sell forklifts without tines.

[SpaceLizard]

Specialty built robots are AWESOME! Legs, wheels, tracks or any other motive combination.

This serves as an exemplary illustration: the transition to reverse direction occurs so swiftly, along with the added flexibility of the arms and fingers, surpassing belief.  See this video.

https://twitter.com/CultureCrave/status/2008456094763676143

Woah...! That's a little...freaky...Cool, but freaky...

[MickQ]

Time for a new  “Do You Love Me “ video.

[catdlr]

Same routine, different camera angle during a rehearsal.

https://twitter.com/SpaceIntel101/status/2009047032682709465

[clongton]

See the guy in the blue shirt in the video on the right? I believe he is teleoperating the Atlas. That's VERY cool, and it's a perfect segway into my next point; that I, personally, do not want to see any robots that are actually self-aware. I do want to see extremely sophisticated programming, where the robot is programmed to do a very large number of very different tasks, where it can be commanded to "go <somewhere> and do <something>" and it then executes that command and returns. If it runs into a problem then it stops and "calls home" where it can be instructed on how to overcome the problem and be able to execute that new instruction set, be teleoperated to fix the problem, or be told to return home. That way it remains an extremely sophisticated robotic worker, and not a fake human. I know that some of the engineers working on these have (secret) dreams of cracking the code to make their machines "self aware", but I do not want to see that. Sophisticated "situational" awareness, not "self" awareness should be the goal, with programming sophisticated enough to handle all known potential conditions and problems. Situational awareness and self awareness are not the same thing. One is useful to humans while the other is dangerous to humans. I want to see this technology developed and deployed to the max possible, but within very specific guidelines wrt awareness. Is anyone aware of the company's official position on this issue?

I notice that when Atlas is walking that it does not lift its feet very high. The gait is almost a shuffle. I hope that will change because at that elevation it would not be able to step over an obstacle.

[Twark_Main]

If it runs into a problem then it stops and "calls home" where it can be instructed on how to overcome the problem and be able to execute that new instruction set, be teleoperated to fix the problem, or be told to return home. That way...

...we get the Waymo situation whenever we have a major system outage?   

[Paul451]

and it's a perfect segway

If that was an intentional pun, colour me whooshed. If not, "segway" is the scooter-thing, "segue" is an uninterrupted transition between segments (or metaphorical rhetorical equivalent.)

[Coastal Ron]

As a reminder, Elon Musk has stated that the Tesla Optimus robot will have these characteristics:

Weight: ~125 lbs (57 kg).
Height: ~5'8" (1.73m).
Payload: ~45 lbs (20 kg)

Oh, and Tesla did not demo the latest version of Optimus of CES. Plus Musk earlier in the year mentioned a goal of producing “5,000 to 10,000 Optimus robots in 2025.” No evidence that happened.

I mention all of this so that expectations can be calibrated for what could end up being sent on the first Starship planned to land on Mars. I have no doubt that Musk will send whatever the latest version of Optimus is to Mars, but I doubt that we can expect it to be very useful.

I don't know if Boston Dynamics Atlas (i.e. Hyundai) wants to get into space exploration, but they were at CES demoing Atlas, and Atlas looks pretty interesting. Not saying Atlas could do much on Mars either, since I don't think humanoid robots are getting "smarter" that quickly, but at least Atlas looks like it is going into serial production.

[InterestedEngineer]

As a reminder, Elon Musk has stated that the Tesla Optimus robot will have these characteristics:

Weight: ~125 lbs (57 kg).
Height: ~5'8" (1.73m).
Payload: ~45 lbs (20 kg)

Oh, and Tesla did not demo the latest version of Optimus of CES. Plus Musk earlier in the year mentioned a goal of producing “5,000 to 10,000 Optimus robots in 2025.” No evidence that happened.

I mention all of this so that expectations can be calibrated for what could end up being sent on the first Starship planned to land on Mars. I have no doubt that Musk will send whatever the latest version of Optimus is to Mars, but I doubt that we can expect it to be very useful.

I don't know if Boston Dynamics Atlas (i.e. Hyundai) wants to get into space exploration, but they were at CES demoing Atlas, and Atlas looks pretty interesting. Not saying Atlas could do much on Mars either, since I don't think humanoid robots are getting "smarter" that quickly, but at least Atlas looks like it is going into serial production.

I eagerly await the first demo where Optimus is handled a shovel and told to dig a ditch

[redneck]

[quote

I eagerly await the first demo where Optimus is handled a shovel and told to dig a ditch

And do it properly. Mumble decades ago I started to write instructions for properly using a shovel. I was out digging most new hires by multiples and they mostly couldn't get it right then. Building footers. Several pages in it finally dawned on me that the target group weren't going to read instructions in the first place. Embarrassing waste of effort. The vast majority of people don't understand the skill required to use a shovel effectively.

I want to see the ivory tower robot guys try to explain shoveling to a machine.  Similar work is bog standard to an excavator by the way. There's a reason nail guns don't look like hammers.

[Coastal Ron]

The 2026 Consumer Electronics Show (CES) just wrapped up, and this article (and video) from The Verge focused on humanoid and non-humanoid robots for the home.

CES 2026: the humanoid robots trying to make their way into your home | The Verge

Watching the video was enlightening from the standpoint of how ineffective current humanoid robots are. It is hard to match the hype with the reality, because there is such a HUGE difference!

This is relevant because any humanoid robots going to Mars will likely go through extensive testing here on Earth, and what we see today is going to be pretty representative of what could go to Mars. And as of today, what could go to Mars won't be able to do much.

One other point to make is the rate of improvement for humanoid robots. So if we were to look at what humanoid robots were able to do at the 2025 CES vs the 2026 CES, I don't think we would see much improvement. In other words, the velocity of change is pretty small. So with the current velocity of change, I think we are more than a decade away from a truly usable humanoid robot that could be useable on the surface of Mars - something that is relied upon as the primary method of doing a particular important work.

[redneck]

The 2026 Consumer Electronics Show (CES) just wrapped up, and this article (and video) from The Verge focused on humanoid and non-humanoid robots for the home.

CES 2026: the humanoid robots trying to make their way into your home | The Verge

Watching the video was enlightening from the standpoint of how ineffective current humanoid robots are. It is hard to match the hype with the reality, because there is such a HUGE difference!

This is relevant because any humanoid robots going to Mars will likely go through extensive testing here on Earth, and what we see today is going to be pretty representative of what could go to Mars. And as of today, what could go to Mars won't be able to do much.

One other point to make is the rate of improvement for humanoid robots. So if we were to look at what humanoid robots were able to do at the 2025 CES vs the 2026 CES, I don't think we would see much improvement. In other words, the velocity of change is pretty small. So with the current velocity of change, I think we are more than a decade away from a truly usable humanoid robot that could be useable on the surface of Mars - something that is relied upon as the primary method of doing a particular important work.

I would like to see a list of expected tasks on Mars that require machines. Then match those tasks to machines that already exist here with remote control. I think most would be surprised at how much is possible right now without invoking the humanoid form. Tractors, mowers, excavators, loaders, and many concrete (my field) machines already can operate remotely. The controller for autonomous is in the computers and software with a relatively modest com link. It doesn't take a hand to push a control on that electromechanical servo when an electron can do the job.

[Twark_Main]

The 2026 Consumer Electronics Show (CES) just wrapped up, and this article (and video) from The Verge focused on humanoid and non-humanoid robots for the home.

CES 2026: the humanoid robots trying to make their way into your home | The Verge

Watching the video was enlightening from the standpoint of how ineffective current humanoid robots are. It is hard to match the hype with the reality, because there is such a HUGE difference!

This is relevant because any humanoid robots going to Mars will likely go through extensive testing here on Earth, and what we see today is going to be pretty representative of what could go to Mars. And as of today, what could go to Mars won't be able to do much.

One other point to make is the rate of improvement for humanoid robots. So if we were to look at what humanoid robots were able to do at the 2025 CES vs the 2026 CES, I don't think we would see much improvement. In other words, the velocity of change is pretty small. So with the current velocity of change, I think we are more than a decade away from a truly usable humanoid robot that could be useable on the surface of Mars - something that is relied upon as the primary method of doing a particular important work.

Thanks, I haven't followed the show closely this year.

How was the Tesla booth? Last I checked they hadn't announced plans to reveal V3 at CES, but stranger thing have happened before!

Or was this only just the "also ran" companies with their lab prototypes?

[JohnFornaro]

I eagerly await the first demo where Optimus is handled a shovel and told to dig a ditch...

Bingo. 

Included in this exercise would be removing big rocks  and the final steps of covering up the trench.  Do this on Earth first.

[Twark_Main]

I eagerly await the first demo where Optimus is handled a shovel and told to dig a ditch...

Bingo. 

Included in this exercise would be removing big rocks  and the final steps of covering up the trench.  Do this on Earth first.

"I eagerly await the first demo where Optimus [does a job way better suited to an excavator, both mechanically and economically]."

Pack a lunch, because you'll be waiting a while. I doubt this "demo" is a high priority within the R&D program. It certainly won't be a priority to use Optimus that way in production. There's no ditch-digging company out there champing to replace their excavators with Optimus.

Light shoveling in the garden? Sure. "Dig this hundred meter ditch?" You're crazy if you don't hire an excavator for a few hundred bucks, rather than risk your $25,000 robot. Even just the wear-and-tear on joints makes it uneconomical for production use.

If I didn't know any better, I'd say certain folks prefer setting their goalpost to a demo they know isn't a real priority for the company...   

[Paul451]

I eagerly await the first demo where Optimus is handled a shovel and told to dig a ditch...

Included in this exercise would be removing big rocks  and the final steps of covering up the trench.  Do this on Earth first.

"I eagerly await the first demo where Optimus [does a job way better suited to an excavator, both mechanically and economically]."
[...]
Light shoveling in the garden? Sure. "Dig this hundred meter ditch?" You're crazy if you don't hire an excavator for a few hundred bucks, rather than risk your $25,000 robot. Even just the wear-and-tear on joints makes it uneconomical for production use.

There have been several comments in this thread about "just bringing 100 Optimus bots with shovels" to Mars instead of Earth-moving equipment.

Criticising Optimus' capabilities at the claimed task is therefore pretty reasonable.

(Ditch digging is also a good example of an unstructured task that would demonstrate the kind of general purpose adaptability that many people in this thread are assuming purely from the humanoid form factor. As opposed to, say, folding small towels by putting them on a flat bench, the CES demo du jour.)

[Twark_Main]

I eagerly await the first demo where Optimus is handled a shovel and told to dig a ditch...

Included in this exercise would be removing big rocks  and the final steps of covering up the trench.  Do this on Earth first.

"I eagerly await the first demo where Optimus [does a job way better suited to an excavator, both mechanically and economically]."
[...]
Light shoveling in the garden? Sure. "Dig this hundred meter ditch?" You're crazy if you don't hire an excavator for a few hundred bucks, rather than risk your $25,000 robot. Even just the wear-and-tear on joints makes it uneconomical for production use.

There have been several comments in this thread about "just bringing 100 Optimus bots with shovels" to Mars instead of Earth-moving equipment.

I was talking about economics for a commercial ditch-digging company. For Mars you could (of course) easily afford to send overpriced hardware if that buys other advantages.

I would advocate sending at least a mini-excavator to Mars. Right tool for the job. I'm not a "hundred shovels should be Plan A" supporter, fwiw.

[Paul451]

I eagerly await the first demo where Optimus is handled a shovel and told to dig a ditch...

Included in this exercise would be removing big rocks  and the final steps of covering up the trench.  Do this on Earth first.

"I eagerly await the first demo where Optimus [does a job way better suited to an excavator, both mechanically and economically]."
[...]
Light shoveling in the garden? Sure. "Dig this hundred meter ditch?" You're crazy if you don't hire an excavator for a few hundred bucks, rather than risk your $25,000 robot. Even just the wear-and-tear on joints makes it uneconomical for production use.

There have been several comments in this thread about "just bringing 100 Optimus bots with shovels" to Mars instead of Earth-moving equipment.

I was talking about economics for a commercial ditch-digging company.

Yeah, that's called a "straw man".

[Twark_Main]

I eagerly await the first demo where Optimus is handled a shovel and told to dig a ditch...

Included in this exercise would be removing big rocks  and the final steps of covering up the trench.  Do this on Earth first.

"I eagerly await the first demo where Optimus [does a job way better suited to an excavator, both mechanically and economically]."
[...]
Light shoveling in the garden? Sure. "Dig this hundred meter ditch?" You're crazy if you don't hire an excavator for a few hundred bucks, rather than risk your $25,000 robot. Even just the wear-and-tear on joints makes it uneconomical for production use.

There have been several comments in this thread about "just bringing 100 Optimus bots with shovels" to Mars instead of Earth-moving equipment.

I was talking about economics for a commercial ditch-digging company.

Yeah, that's called a "straw man".

You may notice I wrote more words than you quoted, and they explain why it isn't. 

Tesla isn't prioritizing a digging demo for the simple reason that there's no burning market on Earth, hence the straw man misunderstood point about ditch-digging companies. That's why there's no demo, which was the (disingenuous?) concern raised.

If you want to send a bunch of $25,000 robots (or even ~$300,000 early prototypes) to Mars and expend them "just" digging a ditch, that might still make sense if it was less landed mass than an excavator. Different planets call for different definitions of "economic viability." Personally I lean toward sending an excavator to Mars too, but I also acknowledge that the Ditch Company Economics argument doesn't apply equally to using shovels on Mars.

Make sense to you now?



Ironically, if there's a straw man here, it's your "eagerly awaiting" a ditch-digging Optimus demo (with the heavy implication that it's doomed otherwise), when you know full well that it's a silly use case for humanoid robots and isn't a real priority in the R&D process.