Humanoid Robots for Moon and Mars

[sanman]

Here we get a view of worker drones sorting packages




But what are the most important tasks a humanoid robot could perform on the Moon or Mars?
Where would they be most needed?

[clongton]

Here we get a view of worker drones sorting packages
<snip>
But what are the most important tasks a humanoid robot could perform on the Moon or Mars?
Where would they be most needed?

Most likely lifting, loading, offloading, positioning.
Basically as a material handler.

[DanClemmensen]

But what are the most important tasks a humanoid robot could perform on the Moon or Mars?
Where would they be most needed?

Preliminary exploration of dangerous terrain, such as lava tubes.

[sanman]

Humanoids by Texas Instruments

[catdlr]

Helix Rpbots Actual use in Industry.

[catdlr]

This robot is a good candidate for Space Station work activities where bipedal movement isn't required.

Sanctuary AI Equips General Purpose Robots with New Touch Sensors

[catdlr]

A candidate for excursions and scouting, very nimble and light weight.

LimX Dynamics Launches Multi-Modal Biped Robot TRON 1

[lamontagne]

Clean solar panels. Very high energy return!

[InterestedEngineer]

A candidate for excursions and scouting, very nimble and light weight.

LimX Dynamics Launches Multi-Modal Biped Robot TRON 1

Either the designers are evil, or they have no sense of esthetics.

There's a reason the bad guys had machines that looked like this in the OG Star Wars.   It's because they look evil.  Props designers are not dummies.

[sanman]

Legged/pedal robots are only advantageous when navigating irregular terrains.

Otherwise, for flat interiors, rolling/wheeled platforms seem more stable and efficient

[Cheapchips]

Legged/pedal robots are only advantageous when navigating irregular terrains.

Otherwise, for flat interiors, rolling/wheeled platforms seem more stable and efficient

Bipeds have a smaller footprint than a platform. They'd have full access to a base. Squeezing behind a sofa, between server racks or vertical farm shelves etc. We're just at the start of seeing full body manipulation as well.  Humans use our full bodies more than you'd think.

In a particular work environment there's always the case for increasingly specialised robots. For general purposes, I still think that bipeds will win out.

[StraumliBlight]

Our new Gemini Robotics model brings Gemini 2.0 to the physical world. It's our most advanced vision language action model, enabling robots that are interactive, dexterous, and general. Learn more about how we're enabling the next generation of robotic AI agents at deepmind.google/robotics

[Twark_Main]

A candidate for excursions and scouting, very nimble and light weight.

LimX Dynamics Launches Multi-Modal Biped Robot TRON 1

...

Either the designers are evil, or they have no sense of esthetics.

There's a reason the bad guys had machines that looked like this in the OG Star Wars.   It's because they look evil.  Props designers are not dummies.

Well fortunately when the same company's full-size robot stands up it doesn't do it like a slow-walker murderbot....

[Coastal Ron]

A candidate for excursions and scouting, very nimble and light weight.

LimX Dynamics Launches Multi-Modal Biped Robot TRON 1

{YouTube video snipped}

There are plenty of robotic options, so you need to understand "what is the job that needs to be performed?"

If it is going out and exploring the local area (or the area near where it gets dropped off), then a bi-pedal robot makes a lot of sense.

If you are doing site prep for building, then something with wheels probably makes sense.

So what are the tasks these humanoids robots for Mars will need to do?

[Paul451]

If it is going out and exploring the local area (or the area near where it gets dropped off), then a bi-pedal robot makes a lot of sense.

I don't think it does. Wheels make more sense for the bulk of exploration as well. Much faster, lower energy use, lower computational burden, lower maintenance, higher payload for a given robot mass, etc etc. Individually controllable wheels and suspension can deal with most rough terrain. You aren't climbing mountains, sure, but realistically, neither is your bipedal robot.

Again, the only times we've put bipedal humanoids on another world (Apollo), the first upgrade we gave them was wheels.

[Cheapchips]

Again, the only times we've put bipedal humanoids on another world (Apollo), the first upgrade we gave them was wheels.

They spent most to their time on legs.  Wheels for distance travel and legs at the work site. It's not and either/or situation.

[Paul451]

Again, the only times we've put bipedal humanoids on another world (Apollo), the first upgrade we gave them was wheels.

They spent most to their time on legs.  Wheels for distance travel and legs at the work site. It's not and either/or situation.

Historically, they get annoyed when you cut their legs off.

But seriously, I think most legged robot development is a "we want it because we want it", not because it's useful. For eg, hardly anyone spending $75k on Spot (BD's quadrupedal robot) or even the $2-3k Spot-clones, are using them in environments where a $50-500 wheeled platform wouldn't work better, faster, more reliably. They are buying it because they want a cool toy, and just put up with it being kind of crap and useless.

The same will be true for bipedal robots. They are not going to be good at anything a more mundane, vastly cheaper and simpler robot couldn't do, they will just be a super-expensive novelty toy.

[For eg, earlier in the thread is a video of (Helix) bipedal robots "sorting" packages... really, really, slowly. Meanwhile, postal and logistics companies have conveyor-based switching systems sorting millions of items a day.]

[SpaceLizard]

[For eg, earlier in the thread is a video of (Helix) bipedal robots "sorting" packages... really, really, slowly. Meanwhile, postal and logistics companies have conveyor-based switching systems sorting millions of items a day.]

I don't think anyone is arguing that purpose-built-specialized-systems aren't more efficient, I think the suggestion is more that a properly designed bipedal robot would serve as a sort of all-purpose-multi-tool: Less efficient at any given task but immediately available to do tasks that the PBSSs aren't built for yet and can be quickly repurposed unlike most PBSSs.

[Coastal Ron]

But seriously, I think most legged robot development is a "we want it because we want it", not because it's useful.

Though there are plenty of exceptions of course, but humanity usually tries to replicate successful examples from nature when it comes to making machines. And bi-pedal humans have been VERY successful at ambulating in a vast number of environments. Things with wheels not so much when things get bumpy or steep, despite how much Land Rover tries to convince us that driving up steep mountain stairs is a good idea... 

For eg, hardly anyone spending $75k on Spot (BD's quadrupedal robot) or even the $2-3k Spot-clones, are using them in environments where a $50-500 wheeled platform wouldn't work better, faster, more reliably.

Most of the use cases here on Earth are for environments that have been constructed to be flat and/or predictable - that isn't the situation on planets not called Earth.

The same will be true for bipedal robots. They are not going to be good at anything a more mundane, vastly cheaper and simpler robot couldn't do, they will just be a super-expensive novelty toy.

Wheeled systems will have their place, and will likely be more and more prevalent as Mars is tamed. But early on there can be use cases for bi-pedal systems.

And I'm actually more known for saying that robots with human-like hands and feet are not yet ready for being relied upon, but I think they should be part of the vast number of experiments we'll be trying out with early exploration of Mars.

[Metalskin]

...
But seriously, I think most legged robot development is a "we want it because we want it", not because it's useful. For eg, hardly anyone spending $75k on Spot (BD's quadrupedal robot) or even the $2-3k Spot-clones, are using them in environments where a $50-500 wheeled platform wouldn't work better, faster, more reliably. They are buying it because they want a cool toy, and just put up with it being kind of crap and useless.
...

I know mining companies using spot to map out underground mines. You can send spot in with lidar, map out the mine in detail and create 3d models far safer and quicker.

I do work for RioTinto, however I see that South 32 have a webpage about spot specifically: https://www.south32.net/news-media/latest-news/meet-spot-the-robot-dog-at-cannington

At the end of the day $75K is small change when it comes to mining and being able to improve both speed and safety is a big feature.