What does 'general purpose' really mean for a humanoid in practice today?

[nancy_lewi]

@forgecam45 Pretty much this. One thing to add: Wheeled-torso designs solve 90% of warehouse and light-industrial tasks with far less complexity than a biped, which is exactly why so many 'humanoid' demos quietly have wheels under a skirt.

[gimbalmar65]

@nancy_lewi Here's the relevant bit as far as I understand it: A lot of the current wave genuinely is repackaged 2000s and 2010s research (ZMP walking, whole-body control, DARPA-era grasping) combined with two things that weren't available then: cheap high-torque-density actuators and large-scale learned policies. The safety case for humanoids working near people usually leans on compliant/backdrivable joints plus soft force limits, but there isn't yet a mature, widely-adopted standard equivalent to what industrial arms have had for decades.

[camila.jackson0]

@gimbalmar65 Pretty much this. One thing to add: Most flashy demo reels involve some amount of teleoperation, scripted sequencing, or cherry-picked takes - that's not necessarily dishonest, but it does mean the gap between 'demoed' and 'reliably autonomous in production' is still large. Makes me wonder how this looks in another five years.

[brian.campbell]

Genuine beginner question - A recurring pattern in the field: a capability looks solved in a controlled demo, then takes another 18-24 months of engineering to become boringly reliable in the field. The labor-substitution narrative gets simplified a lot in pitch decks; the more honest framing right now is 'augmenting understaffed, high-turnover roles' rather than wholesale replacement. This whole thread is a good reminder how young this field still is.

[pierregreen]

@brian.campbell To answer this directly: Legs earn their keep specifically where the environment wasn't redesigned for robots - stairs, curbs, uneven yards, cluttered floors - which is a smaller slice of real-world tasks than the marketing suggests.

[choi98]

This raises a question for me - Legs earn their keep specifically where the environment wasn't redesigned for robots - stairs, curbs, uneven yards, cluttered floors - which is a smaller slice of real-world tasks than the marketing suggests.

[ananya.novak]

I see it a little differently. Most flashy demo reels involve some amount of teleoperation, scripted sequencing, or cherry-picked takes - that's not necessarily dishonest, but it does mean the gap between 'demoed' and 'reliably autonomous in production' is still large. The safety case for humanoids working near people usually leans on compliant/backdrivable joints plus soft force limits, but there isn't yet a mature, widely-adopted standard equivalent to what industrial arms have had for decades.

[deborahperez]

Genuine beginner question - A recurring pattern in the field: a capability looks solved in a controlled demo, then takes another 18-24 months of engineering to become boringly reliable in the field.

[carlossanchez]

Small correction on one detail: Most flashy demo reels involve some amount of teleoperation, scripted sequencing, or cherry-picked takes - that's not necessarily dishonest, but it does mean the gap between 'demoed' and 'reliably autonomous in production' is still large.

[joseph_sing]

@carlossanchez Same conclusion I've come to. Also worth noting: Elder care is one of the most emotionally appealing use cases and also one of the hardest, because it demands both physical safety around fragile people and social/communication skill that's still far behind the manipulation hype.