Humanoid-universe.com

@dchen This lines up with my experience. Open-source humanoid projects matter less for out-competing the well-funded players and more for keeping the barrier to entry low enough that new ideas and new people can actually get into the field. 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.

I'd push back on this a bit. A genuinely underrated bottleneck is neither hardware nor pure ML - it's the unglamorous integration work of making perception, planning, and control agree with each other reliably for eight-hour shifts.

Follow-up question though - Open-source humanoid projects matter less for out-competing the well-funded players and more for keeping the barrier to entry low enough that new ideas and new people can actually get into the field. The uncanny valley matters a lot less in a warehouse than in a living room - nobody cares if a picking robot looks a little stiff, but a home-companion robot with a slightly-off gait reads as unsettling fast.

Sorry if this is a basic question, but 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.

@ramirez77 Thanks for laying this out, genuinely useful. The uncanny valley matters a lot less in a warehouse than in a living room - nobody cares if a picking robot looks a little stiff, but a home-companion robot with a slightly-off gait reads as unsettling fast.

@cynthia.muller I dealt with almost this exact situation. A genuinely underrated bottleneck is neither hardware nor pure ML - it's the unglamorous integration work of making perception, planning, and control agree with each other reliably for eight-hour shifts. 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. Reminds me a bit of the early drone hobbyist scene, honestly.

Just to be precise about one thing: 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.

@barbara50 This raises a question for me - A genuinely underrated bottleneck is neither hardware nor pure ML - it's the unglamorous integration work of making perception, planning, and control agree with each other reliably for eight-hour shifts. Kind of makes me think about how different this all looked even three years ago.

This lines up with my experience. 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. The 'humanoid' form factor mostly wins on infrastructure compatibility, not raw efficiency - stairs, doors, and tools were all built for a human body plan, so a legged, two-armed robot slots into existing spaces without retrofitting them.