Humanoid-universe.com

<t>I don't think that's quite right, for what it's worth.

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. 'General purpose' in 2026 mostly means ...

<t>I'd take that specific number with a grain of salt, honestly.

Motor cogging torque (the 'notchy' feel from magnet-to-slot interactions) shows up as small periodic torque ripple that can translate into visible joint jitter at low speeds - it's usually mitigated with skewed magnets, better ...

<t>@jchen Here's what I know on this:

A field-deployment or reliability engineer's day-to-day work leans much more toward diagnosing real-world failure patterns, managing spare-parts logistics, and working directly with the customer site than toward algorithm development - a genuinely different ...

<t>This is exactly the kind of context I was looking for.

For dynamic walking and recovery, joint control bandwidth in the tens of Hz range is typically necessary to react to a stumble before the center of mass gets too far outside the support polygon.

Makes me wonder how this looks in another ...

<t>Not sure I fully agree here.

Isaac Lab (the successor to Isaac Gym) is widely used for large-scale parallel RL training thanks to GPU-accelerated physics, while MuJoCo is often used as a secondary 'sim-to-sim' validation step because its contact dynamics are generally considered more realistic ...

<t>@deborah59 I'd push back on this a bit.

The humanoid robot market is estimated at roughly $5.41 billion in 2026, with projections reaching around $50 billion by 2035 (about 28% CAGR) - a genuinely huge projected growth curve, and also exactly the kind of number worth treating with healthy ...

<t>@betty.king Not sure I fully agree here.

A strong, well-documented personal project (even a modest DIY build or a solid simulation-based RL project) reportedly carries real weight in hiring for this field, partly because the field is young enough that a demonstrated hands-on track record can ...

@ssantos I don't think that's quite right, for what it's worth. Backdrivability is the property that lets an external force move a joint without destroying the gearbox or the motor - it's central to both safe human-robot contact and to letting a leg comply naturally when the robot stumbles.

<t>@deborah59 I'll believe the stronger version of that claim when it's independently verified.

AgiBot reportedly sold around 5,168 units, putting it roughly in the same commercial volume range as Unitree among Chinese manufacturers, and worth watching alongside the more internationally ...

<t>@hill23 I don't think that's quite right, for what it's worth.

A BMS (battery management system) has to guard against transient current spikes from sudden gait changes or lifting motions, not just steady-state draw - peak current headroom and fast-acting protection logic matter as much as ...