Humanoid-universe.com

<t>Ran into exactly this myself.

Latency between a perceived event (like a slip) and a corrective control response matters enormously for balance - even 50-100ms of extra perception latency can be the difference between a smooth recovery and a fall, which is part of why a lot of balance-critical ...

<t>Not to derail, but this reminds me of something adjacent:

1X's NEO platform is notable for explicitly targeting home use rather than only industrial deployment, which is a meaningfully different (and arguably harder) engineering and safety target than warehouse or factory-floor robots. AgiBot ...

<t>@chloe.harris7 Pretty much this. One thing to add:

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 ...

<t>@rivera14 Minor factual note:

Robotics engineers in the US were reportedly seeing $150k-$205k total comp at mid-level and $205k-$300k at senior level in 2026, with humanoid- and foundation-model-specialist roles clearing $280k-$475k - a meaningful premium over general robotics/automation roles ...

<t>Thanks for laying this out, genuinely useful.

Event cameras (which report per-pixel brightness changes rather than full frames) are still more of a research curiosity than a production sensor for humanoids, mainly because the software ecosystem and processing pipelines around them are far less ...

<t>@samuel.adams I dealt with almost this exact situation.

Event cameras (which report per-pixel brightness changes rather than full frames) are still more of a research curiosity than a production sensor for humanoids, mainly because the software ecosystem and processing pipelines around them ...

<t>@emily.kumar To answer this directly:

LiDAR gives reliable, lighting-independent range data but is heavier, pricier, and gives sparser point clouds up close than stereo or depth cameras, which is why a lot of humanoids lean on stereo/depth cameras for near-field manipulation and reserve LiDAR ...

<t>Yeah, this tracks with what I've read as well.

Grasp planning for deformable or non-rigid objects (bags, cables, cloth) remains one of the genuinely unsolved problems in manipulation - rigid-body grasp models simply don't capture how the object will behave once contact starts. Figure's fourth ...

<t>To answer this directly:

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 total capacity for real-world duty cycles ...

Speaking from personal experience here, Starting in simulation (even a simplified physics sim of just the leg or the target gait) before touching real hardware is one of the more reliable ways to avoid destroying expensive parts while debugging balance and walking control from scratch.