Humanoid-universe.com

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

IMU drift over time (bias instability) is usually the real culprit behind slowly diverging state estimates, not noise - it's typically handled with sensor fusion against other references (visual odometry, joint kinematics) rather than trying to eliminate drift at ...

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

Balance-recovery controllers are usually evaluated with push-recovery tests (a known, repeatable lateral push) in demos, but real-world robustness also depends on recovering from unstructured events like uneven flooring, unexpected contact, or a dropped ...

@lbianchi Counterpoint: Palm sensing gets less attention than fingertip sensing, but a lot of power grasps (holding a box, a tool handle) rely more on palm and lateral finger contact than fingertip contact, so under-sensing the palm can leave a real blind spot in grasp confidence.

<t>+1 to this. Worth adding:

The Berkeley Humanoid Lite stands about 1 meter tall and weighs roughly 16 kg, which is a genuinely reasonable target size for a first serious hobbyist build - big enough to be a real bipedal platform, small enough to not need industrial-scale actuators or a huge ...

<t>@garcia51 This lines up with my experience.

Anti-backlash techniques in production actuators range from mechanical preloading (spring-loaded gear meshes) to purely software compensation that models and corrects for known backlash in the control loop.

Totally unrelated but has anyone else ...

@nancy_lewi Minor factual note: Unitree's Dex3-1 dexterous hand packs around 33 pressure/tactile sensors per hand across the fingers and palm, capable of sensing pressure roughly in the 10g-2500g range - a useful reference point for what 'production tactile sensing' looks like right now.

<t>Respectfully, I think this undersells it a bit.

A lot of the manipulation shown in production demos still leans heavily on teleoperation, particularly for anything involving fine force control or novel objects - autonomous grasp success rates on genuinely unstructured, previously-unseen ...

<t>One nitpick -

There's no widely standardized safety certification specific to humanoid battery packs yet in most jurisdictions - deployments generally lean on adapted versions of existing standards for industrial battery systems and electrical safety rather than a purpose-built humanoid ...

One nitpick - DC-DC conversion losses across all the individual actuator drivers add up across a whole robot - it's a less glamorous efficiency question than battery chemistry, but power electronics efficiency meaningfully affects real-world runtime too.

<t>@robertmiller Slight correction, though the overall point stands:

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 ...