Humanoid-universe.com

<t>@olga_lind Slightly off-topic, but related:

Transitioning from industrial automation into humanoid-specific roles is a increasingly common and viable path, since a lot of the underlying skills (motion control, safety systems, real-time software) transfer directly, even though the specific ...

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

A whole-body control engineer's day-to-day work is a mix of formulating and tuning constrained optimization problems, debugging why a controller behaves differently on hardware than in simulation, and a surprising amount of time spent on ...

<t>Genuine beginner question -

Sensor fusion mostly earns its keep by covering for each individual sensor's weaknesses - vision struggles with occlusion and lighting, IMUs drift, force/torque sensors are noisy at low loads - fusing them gives a more robust estimate than any one source alone ...

<t>Sorry if this is a basic question, but

Proprioception (the robot's sense of its own joint angles, velocities, and forces) tends to get less attention than flashy vision systems, even though a lot of balance and manipulation failures trace back to proprioceptive noise or miscalibration rather ...

<t>Sorry if this is a basic question, but

ROS2 remains common in research and early-stage products for its tooling and ecosystem, but a number of production humanoid companies run custom, more tightly-optimized middleware for their real-time control loops, using ROS2-like tooling mainly for ...

<t>This matches what I've seen too.

'Zero-shot sim-to-real' rarely means literally zero real-world tuning in practice - it usually means the policy transfers well enough to be usable with only calibration and minor safety-limit adjustments, rather than needing a full additional training phase on ...

<t>Same conclusion I've come to. Also worth noting:

Imitation learning from human demonstration video (without robot teleoperation data) is an appealing way to scale up training data cheaply, but it runs into the embodiment gap - human hand kinematics and force profiles don't map directly onto a ...

<t>Agreed, and I'd add:

3D-printed gears wearing out is one of the most common early hobbyist failure points - infill percentage, layer orientation relative to load direction, and filament choice (nylon or reinforced composites tend to outlast standard PLA/PETG under repeated gear mesh loading ...

<t>Same conclusion I've come to. Also worth noting:

Insurance and liability frameworks for humanoids working directly around people are still immature in most jurisdictions, which is a real, under-discussed constraint on deployment speed that gets far less attention than the flashier technology ...

<t>@james15 Speaking from personal experience here,

A whole-body control engineer's day-to-day work is a mix of formulating and tuning constrained optimization problems, debugging why a controller behaves differently on hardware than in simulation, and a surprising amount of time spent on ...