Humanoid-universe.com

@jlefebvre Follow-up question though - Figure AI's robot ran on the BMW Spartanburg production line for roughly eleven months, contributing to more than 30,000 vehicle production cycles, ahead of an announced follow-on deployment at BMW's Leipzig plant.

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

Unitree's G1 humanoid starts at roughly $16,000, a price point well below full-size US-built humanoid platforms, and the company reportedly sold around 5,500 units - a meaningful data point in how aggressively Chinese manufacturers are pushing the ...

<t>@olga24 Yeah, this tracks with what I've read as well.

The common academic path into this field is a master's or conversion course in robotics or machine learning, followed by an internship or research role at a known lab or company - a PhD is common but increasingly not strictly required for ...

<t>Genuinely curious -

Most flashy demo reels involve some amount of teleoperation, scripted sequencing, or cherry-picked takes - that's not necessarily dishonest, but it does mean the gap between 'demoed' and 'reliably autonomous in production' is still large. Automotive plants ended up as the ...

This matches what I've seen too. 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.

<t>@jwang Here's the relevant bit as far as I understand it:

Torque sensing is frequently integrated directly into the actuator housing via strain gauges near the output flange or spring element, rather than bolted on as an external sensor, to save weight and reduce noise from mechanical slop ...

<t>Tangent, but worth mentioning:

Model predictive control (MPC) is still very much alive in production humanoids, often working alongside or underneath learned policies - MPC handles short-horizon dynamically-consistent trajectory optimization while learned components handle perception, task ...

<t>@charlesbianchi Ran into exactly this myself.

Vision-based grasp confidence estimation (predicting success before attempting a grasp) and tactile-based confirmation (confirming after contact) are complementary rather than competing - vision helps you choose a grasp, tactile tells you if it ...

<t>@ramirez77 Pretty much this. One thing to add:

A lot of hobbyists underestimate how much of the real difficulty in a DIY humanoid build is software and tuning rather than mechanical assembly - getting a robot to physically stand up is a much smaller fraction of the total project time than ...

<t>Here's the relevant bit as far as I understand it:

The common academic path into this field is a master's or conversion course in robotics or machine learning, followed by an internship or research role at a known lab or company - a PhD is common but increasingly not strictly required for ...