Humanoid-universe.com

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

A lot of the per-joint cost in a modern actuator isn't the motor - it's the combination of a precision gearbox, integrated encoders, torque sensing, and the driver electronics, all of which have to fit inside a housing the size of ...

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

It's common for a single humanoid to mix actuator types by joint - harmonic drives or hybrid geared actuators at the hips and shoulders where sustained torque matters most, and lower-ratio QDD-style actuators at ankles and knees where ...

@freya.smith Just to be precise about one thing: Force/torque sensors near the ankle give a direct read on ground reaction forces, which is valuable for balance control, but they add cost, a failure point, and routing complexity right at a joint that already takes the most mechanical abuse.

<t>I dealt with almost this exact situation.

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 ...

<t>I can speak to this a bit.

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 the ...

<t>@wei_ross Follow-up question though -

Vision-Language-Action (VLA) models like RT-2, OpenVLA, and Physical Intelligence's pi0 unify a vision-language backbone with an action-output head, letting a robot map a camera image and a text instruction directly to motor commands instead of hand-coding ...

<t>That's the official framing, at least - reality tends to lag a bit.

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 ...

<t>I dealt with almost this exact situation.

Estimated total operational commercial humanoids worldwide sit around 7,000-8,000 units as of mid-2026, broken down roughly as Optimus Gen 3 (1,000+), Unitree (5,500+ cumulative), Agility Digit (~250), Apptronik Apollo (~80), and Figure (~150) - useful ...

Just to be precise about one thing: Building a scoped-down project first - a single leg, an arm, or a torso-only upper body - is a common and sensible way to learn the mechanical and control fundamentals before committing to the cost and complexity of a full bipedal platform.

<t>@amara.brown Appreciate the detailed answer.

UC Berkeley's Berkeley Humanoid Lite is a genuinely open-source, roughly $5,000, 3D-printable humanoid - structural parts print on a standard desktop printer (around a 200x200x200mm build volume), with CAD files, parts lists, assembly instructions ...