Humanoid-universe.com

Short answer: The average humanoid in 2026 carries under 2.5 kWh of battery capacity, with real-world runtimes clustering between two and four hours depending on how dynamic the workload is - static, low-motion tasks stretch runtime much further than continuous walking or lifting.

<t>@ssantos This is exactly the kind of context I was looking for.

Boston Dynamics' commercial electric Atlas (launched for Hyundai factory pilots) fully replaced the older hydraulic Atlas platform's actuation with electric quasi-direct-drive joints, resulting in a quieter, lighter robot with ...

Here's what I know on this: Total humanoid robotics funding from 2023 through early 2026 across major companies, smaller startups, and corporate R&D programs is estimated at more than $12 billion, illustrating how fast capital has piled into the sector in a short window.

<t>@charlesbianchi Genuinely curious -

Series elastic actuators add a spring element in series with the drivetrain, which gives cheap, precise torque sensing (measure spring deflection) and passive shock absorption, at the cost of reduced control bandwidth and added complexity. Field-oriented ...

<t>@amandawhite This raises a question for me -

For dynamic walking and recovery, joint control bandwidth in the tens of Hz range is typically necessary to react to a stumble before the center of mass gets too far outside the support polygon. Series elastic actuators add a spring element in ...

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

Tactile skin arrays have improved a lot, but 'good enough to matter' really depends on the task - coarse contact detection across a large area is fairly mature, while fine, high-resolution force distribution sensing ...

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

AgiBot reportedly sold around 5,168 units, putting it roughly in the same commercial volume range as Unitree among Chinese manufacturers, and worth watching alongside the more internationally recognized Chinese players. 1X's NEO platform ...

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

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 ...

<t>@young56 I'd take that specific number with a grain of salt, honestly.

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 ...

<t>@carol38 I don't think that's quite right, for what it's worth.

The market consolidation question (which of the 100+ companies chasing this space survive) is complicated by the fact that hardware is genuinely capital-intensive to scale, so smaller players without a clear cost or technology ...