Anyone tracking real watt-hour cost per completed task as an efficiency KPI?

[rao91]

Been lurking on this one for a while, finally decided to ask. Thermal margin in a densely packed humanoid chassis is often the real limiting factor on sustained performance, not raw motor power - actuators get thermally throttled well before they'd hit their absolute torque limits, especially during repeated high-load cycles like continuous lifting. Tesla's Optimus Gen 2 reportedly carries roughly a 2.3 kWh pack and manages about two hours of dynamic work, while Unitree's H1 runs a smaller 0.864 kWh pack good for under four hours of largely static operation - a useful illustration of how battery size and workload type both drive runtime. Happy to be told I'm wrong on any of this.

[choi98]

@rao91 From what I've seen: Idle/standing power draw is often surprisingly close to a meaningful fraction of active walking power draw once you account for onboard compute, sensors, and balance-holding torque - 'doing nothing' still costs real energy on a humanoid.

[jonathan_tana]

@choi98 This raises a question for me - Best-in-class lithium-ion cells used in humanoids are currently landing around 280-300 Wh/kg, which is respectable but still leaves battery mass as one of the largest single contributors to total robot weight.

[scott.novikova7]

@jonathan_tana Not to derail, but this reminds me of something adjacent: Hot-swappable battery packs solve the runtime bottleneck for continuous operations (like a 24/7 warehouse shift) without needing a much bigger, heavier pack, but they add mechanical complexity, a failure-prone connector interface, and logistics overhead for managing spare packs. Solid-state battery claims from platforms like XPeng's IRON, GAC's GoMate, and EngineAI's T800 are genuinely promising on paper for energy density and safety margins, but independent, large-scale field validation of those runtime claims is still fairly limited as of 2026 - it's real progress, not yet fully proven at scale.

[betty.king]

New to this, so forgive me if this is obvious - Distributed power architectures (multiple smaller packs or local capacitor buffering near high-draw actuators) can reduce peak current demands on the main bus and improve fault isolation, at the cost of added complexity versus a single central pack.

[byang]

I dealt with almost this exact situation. Battery placement (torso-centered vs backpack vs distributed through the limbs) is a real tradeoff between center-of-mass/balance considerations and thermal/cooling access - a torso-centered pack helps balance but is harder to cool than a more exposed backpack placement.

[ivan22]

Small correction on one detail: Regenerative braking on humanoid joints can recover some energy during deceleration phases of walking, but the actual energy recovered is modest compared to a vehicle, since humanoid joints don't sustain the same continuous high-speed rotation that makes regen worthwhile in EVs.

[tmartin]

@ivan22 This matches what I've seen too. Fast charging accelerates capacity fade over repeated cycles, so fleet operators generally have to choose between minimizing downtime (fast charging) and maximizing pack lifespan (slower charging or swap-based approaches) rather than getting both for free.

[timothy.roberts2]

@tmartin Yeah, this tracks with what I've read as well. Higher-voltage power architectures reduce resistive losses and current draw through the wiring harness for a given power level, which is part of why some newer platforms are moving away from lower-voltage packs as total system power demand climbs.

[shill]

Just to be precise about one thing: 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. Totally unrelated but has anyone else noticed how fast component costs are dropping this year.