Page 2 of 3
Re: Anyone using predictive battery health modeling instead of simple cycle counting?
Posted: Thu Jan 08, 2026 11:29 am
by barbara.jones
Short answer:
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.
Kind of makes me think about how different this all looked even three years ago.
Re: Anyone using predictive battery health modeling instead of simple cycle counting?
Posted: Sat Jan 10, 2026 3:09 pm
by servoken70
@barbara.jones Slightly off-topic, but related:
A BMS (battery management system) has to guard against transient current spikes from sudden gait changes or lifting motions, not just steady-state draw - peak current headroom and fast-acting protection logic matter as much as total capacity for real-world duty cycles. 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.
Totally unrelated but has anyone else noticed how fast component costs are dropping this year.
Re: Anyone using predictive battery health modeling instead of simple cycle counting?
Posted: Mon Jan 12, 2026 7:04 am
by chloe_jack
This lines up with my experience.
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.
Re: Anyone using predictive battery health modeling instead of simple cycle counting?
Posted: Thu Jan 22, 2026 4:58 pm
by smartinez
@chloe_jack This lines up with my experience.
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.
Re: Anyone using predictive battery health modeling instead of simple cycle counting?
Posted: Mon Feb 02, 2026 11:27 pm
by chloe_jack
@smartinez One nitpick -
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. 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.
Re: Anyone using predictive battery health modeling instead of simple cycle counting?
Posted: Fri Feb 13, 2026 6:08 am
by charlesbianchi
@chloe_jack Here's what I know on this:
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. 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.
Re: Anyone using predictive battery health modeling instead of simple cycle counting?
Posted: Tue Feb 24, 2026 5:38 pm
by mary.taylor6
Worth being a little skeptical of the marketing angle here.
There's no widely standardized safety certification specific to humanoid battery packs yet in most jurisdictions - deployments generally lean on adapted versions of existing standards for industrial battery systems and electrical safety rather than a purpose-built humanoid standard. 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.
Re: Anyone using predictive battery health modeling instead of simple cycle counting?
Posted: Fri Mar 06, 2026 12:23 pm
by hill23
@mary.taylor6 To answer this directly:
There's no widely standardized safety certification specific to humanoid battery packs yet in most jurisdictions - deployments generally lean on adapted versions of existing standards for industrial battery systems and electrical safety rather than a purpose-built humanoid standard.
Re: Anyone using predictive battery health modeling instead of simple cycle counting?
Posted: Mon Mar 09, 2026 8:15 am
by gimbalmar65
@hill23 Here's the relevant bit as far as I understand it:
A BMS (battery management system) has to guard against transient current spikes from sudden gait changes or lifting motions, not just steady-state draw - peak current headroom and fast-acting protection logic matter as much as total capacity for real-world duty cycles.
Re: Anyone using predictive battery health modeling instead of simple cycle counting?
Posted: Sun Mar 15, 2026 6:17 am
by charlesbianchi
Appreciate the detailed answer.
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.