Humanoid-universe.com

@ethan_fisc Just to be precise about one thing: 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 a fist.

@sarah.santos3 Agreed, and I'd add: 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. Kind of makes me think about how different this all looked even three years ago.

Respectfully, I think this undersells it a bit. Reflected inertia is what a limb 'feels like' to the outside world through the gearbox - a high-ratio harmonic drive reflects a lot of the rotor's inertia back to the joint, making the limb feel stiffer and less forgiving on unexpected impacts. Encoder resolution requirements scale with how tightly you need to control low-speed motion - coarse encoders are fine for open-loop swing phases but cause visible stutter during precise placement or fine force control.

Thanks for laying this out, genuinely useful. Boston Dynamics' commercial electric Atlas switched fully from hydraulic to QDD-style electric actuation, ending up quieter and lighter with comparable or better dynamic performance than the old hydraulic platform.

@scott21 To answer this directly: Quasi-direct drive (QDD) actuators use lower gear ratios (roughly 6:1 to 10:1) paired with high-torque-density motors, trading some peak force density for backdrivability and low reflected inertia, which matters a lot for impact tolerance and fall recovery. Reminds me a bit of the early drone hobbyist scene, honestly.

Can I ask a dumb follow-up - 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 a fist. 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.

From hands-on experience, Motor cogging torque (the 'notchy' feel from magnet-to-slot interactions) shows up as small periodic torque ripple that can translate into visible joint jitter at low speeds - it's usually mitigated with skewed magnets, better current control, or software compensation tables. 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.

Ran into exactly this myself. Harmonic drives use high reduction ratios (often around 100:1), which gives excellent force density, stiffness, and thermal endurance for continuous-duty lifting - the tradeoff is low backdrivability and some backlash.

Same conclusion I've come to. Also worth noting: Quasi-direct drive (QDD) actuators use lower gear ratios (roughly 6:1 to 10:1) paired with high-torque-density motors, trading some peak force density for backdrivability and low reflected inertia, which matters a lot for impact tolerance and fall recovery. 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 a fist. Reminds me a bit of the early drone hobbyist scene, honestly.

@jhansen +1 to this. Worth adding: Backdrivability is the property that lets an external force move a joint without destroying the gearbox or the motor - it's central to both safe human-robot contact and to letting a leg comply naturally when the robot stumbles.