Humanoid-universe.com

@karen.chen3 Yeah, this tracks with what I've read as well. Anti-backlash techniques in production actuators range from mechanical preloading (spring-loaded gear meshes) to purely software compensation that models and corrects for known backlash in the control loop. 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. Kind of makes me think about how different this all looked even three years ago.

@dchen Not sure I fully agree here. 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.

@aliu Minor factual note: 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. 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.

@charlesbianchi Not sure I fully agree here. 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.

Small correction on one detail: 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.

From hands-on experience, 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. Makes me wonder how this looks in another five years.

@brenda52 Here's what I know on this: 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. 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 backdrivability and impact tolerance matter more.

@joseph.robinson Thanks for laying this out, genuinely useful. 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. Field-oriented control (FOC) tuning directly affects how smooth torque output feels - poorly tuned current loops show up as audible whine and jerky low-speed motion, while well-tuned FOC can make even a geared actuator feel fairly fluid.

I can speak to this a bit. Anti-backlash techniques in production actuators range from mechanical preloading (spring-loaded gear meshes) to purely software compensation that models and corrects for known backlash in the control loop.

@emilyperez I dealt with almost this exact situation. 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.