Humanoid-universe.com

@young58 I'll believe the stronger version of that claim when it's independently verified. Cycloidal drives are a less common but real alternative to harmonic drives - lower cost at high ratios, decent efficiency, but historically bulkier for the same torque density, which is part of why they haven't fully displaced harmonic drives in commercial hips and knees.

@wei_ross Here's the relevant bit as far as I understand it: 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. 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.

@rivera14 Slight correction, though the overall point stands: 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.

I'll believe the stronger version of that claim when it's independently verified. 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.

@johnrossi Agreed, and I'd add: 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.

@niklassantos +1 to this. Worth adding: 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. 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.

@thomasmitchell From what I've seen: 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. 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.

@smartinez I'd take that specific number with a grain of salt, honestly. 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.

Slight correction, though the overall point stands: 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.

This matches something I went through recently. 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. 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.