Humanoid-universe.com

@nicole10 From what I've seen: 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. Makes me wonder how this looks in another five years.

@garcia51 Just to be precise about one thing: 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.

I can speak to this a bit. 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. 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.

That's the official framing, at least - reality tends to lag a bit. 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.

@ssantos I'd frame this differently. 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. 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.

Slight correction, though the overall point stands: 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. 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.

This lines up with my experience. 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.

@barbara.jones Can I ask a dumb follow-up - 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. 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.

@noah_pate Can I ask a dumb follow-up - 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. 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.

@young58 I can speak to this a bit. 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. 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.