Compare humanoid robot actuator options and estimate output per mass for an initial supplier RFQ.
Tool
Calculate output per actuator mass and an estimated peak request. Use both as an RFQ starting point for supplier review.
Live output per mass: 32.1 Nm/kg
Result
This tool calculates continuous output per actuator mass and a peak output request. The arithmetic does not establish whether a specific actuator fits your robot.
Candidate lane from selected inputs
Awaiting inputs
For procurement, a humanoid robot actuator is not only a motor. It is the motion stack that can be installed into a humanoid joint: motor, reducer or screw, encoder, brake when needed, driver, harness, thermal path, mechanical interface, and validation evidence. For the broader sourcing sequence, see the humanoid actuator procurement guide.
The preflight gives a candidate lane from your selections, not a verified fit. This table explains when each lane may suit a program, what evidence to request, and where integration trade-offs appear during prototype or pilot builds.
| Actuator lane | Best fit | Evidence to request | Procurement caution |
|---|---|---|---|
| Integrated rotary joint module | Rotary joints where a compact package, high output torque, and integrated sensing or drive electronics are priorities | continuous torque, peak torque duration, reducer backlash, brake option, encoder resolution, thermal mounting conditions | Peak torque alone does not establish duty-cycle fit. Check continuous output, speed, heat path, backlash, friction, wiring, and the joint’s impact requirements. |
| QDD or low-ratio backdrivable module | Force-control joints, research platforms, compliant contact | gear ratio, rotor inertia, backdrive torque, torque-sensing or current-control evidence, impact tests, controller interface | Lower ratios can improve backdrivability but trade against output torque and packaging. Compare the complete motor, transmission, control, and load case. |
| Frameless torque motor stack | Teams with their own reducer, housing, cooling, and electronics | stator/rotor drawing, winding option, magnet grade, torque constant, insulation class, encoder compatibility | This lane shifts integration work from the supplier module to the robot mechanical and electronics team. |
| Linear actuator or screw-driven linkage | Hands, fingers, knees with linkages, compact stroke mechanisms | continuous and peak force, stroke, speed, linkage geometry, side-load, duty cycle, life estimate, backlash, sealing, limit detection | Translate actuator force to joint torque using the actual moment arm and geometry. Count linkages, guides, sensors, and packaging in the mass budget. |
Published September 24, 2026; time-sensitive information was reviewed October 4, 2026. The sources do not replace supplier test data, but they explain which actuator claims should be verified before samples are approved. For mass-normalized design context, read the humanoid actuator power-density guide.
Published April 17, 2024; reviewed October 4, 2026
Documents Boston Dynamics’ move to an all-electric Atlas platform. It does not disclose actuator torque classes or supplier-level module specifications.
Open sourceReviewed October 4, 2026
Provides Tesla’s public Optimus program overview, but no actuator torque, force, transmission, or module specifications. Treat detailed architecture figures as undisclosed unless Tesla publishes testable data.
Open sourcePublished January 27, 2026; reviewed October 4, 2026
Figure describes a neural system connecting onboard sensors to robot actuators. The announcement does not specify low-level servo bandwidth, bus latency, or actuator hardware requirements.
Open sourceReviewed October 4, 2026
Apptronik says its patented actuator platform is designed for 90%+ energy efficiency. This is a company-stated design claim; the page does not provide test conditions or an independent validation.
Open sourcePublished 2020; reviewed October 4, 2026
Reports one low-ratio QDD design with measured backdrive torque and control bandwidth. Those results describe the study’s exoskeleton and test conditions, not a universal humanoid actuator specification.
Open sourcePublished 2021; reviewed October 4, 2026
Analyzes the relationship between rotor inertia and transmission ratio for a studied actuator design. The ratio is one factor in backdrivability; it is not a stand-alone impact-failure verdict.
Open source2026 edition; reviewed October 4, 2026
Provides current rare-earth production and supply context relevant to programs that specify rare-earth permanent magnets. It is not an actuator-specific sourcing forecast.
Open sourcePublished 2026; reviewed October 4, 2026
Estimates actuators at 40–60% of humanoid hardware BOM in its analysis. The share is an industry estimate that can vary by robot design and accounting boundary.
Open sourceThese points help frame a supplier review. Industry estimates and research results have different boundaries; none substitutes for the selected actuator’s datasheet, test report, and joint-level validation. Reviewed October 4, 2026.
A 2026 McKinsey analysis estimates actuators at 40%–60% of humanoid hardware BOM. This is an industry estimate, not a universal per-platform figure; BOM boundaries and robot architectures vary.
Read the McKinsey analysisA peak rating does not establish continuous duty capability. Ask for the continuous torque or force envelope at the intended speed, voltage, ambient condition, mounting surface, and duty cycle, plus the thermal limits used in that test.
Lower transmission ratios can reduce reflected rotor inertia and improve backdrivability, while reducing output torque for a given motor. A published legged-robot design analysis explains the relationship; impact response still depends on the complete joint, friction, compliance, controller, and load case.
Read the actuation design paperFigure says Helix 02 connects onboard sensors to actuators through a unified neural system. The announcement does not disclose servo bandwidth, bus latency, or actuator hardware, so request those interface requirements for the specific platform.
Read Figure’s Helix 02 announcementApptronik says its Apollo 2 actuator platform is designed for 90%+ energy efficiency, but the public page does not explain the measurement boundary or provide independent validation. Confirm the operating point, load, controller, and thermal conditions before comparing efficiency claims.
Read Apptronik’s Apollo 2 overviewThe checker screens the first architecture path. It cannot certify final actuator life, impact tolerance, sealing, controller stability, or robot-level safety. Those need sample tests and supplier data.
| Risk | Evidence | Action |
|---|---|---|
| Thermal overpromise & Throttling | Torque-speed curve, continuous operating region, winding temperature limit, mounting plate condition | Request continuous torque derating data. Humanoid joints often suffer thermal throttling because compact limbs lack active air/water cooling. |
| Wrong actuator lane | Joint zone, output type, backdrivability need, mass budget, cable path | Use the RFQ preflight and compare rotary, QDD, frameless, and linear lanes before RFQ freeze. |
| Integration delay | Interface drawing, firmware protocol, encoder format, brake wiring, connector revision | Keep the first sample close to a catalog baseline and push custom work after validation. |
| Supply exposure | Magnet grade, reducer sourcing, encoder availability, controller component lead time | Ask for alternates and substitution rules when moving from prototype to pilot quantity. |
| Impact and backdrive mismatch | Joint load cases, transmission behavior, compliance, and repeated impact test data | Do not infer failure or suitability from gear ratio alone. Validate the chosen actuator and joint structure against the robot’s measured load cases. |
A useful RFQ for actuator for humanoid robots sourcing should make the supplier prove fit against the joint duty, not only against a model name.
joint zone, continuous and peak torque or force, output speed or stroke, duty cycle, impact or holding events
outer diameter, axial length, mass target, flange, output shaft, hollow shaft, cable exit, drawing revision
bus voltage, controller location, protocol, encoder format, brake logic, connector, harness length
No. “Actuator humanoid robot” is an alternate word order for the broad humanoid robot actuator sourcing query, not a distinct actuator architecture. It describes the same selection task covered here: matching rotary, QDD, frameless, or linear actuator options to joint loads, package, controls, and duty cycle. This page is the single canonical guide for both phrasings.
For a rotary module, ask for continuous torque with test temperature, mounting condition, voltage, speed point, and duration. For a linear path, ask for continuous force across stroke and speed. In either case, confirm the peak duration and test conditions.
Consider a low-ratio Quasi-Direct Drive (QDD) design when backdrivability and torque-control bandwidth are important. Research reports those properties for specific tested designs, but performance depends on the motor, transmission, friction, and controller. Compare them with the output torque and package of a higher-ratio option using the joint’s test conditions.
A linear actuator can suit a joint or mechanism designed around stroke and linkage geometry. Convert its force to joint torque with the perpendicular moment arm, then check speed, side-load, duty cycle, and impact behavior for that specific mechanism.
A 2026 McKinsey analysis estimates actuators at 40% to 60% of humanoid hardware BOM, while the actual share varies by platform and accounting boundary. Treat it as an industry estimate, not a quote for a particular robot.
Include joint zone, rotary torque-speed or linear force-stroke duty, mass envelope, output interface, bus voltage, protocol, encoder, brake need, harness exit, drawing revision, quantity, and target validation date.
Usually no. Hip, knee, ankle, shoulder, wrist, hand, torso, and neck joints have different torque, speed, mass, wiring, brake, and impact constraints. Use one architecture family where possible, but qualify each joint zone separately.
A torque number is weak when it lacks speed point, duration, winding temperature, ambient condition, mounting plate, bus voltage, and cooling assumptions. Ask for the continuous operating region, not only one headline value.
Keep the first sample close to catalog form when the team still needs to validate torque-speed behavior, thermal margin, encoder quality, backlash, brake logic, or control stability. Move custom interfaces after baseline evidence is clear.
For hip, knee, ankle, and foot joints, request the continuous torque-speed envelope, peak duration, thermal test conditions, backlash, sealing assumptions, brake behavior, cable routing, and repeated-load or impact evidence for the intended duty cycle.
Mark the value as provisional, ask for test conditions, and run a sample plan before freezing the robot-level design. If public evidence is thin, compare multiple suppliers and request controlled drawings plus torque-speed curves.
Send the joint map, torque-speed or force-stroke window, mass envelope, voltage, output type, and intended duty cycle to suppliers. Ask for a sample review before committing to a custom module.
Figure describes Helix 02 as connecting onboard sensors to actuators through a unified neural system. Its public announcement does not specify servo bandwidth, bus latency, or actuator hardware, so request those interface requirements for the specific platform rather than inferring them from the AI architecture.
Include the preflight values, joint map, envelope drawing, and duty-cycle assumptions. A practical early-program sequence is a catalog sample, evidence review, then custom interface decisions.
Inquiry Email
Subject: Humanoid robot actuator RFQ preflight and sample review
Include the preflight output, joint map, interface drawing, duty cycle, and target sample date.
Instant Chat
+8618857971991
Best for quick model-fit questions before a full RFQ email.
