
UBTECH Robotics
UBTECH Walker S1
- Autonomy
- IIAssisted
- Pre-release
- 75/100Promising
- Readiness
- Not assessed
- Price
- Not tracked

UBTECH Robotics

Zeroth
Up to three
All humanoid robots. Every figure below is placed against the whole class, so a gap can be read against how much the class itself varies.
The conditions each robot was assessed against, side by side. Rows marked in gold are where these machines genuinely differ.
| Condition | UBTECH Walker S1 | Zeroth Bridge |
|---|---|---|
| Where it operates | ||
| Home / residentialthey differ | PoorNot available for home use; industrial factory deployment only. | DependsSmall enough for a home at 88 cm and 13 kg, but it ships with motion routines, not household tasks. |
| Office / retailthey differ | PoorRequires automotive-tier manufacturing infrastructure; not applicable to general commercial environments. | DependsZeroth sells it to universities, research teams and developers; no commercial deployment is documented. |
| Warehouse / factorythey differ | GoodDesigned for automotive assembly and electronics manufacturing with on-site integration teams. | PoorA 2 kg gripper payload and 10 N·m joints are sized for development benches, not industrial work. |
| Primary tasks | ||
| Household chores | PoorNo consumer or general-purpose robotic task support; industrial material handling only. | PoorBuilt-in skills are walking, squatting, dancing and backflips; no chore routine appears in any source reviewed. |
| Social / carethey differ | PoorTeleoperation dependency and factory-only deployment exclude social or service-robot use cases. | DependsA microphone array and touch sensing are listed, but no conversational software is described for Bridge. |
| Specialized job | GoodSpecialized industrial logistics and assembly support are the core application domain. | GoodAn open SDK, motion-control APIs and teleoperation let developers build their own specialized skills. |
| Supervision needs | ||
| Fully autonomous | PoorTeleoperation required for task transitions; unattended autonomous operation not supported. | PoorControl is replayed motion or live teleoperation; no unattended task operation is documented. |
| With oversightthey differ | GoodDesigned for on-site technician and operator supervision; teleoperation available as primary backup mode. | DependsFall recovery and emergency-stop behavior are undocumented, so an operator should stay close during dynamic routines. |
| Teleoperated | GoodIndustrial factory pilots with integration teams are the current and intended deployment model. | GoodTele_Bridge gives a developer real-time whole-body control with VR support, the mode Zeroth designed it for. |
| Timeline | ||
| Ready today | PoorNot consumer-ready or generally available; industrial pilots only. | PoorFirst-batch units are a pre-order with no delivery date on Zeroth's store. |
| Near-term (1–2 yrs)they differ | GoodActive deployments in tier-one automotive; scaling timeline and broader industrial applicability TBD. | DependsOrders are open in the US and China, but neither channel states when units deliver. |
| Research phasethey differ | PoorProduction-focused platform; academic research support not documented. | GoodPitched at research teams, with SDK beta and simulation access starting 14 Sep 2026. |
A robot being poor for a condition is a fact about fit, not a fault. “Depends” means the record names a limit worth reading, not that the answer is unknown.
None of these has shipped, so they are assessed on track record, engineering plausibility and how the demonstrations match the claims.
Never averaged into it. These describe how much the maker has disclosed, not what the machine does.
| UBTECH Walker S1 | Zeroth Bridge | |
|---|---|---|
| ReadinessShip-date specificity, pricing transparency, distribution and regulatory status. Published beside the number; never averaged in. | 56/100 | 60/100 |
| DisclosureHow much of the product is disclosed. Higher means fewer fundamental unknowns remain. Published beside the number; never averaged in. | 85/100 | 45/100 |
A number only means something next to the spread it sits in. Each track is the real range across every classified robot in the class, with the median marked.
Not compared, because fewer than two of these robots carry a published figure: Price, Runtime, Charge time, Noise.
Written on each record, and the only thing here every robot on the site carries.
What each design gives up to be good at what it is good at.
Walker S1 runs its pickup routes on its own; the moment a task transitions mid-cycle, an on-site operator or an automated trigger has to step in.
UBTECH reports early positive throughput feedback from the BYD, Foxconn, and Zeekr pilots, but the production metrics behind that feedback remain proprietary and unpublished.
BrainNet coordinates multiple units in parallel, so a pilot’s real throughput depends on fleet size and facility layout, neither of which UBTECH prices publicly.
Three Walker generations preceded the S1 since 2018, yet UBTECH still publishes no price for even a small 3-5 unit pilot deployment.
$3,999 buys a biped with a published joint map and no published runtime.
Because control is replayed motion or live teleoperation, every new behavior is something a developer has to build.
Two weights on one page: about 10 kg in the header, about 13 kg in the spec table.
Stated by the record itself. A robot being wrong for a household is a fact about fit, not a fault.
The upkeep ownership hands back to you, whatever the autonomy level says.
Classifications rest on different depths of evidence. A pre-release assessment and a verified one are not the same kind of claim.
| Robot | Evidence status | Sources reviewed | Last assessed |
|---|---|---|---|
| UBTECH Walker S1 | Not Consumer-Ready | 6 | Aug 2026 |
| Zeroth Bridge | Pre-Release | 6 | Sep 2026 |
Evidence status counts the sources behind a classification, not their kind. A high count can be maker documentation and price coverage, so read it as how much was reviewed rather than as independent testing. How we weigh evidence.
The full recordUBTECH Walker S1Specifications, evidence, the Fit Check in full, and every tracked change.
The full recordZeroth BridgeSpecifications, evidence, the Fit Check in full, and every tracked change.Robovations classifies robots; it does not rank them. Nothing on this page is a recommendation, and no manufacturer influences a classification or its placement here.
Comparing across classes is allowed — the page will switch to per-class positioning and tell you it has.