DYNA Robotics
DYNA 2.1
- Autonomy
- IIIConditional
- Pre-release
- 74/100Promising
- Readiness
- Not assessed
- Price
- Not tracked
ComparisonDYNA 2.1 and Digit 5
Agility Robotics
Digit 5
- Autonomy
- IIIConditional
- Pre-release
- 71/100Promising
- Readiness
- Not assessed
- Price
- Not tracked
Up to three
Autonomy Ladder
- IManual
- IIAssisted
- IIIConditional
- IVEnvironmental
- VGeneralized
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.
Where each one suits you.
The conditions each robot was assessed against, side by side. Rows marked in gold are where these machines genuinely differ.
| Condition | DYNA 2.1 | Digit 5 |
|---|---|---|
| Where it operates | ||
| Home / residential | PoorSold only as a commercial deployment to businesses; no consumer purchase path or home installation exists. | PoorEnterprise-only industrial hardware and a $150,000+ build cost rule out any home deployment path. |
| Office / retailthey differ | GoodPurpose-built for hotels, laundromats and restaurants; already running paid shifts at named sites. | DependsDocumented deployments are warehouse and manufacturing floors; no retail, office or public-facing pilot has been reported. |
| Warehouse / factory | GoodMaker also cites warehouse and fulfillment deployments with throughput and placement figures published. | GoodMatches its documented customer base: GXO, Amazon, Schaeffler and Toyota all run warehouse or manufacturing floors. |
| Primary tasks | ||
| Household choresthey differ | DependsHandles chore-like tasks such as folding and shelving, but only within a staffed commercial workflow, not general household chores. | PoorNo household task set exists; every documented deployment is warehouse material handling, not domestic chores. |
| Social / care | PoorNo conversational, companionship or social-interaction capability is documented for this robot. | PoorNo social, service or customer-facing use case has been documented for this platform. |
| Specialized job | GoodBuilt around one long-horizon commercial workflow at a time. Laundry, housekeeping or food service. Not general-purpose tasks. | GoodBox and tote picking, sorting and transport is the entire documented task envelope, now with a 50 lb repeatable lift. |
| Supervision needs | ||
| Fully autonomousthey differ | DependsRuns unattended for a shift, but the maker's own Mean Time Between Interventions metric assumes periodic human help. | PoorNo unsupervised deployment is documented; every customer site pairs it with trained operators for oversight. |
| With oversight | GoodMatches its documented deployment: autonomous operation with on-site staff present at each launch site. | GoodMatches the documented model: dedicated facility staff handle exceptions, safety zones and task reassignment. |
| Teleoperated | PoorNo teleoperation or remote-pilot mode is documented; the system is designed to run without a human driving it. | PoorDigit 5 runs pre-trained autonomous sequences; it is not a teleoperated or directly piloted platform. |
| Timeline | ||
| Ready todaythey differ | GoodAlready deployed and doing paid commercial work at hotels, laundromats and restaurants as of this launch. | PoorNo unit has shipped to a customer; early access does not begin until the first half of 2027. |
| Near-term (1–2 yrs) | GoodExceeds a near-term timeline. Deployments are running now, not projected for a future quarter. | GoodEarly access is dated for the first half of 2027, with general availability by year-end 2027. |
| Research phase | GoodPast the research stage: this is a fielded commercial product, not a lab-only demo. | GoodA $300 million order book and a dated 2027 timeline place it well past speculative research-stage robots. |
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.
How much the claim can be trusted.
None of these has shipped, so they are assessed on track record, engineering plausibility and how the demonstrations match the claims.
Track Record35% of score
Has this maker shipped what it demoed before, on schedule, with the promised capability?
80
- Digit 580
28median 66 across 85 pre-release records100
Excluded as unevidenced, so it is left out of the number: DYNA 2.1
Engineering35% of score
Are the demonstrated capabilities achievable in shipping form, or do they need breakthroughs not in evidence?
6870
- DYNA 2.168
- Digit 570
35median 70 across 95 pre-release records100
Demo Match30% of score
What has been shown to work, against what is claimed in marketing.
8262
- DYNA 2.182
- Digit 562
30median 66 across 95 pre-release records100
Published beside the number
Never averaged into it. These describe how much the maker has disclosed, not what the machine does.
| DYNA 2.1 | Digit 5 | |
|---|---|---|
| ReadinessShip-date specificity, pricing transparency, distribution and regulatory status. Published beside the number; never averaged in. | 40/100 | 58/100 |
| DisclosureHow much of the product is disclosed. Higher means fewer fundamental unknowns remain. Published beside the number; never averaged in. | 35/100 | 38/100 |
How far apart is a long way?
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.
These robots share no measured specification with enough published figures to plot. That is a gap in the record, not a finding about the robots.
What the numbers leave out.
Written on each record, and the only thing here every robot on the site carries.
The trade-off
What each design gives up to be good at what it is good at.
DYNA 2.1
The whole-body workflow is proven on laundry alone. Folding, sorting, shelving. While food prep and warehouse handling stay marketing claims until a second published demo backs them.
No published price, MTBI figure, or safety certification: a buyer evaluates this on one video and one named laundromat, not a spec sheet.
Digit 5
Digit 5 pairs a proven warehouse task set with unproven redesigned legs.
The payload increase comes from a new leg and actuator design, so the predecessor’s three-year reliability record does not carry over to this generation.
Enterprise-only distribution: no price, retailer or consumer path exists to evaluate it independently.
Who each one is wrong for
Stated by the record itself. A robot being wrong for a household is a fact about fit, not a fault.
DYNA 2.1
- Households wanting a personal home robot
- Sold and deployed only to commercial operators. Hotels, laundromats and restaurants. With no consumer purchase path or home installation documented.
- Buyers who need a published price or ship date
- No manufacturer-listed price, unit cost or standard sales channel has been published; deployments appear to be negotiated commercial placements.
- Deployments needing a proven multi-generation track record
- DYNA Robotics is a young manufacturer; the field record here traces to a small number of commercial sites, not years of shipped hardware.
- Sites requiring independently verified safety or reliability data
- No independent safety certification, incident record or third-party reliability testing has been published beyond the manufacturer's own launch materials.
Digit 5
- Consumers or small businesses seeking direct purchase
- Agility sells and leases only through enterprise deployment partnerships; no consumer or small-business order path is published.
- Buyers wanting a machine deployable today
- No Digit 5 unit has shipped to a customer; early access does not begin until the first half of 2027.
- Operations needing independently verified reliability data
- The redesigned legs, actuators and battery carry no independent field record yet; only the predecessor generation's three-year run is documented.
- Tasks outside structured picking, sorting and material transport
- Every documented deployment is warehouse or manufacturing material handling; no broader task set has been shown.
- Sites unable to fund enterprise-scale integration
- Reported lease estimates run near $8,500 a month before facility integration, safety-zone setup and operator training are added.
What stays your job
The upkeep ownership hands back to you, whatever the autonomy level says.
DYNA 2.1
- As needed: Software and AI-model updates as DYNA Robotics revises the orchestrator and world-action model; no public update cadence documented.
- As needed: Swap between parallel-jaw grippers and dexterous hand end-effectors depending on the assigned workflow.
- As needed: Charging scheduled around shift breaks; no runtime or charge-time figure has been published.
- As needed: On-site technical support from DYNA Robotics for a commercial deployment; no owner-serviceable parts list has been published.
Digit 5
- Daily: Battery charge cycle and dock alignment check given the 9-minute recharge target.
- Daily: Visual inspection of the redesigned legs, actuators and gripper for damage or loose fasteners.
- Weekly: Sensor and camera cleaning to keep the person-detection system reliable.
- Weekly: Safety-zone boundary and stop-distance verification around the deployment area.
- Monthly: Actuator range-of-motion diagnostics on the new cycloidal drive.
- Monthly: Software update review; Agility has not published an independent update cadence for Digit 5.
- Annually: Full battery capacity assessment and structural inspection.
How much each of these is standing on.
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 |
|---|---|---|---|
| DYNA 2.1 | Not Consumer-Ready | 5 | Sep 2026 |
| Digit 5 | Pre-Release | 4 | 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.
Keep going.
The full recordDYNA 2.1Specifications, evidence, the Fit Check in full, and every tracked change.
The full recordDigit 5Specifications, 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.
Add a robot
Comparing across classes is allowed — the page will switch to per-class positioning and tell you it has.