Blog

Shipbuilding and autonomy, written plainly.

Short pieces from the Hullira team on dock economics, weld quality, distortion, the ship twin and what it takes to let software move a weld parameter in a yard. Four so far. Each one is drawn from the thinking in our own planning documents, not from customer work, because there is none yet.

4 postsHullira team2026-10-09

Latest

Six figures a day

A dry dock rents for six figures a day. One warped hull block can cost weeks of it. Most yards still find out at the lift.

2026-10-09 · 5 min read

2026-10-09 · 5 min read · Hullira team

Six figures a day

A dry dock rents for six figures a day. One warped hull block can cost weeks of it. Most yards still find out at the lift.

Ships carry about 90% of world trade, and yards are being asked to build more of them than at any time in decades. Building one is still one of the most craft-bound, labour-starved and schedule-critical heavy industries on earth. A single hull block can weigh hundreds of tons, welds run to hundreds of kilometres per vessel, coatings cover millions of square metres, and mega-blocks have to meet in dock to millimetre accuracy against a hard launch date.

The failures are quiet. A weld parameter drifts, so a block distorts, so it will not fit its neighbour at erection, so the dock slips. A coating goes on outside its humidity window and fails early in a ballast tank nobody wants to re-enter. Each one surfaces late, in rework, a class finding or a dock day, and each one is traced back by hand through paper travelers and periodic inspection.

The insight behind Hullira is that cutting, welding, fairing, coating, outfitting and erection are not separate problems. They are one chain, and the chain is what has to be controlled. Hullira fuses the signals, predicts the defect and the distortion, and acts before the shift where it can and inside approved limits where it cannot.

2026-10-09 · 4 min read · Hullira team

Autonomy is a dial, not a switch

A yard does not go from paper travelers to unattended welding in one step, and a class-critical seam should not be the first thing an agent re-orders.

Design partners start in shadow mode. Hullira connects read-only to weld, scan, NDT, coating, robot, crane and MES signals, measures the baseline for rework, dock time and class outcomes from the yard's own records, and writes nothing. In assist mode it recommends weld, fairing, coating, routing and schedule moves, each with source evidence, confidence, the envelope and a rollback path, and a welding or accuracy-control engineer approves each one.

Supervised control follows for the low-risk actions: inspection routing, coating pauses when an environmental window drifts, weld parameters inside the qualified WPS envelope, robot path variants tested in simulation first. Broader work sequencing and weld adaptation for qualified block types come last, after audited ROI, golden-dataset evaluation, simulation validation, and class, yard and insurer acceptance.

Every action carries its evidence, envelope, confidence, estimated rework, dock-time and schedule impact, rollback path and audit entry. That format is what makes autonomy acceptable to production, quality, class and OT teams, and it is what makes trust possible before autonomy.

2026-10-09 · 4 min read · Hullira team

Hit class quality before the shift

Yards commit a block, a crew and a dock slot before they know the block will fit. The twin changes the order.

Whether a block welds clean, holds its shape, coats inside the window and lands on its neighbour depends on a chain of weld sequence, heat input, material, geometry, environmental conditions and erection order. Today that chain is planned on drawings, checked with periodic scans and corrected by shipwrights after the fact. The physics is known; it is just run too late and too slowly to change the shift.

The Hullira twin is an as-built model of the ship, the block and the yard, built in Omniverse from laser-scan and photogrammetry point clouds. A weld-thermal FEA surrogate forecasts distortion per candidate sequence, crane paths and reach are simulated before the lift, and cuOpt ranks the dock and erection order. The chosen plan is handed to the weld, fairing, coating and erection agents, executed step by step and logged, and every real scan recalibrates the twin.

Weld-thermal FEA, structural simulation and dense point-cloud processing are compute-heavy workloads. Running them fast enough to inform a decision before the shift is the reason the twin is built on GPUs.

2026-10-09 · 3 min read · Hullira team

The craft is retiring

The welders, fitters and shipwrights who hold a hull to spec are leaving faster than yards can hire, while the order books stretch past 2030.

Ask a production director and the same losses come up: welds the surveyor rejects, blocks that need fairing before they fit, coatings that fail early, clashes found after the steel is closed, docks waiting on a block. The craft that prevents these lives in a handful of people who can read an arc, know where a panel will move and feel when a coating window is closing.

Hullira captures that craft as a model: the full chain of weld parameters, sequence, scan-verified distortion, coating conditions, erection fit and class outcome, per block. Every supervised correction trains the system. The yard runs at expert judgment on every shift, and the record of how is written down and tied to the block's genealogy for the class surveyor.

Run timeline · scenario

The scenario the posts refer to

Every Hullira run is an ordered, inspectable sequence. This is run_4b7e19 on Block B-214 · double-bottom block · panel line PL-2 · dock D1. Scenario completes in 10 steps with one approval gate. Predicted distortion at the erection joint fell from 4.2 mm to 1.8 mm after a back-step sequence, one porosity precursor on seam S-31 was cleared inside the WPS envelope, the ballast-tank coat ran inside a 3.4 °C dew-point margin, and the block landed at 1.6 mm with its conformance record written.

run_4b7e19 Block B-214 · double-bottom block · panel line PL-2 · dock D1 illustrative scenario SUCCEEDED
  1. 01 ingest.package SUCCEEDED 0.8 s

    Yard Orchestrator · Pulled the work package for B-214 from the yard MES: 46 plates, 212 seams under WPS-117, erection tolerance 2 mm at the D1 joint, PSPC-grade ballast-tank coating, erection slot on D1 in the dock plan. Locked the qualified WPS envelope and the class scope.

  2. 02 twin.simulate SUCCEEDED 1 m 12 s

    Ship Twin · Simulated 18 candidate weld sequences on the as-built twin with the weld-thermal surrogate, ranked on predicted distortion at the erection joint, crane reach on D1 and shift takt. Standing sequence predicts 4.2 mm; candidate #6 predicts 1.8 mm.

  3. 03 cut.nest SUCCEEDED 3 m 40 s

    Cut-and-Profile · Released the nest for 46 plates on CL-1 with the fit-up gaps candidate #6 assumes. As-cut geometry logged per plate and handed to the panel line; material yield 91.4% against the nest plan.

  4. 04 weld.sequence SUCCEEDED 2 m 05 s

    Panel-and-Weld · Loaded the back-step sequence for the non-critical seams on PL-2 and set heat input and travel speed inside WPS-117. Weld-pool and seam cameras streaming on 12 channels.

  5. 05 approve.human APPROVAL 58 s

    Yard Orchestrator · Candidate #6 also re-orders two class-critical butt seams, S-31 and S-32. Sequence changes on class-critical seams stay with a human, so the step was held for the shift welding engineer and approved at 06:12:44.

  6. 06 inspect.fuse SUCCEEDED continuous

    Quality-and-Anomaly · Twelve weld cameras and the UT station fused at the yard edge. One porosity precursor on S-31 at 06:41 flagged and cleared by a 4% wire-feed trim inside the WPS-117 envelope; the joint was routed to UT and passed.

  7. 07 fair.lineheat SUCCEEDED 4 m 30 s

    Fair-and-Form · Post-weld scan registered against the twin: 2.1 mm at the erection joint. Two line-heating passes planned on the inner bottom and executed by the fairing crew; re-scan read 1.8 mm, inside the 2 mm tolerance.

  8. 08 coat.window SUCCEEDED continuous

    Blast-and-Coat · Ballast-tank blast and first coat scheduled to a window with steel temperature 3.4 °C above dew point. Dry-film thickness read 312 µm against a 280 µm minimum on the stripe coats; PSPC evidence assembled per area.

  9. 09 dock.reoptimise SUCCEEDED 41 s

    Schedule-and-Yard · Re-solved the D1 dock and crane plan with B-214 ready 6 hours early and a neighbouring block late: erection slot pulled forward one shift, crane G2 reassigned, no berth conflict. Planner approved the revised plan.

  10. 10 erect.align SUCCEEDED 1 h 48 m

    Erect-and-Align · Both blocks scanned on D1 and registered against the twin; fit predicted at 1.6 mm. Shimming guidance issued to the erection crew, block landed and welded out, final scan 1.6 mm. Conformance record written: welds, scans, coating readings, approvals and class evidence for B-214.

Autonomy

Four levels, set per agent and per tag

A yard does not go from paper travelers to unattended welding in one step. Hullira makes the level explicit, auditable and reversible at any time. The first release runs shadow mode, then assist mode, then supervised control on low-risk actions. Class-critical seam changes, lift plans and block release stay with named people.

Autonomy levels and the human role at each
LevelWhat the agent doesWhat the human doesWhere it sits in a pilot
L1 · ShadowReads weld, scan, NDT, coating, robot, crane and MES signals; predicts and recommends; writes nothingRuns the process as today; compares predictions to NDT and surveyor outcomesShadow mode; the baseline is measured from the yard's own records
L2 · AssistProposes weld, fairing, coating, routing and schedule moves with evidence, confidence, envelope and rollback pathApproves each action in the review consoleAssist mode, the remainder of the pilot
L3 · Supervised controlExecutes pre-approved low-risk actions: inspection routing, coating pauses when a window drifts, weld parameters inside the WPS envelope, robot path variants tested in simulationApproves class-critical seam changes, lift plans and block releaseGraduated autonomy, after audited accuracy and ROI
L4 · BoundedSupervised work sequencing and weld adaptation for qualified block types, across processes and yardsSets the envelope; reviews the shift record and the evaluation resultsPlanned; after class, yard and insurer acceptance is earned
Accelerated computing

Physical AI, at the arc

A weld pool is decided in milliseconds and a dock waits by the hour. Perception has to be local, deterministic and fast, so Hullira runs GPU inference at the yard edge and keeps training, simulation and optimisation in the cloud or on-prem.

Jetson Orin · DeepStream · Holoscan · TensorRT

Edge perception

6 to 24 cameras per process area plus UT, X-ray, thermal, laser-scan, photogrammetry, robot and coating-instrument streams fused at the yard edge. Sub-50 ms weld alerts and sub-150 ms coating or scan prompts are the design targets. Jetson Thor is planned for higher camera density.

Triton · NIM

Model serving

Weld-defect, distortion-risk, coating-risk, point-cloud and schedule-risk models behind one orchestrator at the yard edge, versioned with rollback, routed by latency, tenant, sensitivity and cost.

DGX or HGX · NeMo

Training

Weld-defect vision, UT and X-ray classification, NeMo class-rule reasoning and weld-thermal FEA surrogates fine-tuned per tenant: 100 to 500 GPU-hours per yard during onboarding, then monthly retraining from engineer corrections and class outcomes. Dedicated training capacity is planned.

Omniverse · OVX · Modulus

Ship and yard twin

Block erection, weld sequence, robot reach, crane paths and yard layout simulated before the shift, as-built against as-designed. GPU weld-thermal and structural FEA is the workload; physics-informed surrogates rank plans at shift cadence.

Cosmos · Omniverse Replicator

Synthetic data

Rare weld defects, coating failures, distortion modes, occluded seams and erection misalignment cases generated and validated against real NDT and scan distributions before promotion. 50k to 250k variants per vessel class is the target. Planned.

cuOpt

Optimisation

Dock, crane and berth schedules, work-package sequencing, yard logistics and erection order, re-solved as progress changes.

Isaac · Isaac ROS

Robot cells and crawlers

Robotic weld, blast, coat and inspection cells and crawler or drone hull inspection, with paths validated in simulation before they run next to a hull.

RAPIDS

GPU ETL

Telemetry ETL across weld parameters, scans, NDT results, coating readings, non-conformance and schedule history, for retraining, drift detection and rework, dock-time and schedule benchmarks.

NeMo Guardrails · Retriever

Policy and grounding

WPS and PQR, class-rule, PSPC, cyber and human-approval policies enforced before any action writes back to robots, MES, QA or work packages; retrieval with citations and tenant isolation.

Who it is for

Built for the people who run the yard

We have no customer quotes to show yet and will not invent any. These are the three roles in a yard we build for, and the problems they bring to the first meeting.

Yard or Production Director

Owns launch dates, the dock schedule, labour, rework and cost.

What this person is dealing with today

  • Paper travelers, manual measurement and periodic inspection that let weld quality, distortion and schedule drift
  • Dock, crane and berth slips cascading across the order book
  • A severe, retiring welder and fitter shortage against order books stretching past 2030

Welding or Accuracy-Control Engineer

Owns weld procedures, distortion and fairing strategy, dimensional accuracy and class approval.

What this person is dealing with today

  • Weld-parameter and sequence drift driving class-rejected welds, distortion and rework
  • Hull-fairing and erection dimensional error costing days of dock time per block
  • Cutting, welding, fairing, coating and erection siloed and reactive across the yard

Quality, HSE and Class-Compliance Lead

Owns weld, coating and dimensional quality, non-conformance, PSPC and classification-society and naval-program traceability.

What this person is dealing with today

  • Coating and surface-prep faults driving premature failure and warranty claims
  • Patchy traceability for class and PSPC audits
  • Outfitting clashes discovered after steel is closed, forcing cut-and-reweld rework
FAQ

Straight answers

The questions production directors, welding engineers and class-compliance leads ask in the first meeting.

Yes, but only within an explicit tag allow-list with per-tag rate and magnitude limits, inside the qualified WPS, coating, dimensional and schedule constraints, and only at the autonomy level your yard has set. Design partners start in shadow mode, where Hullira writes nothing. Class-critical seam changes, lift plans and block release stay with named people.

Get started

Talk to the people who wrote this

Start with one welding, fairing, coating or erection process and one measurable baseline. A paid pilot on weld inspection, distortion control or coating assurance shows the number before you commit further.