ON-THE-FLY PALLETIZING

On-The-Fly Palletizing: AI That Recomputes Mid-Cycle

Viroteq delivers AI on-the-fly palletizing for production lines that refuse to stand still. The runtime recomputes pallet patterns mid-cycle, adapts to changing SKU mixes in real time, and recovers gracefully when production is disrupted. As a result, on-the-fly palletizing cells keep stacking through every variant change, sensor blip, and order reshuffle — without operator intervention, without robot re-teaching, and without scripted downtime between products.

  • ✓  Real-time pattern recompute mid-cycle
  • ✓  No pre-programming or pre-sequencing required
  • ✓  Handles mixed SKUs and disrupted production
RobotStackr OTF mixed palletizing

Real-time

Real-time recompute

<100ms

Per-case decision latency

Mixed

Mixed SKUs supported

Live

Live production tested

Why On-The-Fly Palletizing Is the Answer to Live Production Variability

Live production is messy. Cases arrive out of sequence, an SKU drops mid-shift because of a packaging stockout, a sensor reads a carton dimension that does not match the master data, and the order list reshuffles after a customer call-off. Conventional palletizing software, which depends on a known SKU sequence and a pre-validated pallet pattern, simply stalls in this environment. The line stops, an operator intervenes, and throughput drops. On-the-fly palletizing exists precisely because the production floor never matches the spreadsheet.

However, raw flexibility alone is not enough. On-the-fly palletizing must compute decisions inside the cycle window of a real production line — typically under 100 milliseconds for cadences of 600 to 1200 cases per hour. The AI engine has to balance pattern density, weight stacking rules, overhang limits, and pallet stability all at once, every single placement, every single time. Anything slower, and the robot waits on the software instead of the other way round.

Furthermore, on-the-fly palletizing has to recover from sensor noise without halting. A misread barcode, a partially occluded carton, a vision frame dropped due to lighting — all are routine on a live floor. The runtime degrades to the most reliable input available, recomputes from the new state, and continues building the pallet. According to industry guidance from the Material Handling Industry of America, real-time adaptability is now a baseline expectation for end-of-line automation rather than a premium feature. Viroteq’s edge-first technology platform closes the gap with deterministic response and graceful degradation built into the core runtime.

As a result, on-the-fly palletizing wins exactly where pre-programmed stacking falls over: co-packers running ten variants per shift, FMCG producers with seasonal SKU rotation, e-commerce fulfilment lines with order-driven sequencing, and beverage plants juggling promotional packs alongside core ranges. One software stack, one operator workflow, every production reality.

RobotStackr OS constraint-aware palletizing
pexels imeenhae 2610109 4277794 scaled

How On-The-Fly Palletizing Adapts in Milliseconds

On-the-fly palletizing begins the moment the next case arrives at the cell. Vision sensors and dimensioning scanners feed live geometry to StackrBrain, which compares the actual carton to the SKU master record. If the case matches, the AI updates the pattern. If the case is unexpected — wrong dimensions, missing data, or a substitute pulled by the line — the AI recomputes the remaining pallet from scratch in under 100 milliseconds.

Next, RobotStackr OTF issues the placement command to the robot controller. Communication runs over REST API and WebSocket, so the robot brand is irrelevant — FANUC, ABB, KUKA, Universal Robots, Yaskawa, and Stäubli all work natively. The robot lands the case, sensors confirm placement, and on-the-fly palletizing immediately computes the next move.

Additionally, the runtime carries pattern state forward across the entire pallet. Stability rules, weight distribution, and overhang constraints are evaluated continuously, not just at start. If a previous placement was slightly skewed, on-the-fly palletizing adjusts the next placement to compensate. As a result, the finished pallet is stable enough for a 1500 km truck ride, even though no two cases followed the same path through the cell. For complementary inbound automation, RobotDepalr handles depalletizing of supplier loads with the same vision-driven approach.

Viroteq Products Powering On-The-Fly Palletizing

Three purpose-built products cover the on-the-fly palletizing scope — from real-time mixed-SKU recalculation to consistent single-SKU lines and inbound supplier depalletizing. All three share the StackrBrain AI engine, run on the same Industrial PC hardware, and integrate with major MES, WMS, and PLC platforms via REST API without bespoke development.

Cell1
PRIMARY — REAL-TIME OTF

RobotStackr OTF

RobotStackr OTF is the dedicated runtime for on-the-fly palletizing. Every pallet is computed mid-cycle in under 100 ms — no pre-sequencing, no manual programming, no downtime between SKUs. Ideal for high-mix consumer goods, co-packing operations, and order-driven fulfilment lines.

SINGLE-SKU UNIFORM

RobotStackr OS

RobotStackr OS powers consistent single-SKU production-line palletizing with optimal pre-computed patterns. Ideal companion to on-the-fly palletizing for plants that mix uniform high-volume runs with variable mixed-SKU sequences from one shared runtime.

INBOUND DEPALLETIZING

RobotDepalr

RobotDepalr automates inbound supplier pallet handling with the same vision-driven AI used in on-the-fly palletizing. 3D vision identifies layers on incoming pallets and singulates components onto a conveyor for line-side feed. Closes the loop on full plant automation.

Core Capabilities of On-The-Fly Palletizing

Mid-Cycle Recompute

On-the-fly palletizing recalculates the remaining pallet pattern at any point during the build. When an unexpected SKU arrives, an order updates, or a sensor flags a deviation, the AI generates a new placement plan in under 100 milliseconds without pausing the robot or interrupting the line.

Sensor-Driven Adaptation

Live vision and dimensioning data drive every placement decision. On-the-fly palletizing fuses inputs from 3D cameras, barcode scanners, and weight cells, then degrades gracefully when one source fails. As a result, sensor noise and partial outages no longer halt the line or trigger operator escalation.

Multi-SKU Handling

On-the-fly palletizing accepts any sequence of cases without pre-programming. Mixed cartons, promotional packs, substitutes, and rush items all flow through the same cell. Therefore, co-packers, FMCG plants, and e-commerce fulfilment lines avoid the planner cycles and robot re-teaching that dominate legacy stacking workflows.

Where On-The-Fly Palletizing Delivers the Strongest Returns

On-the-fly palletizing pays back fastest in environments where production variability, mixed SKUs, and order-driven sequencing dominate. The six segments below represent the highest-value applications across the Viroteq customer base. Furthermore, all six share a single runtime and a single operator HMI, which keeps the engineering burden inside the plant team. As a result, on-the-fly palletizing scales from a single co-packer cell to a multi-line FMCG plant without parallel software stacks.

Co-Packers

Contract packers running ten to twenty SKUs per shift across multiple brand owners. On-the-fly palletizing eliminates per-product setup time and absorbs late changes from clients without scripted downtime.

FMCG Variety

Fast-moving consumer-goods plants with seasonal SKU rotation and frequent promotional pack changes. On-the-fly palletizing sequences the live order list without robot re-teaching between variants.

E-Commerce Mixed

Order-driven fulfilment lines where pallet contents reflect the live customer queue. On-the-fly palletizing pulls each next case from the order and stacks it without a fixed pattern, supporting parcel-grade shipping density.

Beverage Mixed

Beverage producers running multipacks, multipack variants, and promotional bundles alongside core SKUs. On-the-fly palletizing handles the size and weight variation without per-pack pattern programming.

Bakery Mix

Industrial bakeries with daily mix changes for retail and food-service customers. On-the-fly palletizing accommodates short-run product schedules and absorbs last-minute sequence reshuffles per outbound truck.

Distribution Outbound

Distribution-centre outbound where each pallet matches a specific store, route, or customer order. On-the-fly palletizing reads the live shipping list and stacks accordingly, no per-store pre-programming required.

<100 ms

Per-case recompute time

1000+ /h

Cases per hour throughput

6-12 weeks

Typical deployment timeline

on-the-fly palletizing

Serving Live-Production Manufacturers and Co-Packers

Live-production environments share one defining trait: the schedule never matches reality. A co-packer signs a brand owner on Friday and runs the new SKU on Monday. A consumer-goods plant pulls forward a promotional bundle to capture a retail window. An e-commerce fulfilment line sequences pallets directly from customer orders that arrive minute-by-minute. In every case, the pre-programmed pallet pattern is obsolete before the first case lands. On-the-fly palletizing exists to absorb that variability without slowing the line.

For co-packers, on-the-fly palletizing collapses the per-product setup window. Where legacy systems require a robot re-teach and a pattern validation cycle for each new SKU, RobotStackr OTF ingests dimensional data, pulls the order list, and starts stacking. As a result, contract packers absorb client changes in real time rather than overnight, and the cell utilisation rate rises sharply across the shift.

FMCG and beverage plants face a similar challenge in a different shape. Seasonal SKU rotation, promotional pack changes, and multipack variants create a constantly shifting product mix. On-the-fly palletizing pulls each next case from the live order list and stacks it without a fixed pattern, so a Monday core run looks the same to the operator as a Friday promotional sequence. Furthermore, brand-agnostic robot support means plants with mixed FANUC, ABB, KUKA, and Universal Robots fleets keep one software stack across cells. Pair the deployment with the broader palletizing solutions portfolio for full plant coverage.

Integrating On-The-Fly Palletizing With Existing Lines

On-the-fly palletizing integrates with your existing line through three modern protocols. REST API is the primary front door for order, batch, and pallet data — well-documented and easy for IT teams to reason about. WebSocket carries live cycle events, sensor feedback, and operator alerts at low latency. OPC-UA bridges the runtime to plant historians, MES, and SCADA without ripping out the data architecture you already have. Furthermore, native PLC handshakes for Siemens S7, Rockwell ControlLogix, and Beckhoff TwinCAT keep the controls team in full ownership of the cell.

As a result, on-the-fly palletizing deployments coexist with installed fieldbus, ladder logic, safety relays, and conveyor PLCs — no proprietary middleware, no replacement of working infrastructure. Robot brand support spans FANUC, ABB, KUKA, Universal Robots, Yaskawa, and Stäubli. In addition, the runtime sits on Industrial PCs inside the cell, so latency is bounded at the controller, not the cloud, and the line stays operational during external network outages or audits.

REST API

Standard request/response over HTTPS for order, batch, and pallet data exchange.

WebSocket

Low-latency event streaming for real-time cycle data, sensor feedback, and HMI updates.

OPC-UA

Bridge to plant historians, MES, and SCADA dashboards via the industrial data standard.

PLC Bridges

Native handshakes for Siemens S7, Rockwell ControlLogix, and Beckhoff TwinCAT.

On-The-Fly Palletizing — Frequently Asked Questions

On-the-fly palletizing is real-time, AI-driven pallet building that computes each placement decision while the line is running. Unlike pre-programmed stacking, on-the-fly palletizing recalculates the pattern mid-cycle based on the actual SKU sequence, sensor feedback, and live order data. As a result, no robot re-teaching or planner downtime is required when the production mix changes.
Pre-programmed stacking assumes a known, static SKU sequence and fixed pallet pattern. On-the-fly palletizing makes no such assumption — it computes the pattern as cases arrive, handling mixed SKUs, missing items, and out-of-sequence cartons without interruption. Therefore, on-the-fly palletizing is the right choice for variable production lines, co-packers, and high-mix consumer-goods plants.
Yes. StackrBrain delivers sub-100ms decisions, so on-the-fly palletizing keeps pace with production cadences exceeding 1000 cases per hour. Computation runs at the edge inside the robot cell, which means latency is bounded by the controller, not the network. The robot remains the bottleneck, not the software.
On-the-fly palletizing handles partial sensor failure gracefully. The runtime degrades to the most reliable sensor input available — vision, dimensioning scanner, or PLC telemetry — and continues building the pallet. Furthermore, an HMI alert flags the degraded state for the operator and maintenance team without halting the line, so production output continues during the diagnostic window.
Viroteq is brand-agnostic. On-the-fly palletizing runs natively on FANUC, ABB, KUKA, Universal Robots, Yaskawa, and Stäubli controllers. Communication uses REST and WebSocket interfaces, so no proprietary teach pendants or vendor SDKs are required. As a result, mixed-fleet plants keep one software stack across cells regardless of robot brand.
Most on-the-fly palletizing projects go live in 6 to 12 weeks. Single-line installations commission in 6 to 8 weeks. Multi-cell mixed-SKU deployments take 8 to 12 weeks. The timeline covers site survey, sensor configuration, robot cell integration, MES handshake, operator training, and a supervised production ramp before full handover. To plan a deployment, book a Viroteq demo and our solutions engineers will scope your line.

Ready to Run On-The-Fly Palletizing on Your Line?

Book a personalised demo and see how on-the-fly palletizing absorbs SKU variability, recovers from sensor noise, and keeps your line running through every production change.

Real-Time Automation Built for Live Production

Bring your line specs, SKU mix profile, and PLC stack — Viroteq specialists will map an on-the-fly palletizing deployment that fits your existing cell footprint and keeps the line running through every production change.