Skip to content
IRIS NEURALContact

Solutions by typeLogistics efficiency

What if the goods leave through the wrong door?

The wrong place makes no noise

It’s 10:20 a.m. on the dock apron. A blue trailer has pulled in crooked at the right-hand door, across the yellow lines, and that dock’s light is red. Its booking was for the door next to it. Nobody has noticed, because both doors are open and the yard is busy. The driver climbs down, a forklift rolls up and starts loading what was never meant for that truck.

5 cameras across 4 sectors

This is how you ask for it

«Tell me when a truck backs into a dock that is not its booking, and tell me which one it should have used.»

Loading is quick; undoing it isn’t. When the mistake surfaces, sometimes at the customer’s gate three hundred miles away, the truck has to come back, a free dock has to be found and the goods have to be turned around again. That dock loses its morning, the next appointment loses its slot and somebody has to call the customer. And back in the warehouse there is a line marked as shipped that isn’t.

You decide once

You decide this once. You say which docks each booking covers, which doors are outbound and which aren’t, how much slack is allowed and who gets told: if a trailer backs into a dock that isn’t its own, alert the yard supervisor with the camera, the plate and the number of the dock it should have used. IRIS applies it across all twenty doors at once, every day, with nobody having to check.

In a warehouse, almost nothing that goes wrong looks like it is going wrong. There’s no crash, no alarm, nobody running. There’s just one thing in a place that isn’t its own: a trailer at the dock next door, a cart of modules going out through the side hallway, a cage crossing the dock door with no open dispatch order, a loaded truck heading down the dirt track instead of over the truck scale. Everything moves normally. Only in the wrong place.

And that’s the problem: an open door says nothing. The system doesn’t know which truck belonged at which dock, and the person who would know is looking at something else. Place mistakes are found later, once they have traveled: at the customer’s gate, in the month-end count, or the day a cage is missing and nobody can say whether it was lost or simply left through the wrong door. It’s both at once, because on paper a mistake and a theft look so alike that they can’t be told apart. And the correction always comes late for a very simple reason: nobody has the booking list and the door in front of them at the same time. The person in the office has the list and can’t see the yard; the person in the yard sees the yard and doesn’t have the list. Twenty docks fit between those two screens, and that’s exactly where the mistake slips through.

IRIS watches the door and compares what it sees with what you decided. It knows which dock was booked, which doors are outbound, which route each cart takes. When something crosses where it shouldn’t, it says so while it’s happening: camera, time, video and, where there’s one, the plate. It accuses nobody. Almost always it is a slip, and a slip corrected in two minutes never becomes a problem: it comes to nothing.

What changes

Before, the mistake surfaced when the truck was already on the road and fixing it cost a whole trip. Now, the moment the trailer settles at the wrong door, the yard supervisor gets the camera and the number of the right dock and walks down before the forklift elevators the first pallet. It gets solved by moving a truck sixty feet, which is what it really cost all along.

Where we have seen it

  • Night shift in the electronic module stockroom. Two operators are pushing carts loaded with gray trays. One is going down the central aisle, over the yellow arrow that marks the route. The other has reached a side door beside the pillar and is taking the cart through it. That door isn’t part of the path painted on the floor. IRIS sees that a loaded cart has left the frame somewhere carts don’t leave.

    CAM-239A cart of modules leaves through a door that isn’t its own

    «Tell me if a loaded cart leaves the stockroom through a door that is not on its route.»

    See this cameraIndustry

  • The face of the dam seen from the crest. In the middle bay, a sluice gate leaf has come to rest at an angle inside its frame, its bottom edge off its guide, and water is coming through the gap. The gate in the bay next door and the one above it in the same bay are seated in place, and serve as the comparison. Up top, a technician leaning on the handrail is looking down at it from the crest.

    CAM-148A gate that isn’t seated in its frame

    «Tell me when a gate is not where it should be in its frame, and show me the movements it has made this week.»

    See this cameraCritical infrastructure

  • Late afternoon in the warehouse. Someone is pushing a pallet jack carrying a wire cage full of boxes down the central aisle, toward the open dock door where a white truck is waiting. On the right, two colleagues with a tablet are checking another despatch. Behind them a forklift works between the racks. That door isn’t the exit for this route, and there’s no outbound order open for that cage. IRIS sees it while it’s happening.

    CAM-260A cage goes out through the wrong door

    «Tell me when a cage or a pallet goes out through a door that is not the one for its route and there is no outbound order open for those goods.»

    See this cameraIndustry

  • Early afternoon at the stockpile yard. One white truck is on the truck scale and another waits its turn. On the right, a red truck loaded with concentrate is heading down a dirt track that starts beside the no-exit sign and skirts the fence downhill. It’s still raising dust. Nobody has logged that trip. IRIS sees a loaded truck crossing a line that nothing is supposed to cross.

    CAM-380A loaded truck leaves by a way that isn’t a way out

    «Tell me if a loaded truck leaves the stockpile by the lower track instead of going over the truck scale.»

    See this cameraIndustry

  • Mid-morning on the dock apron. A blue tractor with a white trailer has come in crooked at the dock on the right, straddling the yellow lines, and the light for that door is red. Two doors along, the lights are green and the bay is free. A worker in a safety vest is checking something on a tablet in front of the cab, and behind him the driver is on the phone. IRIS reads the vehicle code and sees it isn’t the one booked for that dock.

    CAM-263The trailer is at the wrong dock

    «Tell me when a truck parks up at a dock that is not the one for its appointment, and tell me which one it should be at.»

    See this cameraIndustry

What it doesn’t do

IRIS does not know your booking system on its own. It knows which truck is at which dock because you told it which door is which, and if you give us the appointment list it cross-checks against that. Without it, IRIS reports what it sees — a truck at a door marked closed, a departure through a door that is not an exit — but it cannot tell you whose slot it was.

And it stops nothing. It does not close a door, block a forklift or hold a driver. It alerts, and the yard supervisor decides.

Questions

How does IRIS know which dock that truck should have used?
Because you told it, once. Each door is marked on the image with its number and its use — inbound, outbound, closed — and if you pass us the day’s appointment list, IRIS cross-checks it against the plate it has read. When a truck settles at a dock that isn’t its booking, the alert carries the camera, the time, the plate and the number of the right dock, so the yard supervisor doesn’t have to look it up on any screen.
What if we don’t have a booking system?
It still works, with less detail. Without bookings IRIS can’t tell you which dock was the right one, but it can tell you the rest: that there’s a truck at a door marked closed, that a forklift is taking material out through a door that isn’t an exit, that a loaded vehicle has left by a route that doesn’t pass the truck scale. Often that is enough, because most place mistakes are about the door, not the schedule.
Is this about catching theft?
Not primarily. The vast majority of these alerts are mistakes: haste, a nearer door, an instruction misunderstood. IRIS accuses nobody and labels nobody: it says a cage went out through the wrong door and shows the video. If it also turns out there was no open dispatch order for those goods, that fact comes from your system and a person weighs it up. We don’t put labels on people.
Does it work in a warehouse with twenty docks at once?
Yes, and that’s where it shows most. One person can’t watch twenty doors at once, and the wrong-place mistake always happens at the one they weren’t watching. IRIS applies the same rule to every camera in the yard at the same time, with no shifts and no breaks, and only speaks up when something falls outside what you decided. The rest of the day it says nothing, which is exactly the point: a system that flags everything flags nothing.

See all the questions

The real interface, step by step

A camera looks. IRIS understands what it sees.

An extract of the real screen, no voice-over and hands-free. Each round poses another situation. What sits behind it is a good deal bigger than what you see.

  1. It lands in the tray
  2. You open it
  3. You confirm or dismiss
IRIS NEURAL
30ES
IRISDirectoGrabacionesGISIncidencias3996SituaciónCasosLPRAutomatizacionesIRIS DATA
Ask a question or make a request…Send
IRIS · Infinity Neural

Not seeing yours here?

These words are the ones we have built, not the ones IRIS understands. The list falls short on purpose: you ask for it in a sentence, and sentences don’t run out. Tell us what is in front of your cameras and we’ll tell you whether it understands it, or not yet.

See all solutionsTell us what you see

And the best part

A recollection can’t be checked.A number can, and it comes out the same every day.

The number doesn’t depend on who was on shift or how they remember it. It’s measured the same way every day, and that’s why people counting is approved by the Centro Español de Metrología. That approval is Spanish and it isn’t equivalent to any U.S. certification: we say so up front and not at the end.

Tell us your problem and we’ll say whether IRIS understands it, or not yet.

A person answers, the same working day.