LiDAR Crane Anti-Collision — Custom Perception Software

USE CASEANWENDUNGSFALLUSE CASEUSE CASEUSE CASEUSE CASE · Crane anti-collision · LiDAR perception softwareKran-Anti-Kollision · LiDAR-Wahrnehmungs-SoftwareCrane anti-collision · LiDAR perception softwareCrane anti-collision · LiDAR perception softwareCrane anti-collision · LiDAR perception softwareCrane anti-collision · LiDAR perception software

Track bridge, trolley and hook, stop the crane before it hits anything. Brücke, Katze und Haken verfolgen, den Kran stoppen, bevor er etwas trifft. Track bridge, trolley and hook, stop the crane before it hits anything. Track bridge, trolley and hook, stop the crane before it hits anything. Track bridge, trolley and hook, stop the crane before it hits anything. Track bridge, trolley and hook, stop the crane before it hits anything.

LiDAR crane anti-collision is portal-mounted perception software that tracks the position of industrial cranes (bridge, trolley, hook) in real time and drives interlocks into the crane PLC before collisions occur with structure, stockpile, or neighbouring cranes.Kran-Anti-Kollision per LiDAR ist eine portal-montierte Wahrnehmungs-Software, die Position und Bewegung industrieller Krane (Brücke, Katze, Haken) in Echtzeit verfolgt und Verriegelungen in die Kran-SPS schreibt, bevor es zu Kollisionen mit Tragwerk, Halde oder Nachbarkran kommt.LiDAR crane anti-collision is portal-mounted perception software that tracks the position of industrial cranes (bridge, trolley, hook) in real time and drives interlocks into the crane PLC before collisions occur with structure, stockpile, or neighbouring cranes.LiDAR crane anti-collision is portal-mounted perception software that tracks the position of industrial cranes (bridge, trolley, hook) in real time and drives interlocks into the crane PLC before collisions occur with structure, stockpile, or neighbouring cranes.LiDAR crane anti-collision is portal-mounted perception software that tracks the position of industrial cranes (bridge, trolley, hook) in real time and drives interlocks into the crane PLC before collisions occur with structure, stockpile, or neighbouring cranes.LiDAR crane anti-collision is portal-mounted perception software that tracks the position of industrial cranes (bridge, trolley, hook) in real time and drives interlocks into the crane PLC before collisions occur with structure, stockpile, or neighbouring cranes.

The pain is the same in every bay where a crane shares its rails with something it can damage. A misjudged grab descent puts the hook into a stockpile shoulder. A tandem-crane bay loses awareness of who is where and the two bridges close on each other. End-stops get hit at speed because the operator was looking somewhere else, or because the bay was operated semi-automatically and the position estimate drifted. Each event is an hour of downtime at best, a wrecked grab or a safety incident at worst, and an insurance conversation either way.Den Schmerz kennt jede Halle, in der ein Kran sein Schienen-Revier mit etwas teilt, das er beschädigen kann. Eine falsch eingeschätzte Greiferabfahrt setzt den Haken in die Halden-Schulter. Eine Tandem-Halle verliert das Bewusstsein dafür, wer wo ist, und zwei Brücken schließen aufeinander. Endanschläge werden mit Tempo getroffen, weil der Bediener anderswo hingeschaut hat oder weil die Halle teil-automatisch lief und die Positions-Schätzung weggedriftet ist. Jedes Ereignis ist im besten Fall eine Stunde Stillstand, im schlimmsten Fall ein zerstörter Greifer oder ein Sicherheits-Vorfall — und in jedem Fall eine Versicherungs-Diskussion.The pain is the same in every bay where a crane shares its rails with something it can damage. A misjudged grab descent puts the hook into a stockpile shoulder. A tandem-crane bay loses awareness of who is where and the two bridges close on each other. End-stops get hit at speed because the operator was looking somewhere else, or because the bay was operated semi-automatically and the position estimate drifted. Each event is an hour of downtime at best, a wrecked grab or a safety incident at worst, and an insurance conversation either way.The pain is the same in every bay where a crane shares its rails with something it can damage. A misjudged grab descent puts the hook into a stockpile shoulder. A tandem-crane bay loses awareness of who is where and the two bridges close on each other. End-stops get hit at speed because the operator was looking somewhere else, or because the bay was operated semi-automatically and the position estimate drifted. Each event is an hour of downtime at best, a wrecked grab or a safety incident at worst, and an insurance conversation either way.The pain is the same in every bay where a crane shares its rails with something it can damage. A misjudged grab descent puts the hook into a stockpile shoulder. A tandem-crane bay loses awareness of who is where and the two bridges close on each other. End-stops get hit at speed because the operator was looking somewhere else, or because the bay was operated semi-automatically and the position estimate drifted. Each event is an hour of downtime at best, a wrecked grab or a safety incident at worst, and an insurance conversation either way.The pain is the same in every bay where a crane shares its rails with something it can damage. A misjudged grab descent puts the hook into a stockpile shoulder. A tandem-crane bay loses awareness of who is where and the two bridges close on each other. End-stops get hit at speed because the operator was looking somewhere else, or because the bay was operated semi-automatically and the position estimate drifted. Each event is an hour of downtime at best, a wrecked grab or a safety incident at worst, and an insurance conversation either way.

Our approach is a LiDAR cluster — typically two to four sensors at the end-of-bay portals and on the roof — fused into a single redundant position estimate of the crane bridge, the trolley and the hook. Safety bands are defined around structure, walls, stockpiles and (where applicable) the other crane. When the position estimate enters a band, the system writes a slow-down or stop signal into the crane PLC over OPC UA, Profinet or hardwired DI — within a control cycle. Redundant sensors mean a single failure does not silently disable the safety function. The productised flavour of this for waste bunkers already runs in the field — see our OWL EYE® waste-bunker product — but every steel mill, paper mill or scrap yard has its own bay geometry, its own crane vendor and its own existing safety architecture, and that is what the custom build is for.Unser Ansatz ist ein LiDAR-Cluster — typisch zwei bis vier Sensoren an den Hallen-Enden und auf dem Dach — fusioniert zu einer redundanten Positions-Schätzung von Brücke, Katze und Haken. Sicherheits-Bänder werden um Tragwerk, Wände, Halden und (sofern vorhanden) den Nachbarkran definiert. Tritt die Positions-Schätzung in ein Band ein, schreibt das System ein Verlangsamungs- oder Stopp-Signal in die Kran-SPS — über OPC UA, Profinet oder verdrahteten DI, innerhalb eines Steuerungs-Zyklus. Redundante Sensoren bedeuten, dass ein einzelner Ausfall die Sicherheits-Funktion nicht still abschaltet. Die produktisierte Variante für Müll-Bunker läuft schon im Feld — siehe unser OWL EYE® Müll-Bunker-Produkt — aber jedes Stahlwerk, jede Papierfabrik und jeder Schrottplatz hat seine eigene Hallen-Geometrie, seinen eigenen Kranhersteller und seine eigene bestehende Sicherheits-Architektur, und genau dafür gibt es den Custom-Build.Our approach is a LiDAR cluster — typically two to four sensors at the end-of-bay portals and on the roof — fused into a single redundant position estimate of the crane bridge, the trolley and the hook. Safety bands are defined around structure, walls, stockpiles and (where applicable) the other crane. When the position estimate enters a band, the system writes a slow-down or stop signal into the crane PLC over OPC UA, Profinet or hardwired DI — within a control cycle. Redundant sensors mean a single failure does not silently disable the safety function. The productised flavour of this for waste bunkers already runs in the field — see our OWL EYE® waste-bunker product — but every steel mill, paper mill or scrap yard has its own bay geometry, its own crane vendor and its own existing safety architecture, and that is what the custom build is for.Our approach is a LiDAR cluster — typically two to four sensors at the end-of-bay portals and on the roof — fused into a single redundant position estimate of the crane bridge, the trolley and the hook. Safety bands are defined around structure, walls, stockpiles and (where applicable) the other crane. When the position estimate enters a band, the system writes a slow-down or stop signal into the crane PLC over OPC UA, Profinet or hardwired DI — within a control cycle. Redundant sensors mean a single failure does not silently disable the safety function. The productised flavour of this for waste bunkers already runs in the field — see our OWL EYE® waste-bunker product — but every steel mill, paper mill or scrap yard has its own bay geometry, its own crane vendor and its own existing safety architecture, and that is what the custom build is for.Our approach is a LiDAR cluster — typically two to four sensors at the end-of-bay portals and on the roof — fused into a single redundant position estimate of the crane bridge, the trolley and the hook. Safety bands are defined around structure, walls, stockpiles and (where applicable) the other crane. When the position estimate enters a band, the system writes a slow-down or stop signal into the crane PLC over OPC UA, Profinet or hardwired DI — within a control cycle. Redundant sensors mean a single failure does not silently disable the safety function. The productised flavour of this for waste bunkers already runs in the field — see our OWL EYE® waste-bunker product — but every steel mill, paper mill or scrap yard has its own bay geometry, its own crane vendor and its own existing safety architecture, and that is what the custom build is for.Our approach is a LiDAR cluster — typically two to four sensors at the end-of-bay portals and on the roof — fused into a single redundant position estimate of the crane bridge, the trolley and the hook. Safety bands are defined around structure, walls, stockpiles and (where applicable) the other crane. When the position estimate enters a band, the system writes a slow-down or stop signal into the crane PLC over OPC UA, Profinet or hardwired DI — within a control cycle. Redundant sensors mean a single failure does not silently disable the safety function. The productised flavour of this for waste bunkers already runs in the field — see our OWL EYE® waste-bunker product — but every steel mill, paper mill or scrap yard has its own bay geometry, its own crane vendor and its own existing safety architecture, and that is what the custom build is for.

This is not an off-the-shelf box. Every engagement descends from our hub service Industrial Perception AI as a discovery + fixed-scope build — typically four to twelve weeks from contract to live interlock, with code, model parameters and integration documentation handed over to you at the end.Das ist keine Box von der Stange. Jedes Projekt leitet sich aus unserem Hub-Service Industrielle Objekterkennung ab — als Discovery + Festscope-Build, typisch vier bis zwölf Wochen vom Vertrag bis zur produktiven Verriegelung. Quellcode, Kalibrier-Daten und Integrations-Dokumentation gehen am Ende an Sie.This is not an off-the-shelf box. Every engagement descends from our hub service Industrial Perception AI as a discovery + fixed-scope build — typically four to twelve weeks from contract to live interlock, with code, model parameters and integration documentation handed over to you at the end.This is not an off-the-shelf box. Every engagement descends from our hub service Industrial Perception AI as a discovery + fixed-scope build — typically four to twelve weeks from contract to live interlock, with code, model parameters and integration documentation handed over to you at the end.This is not an off-the-shelf box. Every engagement descends from our hub service Industrial Perception AI as a discovery + fixed-scope build — typically four to twelve weeks from contract to live interlock, with code, model parameters and integration documentation handed over to you at the end.This is not an off-the-shelf box. Every engagement descends from our hub service Industrial Perception AI as a discovery + fixed-scope build — typically four to twelve weeks from contract to live interlock, with code, model parameters and integration documentation handed over to you at the end.

„The cheapest collision is the one the crane never finishes." „Die billigste Kollision ist die, die der Kran nie zu Ende fährt." „The cheapest collision is the one the crane never finishes." „The cheapest collision is the one the crane never finishes." „The cheapest collision is the one the crane never finishes." „The cheapest collision is the one the crane never finishes."

Same team and same stack that delivers our LiDAR wagon-detection pipeline and the productised OWL EYE® waste-bunker anti-collision system. Gebaut von demselben Team und auf demselben Stack wie unsere LiDAR-Waggon-Erkennung und das produktisierte OWL EYE® Anfahrschutz-System für Müll-Bunker. Same team and same stack that delivers our LiDAR wagon-detection pipeline and the productised OWL EYE® waste-bunker anti-collision system. Same team and same stack that delivers our LiDAR wagon-detection pipeline and the productised OWL EYE® waste-bunker anti-collision system. Same team and same stack that delivers our LiDAR wagon-detection pipeline and the productised OWL EYE® waste-bunker anti-collision system. Same team and same stack that delivers our LiDAR wagon-detection pipeline and the productised OWL EYE® waste-bunker anti-collision system.

Three stagesDrei StufenThree stagesThree stagesThree stagesThree stages

From sensor cluster to PLC — three stages of the pipeline. Vom Sensor-Cluster bis zur SPS — drei Stufen der Pipeline. From sensor cluster to PLC — three stages of the pipeline. From sensor cluster to PLC — three stages of the pipeline. From sensor cluster to PLC — three stages of the pipeline. From sensor cluster to PLC — three stages of the pipeline.

1 · Sensor cluster on the bay1 · Sensor-Cluster in der Halle1 · Sensor cluster on the bay1 · Sensor cluster on the bay1 · Sensor cluster on the bay1 · Sensor cluster on the bay

Two to four industrial LiDAR sensors mounted at end-of-bay portals and on the roof, covering the bridge rails, the trolley travel and the hook envelope. IP65+ housings, dust-tolerant optics, runs in steam, dust and night light — the kind of conditions where steel-mill, paper-mill and waste-bunker bays actually live. Sensor placement is engineered for your bay, not a generic template. Zwei bis vier industrielle LiDAR an Hallen-Enden und auf dem Dach, die Brücken-Schienen, Katz-Weg und Haken-Hülle abdecken. IP65+-Gehäuse, staubtolerante Optik, läuft in Dampf, Staub und Nacht — also genau in den Bedingungen, in denen Stahlwerks-, Papierfabrik- und Müll-Bunker-Hallen tatsächlich arbeiten. Die Sensor-Platzierung wird für Ihre Halle ausgelegt, nicht aus einer Schablone. Two to four industrial LiDAR sensors mounted at end-of-bay portals and on the roof, covering the bridge rails, the trolley travel and the hook envelope. IP65+ housings, dust-tolerant optics, runs in steam, dust and night light — the kind of conditions where steel-mill, paper-mill and waste-bunker bays actually live. Sensor placement is engineered for your bay, not a generic template. Two to four industrial LiDAR sensors mounted at end-of-bay portals and on the roof, covering the bridge rails, the trolley travel and the hook envelope. IP65+ housings, dust-tolerant optics, runs in steam, dust and night light — the kind of conditions where steel-mill, paper-mill and waste-bunker bays actually live. Sensor placement is engineered for your bay, not a generic template. Two to four industrial LiDAR sensors mounted at end-of-bay portals and on the roof, covering the bridge rails, the trolley travel and the hook envelope. IP65+ housings, dust-tolerant optics, runs in steam, dust and night light — the kind of conditions where steel-mill, paper-mill and waste-bunker bays actually live. Sensor placement is engineered for your bay, not a generic template. Two to four industrial LiDAR sensors mounted at end-of-bay portals and on the roof, covering the bridge rails, the trolley travel and the hook envelope. IP65+ housings, dust-tolerant optics, runs in steam, dust and night light — the kind of conditions where steel-mill, paper-mill and waste-bunker bays actually live. Sensor placement is engineered for your bay, not a generic template.

2 · Position fusion2 · Positions-Fusion2 · Position fusion2 · Position fusion2 · Position fusion2 · Position fusion

A real-time fusion stage takes raw point clouds from the cluster and returns a single redundant position estimate for the bridge, the trolley and the hook — typically under 5 cm error and updated at 10–25 Hz. Redundancy means each axis is observed by at least two sensors; one sensor failure degrades accuracy, it does not silently disable the safety logic. Eine Echtzeit-Fusion nimmt Rohpunktwolken aus dem Cluster und gibt eine einzige redundante Positions-Schätzung für Brücke, Katze und Haken zurück — typisch unter 5 cm Fehler, Updaterate 10–25 Hz. Redundant heißt: jede Achse wird von mindestens zwei Sensoren beobachtet; ein Sensor-Ausfall verschlechtert die Genauigkeit, schaltet aber die Sicherheits-Logik nicht still ab. A real-time fusion stage takes raw point clouds from the cluster and returns a single redundant position estimate for the bridge, the trolley and the hook — typically under 5 cm error and updated at 10–25 Hz. Redundancy means each axis is observed by at least two sensors; one sensor failure degrades accuracy, it does not silently disable the safety logic. A real-time fusion stage takes raw point clouds from the cluster and returns a single redundant position estimate for the bridge, the trolley and the hook — typically under 5 cm error and updated at 10–25 Hz. Redundancy means each axis is observed by at least two sensors; one sensor failure degrades accuracy, it does not silently disable the safety logic. A real-time fusion stage takes raw point clouds from the cluster and returns a single redundant position estimate for the bridge, the trolley and the hook — typically under 5 cm error and updated at 10–25 Hz. Redundancy means each axis is observed by at least two sensors; one sensor failure degrades accuracy, it does not silently disable the safety logic. A real-time fusion stage takes raw point clouds from the cluster and returns a single redundant position estimate for the bridge, the trolley and the hook — typically under 5 cm error and updated at 10–25 Hz. Redundancy means each axis is observed by at least two sensors; one sensor failure degrades accuracy, it does not silently disable the safety logic.

3 · PLC interlock + audit log3 · SPS-Verriegelung + Audit-Log3 · PLC interlock + audit log3 · PLC interlock + audit log3 · PLC interlock + audit log3 · PLC interlock + audit log

The fused position drives configurable safety bands around structure, stockpile and neighbouring cranes. When a band is entered, a slow-down or stop signal is written into the crane PLC over OPC UA, Profinet or hardwired DI — within a control cycle. Every interlock event is logged with timestamp, sensor snapshot and position track for the safety review. Die fusionierte Position bedient konfigurierbare Sicherheits-Bänder um Tragwerk, Halde und Nachbarkran. Tritt ein Band ein, wird ein Verlangsamungs- oder Stopp-Signal in die Kran-SPS geschrieben — per OPC UA, Profinet oder verdrahtetem DI, innerhalb eines Steuerungs-Zyklus. Jedes Verriegelungs-Ereignis wird mit Zeitstempel, Sensor-Schnappschuss und Positions-Spur protokolliert. The fused position drives configurable safety bands around structure, stockpile and neighbouring cranes. When a band is entered, a slow-down or stop signal is written into the crane PLC over OPC UA, Profinet or hardwired DI — within a control cycle. Every interlock event is logged with timestamp, sensor snapshot and position track for the safety review. The fused position drives configurable safety bands around structure, stockpile and neighbouring cranes. When a band is entered, a slow-down or stop signal is written into the crane PLC over OPC UA, Profinet or hardwired DI — within a control cycle. Every interlock event is logged with timestamp, sensor snapshot and position track for the safety review. The fused position drives configurable safety bands around structure, stockpile and neighbouring cranes. When a band is entered, a slow-down or stop signal is written into the crane PLC over OPC UA, Profinet or hardwired DI — within a control cycle. Every interlock event is logged with timestamp, sensor snapshot and position track for the safety review. The fused position drives configurable safety bands around structure, stockpile and neighbouring cranes. When a band is entered, a slow-down or stop signal is written into the crane PLC over OPC UA, Profinet or hardwired DI — within a control cycle. Every interlock event is logged with timestamp, sensor snapshot and position track for the safety review.

Pipeline architecture · #how-it-worksPipeline-Architektur · #how-it-worksPipeline architecture · #how-it-worksPipeline architecture · #how-it-worksPipeline architecture · #how-it-worksPipeline architecture · #how-it-works

How the pipeline works — concretely. Wie die Pipeline arbeitet — konkret. How the pipeline works — concretely. How the pipeline works — concretely. How the pipeline works — concretely. How the pipeline works — concretely.

We keep the architecture boring on purpose. Three loosely coupled stages, each one independently testable, each one swappable when the sensor stack or the crane vendor changes. Built on the same stack we use across all our perception work: PCL, Open3D, OpenCV, PyTorch. Wir halten die Architektur absichtlich langweilig. Drei lose gekoppelte Stufen, jede einzeln testbar, jede einzeln tauschbar, wenn sich der Sensor-Stack oder der Kranhersteller ändert. Gebaut auf demselben Stack, den wir für unsere gesamte Wahrnehmungs-Arbeit nutzen: PCL, Open3D, OpenCV, PyTorch. We keep the architecture boring on purpose. Three loosely coupled stages, each one independently testable, each one swappable when the sensor stack or the crane vendor changes. Built on the same stack we use across all our perception work: PCL, Open3D, OpenCV, PyTorch. We keep the architecture boring on purpose. Three loosely coupled stages, each one independently testable, each one swappable when the sensor stack or the crane vendor changes. Built on the same stack we use across all our perception work: PCL, Open3D, OpenCV, PyTorch. We keep the architecture boring on purpose. Three loosely coupled stages, each one independently testable, each one swappable when the sensor stack or the crane vendor changes. Built on the same stack we use across all our perception work: PCL, Open3D, OpenCV, PyTorch. We keep the architecture boring on purpose. Three loosely coupled stages, each one independently testable, each one swappable when the sensor stack or the crane vendor changes. Built on the same stack we use across all our perception work: PCL, Open3D, OpenCV, PyTorch.

Multi-sensor LiDAR captureMulti-Sensor-LiDAR-AufnahmeMulti-sensor LiDAR captureMulti-sensor LiDAR captureMulti-sensor LiDAR captureMulti-sensor LiDAR capture

The cluster — typically two to four LiDAR per bay — delivers synchronised 3D point clouds covering the bridge rails, the trolley path and the hook envelope. Sensors are time-synchronised at the network layer; raw frames are stamped and locally buffered for the audit trail and for post-incident replay. Der Cluster — typisch zwei bis vier LiDAR pro Halle — liefert synchronisierte 3D-Punktwolken über Brücken-Schienen, Katz-Weg und Haken-Hülle. Sensoren sind auf Netzwerk-Ebene zeit-synchronisiert; Rohdaten werden gestempelt und lokal gepuffert — für den Audit-Trail und für die Wiedergabe nach einem Vorfall. The cluster — typically two to four LiDAR per bay — delivers synchronised 3D point clouds covering the bridge rails, the trolley path and the hook envelope. Sensors are time-synchronised at the network layer; raw frames are stamped and locally buffered for the audit trail and for post-incident replay. The cluster — typically two to four LiDAR per bay — delivers synchronised 3D point clouds covering the bridge rails, the trolley path and the hook envelope. Sensors are time-synchronised at the network layer; raw frames are stamped and locally buffered for the audit trail and for post-incident replay. The cluster — typically two to four LiDAR per bay — delivers synchronised 3D point clouds covering the bridge rails, the trolley path and the hook envelope. Sensors are time-synchronised at the network layer; raw frames are stamped and locally buffered for the audit trail and for post-incident replay. The cluster — typically two to four LiDAR per bay — delivers synchronised 3D point clouds covering the bridge rails, the trolley path and the hook envelope. Sensors are time-synchronised at the network layer; raw frames are stamped and locally buffered for the audit trail and for post-incident replay.

Position fusion + safety-band evaluationPositions-Fusion + Sicherheits-Band-AuswertungPosition fusion + safety-band evaluationPosition fusion + safety-band evaluationPosition fusion + safety-band evaluationPosition fusion + safety-band evaluation

Each frame goes through ground removal, voxel down-sampling and crane-component segmentation; the bridge, the trolley and the hook are extracted and tracked over time. A Kalman-style fusion stage produces a single redundant position estimate per axis — typically <5 cm error, updated at 10–25 Hz — and evaluates it against the configured safety bands around structure, stockpile and neighbouring cranes. Jeder Frame durchläuft Boden-Entfernung, Voxel-Downsampling und Kran-Komponenten-Segmentierung; Brücke, Katze und Haken werden extrahiert und zeitlich verfolgt. Eine Kalman-artige Fusion liefert eine redundante Positions-Schätzung je Achse — typisch <5 cm Fehler, Updaterate 10–25 Hz — und wertet sie gegen die konfigurierten Sicherheits-Bänder um Tragwerk, Halde und Nachbarkran aus. Each frame goes through ground removal, voxel down-sampling and crane-component segmentation; the bridge, the trolley and the hook are extracted and tracked over time. A Kalman-style fusion stage produces a single redundant position estimate per axis — typically <5 cm error, updated at 10–25 Hz — and evaluates it against the configured safety bands around structure, stockpile and neighbouring cranes. Each frame goes through ground removal, voxel down-sampling and crane-component segmentation; the bridge, the trolley and the hook are extracted and tracked over time. A Kalman-style fusion stage produces a single redundant position estimate per axis — typically <5 cm error, updated at 10–25 Hz — and evaluates it against the configured safety bands around structure, stockpile and neighbouring cranes. Each frame goes through ground removal, voxel down-sampling and crane-component segmentation; the bridge, the trolley and the hook are extracted and tracked over time. A Kalman-style fusion stage produces a single redundant position estimate per axis — typically <5 cm error, updated at 10–25 Hz — and evaluates it against the configured safety bands around structure, stockpile and neighbouring cranes. Each frame goes through ground removal, voxel down-sampling and crane-component segmentation; the bridge, the trolley and the hook are extracted and tracked over time. A Kalman-style fusion stage produces a single redundant position estimate per axis — typically <5 cm error, updated at 10–25 Hz — and evaluates it against the configured safety bands around structure, stockpile and neighbouring cranes.

PLC interlock write-backRück-Schreibung in die Kran-SPSPLC interlock write-backPLC interlock write-backPLC interlock write-backPLC interlock write-back

When a safety band is entered, the system writes a slow-down or stop signal into the crane PLC over OPC UA, Profinet or hardwired DI — within a control cycle. Where the plant runs a safety PLC, the integration is FS-aware and can be wired into the existing safety chain. Every event is logged with timestamp, sensor snapshot and position track. Wird ein Sicherheits-Band betreten, schreibt das System ein Verlangsamungs- oder Stopp-Signal in die Kran-SPS — per OPC UA, Profinet oder verdrahtetem DI, innerhalb eines Steuerungs-Zyklus. Wo eine Sicherheits-SPS läuft, ist die Anbindung FS-tauglich und kann in die bestehende Sicherheits-Kette eingebunden werden. Jedes Ereignis wird mit Zeitstempel, Sensor-Schnappschuss und Positions-Spur protokolliert. When a safety band is entered, the system writes a slow-down or stop signal into the crane PLC over OPC UA, Profinet or hardwired DI — within a control cycle. Where the plant runs a safety PLC, the integration is FS-aware and can be wired into the existing safety chain. Every event is logged with timestamp, sensor snapshot and position track. When a safety band is entered, the system writes a slow-down or stop signal into the crane PLC over OPC UA, Profinet or hardwired DI — within a control cycle. Where the plant runs a safety PLC, the integration is FS-aware and can be wired into the existing safety chain. Every event is logged with timestamp, sensor snapshot and position track. When a safety band is entered, the system writes a slow-down or stop signal into the crane PLC over OPC UA, Profinet or hardwired DI — within a control cycle. Where the plant runs a safety PLC, the integration is FS-aware and can be wired into the existing safety chain. Every event is logged with timestamp, sensor snapshot and position track. When a safety band is entered, the system writes a slow-down or stop signal into the crane PLC over OPC UA, Profinet or hardwired DI — within a control cycle. Where the plant runs a safety PLC, the integration is FS-aware and can be wired into the existing safety chain. Every event is logged with timestamp, sensor snapshot and position track.

All three stages run on an industrial PC in the crane-cabinet or control-room rack. No cloud dependency, no external API, no licence dial-home. The code is yours at handover. Alle drei Stufen laufen auf einem Industrie-PC im Kran-Schaltschrank oder im Leitstands-Rack. Keine Cloud-Abhängigkeit, keine externe API, kein Lizenz-Heimruf. Der Code gehört Ihnen bei der Übergabe. All three stages run on an industrial PC in the crane-cabinet or control-room rack. No cloud dependency, no external API, no licence dial-home. The code is yours at handover. All three stages run on an industrial PC in the crane-cabinet or control-room rack. No cloud dependency, no external API, no licence dial-home. The code is yours at handover. All three stages run on an industrial PC in the crane-cabinet or control-room rack. No cloud dependency, no external API, no licence dial-home. The code is yours at handover. All three stages run on an industrial PC in the crane-cabinet or control-room rack. No cloud dependency, no external API, no licence dial-home. The code is yours at handover.

What you getWas Sie bekommenWhat you getWhat you getWhat you getWhat you get

Three deliverables — from the same pipeline. Drei Liefer-Ergebnisse — aus derselben Pipeline. Three deliverables — from the same pipeline. Three deliverables — from the same pipeline. Three deliverables — from the same pipeline. Three deliverables — from the same pipeline.

Anti-collision interlocksAnti-Kollisions-VerriegelungenAnti-collision interlocksAnti-collision interlocksAnti-collision interlocksAnti-collision interlocks

Configurable slow-down and stop signals written into the crane PLC over OPC UA, Profinet or hardwired DI. Safety bands are defined per obstacle — structure, walls, stockpiles, tandem-bridge buffer — and tuned together with the crane operators and the safety engineer. Konfigurierbare Verlangsamungs- und Stopp-Signale in die Kran-SPS — per OPC UA, Profinet oder verdrahtetem DI. Sicherheits-Bänder werden je Hindernis definiert — Tragwerk, Wände, Halden, Tandem-Brücken-Puffer — und gemeinsam mit Kran-Bedienern und Sicherheits-Ingenieur eingestellt. Configurable slow-down and stop signals written into the crane PLC over OPC UA, Profinet or hardwired DI. Safety bands are defined per obstacle — structure, walls, stockpiles, tandem-bridge buffer — and tuned together with the crane operators and the safety engineer. Configurable slow-down and stop signals written into the crane PLC over OPC UA, Profinet or hardwired DI. Safety bands are defined per obstacle — structure, walls, stockpiles, tandem-bridge buffer — and tuned together with the crane operators and the safety engineer. Configurable slow-down and stop signals written into the crane PLC over OPC UA, Profinet or hardwired DI. Safety bands are defined per obstacle — structure, walls, stockpiles, tandem-bridge buffer — and tuned together with the crane operators and the safety engineer. Configurable slow-down and stop signals written into the crane PLC over OPC UA, Profinet or hardwired DI. Safety bands are defined per obstacle — structure, walls, stockpiles, tandem-bridge buffer — and tuned together with the crane operators and the safety engineer.

Position telemetry streamPositions-Telemetrie-StromPosition telemetry streamPosition telemetry streamPosition telemetry streamPosition telemetry stream

A continuous bridge / trolley / hook coordinate stream into your historian, MES or yard-management system — typical update rate 10–25 Hz. The same data we use to drive interlocks is available for production analytics, semi-automated grab routing, or feeding into our stockpile-monitoring pipeline. Ein kontinuierlicher Koordinaten-Strom für Brücke, Katze und Haken in Ihren Historian, ins MES oder ins Hof-Management — typische Updaterate 10–25 Hz. Dieselben Daten, die wir für die Verriegelungen verwenden, stehen für Produktions-Analytik, teil-automatisches Greifer-Routing oder die Anbindung an unser Halden-Monitoring zur Verfügung. A continuous bridge / trolley / hook coordinate stream into your historian, MES or yard-management system — typical update rate 10–25 Hz. The same data we use to drive interlocks is available for production analytics, semi-automated grab routing, or feeding into our stockpile-monitoring pipeline. A continuous bridge / trolley / hook coordinate stream into your historian, MES or yard-management system — typical update rate 10–25 Hz. The same data we use to drive interlocks is available for production analytics, semi-automated grab routing, or feeding into our stockpile-monitoring pipeline. A continuous bridge / trolley / hook coordinate stream into your historian, MES or yard-management system — typical update rate 10–25 Hz. The same data we use to drive interlocks is available for production analytics, semi-automated grab routing, or feeding into our stockpile-monitoring pipeline. A continuous bridge / trolley / hook coordinate stream into your historian, MES or yard-management system — typical update rate 10–25 Hz. The same data we use to drive interlocks is available for production analytics, semi-automated grab routing, or feeding into our stockpile-monitoring pipeline.

Operator HUD + incident replayBediener-HUD + Vorfall-WiedergabeOperator HUD + incident replayOperator HUD + incident replayOperator HUD + incident replayOperator HUD + incident replay

A control-room display showing live position, active safety bands and recent interlock events, plus a post-incident replay tool — sensor snapshots, position tracks and PLC outputs aligned on a single timeline. Built for the way crane operators and safety engineers actually do reviews. Eine Leitstands-Anzeige mit Live-Position, aktiven Sicherheits-Bändern und letzten Verriegelungs-Ereignissen, plus ein Wiedergabe-Tool nach einem Vorfall — Sensor-Schnappschüsse, Positions-Spuren und SPS-Ausgaben auf einer gemeinsamen Zeitachse. Gebaut für die Art, wie Kran-Bediener und Sicherheits-Ingenieure tatsächlich Vorfälle aufarbeiten. A control-room display showing live position, active safety bands and recent interlock events, plus a post-incident replay tool — sensor snapshots, position tracks and PLC outputs aligned on a single timeline. Built for the way crane operators and safety engineers actually do reviews. A control-room display showing live position, active safety bands and recent interlock events, plus a post-incident replay tool — sensor snapshots, position tracks and PLC outputs aligned on a single timeline. Built for the way crane operators and safety engineers actually do reviews. A control-room display showing live position, active safety bands and recent interlock events, plus a post-incident replay tool — sensor snapshots, position tracks and PLC outputs aligned on a single timeline. Built for the way crane operators and safety engineers actually do reviews. A control-room display showing live position, active safety bands and recent interlock events, plus a post-incident replay tool — sensor snapshots, position tracks and PLC outputs aligned on a single timeline. Built for the way crane operators and safety engineers actually do reviews.

Why customWarum CustomWhy customWhy customWhy customWhy custom

Why a custom build — not an off-the-shelf product. Warum nach Maß — und nicht von der Stange. Why a custom build — not an off-the-shelf product. Why a custom build — not an off-the-shelf product. Why a custom build — not an off-the-shelf product. Why a custom build — not an off-the-shelf product.

Every crane bay has its own obstacles, its own crane vendor and its own existing safety architecture. A generic anti-collision box solves the generic case; your bay is not the generic case. Jede Kran-Halle hat eigene Hindernisse, einen eigenen Kranhersteller und eine eigene bestehende Sicherheits-Architektur. Eine generische Anfahrschutz-Box löst den generischen Fall; Ihre Halle ist nicht der generische Fall. Every crane bay has its own obstacles, its own crane vendor and its own existing safety architecture. A generic anti-collision box solves the generic case; your bay is not the generic case. Every crane bay has its own obstacles, its own crane vendor and its own existing safety architecture. A generic anti-collision box solves the generic case; your bay is not the generic case. Every crane bay has its own obstacles, its own crane vendor and its own existing safety architecture. A generic anti-collision box solves the generic case; your bay is not the generic case. Every crane bay has its own obstacles, its own crane vendor and its own existing safety architecture. A generic anti-collision box solves the generic case; your bay is not the generic case.

Bay-specific calibrationHallen-spezifische KalibrierungBay-specific calibrationBay-specific calibrationBay-specific calibrationBay-specific calibration

Every bay has different obstacles — pillars, walls, stockpile shoulders, neighbouring cranes, end-stops at non-standard distances. We survey the bay, place the sensor cluster for the geometry you actually have, and tune safety bands together with the operators and the safety engineer. We re-calibrate when the bay layout changes. Jede Halle hat andere Hindernisse — Stützen, Wände, Halden-Schultern, Nachbarkrane, Endanschläge auf nicht-Standard-Abständen. Wir vermessen die Halle, platzieren den Sensor-Cluster für die Geometrie, die Sie tatsächlich haben, und stimmen die Sicherheits-Bänder mit Bedienern und Sicherheits-Ingenieur ab. Wir re-kalibrieren, wenn sich das Hallen-Layout ändert. Every bay has different obstacles — pillars, walls, stockpile shoulders, neighbouring cranes, end-stops at non-standard distances. We survey the bay, place the sensor cluster for the geometry you actually have, and tune safety bands together with the operators and the safety engineer. We re-calibrate when the bay layout changes. Every bay has different obstacles — pillars, walls, stockpile shoulders, neighbouring cranes, end-stops at non-standard distances. We survey the bay, place the sensor cluster for the geometry you actually have, and tune safety bands together with the operators and the safety engineer. We re-calibrate when the bay layout changes. Every bay has different obstacles — pillars, walls, stockpile shoulders, neighbouring cranes, end-stops at non-standard distances. We survey the bay, place the sensor cluster for the geometry you actually have, and tune safety bands together with the operators and the safety engineer. We re-calibrate when the bay layout changes. Every bay has different obstacles — pillars, walls, stockpile shoulders, neighbouring cranes, end-stops at non-standard distances. We survey the bay, place the sensor cluster for the geometry you actually have, and tune safety bands together with the operators and the safety engineer. We re-calibrate when the bay layout changes.

Crane-vendor agnosticHerstelleragnostischCrane-vendor agnosticCrane-vendor agnosticCrane-vendor agnosticCrane-vendor agnostic

The interlock layer talks OPC UA, Profinet and hardwired DI, so it works with Demag, ABUS, Konecranes, Stahl, Kone, ZPMC and the older nameplates nobody quite remembers — and with mixed fleets in the same bay. The perception layer doesn't care which vendor built the crane. Die Verriegelungs-Schicht spricht OPC UA, Profinet und verdrahteten DI — und arbeitet damit mit Demag, ABUS, Konecranes, Stahl, Kone, ZPMC und den älteren Typenschildern, an die sich niemand mehr ganz erinnert — auch in gemischten Flotten in derselben Halle. Die Wahrnehmungs-Schicht ist es egal, welcher Hersteller den Kran gebaut hat. The interlock layer talks OPC UA, Profinet and hardwired DI, so it works with Demag, ABUS, Konecranes, Stahl, Kone, ZPMC and the older nameplates nobody quite remembers — and with mixed fleets in the same bay. The perception layer doesn't care which vendor built the crane. The interlock layer talks OPC UA, Profinet and hardwired DI, so it works with Demag, ABUS, Konecranes, Stahl, Kone, ZPMC and the older nameplates nobody quite remembers — and with mixed fleets in the same bay. The perception layer doesn't care which vendor built the crane. The interlock layer talks OPC UA, Profinet and hardwired DI, so it works with Demag, ABUS, Konecranes, Stahl, Kone, ZPMC and the older nameplates nobody quite remembers — and with mixed fleets in the same bay. The perception layer doesn't care which vendor built the crane. The interlock layer talks OPC UA, Profinet and hardwired DI, so it works with Demag, ABUS, Konecranes, Stahl, Kone, ZPMC and the older nameplates nobody quite remembers — and with mixed fleets in the same bay. The perception layer doesn't care which vendor built the crane.

Safety-rated integration pathSicherheits-tauglicher Integrations-PfadSafety-rated integration pathSafety-rated integration pathSafety-rated integration pathSafety-rated integration path

Where the plant runs a safety PLC, the integration is FS-aware: the LiDAR layer provides the position estimate, the safety PLC owns the trip. Where the bay runs a standard PLC only, we wire a hardwired DI shutdown alongside the OPC UA path so the trip survives a network outage. We work with your safety engineer, not around them. Wo eine Sicherheits-SPS läuft, ist die Anbindung FS-tauglich: die LiDAR-Schicht liefert die Positions-Schätzung, die Sicherheits-SPS besitzt die Auslösung. Wo nur eine Standard-SPS in der Halle steht, verdrahten wir parallel zum OPC UA-Pfad einen DI-Notabschalt — damit die Auslösung einen Netzwerk-Ausfall überlebt. Wir arbeiten mit Ihrem Sicherheits-Ingenieur, nicht an ihm vorbei. Where the plant runs a safety PLC, the integration is FS-aware: the LiDAR layer provides the position estimate, the safety PLC owns the trip. Where the bay runs a standard PLC only, we wire a hardwired DI shutdown alongside the OPC UA path so the trip survives a network outage. We work with your safety engineer, not around them. Where the plant runs a safety PLC, the integration is FS-aware: the LiDAR layer provides the position estimate, the safety PLC owns the trip. Where the bay runs a standard PLC only, we wire a hardwired DI shutdown alongside the OPC UA path so the trip survives a network outage. We work with your safety engineer, not around them. Where the plant runs a safety PLC, the integration is FS-aware: the LiDAR layer provides the position estimate, the safety PLC owns the trip. Where the bay runs a standard PLC only, we wire a hardwired DI shutdown alongside the OPC UA path so the trip survives a network outage. We work with your safety engineer, not around them. Where the plant runs a safety PLC, the integration is FS-aware: the LiDAR layer provides the position estimate, the safety PLC owns the trip. Where the bay runs a standard PLC only, we wire a hardwired DI shutdown alongside the OPC UA path so the trip survives a network outage. We work with your safety engineer, not around them.

IP ownership + clean handoverIP-Eigentum + saubere ÜbergabeIP ownership + clean handoverIP ownership + clean handoverIP ownership + clean handoverIP ownership + clean handover

You own the source code, the calibration data and the integration documentation at handover. We document the system, train your crane and safety teams, and walk away clean. No black box, no monthly per-crane licence, no service contract you can't exit. See our FAQs on IP and engagement model for the standard terms. Sie besitzen Quellcode, Kalibrier-Daten und Integrations-Dokumentation nach der Übergabe. Wir dokumentieren das System, schulen Ihre Kran- und Sicherheits-Teams und gehen sauber raus. Keine Black Box, keine monatliche Pro-Kran-Lizenz, kein Servicevertrag, aus dem Sie nicht rauskommen. Standard-Bedingungen siehe unsere FAQs zu IP und Zusammenarbeits-Modell. You own the source code, the calibration data and the integration documentation at handover. We document the system, train your crane and safety teams, and walk away clean. No black box, no monthly per-crane licence, no service contract you can't exit. See our FAQs on IP and engagement model for the standard terms. You own the source code, the calibration data and the integration documentation at handover. We document the system, train your crane and safety teams, and walk away clean. No black box, no monthly per-crane licence, no service contract you can't exit. See our FAQs on IP and engagement model for the standard terms. You own the source code, the calibration data and the integration documentation at handover. We document the system, train your crane and safety teams, and walk away clean. No black box, no monthly per-crane licence, no service contract you can't exit. See our FAQs on IP and engagement model for the standard terms. You own the source code, the calibration data and the integration documentation at handover. We document the system, train your crane and safety teams, and walk away clean. No black box, no monthly per-crane licence, no service contract you can't exit. See our FAQs on IP and engagement model for the standard terms.

FAQ

Questions about crane anti-collision. Fragen zur Kran-Anti-Kollision. Questions about crane anti-collision. Questions about crane anti-collision. Questions about crane anti-collision. Questions about crane anti-collision.

The engagement-model questions we hear from every plant considering a custom anti-collision build. Need something more specific to your bay and your crane vendor? Ask us. Die Fragen zum Zusammenarbeits-Modell, die wir von jeder Anlage hören, die einen Custom-Anfahrschutz erwägt. Brauchen Sie etwas Spezifischeres zu Ihrer Halle und Ihrem Kranhersteller? Sprechen Sie uns an. The engagement-model questions we hear from every plant considering a custom anti-collision build. Need something more specific to your bay and your crane vendor? Ask us. The engagement-model questions we hear from every plant considering a custom anti-collision build. Need something more specific to your bay and your crane vendor? Ask us. The engagement-model questions we hear from every plant considering a custom anti-collision build. Need something more specific to your bay and your crane vendor? Ask us. The engagement-model questions we hear from every plant considering a custom anti-collision build. Need something more specific to your bay and your crane vendor? Ask us.

Industrial Perception AIIndustrielle ObjekterkennungIndustrial Perception AIIndustrial Perception AIIndustrial Perception AIIndustrial Perception AI

What does custom perception AI software cost?Was kostet maßgeschneiderte Wahrnehmungs-Software?What does custom perception AI software cost?What does custom perception AI software cost?What does custom perception AI software cost?What does custom perception AI software cost? ＋

 We don't publish list prices because every project is scoped against your data and your decision logic — but we work to three predictable tiers.

Discovery & Assessment — a 1–3 day workshop, on-site or remote, fixed price in the low-four-figure range. You receive a written feasibility note, a recommended next step and (if applicable) a fixed-price quote for the follow-on project. Useful even if you don't then go ahead — many customers use the note to evaluate two or three vendors.

Custom Pipeline / Tool — a 4–12 week project delivering a working perception pipeline (parser + algorithm + dashboard or OPC UA integration). Fixed scope, fixed price, you own the code at handover. Typical project size is in the mid-five to low-six-figure range depending on data volume, sensor count and integration depth.

Long-term Partnership — a monthly retainer for ongoing development and on-call support. Sized to the team capacity you need (typically 0.5–2 FTE equivalent). Quarterly road-mapping included.

All three tiers include source code, written documentation and a clean handover — no licence dependence on us. See our Industrial Perception AI service for the full engagement model.
Wir veröffentlichen keine Listenpreise, weil jedes Projekt auf Ihre Daten und Ihre Entscheidungs-Logik zugeschnitten wird — aber wir arbeiten in drei berechenbaren Tiers.

Discovery & Assessment — ein 1–3-tägiger Workshop, vor Ort oder remote, Festpreis im unteren vierstelligen Bereich. Sie erhalten eine schriftliche Machbarkeits-Note, einen empfohlenen nächsten Schritt und ggf. ein Festpreis-Angebot für das Folge-Projekt. Lohnt sich auch ohne Folge-Auftrag — viele Kunden nutzen die Note, um zwei oder drei Anbieter zu vergleichen.

Custom Pipeline / Tool — ein 4–12-Wochen-Projekt, das eine fertige Wahrnehmungs-Pipeline liefert (Parser + Algorithmus + Dashboard oder OPC-UA-Anbindung). Fester Scope, Festpreis, Code-Übergabe am Ende. Übliche Projektgröße liegt im mittleren fünf- bis unteren sechsstelligen Bereich, je nach Datenvolumen, Sensor-Anzahl und Integrations-Tiefe.

Langfristige Partnerschaft — monatlicher Retainer für laufende Entwicklung und On-Call-Support. Dimensioniert nach benötigter Team-Kapazität (typisch 0,5–2 FTE-Äquivalente). Quartalsweise Roadmap inklusive.

Alle drei Tiers enthalten Quellcode, schriftliche Dokumentation und saubere Übergabe — keine Lizenz-Abhängigkeit von uns. Vollständiges Zusammenarbeits-Modell siehe unsere Industrielle Objekterkennung.
We don't publish list prices because every project is scoped against your data and your decision logic — but we work to three predictable tiers.

Discovery & Assessment — a 1–3 day workshop, on-site or remote, fixed price in the low-four-figure range. You receive a written feasibility note, a recommended next step and (if applicable) a fixed-price quote for the follow-on project. Useful even if you don't then go ahead — many customers use the note to evaluate two or three vendors.

Custom Pipeline / Tool — a 4–12 week project delivering a working perception pipeline (parser + algorithm + dashboard or OPC UA integration). Fixed scope, fixed price, you own the code at handover. Typical project size is in the mid-five to low-six-figure range depending on data volume, sensor count and integration depth.

Long-term Partnership — a monthly retainer for ongoing development and on-call support. Sized to the team capacity you need (typically 0.5–2 FTE equivalent). Quarterly road-mapping included.

All three tiers include source code, written documentation and a clean handover — no licence dependence on us. See our Industrial Perception AI service for the full engagement model.
We don't publish list prices because every project is scoped against your data and your decision logic — but we work to three predictable tiers.

Discovery & Assessment — a 1–3 day workshop, on-site or remote, fixed price in the low-four-figure range. You receive a written feasibility note, a recommended next step and (if applicable) a fixed-price quote for the follow-on project. Useful even if you don't then go ahead — many customers use the note to evaluate two or three vendors.

Custom Pipeline / Tool — a 4–12 week project delivering a working perception pipeline (parser + algorithm + dashboard or OPC UA integration). Fixed scope, fixed price, you own the code at handover. Typical project size is in the mid-five to low-six-figure range depending on data volume, sensor count and integration depth.

Long-term Partnership — a monthly retainer for ongoing development and on-call support. Sized to the team capacity you need (typically 0.5–2 FTE equivalent). Quarterly road-mapping included.

All three tiers include source code, written documentation and a clean handover — no licence dependence on us. See our Industrial Perception AI service for the full engagement model.
We don't publish list prices because every project is scoped against your data and your decision logic — but we work to three predictable tiers.

Discovery & Assessment — a 1–3 day workshop, on-site or remote, fixed price in the low-four-figure range. You receive a written feasibility note, a recommended next step and (if applicable) a fixed-price quote for the follow-on project. Useful even if you don't then go ahead — many customers use the note to evaluate two or three vendors.

Custom Pipeline / Tool — a 4–12 week project delivering a working perception pipeline (parser + algorithm + dashboard or OPC UA integration). Fixed scope, fixed price, you own the code at handover. Typical project size is in the mid-five to low-six-figure range depending on data volume, sensor count and integration depth.

Long-term Partnership — a monthly retainer for ongoing development and on-call support. Sized to the team capacity you need (typically 0.5–2 FTE equivalent). Quarterly road-mapping included.

All three tiers include source code, written documentation and a clean handover — no licence dependence on us. See our Industrial Perception AI service for the full engagement model.
We don't publish list prices because every project is scoped against your data and your decision logic — but we work to three predictable tiers.

Discovery & Assessment — a 1–3 day workshop, on-site or remote, fixed price in the low-four-figure range. You receive a written feasibility note, a recommended next step and (if applicable) a fixed-price quote for the follow-on project. Useful even if you don't then go ahead — many customers use the note to evaluate two or three vendors.

Custom Pipeline / Tool — a 4–12 week project delivering a working perception pipeline (parser + algorithm + dashboard or OPC UA integration). Fixed scope, fixed price, you own the code at handover. Typical project size is in the mid-five to low-six-figure range depending on data volume, sensor count and integration depth.

Long-term Partnership — a monthly retainer for ongoing development and on-call support. Sized to the team capacity you need (typically 0.5–2 FTE equivalent). Quarterly road-mapping included.

All three tiers include source code, written documentation and a clean handover — no licence dependence on us. See our Industrial Perception AI service for the full engagement model.

How long does it take to build a custom perception pipeline?Wie lange dauert eine maßgeschneiderte Wahrnehmungs-Pipeline?How long does it take to build a custom perception pipeline?How long does it take to build a custom perception pipeline?How long does it take to build a custom perception pipeline?How long does it take to build a custom perception pipeline? ＋

 From signed contract to a working tool in production, expect 4–12 weeks for a standard custom-pipeline engagement. The spread is driven by three factors.

Data readiness. If you already have labelled data or representative recordings, we start training in week 1. If we need to set up data collection, add a sensor, or label from scratch, the front end adds 1–3 weeks.

Integration depth. A standalone dashboard with REST output is the fastest path — typically 4–6 weeks. OPC UA integration into a running control system, with interlocks, factory-acceptance tests and a customer change-management process, is closer to 8–12 weeks.

Sensor count and site complexity. One LiDAR + one camera in a clean indoor environment is faster than a six-sensor outdoor portal with dust, snow and dynamic lighting. We scope the difference up-front in the Discovery workshop.

For a faster first signal we recommend the Discovery & Assessment tier — 1–3 days, fixed price, written feasibility note within a week. See Industrial Perception AI for the full model.
Vom unterzeichneten Vertrag bis zum produktiven Tool rechnen Sie mit 4–12 Wochen für ein Standard-Custom-Pipeline-Projekt. Die Spanne wird von drei Faktoren bestimmt.

Datenlage. Wenn Sie bereits gelabelte Daten oder repräsentative Aufnahmen haben, starten wir in Woche 1 mit dem Training. Müssen wir Datenerfassung aufsetzen, einen Sensor ergänzen oder von Null labeln, kommt vorne 1–3 Wochen dazu.

Integrations-Tiefe. Ein eigenständiges Dashboard mit REST-Schnittstelle ist der schnellste Weg — typisch 4–6 Wochen. OPC-UA-Anbindung in eine laufende Leittechnik, mit Verriegelungen, Werks-Abnahme und kundenseitigem Change-Management, eher 8–12 Wochen.

Sensor-Anzahl und Anlagen-Komplexität. Ein LiDAR + eine Kamera in einer sauberen Innen-Umgebung geht schneller als ein 6-Sensor-Portal im Freien mit Staub, Schnee und wechselndem Licht. Den Unterschied schneiden wir vorab im Discovery-Workshop sauber zu.

Für ein schnelleres erstes Signal empfehlen wir das Discovery & Assessment-Tier — 1–3 Tage, Festpreis, schriftliche Machbarkeits-Note innerhalb einer Woche. Vollständiges Modell siehe Industrielle Objekterkennung.
From signed contract to a working tool in production, expect 4–12 weeks for a standard custom-pipeline engagement. The spread is driven by three factors.

Data readiness. If you already have labelled data or representative recordings, we start training in week 1. If we need to set up data collection, add a sensor, or label from scratch, the front end adds 1–3 weeks.

Integration depth. A standalone dashboard with REST output is the fastest path — typically 4–6 weeks. OPC UA integration into a running control system, with interlocks, factory-acceptance tests and a customer change-management process, is closer to 8–12 weeks.

Sensor count and site complexity. One LiDAR + one camera in a clean indoor environment is faster than a six-sensor outdoor portal with dust, snow and dynamic lighting. We scope the difference up-front in the Discovery workshop.

For a faster first signal we recommend the Discovery & Assessment tier — 1–3 days, fixed price, written feasibility note within a week. See Industrial Perception AI for the full model.
From signed contract to a working tool in production, expect 4–12 weeks for a standard custom-pipeline engagement. The spread is driven by three factors.

Data readiness. If you already have labelled data or representative recordings, we start training in week 1. If we need to set up data collection, add a sensor, or label from scratch, the front end adds 1–3 weeks.

Integration depth. A standalone dashboard with REST output is the fastest path — typically 4–6 weeks. OPC UA integration into a running control system, with interlocks, factory-acceptance tests and a customer change-management process, is closer to 8–12 weeks.

Sensor count and site complexity. One LiDAR + one camera in a clean indoor environment is faster than a six-sensor outdoor portal with dust, snow and dynamic lighting. We scope the difference up-front in the Discovery workshop.

For a faster first signal we recommend the Discovery & Assessment tier — 1–3 days, fixed price, written feasibility note within a week. See Industrial Perception AI for the full model.
From signed contract to a working tool in production, expect 4–12 weeks for a standard custom-pipeline engagement. The spread is driven by three factors.

Data readiness. If you already have labelled data or representative recordings, we start training in week 1. If we need to set up data collection, add a sensor, or label from scratch, the front end adds 1–3 weeks.

Integration depth. A standalone dashboard with REST output is the fastest path — typically 4–6 weeks. OPC UA integration into a running control system, with interlocks, factory-acceptance tests and a customer change-management process, is closer to 8–12 weeks.

Sensor count and site complexity. One LiDAR + one camera in a clean indoor environment is faster than a six-sensor outdoor portal with dust, snow and dynamic lighting. We scope the difference up-front in the Discovery workshop.

For a faster first signal we recommend the Discovery & Assessment tier — 1–3 days, fixed price, written feasibility note within a week. See Industrial Perception AI for the full model.
From signed contract to a working tool in production, expect 4–12 weeks for a standard custom-pipeline engagement. The spread is driven by three factors.

Data readiness. If you already have labelled data or representative recordings, we start training in week 1. If we need to set up data collection, add a sensor, or label from scratch, the front end adds 1–3 weeks.

Integration depth. A standalone dashboard with REST output is the fastest path — typically 4–6 weeks. OPC UA integration into a running control system, with interlocks, factory-acceptance tests and a customer change-management process, is closer to 8–12 weeks.

Sensor count and site complexity. One LiDAR + one camera in a clean indoor environment is faster than a six-sensor outdoor portal with dust, snow and dynamic lighting. We scope the difference up-front in the Discovery workshop.

For a faster first signal we recommend the Discovery & Assessment tier — 1–3 days, fixed price, written feasibility note within a week. See Industrial Perception AI for the full model.

Who owns the code and IP we pay you to build?Wem gehören Code und IP, die wir bei Ihnen beauftragen?Who owns the code and IP we pay you to build?Who owns the code and IP we pay you to build?Who owns the code and IP we pay you to build?Who owns the code and IP we pay you to build? ＋

 You do. Our standard contract transfers full ownership of the project-specific code, model weights, training data (where the data is yours) and documentation to you on final acceptance. We don't keep a back-door licence and we don't lock you into a maintenance contract.

What we retain is our pre-existing toolbox — reusable libraries, calibration utilities, generic data parsers, the OWL EYE® core — which we license to you, royalty-free, for use on the delivered tool. This is the same boundary that any reputable engineering firm draws: we bring the toolbox, you keep the deliverable.

If you want a different IP arrangement — for example a joint patent on a novel algorithm, or a co-developed model that we both reuse with consent — we structure that explicitly in the project contract. Tell us up-front in the Discovery workshop.

Full engagement details on our Industrial Perception AI page.
Ihnen. Unser Standard-Vertrag überträgt das volle Eigentum am projektspezifischen Code, an den Modell-Gewichten, an Trainingsdaten (soweit die Daten Ihnen gehören) und an der Dokumentation bei der Abnahme an Sie. Wir behalten keine Hintertür-Lizenz und binden Sie nicht an einen Wartungsvertrag.

Was bei uns bleibt, ist unser vorhandener Werkzeugkasten — wiederverwendbare Bibliotheken, Kalibrier-Utilities, generische Daten-Parser, der OWL EYE®-Kern — den wir Ihnen lizenzgebührenfrei für das gelieferte Tool lizenzieren. Das ist dieselbe Grenze, die jedes seriöse Ingenieurbüro zieht: Wir bringen den Werkzeugkasten, Sie behalten das Ergebnis.

Wenn Sie eine andere IP-Vereinbarung wollen — etwa ein gemeinsames Patent auf einen neuartigen Algorithmus oder ein gemeinsam entwickeltes Modell, das wir beide mit Einwilligung wiederverwenden — regeln wir das explizit im Projektvertrag. Sagen Sie es vorab im Discovery-Workshop.

Vollständige Details auf unserer Seite zur Industriellen Objekterkennung.
You do. Our standard contract transfers full ownership of the project-specific code, model weights, training data (where the data is yours) and documentation to you on final acceptance. We don't keep a back-door licence and we don't lock you into a maintenance contract.

What we retain is our pre-existing toolbox — reusable libraries, calibration utilities, generic data parsers, the OWL EYE® core — which we license to you, royalty-free, for use on the delivered tool. This is the same boundary that any reputable engineering firm draws: we bring the toolbox, you keep the deliverable.

If you want a different IP arrangement — for example a joint patent on a novel algorithm, or a co-developed model that we both reuse with consent — we structure that explicitly in the project contract. Tell us up-front in the Discovery workshop.

Full engagement details on our Industrial Perception AI page.
You do. Our standard contract transfers full ownership of the project-specific code, model weights, training data (where the data is yours) and documentation to you on final acceptance. We don't keep a back-door licence and we don't lock you into a maintenance contract.

What we retain is our pre-existing toolbox — reusable libraries, calibration utilities, generic data parsers, the OWL EYE® core — which we license to you, royalty-free, for use on the delivered tool. This is the same boundary that any reputable engineering firm draws: we bring the toolbox, you keep the deliverable.

If you want a different IP arrangement — for example a joint patent on a novel algorithm, or a co-developed model that we both reuse with consent — we structure that explicitly in the project contract. Tell us up-front in the Discovery workshop.

Full engagement details on our Industrial Perception AI page.
You do. Our standard contract transfers full ownership of the project-specific code, model weights, training data (where the data is yours) and documentation to you on final acceptance. We don't keep a back-door licence and we don't lock you into a maintenance contract.

What we retain is our pre-existing toolbox — reusable libraries, calibration utilities, generic data parsers, the OWL EYE® core — which we license to you, royalty-free, for use on the delivered tool. This is the same boundary that any reputable engineering firm draws: we bring the toolbox, you keep the deliverable.

If you want a different IP arrangement — for example a joint patent on a novel algorithm, or a co-developed model that we both reuse with consent — we structure that explicitly in the project contract. Tell us up-front in the Discovery workshop.

Full engagement details on our Industrial Perception AI page.
You do. Our standard contract transfers full ownership of the project-specific code, model weights, training data (where the data is yours) and documentation to you on final acceptance. We don't keep a back-door licence and we don't lock you into a maintenance contract.

What we retain is our pre-existing toolbox — reusable libraries, calibration utilities, generic data parsers, the OWL EYE® core — which we license to you, royalty-free, for use on the delivered tool. This is the same boundary that any reputable engineering firm draws: we bring the toolbox, you keep the deliverable.

If you want a different IP arrangement — for example a joint patent on a novel algorithm, or a co-developed model that we both reuse with consent — we structure that explicitly in the project contract. Tell us up-front in the Discovery workshop.

Full engagement details on our Industrial Perception AI page.

Can you use our existing cameras and LiDAR sensors?Können Sie unsere vorhandenen Kameras und LiDAR-Sensoren weiterverwenden?Can you use our existing cameras and LiDAR sensors?Can you use our existing cameras and LiDAR sensors?Can you use our existing cameras and LiDAR sensors?Can you use our existing cameras and LiDAR sensors? ＋

 Yes — in most cases. Our toolchain is sensor-agnostic on the data layer. If your sensors deliver a standard format (PCD, LAS, E57 for point clouds; RTSP, GigE Vision, USB3 Vision for cameras) we can ingest them in a day. We've worked with Riegl, Livox, Faro, Hesai, Velodyne, Ouster, Basler, FLIR, Allied Vision and IDS cameras.

We'll tell you honestly when the existing hardware isn't the right tool. Common cases where we recommend a replacement:

- The existing LiDAR is too narrow (FoV or range) to cover the area you want classified — usually solved by repositioning before buying anything new.
- The camera is auto-exposing on a high-contrast scene (sun + shadow at a gate), which breaks classification reliability — solved by switching to a manual-exposure industrial camera with HDR sensor.
- The existing sensor's vendor lock-in (proprietary stream format, no documented SDK) makes integration cost more than a Livox replacement.

We don't earn a margin on reselling hardware to you. If you do want us to source new sensors, we do that through our normal Hardware & products channel at list price. See Industrial Perception AI for how we scope it.
In den meisten Fällen ja. Unsere Toolchain ist auf der Datenebene sensor-agnostisch. Wenn Ihre Sensoren ein Standard-Format liefern (PCD, LAS, E57 für Punktwolken; RTSP, GigE Vision, USB3 Vision für Kameras), binden wir sie an einem Tag an. Wir haben mit Riegl, Livox, Faro, Hesai, Velodyne, Ouster, Basler, FLIR, Allied Vision und IDS gearbeitet.

Wir sagen Ihnen ehrlich, wenn die vorhandene Hardware nicht das richtige Werkzeug ist. Übliche Fälle, in denen wir zum Tausch raten:

- Der vorhandene LiDAR ist zu schmal (FoV oder Reichweite), um den gewünschten Bereich abzudecken — meist durch Repositionierung gelöst, bevor neu gekauft wird.
- Die Kamera auto-belichtet auf einer Szene mit hohem Kontrast (Sonne + Schatten am Tor), das bricht die Klassifikations-Zuverlässigkeit — gelöst durch Wechsel auf eine manuell belichtbare Industrie-Kamera mit HDR-Sensor.
- Vendor-Lock-in des vorhandenen Sensors (proprietärer Stream, kein dokumentiertes SDK) macht die Anbindung teurer als ein Livox-Ersatz.

Wir verdienen nicht am Weiterverkauf von Hardware an Sie. Wenn Sie wollen, dass wir neue Sensoren beschaffen, läuft das über unseren regulären Kanal Handelsware & Produkte zum Listenpreis. Scoping-Modell siehe Industrielle Objekterkennung.
Yes — in most cases. Our toolchain is sensor-agnostic on the data layer. If your sensors deliver a standard format (PCD, LAS, E57 for point clouds; RTSP, GigE Vision, USB3 Vision for cameras) we can ingest them in a day. We've worked with Riegl, Livox, Faro, Hesai, Velodyne, Ouster, Basler, FLIR, Allied Vision and IDS cameras.

We'll tell you honestly when the existing hardware isn't the right tool. Common cases where we recommend a replacement:

- The existing LiDAR is too narrow (FoV or range) to cover the area you want classified — usually solved by repositioning before buying anything new.
- The camera is auto-exposing on a high-contrast scene (sun + shadow at a gate), which breaks classification reliability — solved by switching to a manual-exposure industrial camera with HDR sensor.
- The existing sensor's vendor lock-in (proprietary stream format, no documented SDK) makes integration cost more than a Livox replacement.

We don't earn a margin on reselling hardware to you. If you do want us to source new sensors, we do that through our normal Hardware & products channel at list price. See Industrial Perception AI for how we scope it.
Yes — in most cases. Our toolchain is sensor-agnostic on the data layer. If your sensors deliver a standard format (PCD, LAS, E57 for point clouds; RTSP, GigE Vision, USB3 Vision for cameras) we can ingest them in a day. We've worked with Riegl, Livox, Faro, Hesai, Velodyne, Ouster, Basler, FLIR, Allied Vision and IDS cameras.

We'll tell you honestly when the existing hardware isn't the right tool. Common cases where we recommend a replacement:

- The existing LiDAR is too narrow (FoV or range) to cover the area you want classified — usually solved by repositioning before buying anything new.
- The camera is auto-exposing on a high-contrast scene (sun + shadow at a gate), which breaks classification reliability — solved by switching to a manual-exposure industrial camera with HDR sensor.
- The existing sensor's vendor lock-in (proprietary stream format, no documented SDK) makes integration cost more than a Livox replacement.

We don't earn a margin on reselling hardware to you. If you do want us to source new sensors, we do that through our normal Hardware & products channel at list price. See Industrial Perception AI for how we scope it.
Yes — in most cases. Our toolchain is sensor-agnostic on the data layer. If your sensors deliver a standard format (PCD, LAS, E57 for point clouds; RTSP, GigE Vision, USB3 Vision for cameras) we can ingest them in a day. We've worked with Riegl, Livox, Faro, Hesai, Velodyne, Ouster, Basler, FLIR, Allied Vision and IDS cameras.

We'll tell you honestly when the existing hardware isn't the right tool. Common cases where we recommend a replacement:

- The existing LiDAR is too narrow (FoV or range) to cover the area you want classified — usually solved by repositioning before buying anything new.
- The camera is auto-exposing on a high-contrast scene (sun + shadow at a gate), which breaks classification reliability — solved by switching to a manual-exposure industrial camera with HDR sensor.
- The existing sensor's vendor lock-in (proprietary stream format, no documented SDK) makes integration cost more than a Livox replacement.

We don't earn a margin on reselling hardware to you. If you do want us to source new sensors, we do that through our normal Hardware & products channel at list price. See Industrial Perception AI for how we scope it.
Yes — in most cases. Our toolchain is sensor-agnostic on the data layer. If your sensors deliver a standard format (PCD, LAS, E57 for point clouds; RTSP, GigE Vision, USB3 Vision for cameras) we can ingest them in a day. We've worked with Riegl, Livox, Faro, Hesai, Velodyne, Ouster, Basler, FLIR, Allied Vision and IDS cameras.

We'll tell you honestly when the existing hardware isn't the right tool. Common cases where we recommend a replacement:

- The existing LiDAR is too narrow (FoV or range) to cover the area you want classified — usually solved by repositioning before buying anything new.
- The camera is auto-exposing on a high-contrast scene (sun + shadow at a gate), which breaks classification reliability — solved by switching to a manual-exposure industrial camera with HDR sensor.
- The existing sensor's vendor lock-in (proprietary stream format, no documented SDK) makes integration cost more than a Livox replacement.

We don't earn a margin on reselling hardware to you. If you do want us to source new sensors, we do that through our normal Hardware & products channel at list price. See Industrial Perception AI for how we scope it.
 

LiDAR crane anti-collision
for industrial bays. Kran-Anti-Kollision per LiDAR
für industrielle Hallen. LiDAR crane anti-collision
for industrial bays. LiDAR crane anti-collision
for industrial bays. LiDAR crane anti-collision
for industrial bays. LiDAR crane anti-collision
for industrial bays.