Skip to content
TriRide
Contact Us

This is your Hall

3D stereo safety sensor for AMRs and AGVs with automotive series cameras. Protective field and perception in one device.

AGVs with warning and protection fields in a warehouseVisualization

Engineering Kit

Your engineering kit for every robot that shares space with people.

The same qualified building blocks, combined per vehicle: surround safety for AMRs, front and rear fields for pallet AGVs, wide 3D perception for humanoids, long range for outdoor machines.

SoC

NVIDIA Jetson Orin NX

Depth, perception and the safety wrapper run on board. Your robot gets results, not raw pixels.

NVIDIA Jetson compute module
Output
Ethernet · SDK · ROS 2
Safety
SIL 2 / PL d (target)
C2 · C3

Two 200° fisheye cameras

Wide 3D stereo depth right around the vehicle: raised forks, overhanging loads, people bending over.

Resolution
2 × 3 MP
FoV
200° each
Depth
0.2 – 15 m
TriRide reference sensor head
C1

8 MP sensing camera

A 120° long-range eye for object and boundary detection, far beyond the stop distance.

Resolution
8 MP
FoV
120°
Range
up to 80 m
L

LiDAR, SONY AS-DT1

A metric cross-check of the stereo depth for applications that want a second physical principle.

Role
diverse redundancy
Status
optional

How it works

From three cameras to one safety decision.

Three perception algorithms run in parallel and are fused into one 3D free-space map. The safety function decides on that map, while object classes and tracks come on top for docking, navigation without additional hardware needs.

  1. 01 · Input

    Three-camera sensor head

    • 1 × 8 MP sensing camera, 120°
    • 2 × 3 MP fisheye cameras, 200°
    • Optional LiDAR for a metric cross-check

    Sees the aisle ahead and the area right around the vehicle, in 3D, not just in a single scan plane.

  2. 02 · Perception

    Three algorithms in parallel

    1. 2D fence detection: boundaries and drivable-area edges
    2. 2D object detection: people, vehicles, infrastructure
    3. 3D stereo depth across the three cameras

    Your robot knows where it may drive, what is in its way (a person, a forklift or a rack) and how far away it is.

  3. 03 · Fusion

    One 3D free-space map

    Low- and mid-level fusion of all three algorithms. Every result is checked against the others before it counts.

    One reliable picture of the shop floor for safety, path planning and docking.

  4. 04 · Safety output

    Free vs. occupied: one clear decision

    The safety function, designed for SIL 2 / PL d, decides on the free space map and triggers the safe state.

    With object classes and tracks, navigation in mixed traffic and smarter fleet behavior with reduced downtime is enabled.

FuSa AI Agents

Safety evidence in weeks, not months.

TriRide's agentic FuSa AI system verifies hardware and software functional safety requirements from building blocks that are qualified once, their integration, and automatically generates standards-compliant work products.

  • Faster time to market
  • Lower cost
  • Predictable certification

done · package ready for engineer review and sign-off

Inputs

  • Item definitionassumed item and safety goals
  • Architectureelements, interfaces, variants
  • Supplier datacomponent safety manuals, FMEDAs, FIT rates
    • sys-sads, done
    • sys-tsr, done
    • sys-tsc, done
    • sys-hsi, done
    • hw-hsr, done
    • sw-ssr, done
    • sys-fmea, done
    • sys-fta, done
    • sys-dfa, done
    • hw-design, done
    • hw-fmea, done
    • hw-fta, done
    • hw-dfa, done
    • sw-arch, done
    • sw-fmea, done
    • sw-fta, done
    • sw-dfa, done
    • sw-calib, done
    • hw-fmeda, done
    • sm-catalog, done
    • test-spec, done
    • traceability, done
  • Review & QAIndependent review

    • verification-review, done

    separate from every author

  • safety-orchestratorcreation order, gating, status write-back
  • process registerlive status, dependencies, open markers
  • 21 tool scriptsgeneration, rendering, structural checks

Outputs

  • Safety work productsTSR, TSC, HSI, HSR, SSR
  • Safety analysesFMEA, FTA, DFA, FMEDA
  • SEooC safety packageSafety Manual and assumptions of use
  • Traceability matrixrequirement to test, both ways
  • Verification evidencetest specification and review records
Seven groups, one direction.

Requirements first, then system, hardware and software analysis, then the quantitative metrics, the safety mechanisms and finally verification. Each phase is gated by the orchestrator.

Applications

Pick a vehicle. See what it sees.

Top view, schematic. Blue is the 3D field of view, red the protective field that triggers the safe state, amber the warning field that slows the vehicle down.

Choose an application
Visualization

Autonomous mobile robots

Goods-to-person and transport robots in shared aisles. One module covers 240° in 3D around the front and sides, so people stepping out of a rack row are seen before they are in the path. The warning field adapts to speed, so the robot slows down instead of stopping, and keeps moving when the aisle is clear.

Configuration
1 module · 1 × 8 MP + 2 × 3 MP
Fields
Protective 0–3 m, warning field adapts with speed
Standards
ISO 3691-4 · IEC 61508 SIL 2 · ISO 13849 PL d
Bonus
Objects and tracks for navigation and fleet analytics

Data Footage

Safety camera with self-calibrating 3D depth

One device for perception and safety on mobile machines, dense 3D stereo depth, free space and 2D perception. The camera calibrates itself during runtime.

Recorded with the prototype
Camera colour: Virtual camera sweep through the point cloud
Camera colourVirtual camera sweep through the point cloud
Range from sensor: 0.3 – 6 m colour scale · white-ringed dots: AS-DT1 LiDAR
Range from sensor0.3 – 6 m colour scale · white-ringed dots: AS-DT1 LiDAR
Free space · top view: Drivable area in green, obstacles in red
Free space · top viewDrivable area in green, obstacles in red
Person detection: Person segmented on the free space, perspective view
Person detectionPerson segmented on the free space, perspective view

What you get

Start with a kit. Build the pilot with us.

  1. Evaluation kit

    Unbox it. Mount it.See your hall in 3D.

    Test TriRide on your own vehicle, in your own hall.

    • Sensor head + Jetson Orin
    • Ethernet
    • SDK
    • ROS 2
    • Your recordings
    Request a kit →
    TriRide reference sensor head
  2. Pilot project · together

    Your vehicle.Your safety case.

    We work out the safety solution for your vehicle with you, from mounting to the documents your assessor needs.

    1. Variant and mounting
    2. Safety delta for your variant
    3. Safety Manual for your assessor
    Talk about a pilot →
    Safety ManualISO 13849 · IEC 61508
  3. Roll out · scale

    Next robot?Only the Δ is new.

    Qualified blocks are reused for every new variant. Instead of starting from scratch, you only qualify what changed.

    Let's talk about your robot →
    • AMR
    • AGV
    • Humanoid
    • Outdoor
    • + your next one
← Drag or scroll →
  1. Kit
  2. Pilot
  3. Roll-out

Brochure

Specifications

Features
TechnologyPassive 3D stereo, multi-baseline, with LiDAR
Protective field range4.0 m (body, 200 mm) · 3.0 m (leg, 70 mm) · 2.0 m (arm, 40 mm)
Warning field range10 m
Field of view175° × 165° (3D Stereo) / 240° × 165° (2D Mono)
Response time≤ 100 ms
Simultaneously monitored fields3 per field set (1 protective, 2 warning); ≥ 32 field sets
Safety-related parameters
Safety integrity levelSIL 2 (IEC 61508)
CategoryCategory 3 (ISO 13849-1)
Performance levelPL d (ISO 13849-1)
PFHD< 1 × 10−7 /h
Architecture2oo3D over 3 stereo pairs, 1oo2D with LiDAR (HFT 1)
Functions
Protective field switching✓ (by vehicle speed, steering angle)
Self-monitoring of camera alignment✓
Deterministic (Safety) + AI (Comfort)✓
Measured data output✓ Point Cloud+, BEV, Moving Objects with TTC
Depth and image sensors
Image sensors2 × 3 MP fisheye 200°, 1 × 8 MP 120°; automotive series
Depth range0.2 m … 15 m
Depth precision≤ 1 % at 2 m, ≤ 2 % at 4 m, ≤ 3 % at 8 m
Frame rate≥ 15 Hz (goal 30 Hz)
Interfaces
InterfaceCamera: GMSL2, LiDAR: USB-C
Data interface10GbE via sensor aggregator (optional)
SoftwareSDK, ROS 2 driver
Electrical and ambient data
Supply voltageCompute unit: 24 V DC (16.8 V … 30 V); cameras: 12 V via GMSL2 (PoC); LiDAR: 5 V via USB-C
Power consumption≤ 40 W system, incl. cameras and LiDAR (25 W compute mode)
Enclosure ratingIP65 / IP67
Ambient operating temperature−40 °C … +85 °C (Cameras) - -20°C …+55°C (LIDAR)
Ambient light immunity3 klx, operation up to 40 klx

Product images show the reference sensor head. Specifications are preliminary and subject to change.

Download brochure

Let's talk

Let's talk about your robot.