Skip to main content
Contact Us
CASE STUDY · LOGISTICS AND MANUFACTURING

Rugged Fanless PC Powers Real-Time AI Inference on Smart Factory Floor

TypeCase study
Published1 Dec 2024
AuthorAndrew WhitehouseManaging Director
Reading time9 min

A leading provider of material handling equipment, from electric forklifts and pallet jacks to reach trucks and AGVs, asked us for a rugged fanless PC with built-in AI processing. Its vehicles serve retail, warehousing and distribution customers, and the next step was smarter, safer autonomy on the smart factory floor.

The computer had to run real-time AI for pedestrian avoidance and route navigation, on a vehicle, in a dusty building full of shock and vibration. It is the kind of system we supply for logistics and warehousing and factory automation.

02Challenge

Why AI on a factory vehicle is hard

Smart factories change layout and traffic constantly. Legacy detection systems struggle with that, raising false alarms or missing hazards, which costs time and creates risk. Autonomous vehicles need real-time AI inference to watch their surroundings, avoid collisions and adapt as conditions change.

A discrete GPU could provide the AI, but it brings high power draw and fans for cooling, and a vehicle exposes both to constant shock, vibration and dust. NVIDIA Jetson Orin NX offers another route, with up to 100 TOPS at 10–25 W in a module that runs inside a sealed, fanless chassis.

Factor Discrete GPU Jetson Orin NX
Power draw High, needs a large supply 10–25 W
Cooling Fans and airflow Fanless, through the chassis
Shock, vibration and dust Fans and slots are weak points Solid-state, sealed design
AI performance Very high, at a cost in power and heat Up to 100 TOPS

Without a fan, heat leaves through the chassis itself; our explainer on how a fanless PC works covers the thermal design.

Products · 2Solution

The Premio JCO‑3000

A rugged fanless Jetson Orin NX computer from Premio (formerly C&T Solution); the 4× PoE+ build suits camera and LiDAR-equipped vehicles.

Premio JCO-3000-ORN-B-4P-P
Premio JCO‑3000‑ORN‑B‑4P‑P

NVIDIA Jetson Orin NX/Nano Rugged Edge AI Computer with 4x PoE+ GbE

AI
20–100 TOPS
SOM
NVIDIA Jetson Orin NX 16 GB
Ethernet
4× GbE (4× PoE)
View product
Premio JCO-3000-ORN-B-4L-P
Premio JCO‑3000‑ORN‑B‑4L‑P

NVIDIA Jetson Orin NX or Orin Nano Fanless Edge AI Computer with 4x Gigabit LAN

AI
20–100 TOPS
SOM
NVIDIA Jetson Orin NX 16 GB
Ethernet
4× GbE
View product
Key features · 3Solution

What made the JCO-3000 fit

Three features matched the customer’s criteria for deployment across its vehicle range.

Rugged chassis with fanless cooling

A dustproof, fanless enclosure and solid-state design resist shock and vibration, with low power draw and reliable thermal management. Preventing collisions and minimising downtime keeps operating costs down.

PoE for cameras and LiDAR

Four Gigabit Ethernet ports with Power over Ethernet power and connect the cameras and LiDAR sensors on each vehicle over one cable, with the bandwidth for real-time processing.

Out-of-band remote management

Allxon out-of-band management lets administrators monitor, diagnose and recover systems remotely, even when the main system is offline, cutting site visits and downtime across distributed fleets.

Solution

A closer look

  1. 01

    Rugged fanless chassis

    The Jetson Orin NX computer built for edge AI on vehicles.

    View range
  2. 02

    Four PoE ports

    Power and data for cameras and LiDAR over single cables.

  3. 03

    Allxon out-of-band

    Remote monitoring and recovery for distributed systems.

    View range
Results · 4 outcomesSmart factory floor

What changed on the factory floor

With the JCO-3000 onboard, the customer's autonomous vehicles see and adapt in real time.

  1. Outcome 01

    Real-time pedestrian avoidance

    AI object detection spots people around the vehicle as it moves, promoting workplace safety.

  2. Outcome 02

    Smarter route navigation

    Imaging data processed on the vehicle lets it adapt to shifting layouts and traffic patterns.

  3. Outcome 03

    Fewer collisions and stoppages

    Preventing collisions and minimising downtime reduces operating costs for the customer's clients.

  4. Outcome 04

    Remote fleet maintenance

    Out-of-band management resolves issues without travelling to each site.

05FAQs

Smart factory FAQs

  1. What Is a Pedestrian Detection System?

    A pedestrian detection system uses sensors on a vehicle, such as AI cameras, radar, LiDAR or worker-worn tags, to spot people nearby and warn the operator or slow and stop the vehicle. In cars it supports automatic emergency braking. On forklifts and AGVs it reduces collisions in busy warehouses and factories.

  2. AGV vs AMR: What Is the Difference?

    An AGV (automated guided vehicle) follows fixed routes marked by magnetic tape, wires, reflectors or floor codes, and stops when something blocks its path. An AMR (autonomous mobile robot) builds a map of its surroundings with sensors and plans its own route, steering around people and obstacles. AGVs suit stable, repetitive routes; AMRs suit changing layouts.

  3. What Is an AGV?

    An AGV (automated guided vehicle) is a driverless vehicle that moves materials around factories and warehouses along predefined routes, guided by wires, magnetic tape, lasers or floor markers. Common types include tow tractors, load carriers, automated forklifts and pallet jacks. AGVs take repetitive transport jobs off people and repeat the same route reliably, shift after shift.

  4. What Is Out-of-Band Management?

    Out-of-band (OOB) management is a way to control a device remotely through a separate channel that does not depend on its main operating system or network. It lets administrators power-cycle, monitor and recover a computer even when it has crashed or gone offline, without a site visit.

  5. What Are the Advantages of Fanless Computers?

    Fanless computers cool themselves passively, through a finned heatsink chassis and heat pipes, instead of a fan. With no moving parts and no airflow drawing in dirt, they are more reliable in dusty or vibrating places, silent, low maintenance and easy to seal, which is why they are the standard choice for industrial and embedded use.

  6. Jetson Orin Nano vs Orin NX: What Is the Difference?

    The Jetson Orin Nano delivers up to 67 TOPS in 7 to 25 W with 4 to 8 GB of memory, suited to entry-level, low-power vision. The Orin NX steps up to 157 TOPS in 10 to 40 W with 8 to 16 GB, adds deep learning accelerators and a hardware video encoder, and handles multi-camera, heavier inference.

// Next Step

Adding AI to vehicles on the factory floor?

Tell us about your application and a member of the team will get right back to you.

Phone · UK +44(0)1785 558 300
Email sales@things-embedded.com