1. Home
  2. Case Studies
  3. AI fleet optimisation
Case study · Logistics

AI fleet optimisation: route planning and delivery time prediction for a logistics fleet

ScalaCode built an AI fleet optimisation system for a logistics enterprise. A Python and TensorFlow engine plans routes from live traffic and weather data and predicts delivery times, and fleet managers monitor every vehicle from a Vue.js dashboard.

IndustryLogistics
ProductFleet route optimisation and monitoring
Scala AIAITensorFlow route and delivery time models
IntegrationsGPS devices and ERP systems
The client

A logistics enterprise with a large fleet

The client wanted to optimise its fleet operations, reduce fuel and operating costs, and improve delivery efficiency. Fleet managers needed live route optimisation, accurate delivery time predictions and a dashboard simple enough to use every day.

The challenge

What made fleet optimisation hard

1

Traffic and weather change constantly

Routes had to respond to live traffic and weather conditions as they changed.

2

Legacy systems and GPS devices

The platform had to work with the client's existing legacy systems and in-vehicle GPS devices.

3

Data from a large fleet

Every vehicle sends data, so the system had to scale to the full size of the fleet.

The solution

Route optimisation driven by live conditions

An AI engine plans and adjusts routes, and a dashboard gives fleet managers a live view of the whole fleet.

  1. 01

    Route optimisation engine

    Python and TensorFlow models plan routes and adjust them as conditions change.

  2. 02

    Live traffic and weather feeds

    Real-time data feeds supply traffic and weather updates to the engine.

  3. 03

    Delivery time and fuel models

    Predictive models estimate delivery times and fuel efficiency.

  4. 04

    Fleet management dashboard

    A Vue.js dashboard shows vehicles and fleet performance analytics in real time.

  5. 05

    Alerts for fleet managers

    Managers get alerts for delays, maintenance and fuel optimisation.

  6. 06

    GPS and ERP integration

    A Node.js backend connects the platform to existing GPS devices and ERP systems.

The results

Fleet managers see and adjust every route live

Routes adjust to traffic and weather as conditions change, delivery times come from predictive models, and fleet managers follow performance, delays and maintenance alerts from one dashboard.

Real-time

route adjustments

GPS + ERP

systems integrated

Tech stack

What AI fleet optimisation runs on

AI

Python, TensorFlow

Frontend

Vue.js

Backend and data

Node.js, PostgreSQL

Book a free strategy call

Plan a build like AI fleet optimisation for your business

  • 30 minutes with the ScalaCode team
  • What is realistic, what it costs and how long it takes
  • You decide afterwards whether to build with us

Book your strategy call

Takes 20 seconds