Inspiration
We wanted to solve a real logistics problem: choosing the best freight route is not always about taking the shortest path. Fuel cost, traffic, weather, road quality, safety, cargo type, and delivery deadlines all matter.
What it does
SmartFreight compares multiple routes and uses AI to rank them based on fuel efficiency, traffic, weather, safety, road quality, cost, and delivery time. It recommends the best route and explains why it was selected.
How we built it
We built the system using Python Flask, Random Forest, OSRM, Nominatim, Leaflet.js, SQLite, HTML, Tailwind CSS, and JavaScript. The backend handles routing, geocoding, validation, route calculations, and AI scoring, while the frontend provides an interactive logistics dashboard.
Challenges we ran into
One of our biggest challenges was making sure locations were correctly identified within India. We also had to handle ambiguous locations, generate multiple routes, combine different factors into a meaningful score, and make the AI's decision easy for users to understand.
Accomplishments that we're proud of
We built a complete freight route optimization system that not only recommends the best route but also explains the reasoning behind it. We're especially proud of the AI-based ranking, strict location validation, route comparison, and interactive map.
What we learned
We learned how to bring together AI, routing APIs, geocoding, maps, logistics calculations, and explainable AI into one practical application. We also learned that an AI system should not just give an answer but should explain the reason behind its decision.
What's next for AI Smart Freight Route Optimizer
Next, we want to integrate live traffic and weather data, real-time GPS tracking, advanced ML models, dynamic rerouting, fuel-price updates, and fleet-level optimization to make SmartFreight more useful for real-world logistics.
Log in or sign up for Devpost to join the conversation.