Team Details

​

• Team name: RouteMind AI
• Team leader name: Bhavesh Arun Vadnere
• Problem Statement: Unpredictable weather and traffic along logistics corridors cause massive shipment delays, resulting in financial losses and supply chain disruptions. Route managers currently lack proactive, AI-driven foresight to reroute shipments before they hit these bottlenecks.

​

Brief about solution

RouteMind AI is an AI-powered route disruption prediction platform that helps logistics planners identify delivery risks before shipment starts.

​

The system allows users to enter a source and destination route. It then:

​

• Fetches route geometry
• Samples weather conditions along the route
• Analyzes disruption signals
• Uses Google Gemini AI to predict delay probability
• Suggests alternate safer routes

​

This enables proactive decision-making and prevents cascading delivery failures.

Opportunities

​

• How different is it? Unlike standard GPS that only shows current traffic, RouteMindAI samples micro-weather data across the entire future route and uses GenAI to predict complex delay risks.

​

• How will it solve the problem? It provides early warnings and actionable alternate route suggestions, shifting logistics from a reactive "damage control" model to a proactive planning model.

​

• USP: The seamless pipeline combining geographic data (OpenRouteService) and weather data (OpenWeatherMap) directly into Google Gemini 2.5 Flash for human-readable risk assessments and automated analytics logging.

List of features

• Automated Route Geometry Extraction: Instantly maps coordinate paths from Source to Destination.

​

• Micro-Weather Route Sampling: Dynamically samples rain, cloud cover, and storm probability along the exact shipment path.

​

• Gemini-Powered Risk Prediction: Generates a Low/Medium/High risk classification with exact delay probabilities (%) and actionable alternate routes.

​

• High-Risk Corridor Analytics: A Firestore-backed dashboard tracking historically problematic routes to aid long-term supply chain planning.

Process flow diagram or Use-case diagram

User enters source city

User enters destination city

↓

RouteMind AI fetches route geometry

↓

Weather signals sampled along route

↓

Structured route data sent to Gemini API

↓

Gemini predicts disruption probability

↓

System returns: Risk Level, Delay Probability %

Explanation

Alternate Route Suggestion

↓

Prediction stored in Firestore

↓

Analytics dashboard updated

Wireframes/Mock diagrams

Architecture diagram

Flutter Frontend

↓

Route Input Module

↓

Route Service (OpenRouteService API)

↓

Weather Sampling Module (OpenWeather API)

↓

Gemini Prediction Engine

↓

Firestore Database Storage

↓

Analytics Dashboard + Map Visualization

Technologies to be used in the solution

• Frontend: Flutter

​

• Backend: Firebase Firestore

​

• AI Layer: Google Gemini API

​

• Routing Engine: OpenRouteService API

​

• Weather Intelligence: OpenWeather API

​

• Visualization: Flutter Map

​

• Analytics: fl_chart

​

• Cloud Infrastructure: Firebase ecosystem

Estimated implementation cost

Prototype stage: ₹0 (Free-tier services used)

​

Production deployment estimate:

​

Snapshots of the MVP

Additional Details/Future Development

• Live traffic congestion API integration

�• ML-based corridor risk learning

�• Warehouse bottleneck detection

�• Multi-route comparison predictions

�• Driver mobile alert interface

�• Predictive ETA forecasting

�• Enterprise logistics dashboard version

Provide links to your:

​

1. GitHub Public Repository: https://github.com/BhaveshV23/RouteMindAI

​

• Demo Video Link (3 Minutes): https://drive.google.com/file/d/1MWeILciarlwSSka0yaAojNnoKOIhwD_v/view

​

3. MVP Link: https://routemind-ai-27861.web.app

​

4. Working Prototype Link: https://routemind-ai-27861.web.app

​