🚂 RASTA (Railway AI Scheduling & Traffic Assistant)

Maximizing Section Throughput Using AI-Powered Precise Train Traffic Control

• Report Bug • Request Feature

---

📋 Table of Contents

• About The Project
• Key Features
• Tech Stack
• Getting Started
• AI Algorithms
• API Documentation
• Team

---

🎯 About The Project

An intelligent decision-support system for Indian Railways that optimizes train scheduling, resolves conflicts in real-time, and maximizes section throughput using advanced AI algorithms.

Problem Statement (SIH25022)

Develop an AI-powered system to assist section controllers in making optimized, real-time decisions for train precedence and crossings to enhance efficiency and reduce delays.

Solution Highlights

• ✅ Real-time conflict detection and resolution
• ✅ Multi-algorithm AI optimization (MILP, GA, CP)
• ✅ Dynamic platform allocation
• ✅ Interactive monitoring dashboard
• ✅ Smart pathfinding with obstacle avoidance

---

✨ Key Features

Feature	Description	Status
🔄 Real-Time Monitoring	Track 1,247+ trains simultaneously	✅ Active
🤖 AI Optimization	Multi-algorithm approach for optimal routing	✅ Active
⚡ Conflict Resolution	Automated detection and resolution	✅ Active
📊 Interactive Dashboard	Live visualization and control interface	✅ Active
🛤️ Dynamic Routing	Smart platform allocation using Dijkstra's algorithm	✅ Active
📈 Performance Analytics	Real-time metrics and KPI tracking	✅ Active

---

🛠️ Tech Stack

Backend

Frontend

Map Visualization

---

🚀 Getting Started

Prerequisites

• 
• 
• 

Installation

1. Clone the repository

   git clone https://github.com/shivansh-source/SIH-hackathon.git
   cd SIH-hackathon

2. Setup Backend

   pip install fastapi uvicorn pydantic
   python main.py
   # Server runs on http://127.0.0.1:8000

3. Setup Frontend Dashboard

   cd frontend
   # Open index.html in browser or serve locally
   python -m http.server 8080

4. Setup Railway Map

   cd railway-map
   npm install
   npm run dev
   # Runs on http://localhost:5173

---

🧠 AI Algorithms

Algorithm	Success Rate	Runtime	Use Case
🎲 MILP Optimizer	94%	45s	Optimal train scheduling
⚡ Constraint Programming	89%	12s	Real-time conflict resolution

|

🔧 API Documentation

Get Optimized Route

POST /api/get-route
Content-Type: application/json

{
  "train_id": "19670",
  "yard_data": {
    "tracks": [...],
    "points": [...], 
    "platforms": [...],
    "signals": [...]
  }
}

Response:

{
  "id": "19670",
  "route": ["T_W_UP_IN", "ML_UP", "P_W_UP_PL4", "PL4", "P_E_PL4_UP", "T_E_UP_OUT"]
}

---

System Architecture

🌐 Frontend Dashboard ↔️ 🔗 FastAPI Backend ↔️ 🗂️ Train Database
        ↓                      ↓                    ↓
📊 Real-time UI         🤖 AI Optimization    📋 75+ Trains Data

---

👥 Team

Developer	Role	GitHub
shivansh-source	Backend Engineer
KariraLakshya	Data Management & Frontend
Akshat-Raj	AI-ML Engineer
Astuti-Singh	Frontend Engineer
Aman-Thakur	AI-ML engineer
Nishi-Mittal	AI-ML engineer

---

🇮🇳 Built with ❤️ for Smart India Hackathon 2025

Revolutionizing Indian Railways through AI-powered intelligent traffic management