This project explores a genetic algorithm-based solution for optimizing delivery routes across multiple cities using several trucks. It simulates city coordinates, generates a distance matrix, and applies evolutionary strategies to minimize total travel cost.

To design and implement a scalable algorithm that finds efficient delivery routes for multiple trucks across a randomly generated map of cities minimizing total travel distance and demonstrating the effectiveness of heuristic-based problem solving.

• Developed a Genetic Algorithm from scratch for multi-truck route planning
• Simulated city coordinate data and computed real-time distance matrices
• Visualized logistics data using Seaborn and Matplotlib for better interpretability
• Implemented a fitness-based evolution strategy with custom mutation and crossover logic
• Fine-tuned algorithm parameters to optimize convergence speed and solution quality

The model allows full control over simulation settings:

POPULATION_SIZE = 100
NUM_GENERATIONS = 100
CITY_COUNT = 10
TRUCK_COUNT = 5
Mutation_probability = 0.01

Python – Core implementation

NumPy – Data handling and distance calculations

Matplotlib & Seaborn – Visual analytics

NetworkX – Graph-based representations of city networks

Clone the repository:

git clone https://github.com/ABE1617/Multi-Truck-Delivery-Route-Optimization-Using-Genetic-Algorithm.git
cd Multi-Truck-Delivery-Route-Optimization-Using-Genetic-Algorithm

Install required libraries:

pip install -r requirements.txt

Run the notebook:

jupyter notebook ALGO_G2_SEMI_Final_ABE.ipynb

Successfully demonstrated a scalable approach to vehicle routing problems using evolutionary algorithms highlighting both the flexibility of heuristic methods and the power of data visualization for logistics optimization.