Fleet Simulator: UMINHO AI 25/26

A comprehensive fleet simulation for analyzing EVs and Gas vehicles in urban environments.

Fleet Simulator is a desktop application developed for the Artificial Intelligence class at Universidade do Minho. It provides a robust environment to simulate and optimize fleet operations, comparing the efficiency and environmental impact of Electric Vehicles (EVs) versus Gas Vehicles using real-world map data.

Overview

We built this project to simulate and analyze the complexities of urban fleet management. Fleet Simulator models traffic conditions, hotspot demands, charging/fueling logistics, and vehicle dispatching. It demonstrates how AI strategies can be used to optimize routes and manage a mixed fleet of vehicles efficiently across large city maps (e.g., Braga).

Screenshots

Key Features

Realistic Map Data

• OSM Integration: Uses real-world mapping data (OpenStreetMap) for node generation, edge mapping, and realistic coordinate systems.

Dynamic Fleet Simulation

• Mixed Fleet Engine: Models both Electric Vehicles (EVs) and Gas Vehicles, natively handling battery/fuel constraints and charging speeds.
• Traffic & Hotspots: Simulates varying traffic conditions and demand hotspots that shift dynamically throughout the day.

Advanced Dispatching

• AI Routing: Assigns pending ride requests and manages dynamic routing based on changing environments.
• Station Management: Simulates charging station usage, queuing, and unexpected stochastic station failures.

Tech Stack

The project was built using:

Application & Simulation Engine

• Language: Python
• GUI Framework: Tkinter for displaying vehicle metrics, map views, and weather states.
• Geographic Data: OpenStreetMap data retrieved via OSMnx.
• Data Handling: Custom simulation engine with deterministic and stochastic components, tracking detailed continuous simulation stats.

The Team

Fleet Simulator was created by:

Member	Institution	Role / Study Area
Herculano Esteves (a106839)	Universidade do Minho	Software Engineering
Nuno Fernandes (a107317)	Universidade do Minho	Software Engineering
Salomé Faria (a108487)	Universidade do Minho	Software Engineering
Tiago Alves (a106883)	Universidade do Minho	Software Engineering

Getting Started

Follow these instructions to set up the project locally.

Prerequisites

• Python 3.9+

1. Clone the Repository

git clone https://github.com/Herculano-Esteves/AI-25-26.git
cd AI-25-26

2. Setup Environment

# Create a virtual environment
python -m venv venv

# Activate the virtual environment
# On Linux/MacOS:
source venv/bin/activate
# On Windows:
# venv\Scripts\activate

# Install python dependencies
pip install -r requirements.txt

3. Run the Simulation

Launch the primary GUI and simulation engine.

python main.py

License

This project is licensed under the MIT License - see the LICENSE file for details (if applicable).