Our project focuses on creating a Digital Twin for self-driving cars—a virtual counterpart that learns from extensive datasets rather than specialized sensors. This intelligent twin mirrors the real car’s behavior, helping it navigate safely, especially by detecting signs of driver fatigue or distraction. We’re developing a user-friendly web application for easy interaction, real-time behavior monitoring, and visualizing sensor data. This initiative marks a significant step in merging cutting-edge technology with the future of transportation. By combining real-world experiences with virtual experiments, our aim is to enhance the safety and efficiency of selfdriving cars. This project offers a unique approach, utilizing abundant data to create a virtual companion for cars, contributing to the ongoing evolution of autonomous vehicles.

This document provides the detailed functional and non-functional requirements, as well as the main functionalities of our system, such as generating test cases from three different inputs: the source code, the UML class diagram, and test scenarios. It will also provide detailed descriptions of the system’s architecture, methods, algorithms, and the various stages it goes through.

1. Develop a digital twin that accurately simulates the behavior and functionality of autonomous vehicles in real-world scenarios.

2. Ensure high-fidelity representation of the vehicle’s sensors, actuators, and decision-making processes within the digital twin.

3. Integrate real-time data from the physical autonomous vehicle environmental conditions, into the digital twin for continuous synchronization.

4. Implement mechanisms for seamless data flow between the physical vehicle and its digital counterpart.