What do Calculus, Probability, Python, and ML have to do with Self-driving Cars?

Mathematics can sometimes feel disconnected from everyday life, especially when students encounter equations and formulas without seeing where they apply. Yet, many technologies people use today rely on these concepts.
The information-sharing session, “What do Calculus, Probability, Python and ML have to do with Self-driving Cars?” facilitated by Zaw Htut Aung (Mason), Manager of the Information and Communication Technology (ICT) team at Parami University, gave Parami students an opportunity to explore this connection, showing how classroom knowledge can be applied in the real world.
Drawing on his background in automotive engineering, Mason showed how calculus helps engineers understand vehicle motion. To illustrate this, he presented a car accelerating from 10 to 20 meters per second over five seconds, showing how mathematical concepts describe changes in speed and position. He said, “Basically, we use calculus to actually describe a system and a behavior.”
This example is a way of looking at mathematics: not simply as a subject of equations to solve, but as a tool for understanding how things work. Using MATLAB and Simulink, Mason also showed how engineers turn mathematical calculations into visual simulations. These tools make it possible to observe how a system behaves over time and explore different outcomes before testing them in the physical world.
Then, the facilitator used Waymo as a real-world example of how autonomous vehicles use cameras and sensors to recognize their surroundings and make decisions. Developing such technology requires more than expertise in one subject; it depends on engineering, statistics, machine learning, and data science to bring this technology to life.
The session also highlighted why practical testing remains important in engineering. Looking at a racing car accident at the 1999 Le Mans race, the facilitator discussed how vehicle design and airflow can affect safety. During the session, when a student asked about applying AI-generated solutions to complex problems like these, Mason reminded everyone that technology alone cannot replace real-world verification: “You still need to set up your physical system to validate your claim.”
This sharing session provided a broader perspective on the value of interdisciplinary learning, from theory to application. By combining concepts across mathematics, programming, data science, and engineering, ideas that may seem abstract in theory can become practical when applied to real-world problems beyond the classroom. Whether understanding how a vehicle moves or developing technology to navigate a road, solving real-world problems requires connecting ideas across disciplines and approaching challenges from different perspectives.





Comments