This student story was published as part of the 2025 NASW Perlman Virtual Mentoring Program organized by the NASW Education Committee, providing science journalism experience for undergraduate and graduate students.
Story by Noor Ul Huda Rasool
Mentored and edited by Sonali Kudva
The rapid adoption of small-scale autonomous vehicles is transforming both interactive education and applied research in the self-driving industry.
The VEX Robotics World Championship provides a platform for students—from elementary schools through college level—to participate in age-based robotics challenges. Students solve an engineering challenge using a gamified approach and applying skills in coding, mechanics, and electronics to construct robots with speed, precision, and strategy.
Noor Ul Huda Rasool, author, with Nicole Champagne (right) at the Grand Finale of the VEX Robotics National Championship in Sydney, 2024.
But these platforms do not just provide virtual learning; they are also practical learning experiences.
Educational platforms like Duckietown, F1TENTH (now RoboRacer), and VEX Robotics make robotics kits to introduce students to operating self-driving cars, their components, and their unification. The robots built using these kits outside their classrooms can perform designated operations such as racing, managing traffic systems, avoiding obstacles, or lane following.
The growing interest in small robotic cars among students led Dianzhao Li, a professor of economics and statistics at Dresden University, to study the impact of model cars. Li's extensive research on the recent developments of the small-car industry was published in IEEE Transactions on Intelligent Transportation Systems in January 2025.
A rectangular setup for 2024 VEX robotics theme “Rapid Relay."
The kits used for simulation testing before the robotic cars are deployed to the real world.
But in reality, it is not sufficient for the researchers to evaluate the performance of their designed machine learning models to perform designated tasks, solely through simulation. This is known as the sim-to-real gap.
Researchers experiment with small-scale robots to bring their machine learning models into real-world scenarios, thereby minimizing the sim-to-real gap.
Li described for instance, how he used the Duckiebot model system to develop a Deep Reinforcement learning model (DRL)—a type of artificial intelligence algorithm—to simultaneously perform lane-following and car-following manoeuvres with improved sim-to-real transferability while still a research student.
Small-scale autonomous vehicles give researchers a low-maintenance and low-cost alternative to full-size vehicles. Working with larger vehicles can be tedious and time-consuming, according to Dr. Bassam Alrifaee, a professor at RWTH Aachen University in Aachen, Germany. "It's exhausting and often dependent on weather conditions, even with adequate funding and real vehicles," he said. "Using this [small car] network, we can extend the number of vehicles in a dynamic environment."
An overview of self-driving cars.
What is especially remarkable is that the entire documentation is open source for learners. “Many developing countries cannot afford to have access to resources; that is why we are building such labs remotely, so robotics resources are available and affordable for a larger community, without the need of higher computation power or affiliation to any university.” Alrifaee said.
Alrifaee said small-scale cars can provide a better choice over simulation with their designed labs. "What we do is create a controllable and repeatable way of testing ideas before we find them in the real world." Alrifaee's next goal is to make his endeavours into global and accessible projects customised for countries like India which have different requirements from Europe or Australia.
Li credits Alrifaee’s work for establishing test beds for connected and automated vehicles. “It's better for us to get familiar with others’ research and to move together,” he said.
“This approach encourages future generations to build confidence in the emerging trend of autonomous driving by having experience early on,” Li said.
Noor Ul Huda Rasool
Top image: Dr. Bassam Alrifaee’s indoor lab setup at RWTH Aachen University. (Image courtesy of: A Survey on Small-Scale Testbeds for Connected and Automated Vehicles and Robot Swarms)
The NASW Perlman Virtual Mentoring program is named for longtime science writer and past NASW President David Perlman. Dave, who died in 2020 at the age of 101 only three years after his retirement from the San Francisco Chronicle, was a mentor to countless members of the science writing community and always made time for kind and supportive words, especially for early career writers.
You can contact the NASW Education Committee at education@nasw.org. Thank you to the many NASW member volunteers who lead our #SciWriStudent programming year after year.
Founded in 1934 with a mission to fight for the free flow of science news, NASW is an organization of ~2,600 professional journalists, authors, editors, producers, public information officers, students and people who write and produce material intended to inform the public about science, health, engineering, and technology. To learn more, visit www.nasw.org.
