TEACar: An Open-Source Autonomous Driving Platform
Build and test self-driving cars at 1/14 scale with modular hardware and ROS 2.
Researchers from the University of Florida and other institutions have released TEACar, an open-source autonomous driving platform designed for small-scale validation. Built at 1/14 to 1/16 scale, TEACar emphasizes modularity through a four-layer deck structure that physically separates sensing, computation, actuation, and power subsystems. This design improves structural rigidity while simplifying reconfiguration, addressing common issues in existing platforms like limited modularity and high integration complexity. The software stack is based on ROS 2, enabling flexible hardware abstraction and integration with learning-based control systems.
In comprehensive evaluations, the team tested three CNN-based steering controllers, measuring inference latency, power consumption, and system operating time to assess computational capability and robustness. Results demonstrated that TEACar offers a scalable, modular, and cost-effective testbed for intelligent transportation systems (ITS) research, education, and development. The platform is fully open-source, with the project repository available on GitHub, making it accessible for academic and hobbyist use. This release lowers the barrier for hardware-in-the-loop validation of autonomous driving algorithms, potentially accelerating innovation in the field.
- TEACar is a 1/14 to 1/16 scale open-source autonomous driving platform with a four-layer modular deck for sensing, computation, actuation, and power.
- Built on ROS 2, it supports CNN-based steering controllers and was tested for inference latency, power consumption, and operating time.
- The project is fully open-source on GitHub, providing a scalable and cost-effective testbed for ITS research and education.
Why It Matters
TEACar offers an accessible, modular platform for validating autonomous driving algorithms at scale, accelerating ITS research.