group

What campus are you from?

Daytona Beach

Authors' Class Standing

Carmen Dimario, Senior Ihan Ventura, Senior Austin Rollfing, Senior Michael Ulivarri, Senior Daniel Minks, Senior

Lead Presenter's Name

Carmen Dimario

Faculty Mentor Name

Dr. Akbas

Abstract

ERAU RoboRacer's autonomous racing presents unique challenges for real-time decision-making, requiring vehicles to operate at the limits of performance while maintaining safety in dynamic environments. It aims to create a 1:10-scale autonomous race car that integrates perception, planning, and control to compete in RoboRacer competitions while serving as a research platform for high-speed autonomy. The system fuses data from LiDAR, cameras, and IMU sensors to perform simultaneous localization and mapping, detect obstacles and competitors, and plan optimal racing lines for both time-trial and head-to-head racing. Control is achieved through a hybrid approach combining pure pursuit, PID velocity control, and model predictive control, all running onboard an NVIDIA Jetson embedded compute module. Safety is integrated throughout the architecture via startup diagnostics, continuous sensor health monitoring, and automatic emergency stop capabilities. Beyond competition readiness, this work contributes a maintainable ROS2-based development framework including a simulation environment for algorithm validation before hardware deployment. This platform enables investigation of multi-sensor fusion, safe control under uncertainty, and the practical tradeoffs inherent in physical autonomous racing systems.

Did this research project receive funding support from the Office of Undergraduate Research.

No

Share

COinS
 

ERAU RoboRacer

ERAU RoboRacer's autonomous racing presents unique challenges for real-time decision-making, requiring vehicles to operate at the limits of performance while maintaining safety in dynamic environments. It aims to create a 1:10-scale autonomous race car that integrates perception, planning, and control to compete in RoboRacer competitions while serving as a research platform for high-speed autonomy. The system fuses data from LiDAR, cameras, and IMU sensors to perform simultaneous localization and mapping, detect obstacles and competitors, and plan optimal racing lines for both time-trial and head-to-head racing. Control is achieved through a hybrid approach combining pure pursuit, PID velocity control, and model predictive control, all running onboard an NVIDIA Jetson embedded compute module. Safety is integrated throughout the architecture via startup diagnostics, continuous sensor health monitoring, and automatic emergency stop capabilities. Beyond competition readiness, this work contributes a maintainable ROS2-based development framework including a simulation environment for algorithm validation before hardware deployment. This platform enables investigation of multi-sensor fusion, safe control under uncertainty, and the practical tradeoffs inherent in physical autonomous racing systems.

 

To view the content in your browser, please download Adobe Reader or, alternately,
you may Download the file to your hard drive.

NOTE: The latest versions of Adobe Reader do not support viewing PDF files within Firefox on Mac OS and if you are using a modern (Intel) Mac, there is no official plugin for viewing PDF files within the browser window.