Research

NOVA Research Involvement

I am an active member of the NOVA research group, which focuses on advancing autonomous driving technologies. As part of this program, we have developed a fully functional vehicle prototype, equipped with cutting-edge sensors, AI-driven systems, and advanced algorithms for real-world autonomous navigation.

Our work aims to push the boundaries of autonomous vehicle research, leveraging deep learning, robotics, and state-of-the-art machine learning techniques to solve complex problems in the field.

GitHub: https://github.com/Nova-UTD/navigator.git

Brake Light Detection

One of my key contributions to the NOVA program is the development of a brake light detection system. This system utilizes YOLOv8, a state-of-the-art object detection model, to identify and classify braking behaviors of vehicles in real-time. By integrating this with ROS2, we aim to enhance the decision-making capabilities of our autonomous vehicle prototype.

Annotated Brake Light Detection - Example 1 Annotated Brake Light Detection - Example 2

Base images and dataset courtesy of IM Lab, Kookmin University via Roboflow Universe, licensed under CC BY 4.0. Annotations created using YOLOv8 by Sai Peram.
Dataset link: Brake-Light-Detection Dataset