Back to Projects
ActiveStarted 2025-09

TEDU Autonomous RC Car

Our flagship project combines cutting-edge technologies to create a self-driving RC vehicle capable of navigating complex environments. The car uses deep reinforcement learning for decision making, computer vision for perception, and sensor fusion for robust localization. This project serves as a testbed for our research on efficient singular autonomous systems.

Reinforcement LearningComputer VisionRoboticsROS2

Key Features

Reinforcement Learning

Deep RL algorithms enable our car to learn optimal driving policies through trial and error, continuously improving its performance.

Computer Vision

Advanced object detection and tracking using deep learning models to perceive and understand the environment in real-time.

Sensor Fusion

Integrating data from multiple sensors including cameras, LiDAR, and IMU for robust perception and localization.

Technology Stack

Framework

ROS2

Robot Operating System

ML

PyTorch

Deep Learning

Vision

OpenCV

Computer Vision

Vision

YOLO

Object Detection

Simulation

Gazebo

Simulation

Hardware

NVIDIA Jetson

Edge Computing

Hardware

ZED Camera

Stereo Vision

Language

Python

Programming

Project Goals

1

Develop efficient RL models for autonomous navigation

2

Implement real-time object detection and avoidance

3

Create a robust sensor fusion pipeline

4

Test and validate in both simulation and real-world environments

Project Team

Advisor: Prof. Dr. Tolga Kurtuluş Çapın

Umay ŞamlıAli BolatAhmet Engin BüyükdığanKaan GülerÖzgür BasıkDeniz Ertuğrul