https://omerkurkutlu.github.io/tags/reinforcement-learning/Reinforcement LearningHugoBlox Kit (https://hugoblox.com)en-usThu, 02 Jul 2026 00:00:00 +0000https://omerkurkutlu.github.io/media/icon_hu_eee4a95885829ab2.pnghttps://omerkurkutlu.github.io/tags/reinforcement-learning/https://omerkurkutlu.github.io/projects/salamander-robot/Thu, 02 Jul 2026 00:00:00 +0000https://omerkurkutlu.github.io/projects/salamander-robot/<h2 id="overview">Overview</h2> <p>The Salamander Robot project investigates how spinal joint actuation can improve the locomotion efficiency, stability, and adaptability of bio-inspired quadruped robots. The project combines reinforcement learning with robotic simulation and real-world experiments to study coordinated spine–limb motion across different terrains.</p> <h2 id="motivation">Motivation</h2> <p>Many quadruped robots rely solely on leg motion for locomotion. Inspired by salamanders and other sprawling animals, this research explores how an actively controlled spinal joint can improve mobility and robustness.</p> <h2 id="key-features">Key Features</h2> <ul> <li>Bio-inspired quadruped robot</li> <li>Deep Reinforcement Learning (DQN)</li> <li>Active spinal joint</li> <li>ROS and Gazebo simulation</li> <li>Sim-to-real deployment</li> <li>Raspberry Pi onboard control</li> <li>Terrain adaptability analysis</li> </ul> <h2 id="hardware">Hardware</h2> <ul> <li>Custom Salamander Robot</li> <li>Dynamixel Servo Motors</li> <li>Raspberry Pi</li> <li>Custom mechanical design</li> </ul> <h2 id="software">Software</h2> <ul> <li>ROS</li> <li>Gazebo</li> <li>Python</li> <li>C++</li> <li>Deep Q-Network (DQN)</li> </ul> <h2 id="research-contributions">Research Contributions</h2> <p>The project investigates:</p> <ul> <li>Coordinated spinal and limb dynamics</li> <li>Reinforcement learning for locomotion</li> <li>Terrain adaptation</li> <li>Efficient gait generation</li> <li>Bio-inspired robot control</li> </ul> <h2 id="publications">Publications</h2> <p>Related publications include work presented at robotics workshops and conferences on bio-inspired locomotion and reinforcement learning.</p> <h2 id="future-work">Future Work</h2> <p>Future research includes:</p> <ul> <li>Vision-based locomotion</li> <li>Model-based reinforcement learning</li> <li>Outdoor terrain adaptation</li> <li>Foundation models for robot locomotion</li> </ul> <h2 id="project-status">Project Status</h2> <p><strong>Status:</strong> ✅ Completed Research Project</p> <p>This project was developed during my research at the University of Notre Dame under the supervision of Dr. Yasemin Ozkan Aydin.</p>https://omerkurkutlu.github.io/projects/tinydrone-micronav/Thu, 02 Jul 2026 00:00:00 +0000https://omerkurkutlu.github.io/projects/tinydrone-micronav/<h2 id="overview">Overview</h2> <p>TinyDrone-MicroNav is an autonomous navigation framework for nano aerial vehicles that enables safe and efficient navigation using onboard perception and lightweight planning algorithms. The project focuses on resource-constrained platforms such as the Crazyflie 2.1 and aims to bridge the gap between simulation and real-world deployment.</p> <h2 id="motivation">Motivation</h2> <p>Autonomous navigation remains challenging for ultra-lightweight drones because of their limited sensing, computation, memory, and battery capacity. This project investigates how lightweight perception, planning, and learning algorithms can enable reliable navigation in dynamic environments.</p> <h2 id="key-features">Key Features</h2> <ul> <li>Vision-based autonomous navigation</li> <li>Dynamic obstacle avoidance</li> <li>Local path planning</li> <li>Global recovery strategy</li> <li>Webots simulation</li> <li>Crazyflie 2.1 deployment</li> <li>Simulation-to-real transfer</li> <li>Lightweight algorithms for embedded platforms</li> </ul> <h2 id="hardware">Hardware</h2> <ul> <li>Crazyflie 2.1</li> <li>Multi-ranger Deck</li> <li>Flow Deck</li> <li>Onboard IMU</li> </ul> <h2 id="software">Software</h2> <ul> <li>Python</li> <li>Webots</li> <li>Crazyflie Python Library</li> <li>OpenCV</li> <li>NumPy</li> </ul> <h2 id="current-research">Current Research</h2> <p>Current work focuses on integrating:</p> <ul> <li>Deep Reinforcement Learning</li> <li>Vision-Language-Action Models</li> <li>TinyML</li> <li>Embedded AI</li> <li>Efficient onboard perception</li> </ul> <p>to improve autonomous navigation under severe computational constraints.</p> <h2 id="future-work">Future Work</h2> <p>Future directions include:</p> <ul> <li>End-to-end visual navigation</li> <li>Multi-drone collaboration</li> <li>Real-world outdoor navigation</li> <li>Embedded deployment of foundation models</li> <li>Fully onboard autonomous flight</li> </ul> <h2 id="project-status">Project Status</h2> <p><strong>Status:</strong> 🚧 Active Research Project</p> <p>This project is currently under active development as part of my PhD research at the University of Illinois Chicago.</p>