Frank Zhao — Teaching & Course Materials
Overview
This site hosts the lecture materials, notes, and reference resources for the courses I teach. It is intended as a study reference for students — a place to review concepts, follow the worked examples, and access the code accompanying each lesson.
My teaching emphasizes a progressive, hands-on approach: build intuition through runnable examples first, then develop the underlying theory, and finally implement the methods independently.
Biography
I am a Ph.D. candidate in Electrical Engineering at Hanyang University, South Korea. My research and teaching interests lie in robotics and control systems, reinforcement learning, and computer vision. My master's research addressed Reinforcement Learning for the Door-Opening Task of a Robotic Manipulator, which continues to inform how I introduce reinforcement learning to students — grounded in real robotic control problems.
Education
| Degree | Institution | Field | Date |
|---|---|---|---|
| Ph.D. (in progress) | Hanyang University, Korea | Electrical Engineering | Expected 2026-08 |
| M.Sc. | Hanyang University, Korea | Electrical Engineering | 2021-08 |
| B.Sc. | Tianjin University, China | Automation | 2014-07 |
Selected Work
- Korean Invention Patent — Visual–Tactile Sensor-Based Robot Gripper (No. 10-2739485, 2024)
- UR 2022, Late-Breaking Result — RGB-D Camera Data Enhancement via Image Resolution Techniques
- M.Sc. Thesis — Reinforcement Learning for the Door-Opening Task of a Robotic Manipulator
Areas — Robotics & Control · Reinforcement Learning · Computer Vision · Python · ROS2 · PyTorch
Courses
The following courses are documented on this site. Each course page contains the full syllabus, lecture notes, and accompanying code.
Course I — AI Robotics
An introductory robotics course based on ROS2, Python, and simulation. It progresses from environment setup to autonomous navigation, covering robot fundamentals, sensing, computer vision, closed-loop control, and a team capstone project.
Course II — Reinforcement Learning
A structured introduction to reinforcement learning, developed in five progressive parts: mathematical foundations (linear algebra), Markov decision processes, core reinforcement learning concepts, application environments, and reinforcement learning algorithms. Each part pairs theoretical development with runnable code.