We welcome motivated students and collaborators interested in robotics and embodied AI. Ro\(\Phi\) Lab develops general robot intelligence by integrating learning with priors from physics, geometry, and control.

How to Apply

Email Yonghyeon Lee at apply2rophilab@gmail.com with:

• CV
• Brief statement of research interests
• Links to projects or code, if available

About Ro\(\Phi\) Lab

Relevant topics:

• Perception, planning, control, and learning for robotics
• Generative modelling and reinforcement learning
• Physics-informed learning algorithms
• Geometric algorithms

We aim to make real-world impact through robotics and embodied AI—building systems that perceive, plan, act, and adapt in the physical world. See Research and Publications for current directions and papers.

Target venues:

• Robotics: ICRA, IROS, RSS, RA-L, T-RO, IJRR
• Robot Learning: CoRL, T-RL
• Machine Learning: ICLR, ICML, NeurIPS

Who We Are Looking For

Background. We welcome students from diverse fields—computer science, electrical and electronic engineering, mechanical engineering, mathematics, physics, and related disciplines. Robotics and physical AI are deeply interdisciplinary.

Skills and goals. We look for students who want to build strong foundations in mathematics, physics, and learning algorithms, while developing practical skills for real-world robotic systems in both software and hardware.

Research attitude. We value students who are humble, sincere, passionate, and open-minded, with a strong desire to identify meaningful research directions of their own, pursue them in depth, and contribute to the field of robotics and physical AI.

Notes for Undergraduate Students

Undergraduates at all stages are welcome to contact the PI.

• After your second year (2+ years of study): We especially encourage you to reach out early—even before applying for a formal lab position. We are happy to offer feedback on future coursework and how to prepare for research in the lab.

We also welcome collaboration inquiries from researchers in academia and industry. For team members and the PI’s profile, see People.

Recommended Courses

You do not need to have completed all of the following before applying. If some topics are new to you, that is fine—we expect you to pick up the core ideas once you join the lab. Topics marked Must-Know are the essential foundations we expect you to be comfortable with before joining.

Mathematics

• Linear Algebra Must-Know — video lectures
• Probability and Statistics
• Multivariate Calculus
• Differential Equations
• (Optional) Differential Geometry — for students interested in deeper geometric formulations:
  • Lecture 1
  • Lecture 2

Learning

• Machine Learning Basics Must-Know — Murphy, Probabilistic Machine Learning: An Introduction; Stanford CS229, Andrew Ng (lecture series)
• Deep Reinforcement Learning — Berkeley CS285 (lecture series)
• Deep Generative Models — Stanford CS236 (lecture series)
• Deep Learning for Computer Vision — Michigan EECS 498 (leture series)

Robotics

• Modern Robotics: Mechanics, Planning, and Control Must-Know — textbook (PDF); video lectures
• Advanced Robotics — MIT Underactuated Robotics (lecture series)

Optimization

• Convex Optimization — Stanford EE364A (lecture series)
• Optimal Control