About Me
I am the co-founder and CTO of Mondo Robotics, a consumer robot company founded in 2025. Previously, I was a staff humanoid AI/robotics engineer at Tesla, working on the Optimus robot. Before moving to the Bay Area, I was a PhD student at Carnegie Mellon University (CMU), where I worked in the Robot Exploration Lab and the Biorobotics Lab in the Robotics Institute. My research advisors were Professor Zachary Manchester and Professor Howie Choset. My PhD research focused on state estimation for legged robots and complex robotic systems.
I obtained my B.Eng. in Computer Engineering and M.Phil. in Electronic and Computer Engineering from the Hong Kong University of Science & Technology (HKUST) in 2012 and 2015, respectively. During my undergraduate studies, I was the team leader of the HKUST Robotics Team for three years. This team represented Hong Kong in the ABU Robocon. During my graduate studies, I was the team leader of the HKUST IARC team in 2014. The team performed very well in the IARC competition, an aerial vehicle competition with more than 20 years of history. Some of my master’s research contributed to the flight control algorithm for DJI’s A3 autopilot.
Before joining CMU, I worked at DJI for five years. It was an honor to work with the company as it changed the world with drone technology. Starting as an algorithm engineer, I became a project technical director, leading the research and development of many well-known drone and robotics products. The projects I was directly involved in include Inspire 1, Phantom 3, Phantom 4, Matrice 100, Mavic, and various robotics products. The Matrice 100 research drone platform, developed by my team and me, has been one of the most popular drone research platforms in recent years.
In addition to robotics research, I am also enthusiastic about robotics education. At DJI, I led an educational project called RoboMaster. Through this project, we created opportunities for students to work on practical robots and be recognized by the broader public. Many well-known international media outlets have covered my work on these projects.
Research Statement
I use numerical optimization methods to enable legged robots to achieve stable control performance and precise, low-drift, long-term state estimation. A key insight driving my research is that control and estimation are inherently connected. Because control and estimation are dual problems, mathematical tools developed for one can be applied to the other, such as factor graphs and constrained trajectory optimization.
All of my research ideas are validated through rigorous mathematical derivations or hardware experiments. All of my control and estimation software projects are open source on GitHub.
Robot Gallery
