Ying-Sheng Luo

I work on

About

Ying-Sheng Luo 羅應陞

I'm currently a Robotics Engineer at Inventec AI Center, where I work on robot learning for industrial automation. My current research focuses on robotic manipulation and assembly, using imitation learning and reinforcement learning to train policies for contact-rich tasks such as RJ45 and PSU insertion in physics simulation. My broader research interests include robot learning, reinforcement learning, imitation learning, sim-to-real transfer, robotic manipulation, and perception. Previously, I worked extensively on quadruped locomotion, skill composition, motion quality, and perception-based navigation, including transferring reinforcement learning policies from simulation to the real-world Unitree A1 robot.

Phone: +886-912-378590
Email: tray307969@gmail.com

City: Taipei, Taiwan
Language: English, Chinese (Native)

I received my M.Sc in Computer Science from the National Taiwan University of Science and Technology (2018), advised by Professor Yu-Chi Lai. My research has resulted in publications at venues including SIGGRAPH, ICRA, and IROS.

I'm also a computer graphics enthusiast and like to apply computer graphics knowledge I've learned in my other hobbies & side projects. There are examples from my piano cover videos where I seamlessly added 3D virtual objects with convincing lighting and reflections to make the video more interesting.

Resume [PDF]

Education

Master of Computer Science

Sep 2016 - June 2018

National Taiwan University of Science and Technology, Taipei, Taiwan

Thesis: Intuitive and Easily-Installed Fenestration and Light Control Framework
Implemented precomputed radiance transfer method to estimate global illumination
Graduated with 4.18 out of 4.3 GPA

Bachelor of Computer Science

Sep 2013 - June 2016

National Taiwan University of Science and Technology, Taipei, Taiwan

Ranked 1 in undergrde class
Received presidential award
Graduated with 3.94 out of 4.0 GPA

Work Experience

Robotics Engineer

July 2018 - Present

Inventec Corp., Taiwan

Develop robot manipulation policies for industrial assembly tasks, including RJ45 and PSU insertion, using imitation learning and reinforcement learning in the Newton simulator.
Conduct research on robot learning, including reinforcement learning, imitation learning, sim-to-real transfer, locomotion, manipulation, perception, and navigation.
Published research on quadruped robotics covering diverse skill learning, policy transitions, motion smoothness, perception, and navigation over complex terrains.
Successfully transferred reinforcement learning policies from simulation to the real-world Unitree A1 quadruped robot using Sim-to-Real techniques.
Developed reinforcement learning frameworks for locomotion and physics-based control of quadruped robots, biped characters, and simulated agents.

Graphics Engineer Intern

June 2015 - Sep 2015

International Games System Corp., Taiwan

Developed VFX effects using GLSL in a mobile car racing game
Implemented color grading, dynamic clouds, lightmaps, and HDR cubemap using GLSL and Cocos2d
Explored GPU performance analysis tool to improve rendering performance on mobile devices