Photo

Lujie Yang

I am an Applied Scientist at Amazon Frontier AI & Robotics (FAR). I obtained my PhD from MIT EECS advised by Prof. Russ Tedrake and my bachelor's degree from UC Berkeley advised by Prof. Francesco Borrelli.

I aim to enable robots with human-like dexterity, agility, and intelligence in contact-rich manipulation and whole-body loco-manipulation. My research fuses model-based optimization with data-driven techniques to create robust, data-efficient solutions for complex physical interaction.

I love playing badminton, visiting museums and writing classical Chinese poetry. Here is a selected collection of my poems.

   /      /   lujie [at] mit (dot) edu



News


Selected Publications

(* indicates equal contribution)
OmniRetarget: Interaction-Preserving Data Generation for Humanoid Whole-Body Loco-Manipulation and Scene Interaction
Lujie Yang*, Xiaoyu Huang*, Zhen Wu*, Angjoo Kanazawa†, Pieter Abbeel†, Carmelo Sferrazza†, C. Karen Liu†, Rocky Duan†, Guanya Shi†
Under Review
[Project] [Video] [Paper]
Physics-Driven Data Generation for Contact-Rich Manipulation via Trajectory Optimization
Lujie Yang, H.J. Terry Suh*, Tong Zhao*, Bernhard Paus Græsdal, Tarik Kelestemur, Jiuguang Wang, Tao Pang, Russ Tedrake
Robotics: Science and Systems (RSS) 2025
[Project] [Video] [Paper] [MIT News]
A New Semidefinite Relaxation for Linear and Pieceweise-Affine Optimal Control with Time Scaling
Lujie Yang, Tobia Marcucci, Pablo Parrilo, Russ Tedrake
International Conference on Robotics and Automation (ICRA) 2025
[Paper]
Lyapunov-stable Neural Control for State and Output Feedback: A Novel Formulation
Lujie Yang*, Hongkai Dai*, Zhouxing Shi, Cho-Jui Hsieh, Russ Tedrake, Huan Zhang
International Conference on Machine Learning (ICML) 2024
[Paper] [Code] [MIT News]
Fighting Uncertainty with Gradients: Offline Reinforcement Learning via Diffusion Score Matching
H.J. Terry Suh, Glen Chou*, Hongkai Dai*, Lujie Yang*, Abhishek Gupta, Russ Tedrake
Conference on Robot Learning (CoRL) 2023
[Project] [Paper] [Code]
Approximate Optimal Controller Synthesis for Cart-Poles and Quadrotors via Sums-of-Squares
Lujie Yang, Hongkai Dai, Alexandre Amice, Russ Tedrake
Robotics and Automation Letters (RA-L) 2023
MIT LIDS Student Conference 2023, Best Presentation Award
[Video] [Paper] [Code]
Global Planning for Contact-Rich Manipulation via Local Smoothing of Quasi-Dynamic Contact Models
Tao Pang*, H.J. Terry Suh*, Lujie Yang, Russ Tedrake
Transactions on Robotics (T-RO) 2023, King-Sun Fu Memorial Best Paper Award Honorable Mention
[Project] [Paper] [Code] [MIT News]
Discrete Approximate Information States in Partially Observable Environments
Lujie Yang, Kaiqing Zhang, Alexandre Amice, Yunzhu Li, Russ Tedrake
American Control Conference (ACC) 2022
[Paper]
Lyapunov-stable neural-network control
Hongkai Dai, Benoit Landry, Lujie Yang, Marco Pavone, Russ Tedrake
Robotics: Science and Systems (RSS) 2021
[Paper] [Code]


Selected Honors


Teaching


© Massachusetts Institute of Technology 2020