Humanoid Robotics | Whole-Body Control | Robot Dynamics
WBC聽聽 MPC聽聽 BFM聽聽 VLA
M.S. Student at Shanghai Jiao Tong University 聽|聽 Enrolled in 2025 聽|聽 Shanghai, China
I am an M.S. student at Shanghai Jiao Tong University, enrolled in 2025. My research focuses on motion control for humanoid robots, high-bandwidth harmonic disturbance rejection, robotic mechanism design, and dynamics modeling.
I am interested in control architectures that connect rigorous physical modeling with learning-based behavior representations. My goal is to improve the precision, robustness, and whole-body capability of humanoid robotic systems in demanding real-world tasks.
Developing high-precision, drift-free whole-body robot teleoperation methods and systems based on closed-loop control, with an emphasis on long-horizon stability, motion consistency, and accurate human-to-robot motion retargeting.
Developing an MPC-guided Behavior Foundation Model (BFM) framework for high-payload humanoid robots. The work combines predictive guidance with learned behavior representations to pursue dynamically feasible whole-body motion, robust balance control, and coordinated manipulation under substantial payloads.
Building a whole-body Vision-Language-Action (VLA) benchmark and data acquisition system for synchronized multimodal observations, whole-body trajectories, robot states, control signals, and task-level semantic annotations.
Robot-to-Robot Retargeting
Motion retargeting from the Unitree G1 humanoid to the PNDbotics Adam Pro, developed on top of the GMR framework.
Parallel Ankle Simulation
Forward and inverse kinematics, dynamics analysis, and MuJoCo simulation for the PNDbotics parallel ankle mechanism.
TeleVision Lab
An Isaac Lab and Isaac Sim migration workspace for immersive humanoid teleoperation based on Open-TeleVision.
PND Robot Models
Simulation and control assets for the PNDbotics Adam Pro, including URDF/MJCF descriptions, meshes, and supporting model resources.
| Control and Optimization | Modeling and Simulation | Embodied Robot Systems |
|---|---|---|
| Model Predictive Control | Kinematics and Dynamics | Whole-Body Teleoperation |
| Whole-Body Control | Mechanism Design | Motion Retargeting |
| Disturbance Rejection | System Identification | Behavior Foundation Models |
| Trajectory Optimization | MuJoCo / Isaac Sim | Vision-Language-Action Systems |
Python 聽 C++ 聽 MATLAB/Simulink 聽 ROS 2 聽 MuJoCo 聽 Isaac Sim 聽 Isaac Lab
Model the dynamics. Close the loop. Build the system.

