Lixin Xu

Robotics Researcher | Ph.D. Student in Robotics

Atlanta, US.

About

Highly motivated Ph.D. student in Robotics with a profound commitment to advancing robotics foundation models by integrating cognitive and athletic intelligence. Leveraging expertise in deep learning, computer vision, and control systems, I aim to revolutionize modern industry and society through innovative robotic solutions. My research focuses on complex manipulation tasks, teleoperation, and real-time visual perception, consistently driving impactful contributions to the field.

See more

Work

·

Tsinghua University, Institute for AI Industry Research (AIR)

Research Intern

·

National University of Singapore, School of Computing

Research Intern

See more

Education

·

Robotics

The Hong Kong University of Science and Technology

·

Electrical and Computer Engineering

Georgia Institute of Technology

·

Mechanical Engineering

Qingdao University

See more

Awards

·

National Scholarship

Awarded for outstanding academic achievement as part of the top 1% of the graduating class.

·

Special Prize

Recognized for exceptional performance in the Material Handling Robot competition, demonstrating superior engineering and problem-solving skills.

See more

Publications

·

Taming VR Teleoperation and Learning from Demonstration for Multi-Task Bimanual Table Service Manipulation

ICRA 2025 WBCD Challenge

·

DexSinGrasp: Learning a Unified Policy for Dexterous Object Singulation and Grasping in Densely Cluttered Environments

R-AL Submission

See more

Languages

Mandarin

English

Cantonese

German

Japanese

See more

Skills

Programming & Tools

Python, PyTorch, C/C++, Isaac Gym, MATLAB/Simulink, ROS, Cmake, LaTeX, Solidworks

ML & Decision Making

Imitation Learning, Reinforcement Learning, LLM/VLM, Deep Learning, Machine Learning

Control & Actuation

Nonlinear control, Disturbance rejection control, Dynamics modeling, Linear Systems and Control

Computer Vision

Digital Image Processing, Monocular Depth Estimation, Video Inpainting, Stereo Vision Odometry, Object Recognition

Robotics Frameworks

ROS (Robot Operating System)

See more

Projects

·

ICRA WBCD Challenge

Participated in the ICRA WBCD Challenge, a prestigious robotics competition, achieving recognition for innovative solutions in bimanual manipulation.

·

Monocular Depth Estimation - FADE Ain't Depth Estimation

A deep learning project focused on enhancing monocular depth estimation using large-scale networks and advanced boosting methods.

·

C++ Simulation, Games and Visualization

Engaged in multiple C++ projects focusing on simulation, game development, and visualization, showcasing expertise in OpenGL and SFML.

·

An Attention-Based Video Inpainting Technique for Wire-Removal Scenarios

Developed an innovative autoencoder-based video inpainting model specifically designed for wire-removal in cinematic applications.

·

An ORB-based Stereo Vision Odometry (Undergrad thesis)

Designed and implemented PyVO, a Python-based visual stereo odometer, as part of an undergraduate thesis project.

·

The 6th National Engineering Training Competition - Material Handling Robot

Built an STM32-based Mecanum Wheel robot for a national engineering competition, focusing on material handling and object recognition.

See more