Education
Bachelor's Degree, Northwestern University
2025 - 2029
IBDP Candidate, Shanghai Pinghe School
2023 - 2025
Graduated on the Principal's List (top 5% of class)
Work Experience
Undergraduate Research Assistant, Xenobot Lab
October 2025 - Present
- • Developed and implemented a UWB-based localization system using the DW1000 transceiver
- • Achieved accurate 3D positioning with a three-anchor, one-tag setup
- • Working on modular robot with PHD
- • Working on using RL methods to train in real life of a single motor ball with IMU data
Engineer, HaptE
September 2025 - Present
- • Developed edge AI inference pipeline for warehouse automation using TensorFlow on Nvidia Jetson Orin Nano
- • Trained and optimized multi-modal recognition system (segmentation, OCR, QR/barcode detection) for real-time local processing
- • Built multi-edge device coordination system with AWS IoT Core for distributed warehouse pick-and-place operations
- • Achieved fully local inference without cloud dependency, enabling autonomous item tracking and error prevention from camera input alone
Research Intern, Machine Learning & Language Lab, Northwestern University
September 2025 - Present
- • Researching spatial intelligence agents and helping PHD research projects in embodied AI
- • Developing comprehensive training playground for object manipulation using Genesis physics simulator
- • Designed automated system to import 3D objects, generate target/initial states, and produce optimal image-text sequences for standardized multi-modal training pipelines
Research Intern (Algorithm), Differential Robotics
June 2025 - August 2025
Worked on two autonomous drone projects:
- • Optimized sparse reward RL for obstacle avoidance navigation
- • Implemented real-time computer vision for high-speed stunt maneuvers, achieved 90% success rate in extreme conditions using MobileNetV3 architecture
Projects
End-to-End High-Speed Drone Frame Navigation System
2025
Visualized Results →- • Developed an end-to-end vision navigation system enabling drones to traverse 85° tilted frames at 4–6 m/s with near-100% success.
- • Optimized MobileNetV3 + DeepLabV3+ backbone on Jetson Xavier NX via TensorRT, achieving ~3ms inference latency and >60Hz control frequency.
- • Trained RL control policies with shaped rewards and distillation-aware regularization to ensure stable high-speed maneuvering.
End-to-End RL Drone Navigation System
2025
- • Built an end-to-end navigation pipeline in IsaacLab using deep reinforcement learning (PPO), mapping high-dimensional sensor inputs (depth images + proprioceptive states) directly to low-level motor actions.
- • Implemented curriculum learning & domain randomization (obstacle density, dynamic disturbances, sensor noise) to improve generalization and enable sim-to-real transfer.
- • Designed hybrid reward shaping: integrated Dijkstra-based path priors, directional distance rewards, ESDF collision penalties, and smoothness constraints to stabilize long-horizon flight.
Modeling Soccer Ball Trajectory
2023
- • Developed computational simulation using Python, hydrodynamics, and ML
- • Incorporated Magnus effect for accurate modeling
- • Achieved <40cm trajectory error in windless conditions
Skills
LaTeX
Python
Data Analysis
Machine Learning
Reinforcement Learning
Computer Vision
Web Development
Drone Operation
Photography
Video Editing
3D Modeling
Awards
Mathematics & Modeling
- • High School Mathematical Contest in Modeling (HiMCM): Outstanding (Global Top 1%) [pdf link]
- • American Regions Mathematics League (ARML): Global Top 10
Languages
Chinese (Native), English (Native), German (Basic)
Interests
Photography, Filmmaking, Travel, Soccer, Badminton. View my photography portfolio for creative work samples.