Shengwei Li

I'm a Master of Professional Engineering student in electrical engineering at the University of Sydney, looking for an MPhil position.

I'm interested in embodied intelligence, robotics and control, and in AI and deep learning more broadly. The projects below are ones I've built along the way, mostly in simulation.

Before Sydney I studied automation at Jiangnan University, where I wrote papers on model-free control for low-altitude vehicles and on metal detection.

Projects

Learning-assisted control under unknown payloads

Completed · Oct – Nov 2026

A robot arm holds a payload of unknown mass. Its controller's model is then wrong, and a policy that learned from demonstrations on the empty arm does not reach its targets. I compare ways to correct the model, monitors that detect when the policy fails, and a handover to a model-based controller. Simulation in MuJoCo, on a two-link arm and a Franka Panda.

Ride-height control of a fully submerged hydrofoil boat

Completed · Oct – Nov 2026 · Course project, ELEC9304

A boat on fully submerged foils cannot hold its height without feedback, and its only height sensor, at the bow, measures the distance to the water surface, so it sees the waves as well as the boat. I model the heave and pitch of a solar boat, design an observer-based controller that runs at 50 Hz, compare the observer with pole placement, and run the controller as a separate real-time process against a Simulink model of the boat.

City driving in Webots on a modular perception library

Completed · Sep – Nov 2026 · Course project, ELEC5308

Our team of five extended a lane-following library into a car that drives a city loop in Webots. It stops at STOP signs and red lights, yields to cars that cross its path and plans around obstacles, and it uses only the sensors a real car has. I built the shared interfaces, the bird's-eye-view grid and the segmentation model it depends on, and I integrated the system. An evaluation harness scores every drive against the simulator's ground truth.

Publications

  1. A Dual-Channel Metal Detection Method Based on the RIME Optimization Algorithm

    Shengwei Li, et al.

    EI-indexed conference, 2025

  2. Trajectory Tracking Control for Low-Altitude Vehicles Based on Model-Free Dynamic Linearization

    Shengwei Li, et al.

    EI-indexed conference, 2025 · Corresponding author

Education

  1. Master of Professional Engineering (Electrical)
    The University of Sydney

    2026 –

  2. B.Eng. in Automation
    Jiangnan University

    2022 – 2026

Experience

  1. LLM application development intern
    Shanghai Zhiji Information Technology

    2025 – 2026

    Built and deployed a retrieval-augmented Q&A system used daily by medical students, and the dialogue and scoring engine of a virtual standardised-patient exam.

Skills

Programming
Python, PyTorch, MATLAB
Simulation
MuJoCo, Webots, Simulink
Hardware
PCB design up to four layers; basic CAD in Fusion 360
Writing
LaTeX, Beamer