Projects & artifacts

SRTP: fully automated incremental AICLD corpus (~1.4M samples / 5k+ speakers), lip-reading models and training, outputs include IEEE TIP and other Q1 papers, plus invention patents and software copyrights.

Contributions : Project lead — AICLD automated ingest and corpus scaling, lip-reading model development and training, metadata standards and exploratory experiments, data platform, and field research synthesis.

Stack : Python, PyTorch, Swin Transformer, FFmpeg tooling

Tags : Computer Vision

For on-orbit servicing needs, delivered the simulation platform, multi-sensor proximity reconstruction, and solid-state LiDAR with stereo depth perception; multiple conference papers including ICGNC, AIT, and PRCV.

Contributions : Core member (vision & control) — multi-sensor simulation platform, LiDAR degradation and reconstruction pipeline, RoboSense bring-up and darkroom dataset collection, modular perception integration.

Stack : Python, Open3D-style tooling, RoboSense SDK

Tags : Computer Vision, Space, Simulation

16U RVD & proximity GNC: vision pose & Jetson deployment, CKF fusion, electrospray control; IAC, ICGNC, and other papers plus multiple invention patents.

Contributions : Core member (vision & control) — rendezvous pose datasets and Jetson deployment, navigation/propulsion simulation, electrospray bench workflows.

Stack : Python, PyTorch, TensorRT, MATLAB/Simulink, Jetson Orin NX

Tags : Computer Vision, Control, Space

Two scenario robots from perception to deployment: inspection rover (LSTM, YOLO, PyQt/Streamlit/mobile + DeepSeek) and industrial AMR (PID, MobileNet).

Contributions : Project lead — LSTM environmental forecasting and host software, object detection and image classification, PID line following.

Stack : Python, PyQt, Streamlit, MobileNet, YOLO

Tags : Computer Vision, Robotics

Provincial technology commissioner team, service engagement at Fujian Xi'enkai Electronics — vision-guided robotics, PyQt industrial host, and a closed loop for inspection, sorting, placement, and labeling.

Contributions : Core member (vision & software) — vision station integration, hand–eye calibration and labeling motion, PyQt host and closed-loop commissioning.

Stack : Python, PyQt, Industrial cameras, PLC-facing APIs

Tags : Computer Vision, Industrial

University–industry project: suppress tornado-effect rotary spreading via simulation-based corpus build, embedded trajectory prediction with feedforward CNC, and local software plus Web remote co-control.

Contributions : Core member (software & algorithms) — pellet-dynamics simulation and trajectory dataset, embedded prediction with feedforward CNC, local Web dual-end control and field trials.

Stack : Python, PyTorch, Embedded C, Web dashboard, MQTT-friendly buses

Tags : Control, Industrial

DKASC PV forecasting: physics-informed losses, SHAP + TPE tuning, SimpleADWIN drift adaptation; produced an IEEE SMC conference paper.

Contributions : Core member (algorithms) — physics-informed losses and backbone experiments, SHAP monitoring with TPE tuning, SimpleADWIN online fine-tuning and DKASC validation.

Stack : Python, PyTorch, SHAP, Bayesian optimization (TPE), SimpleADWIN

Tags : Time Series