Applied scientist working where perception meets language models, with a PhD research track in autonomous systems at Simon Fraser University and 10+ years shipping production software. On the perception side, built bird's-eye-view camera perception, IMU and camera sensor fusion for localization, and vision-based lateral control, validated in CARLA and on physical robots. On the language side, built an agentic multimodal architecture on the Model Context Protocol with retrieval-grounded reasoning and an act-versus-advise guardrail (under review, IEEE Transactions on Intelligent Vehicles), and a speech and LLM system deployed in BC's court system. Turns research into production systems: architects large-scale ML inference pipelines on AWS SageMaker and worked in a team that won the RoboCup 2015 humanoid world championship. Let’s connect and build something remarkable together!
Pinned Loading
-
DriverStateNet
DriverStateNet PublicDriver-impairment detection (distraction/intoxication) from multimodal sensor + video data
Jupyter Notebook
-
HumanoidSoccerRobot
HumanoidSoccerRobot PublicA modularized software framework for humanoid soccer robot research & development
C#
-
AccurateBirdEyeView
AccurateBirdEyeView PublicThis project was implemented to improve localization accuracy in soccer robots by concatenation Inertial Measurement Unit data and camera input
C#
-
LookDownLaneDetection
LookDownLaneDetection PublicReal-time lane detection for self-driving cars using OpenCV, color masking, and edge detection with a bird’s-eye “look-down” view.
Python
-
Something went wrong, please refresh the page to try again.
If the problem persists, check the GitHub status page or contact support.
If the problem persists, check the GitHub status page or contact support.




