ros2qnukf — ROS 2 Quaternion-based Unscented Kalman Filter c++ package
Real-time ROS 2 C++ package: quaternion-based unscented Kalman filtering for GPS-denied VINS, fusing stereo and IMU with EuRoC validation.
Featured Projects
Quaternion-Based Unscented Kalman Filter for 6-DoF Vision-Based Inertial Navigation in GPS-Denied Regions
Developed a novel quaternion-based visual-inertial algorithm using SO(3) and custom computations, achieving higher accuracy with the same computational complexity as linearized Extended Kalman Filter (EKF) based approaches.
DeepUKF-VIN: Adaptively-Tuned Deep Learning Unscented Kalman Filter for 3D Visual-Inertial Navigation Based on IMU-Vision-Net
A deep learning–based adaptation mechanism (DLAM) is proposed to adaptively tune the previously proposed QNUKF. A custom training and evaluation framework was developed.
Smartphone Warranty Risk Assessment
Built tools such as drop height detection, AI screen crack detection and drop visualization tools to quantify user warranty-related risks.
Mechatronics Housing Design
Designed complex mechanical housings for automotive electrification components such as battery packs and converters.