Ali Badreddine

Seasoned Integration and Functional Safety Software Engineer with extensive expertise in programming, project management, and systems and software development life cycles. Skilled in utilizing Six Sigma techniques for swift identification and resolution of product development challenges, aligning with program schedules. Senior-level proficiency in delivering ASIL-rated functional safety solutions, implementing Embedded AUTOSAR Software in Agile settings. Adept in verification, validation, automated testing, and requirements development with a focus on traceability, ensuring robust engineering and design principles.

Autonomous-Cohort ADAS Perception & Mapping Project:

• Identified downsides to current target-based Camera calibration method & researched multiple target-less methods that would meet customer expectation & reduce need for calibration booths, tooling, & labor.
• Utilized Domino, Linux, Docker to create flashable environments & work with large LIDAR/Image data as well as Structure for Motion to yield workable Camera point cloud.
• Implemented/Presented algorithm using C++, ROS, & python to identify discontinuous edges in LIDAR & Camera point clouds registering them to estimate camera extrinsic & correct for errors in vehicle tracking.
• Delivered proof of concept to ADAS team for further development; tracked progress using Gantt chart.

Computer Vision: Paper Flattening & Template Matching  (Python): [GitHub]

• Generated training data set of crumbled worksheets and their 2D flow graphs.
• Trained a U-net to map image patches from distorted images to respective flow maps allowing us to restore flattened image.
• Utilized template matching & K means clustering to identify math problems in worksheet & generate answer key.

Kalman Filter in V2I & EKF in Velocity Motion Model (Matlab): [GitHub]

• Simulated a V2I environment by generating noisy measurements from 3 separate radar towers and propagated them through a KF to estimate the current state of the vehicle in random walk motion model.
• Utilized EKF, UKF, & PF to generate odometry for a velocity motion model SE(2).

Semantic LIDAR Odometry Project (C++, Matlab) [GitHub& YouTube]

• Utilized semantic KITTI dataset and applied SICP & GICP to generate pose transformations. Fed factor graph into ISAM to generate smoothed trajectory. Compared odometry results.
• Attempted SLAM by generating loop closure transformations when the vehicle crossed (came close to previous poses) and fed these loop closures as part of the factor graph to ISAM2. GitHub & YouTube.

Machine Learning Applied Knowledge (Julia & Python)

• Video background subtraction using SVD ● Low rank matrix/image completion ● Polynomial fitting using ordinary LS ● SVD nearest subspace classification ● Procrustes analysis for lining up image; and MDS (distance to coordinates) ● Image Inpainting and matrix completion utilizing regularized LS.

• Scaled Agiled SAFe certified
• AUTOSAR MBD & Handcode certified
• Functional Saftey Fundementals certified