MG Portfolio

Projects

Delve into a collection of my notable projects, each representing a fusion of creativity and skill.

2024

Learning-assisted Drifting for F1Tenth Autonomous Race Cars

TUe-logo-scarlet-L-1
Associated with TU/e (MSc Thesis)
Jan 2024 - Oct 2024
Machine Learning
Feedback Control System
Matlab
Python
R.O.S
Developed an advanced control framework for autonomous drifting using small-scale F1Tenth vehicles, integrating automated gain tuning and Gaussian Process-based model augmentation to enhance control accuracy and path tracking in complex trajectories.
Read Project Paper

2023

High-Performance Control Design for a Fourth-Order Rotational Motion Setup

TUe-logo-scarlet-L-1
Associated with TU/e
Sep 2023 - Nov 2023
Feedback Control Systems
Feedforward Control
Matlab
Simulink
Designed and implemented a high-performance control system for a fourth-order rotational motion setup, significantly improving trajectory tracking accuracy using advanced feedback and feedforward techniques.
Read Project Paper

Depth-Aware Video Panoptic Segmentation & Monocular Depth Estimation

TUe-logo-scarlet-L-1
Associated with TU/e
Apr 2023 - Jun 2023
Deep Learning
Neural Networks
High Performance Computing
Python
Developed a multimodal deep neural network for simultaneous panoptic segmentation and monocular depth estimation from still images, enhancing depth-aware scene understanding.
Read Project Paper

Perception-Enabled Pure Pursuit for Small Scale Racing Cars

TUe-logo-scarlet-L-1
Associated with TU/e
Feb 2023 - Jun 2023
Perception
Reinforcement Learning
Object Detection
Python
R.O.S
Developed an autonomous agent for small-scale racing cars to navigate unknown racetracks using object detection for cones and a 2D environmental map. Implemented and modified a geometric controller for improved adaptability and speed while conducting a theoretical analysis of reinforcement learning for decision-making.
Read Project Paper

Policy Learning for an Unbalanced Disc

TUe-logo-scarlet-L-1
Associated with TU/e
Apr 2023 - Jun 2023
Reinforcement Learning
Artificial Neural Networks
Gaussian Processes

Developed a control policy for an unbalanced disc pendulum system using Gaussian Processes, Neural Networks, and Reinforcement Learning, enabling successful swing-up and stabilization while extending control to multiple target positions.

Read Project Paper

Semantic Segmentation using a UNet-based Architecture

TUe-logo-scarlet-L-1
Associated with TU/e
Feb 2023 - May 2023
Deep Learning
Sematic Segmentation
Python
Developed a robust semantic segmentation model for urban street scenes using a U-Net-based architecture, addressing challenges in class imbalance, image quality degradation, and generalization. Enhanced performance through data augmentation, external datasets, transfer learning, and adaptive class weighting, demonstrating improved segmentation on the Cityscapes dataset.
Read Project Paper

More projects

For additional projects, check out my LinkedIn profile and GitHub repositories below.
Scroll to Top