"I don’t know anything, but I do know that everything is interesting if you go into it deeply enough."

- Richard Feynmann

My interests lies in machine learning, artificial intelligence, computer vision and robotics. I aspire to develop systems of intelligent robotic agents that can collaborate or compete with each other to achieve goals in reality. I aim to pursue a Master's in Computer Science, focusing on artificial intelligence and computer vision, to further develop my interests. In addition, I am also passionate about physics, in particular quantum mechanics and its related fields.

Projects

Smart Collaborative Drones   [In Progress]

Development of novel algorithms to develop a system for a team of smart drones to act intelligently and collaboratively to achieve common goals against adversarial teams of drones in a suitably realistic simulated environment.

Machine Learning for Drone Detection   [Paper]   [Repo]

Investigation of the concept of night-time drone detection through their thermal signature using thermal imaging.

Artificial Intelligence in Onitama   [Report]   [Repo]

Investigation of various approaches to create artificial intelligent agents to play the board game Onitama with beyond human-level performance.

Embedding Artificial Intelligence into a Flapping-Wing MAV   [Report]   [Repo]

Modification of an existing state-of-the-art Flapping-Wing Micro-Aerial Vehicle (MAV) and development of an integrated system setup to train the Flapping-Wing MAV to fly.

Deep Reinforcement Learning for SpiderBot   [Report]   [Repo]

A custom-designed spider robot trained to walk using deep reinforcement learning in a PyBullet simulation.

Machine Vision and Image Processing   [Report]   [Repo]

A full workflow of a series of digital image processing tools written from scratch in MATLAB.

Frozen Lake Reinforcement Learning   [Report]   [Repo]

Implementation of reinforcement learning techniques on a grid world based problem.

Machine Learning for Electrode Voltage Prediction   [Report]   [Repo]

Supervised machine learning to predict voltage of novel battery electrode materials using general chemical properties.