23 Mar 2026 -
8 min read
[
hackathon
]
Before a robot can do anything useful in an unknown space, you need an extensive understanding of the environment it will operate in. Traditional solutions use SLAM (Simultaneous Localization and Mapping) to create accurate 2D and 3D maps, and also create semantic graphs with pre-tagged objects using sensor rigs like LiDAR or cameras. At the recent Gemini 3 Singapore Hackathon hosted by CerebralValley, Anurag and I wanted to see how far we could get by just leveraging the multimodal capabilities and world understanding of the Gemini models. We developed Robotic Planning with Gemini (RPG), an embodied AI project that lets a robot understand and plan tasks in an unfamiliar indoor environment using only sequential photographs.
12 Jan 2026 -
6 min read
[
hackathon
]
I first stumbled upon Singapore Sign Language while I was looking for electives at NTU. While I was never able to take the module myself, NTU’s excellent website allowed me to learn more about the history of Sign Language in Singapore. In particular, I was impressed by their extensive recording and documentation of more than a thousand unique signs.
28 Jul 2025 -
7 min read
[
publications
]
Figure 1. Video Frame Before Masking.
After my first URECA project on football analytics, I was eager to embark on a second research journey. Working again with Assoc Prof John Komar and Julian Tan from NIE, we tackled the challenge of building a data collection pipeline for badminton using computer vision and machine learning. This article outlines our journey in developing the system and our initial findings.
03 Jul 2025 -
2 min read
[
projects
]
Data has never been more accessible in sports analytics. Companies like Hudl Statsbomb, Second Spectrum, and Opta provide in-depth coverage of almost every sport and well-known league in the world, available through released datasets, data scraping, or commercial licenses. But how would you go about collecting data for grassroots teams or less popular sports, when there’s no vendor available?
31 May 2023 -
2 min read
[
football
publications
]
From August 2022 to May 2023, I had the opportunity to work on my first research project as a participant of NTU’s URECA1 program. I’ll write a full recap of my journey as an undergraduate researcher after the next academic year, but in many ways, this was the perfect project for me. It allowed me to work on a field that I have been passionate about for many years - sports analytics in football.
