Daniel Choi

I am a MASc student at the University of Toronto, Robotics Institute, where I work on Embodied AI and Deep Reinforcement Learning for Autonomous Robot Navigation and Planning. My MASc advisor is Goldie Nejat.

I have a BASc in Mechanical Engineering from University of Toronto, MIE Department. I was also a part of Neural Robotics Lab's Reinforcement Learning Team for Muskoskeletal Locomotion under Brokoslaw Laschowski.

Outside of academia, I like to make music, snowboard and read.

Email  /  Resume  /  GitHub  /  Google Scholar  /  LinkedIn  /  X

Research

Find Everything: A General Vision Language Model Approach to Multi-Object Search

We present Finder, a novel approach to the multi-object search problem that leverages vision language models (VLMs) to efficiently locate multiple objects in diverse unknown environments. Our method combines semantic mapping with spatio-probabilistic reasoning and adaptive planning, improving object recognition and scene understanding through VLMs.

OLiVia-Nav: An Online Lifelong Vision Language Approach for Mobile Robot Social Navigation

We introduce OLiVia-Nav, an online lifelong vision language architecture for mobile robot social navigation. By leveraging large vision-language models (VLMs) and a novel distillation process called SC-CLIP, OLiVia-Nav efficiently encodes social and environmental contexts, adapting to dynamic human environments.

4CNet: A Diffusion Approach to Map Prediction for Decentralized Multi-Robot Exploration

We present a novel robot exploration map prediction method called Confidence-Aware Contrastive Conditional Consistency Model (4CNet), to predict (foresee) unknown spatial configurations in unknown unstructured multi- robot environments with irregularly shaped obstacles.

Trajectory Prediction and LLM Reward Tuning for Robot Social Navigation with Deep Reinforcement Learning

We show a mobile robot social navigation system combining trajectory prediction with reinforcement learning and Large Language Model (LLM) reward tuning in Omniverse Isaac Gym Environment (OIGE).

Other Projects

These include coursework, side projects and unpublished research work.

ESP32 Fitness Tracker

We developed and built a wireless, wearable fitness tracker capable of monitoring user steps and heart rate, aiding individuals in achieving their health and fitness targets.

Face Tracker Camera

The camera has a detection model trained from scratch to work closely with image augumentation, classification, loss metrics and regression techniques.

Recognition

Awards, Scholarships, and Fellowships

• 2024: Healthcare Robotics (HeRo) NSERC CREATE Fellowships ($10k)
• 2019-2023: Dean's Honour List
• 2022: NSERC Undergraduate Student Research Award ($5k)
• 2018: University of Toronto Scholars Program ($10k)

Teaching

Teaching Assistantships

• MIE342: Circuits with Applications to Mechanical Engineering Systems

Design and source code from Jon Barron's website