Aaron Hao Tan

I just finished my PhD, advised by Dr. Goldie Nejat, at the University of Toronto, where I work on giving robots the ability to anticipate the world via deep MARL, diffusion, and language models.

I am an incoming postdoctoral researcher at Stanford (Spring 2025). Previously, I was nominated as a PhD Apple Scholar in AI/ML.

In my free time, I am either 1) building Syncere with Angus Fung to bring robots in to every household, or 2) writing medical papers with Dr. Lang, Dr. Margolin, or Dr. Boutet.

Updated: 10/24

Email  /  Twitter  /  CV  /  Resume  /  Google Scholar

profile photo
Primary Research

4CNet: A Diffusion Approach to Map Prediction for Decentralized Multi-Robot Exploration
Aaron Hao Tan, Siddarth Narasimhan, Goldie Nejat
Under Review at T-RO, 2024
Paper / Video

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.

OLiVia-Nav: An Online Lifelong Vision Language Approach for Mobile Robot Social Navigation
Siddarth Narasimhan, Aaron Hao Tan, Daniel Choi, Goldie Nejat
CoRL Workshop: Lifelong Learning for Home Robots, 2024
Under Review at ICRA 2025
Paper / Poster / Video

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.

Find Everything: A General Vision Language Model Approach to Multi-Object Search
Daniel Choi, Angus Fung, Haitong Wang, Aaron Hao Tan
CoRL Workshop: Language and Robot Learning, 2024
Under Review at ICRA 2025
Paper / Website / Video / Code

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.

NavFormer: A Transformer Architecture for Robot Target-Driven Navigation in Unknown and Dynamic Environments
Haitong Wang, Aaron Hao Tan, Goldie Nejat
IEEE Robotics and Automation Letters, 2024
Paper / Video

We propose NavFormer, a novel end-to-end DL architecture consisting of a dual-visual encoder module and a transformer-based navigation network to address for the first time the problem of TDN in unknown and dynamic environments.

Deep Reinforcement Learning for Decentralized Multi-Robot Exploration with Macro Actions
Aaron Hao Tan, Federico Pizzaro Bejarano, Yuhan Zhu, Richard Ren, Goldie Nejat
IEEE Robotics and Automation Letters + ICRA, 2023
Paper / Video / Talk / Poster

The first Macro Action Decentralized Exploration Network (MADE-Net) using multi-agent deep reinforcement learning to address the challenges of communication dropouts during multi-robot exploration in unseen, unstructured, and cluttered environments.

Enhancing Robot Task Completion Through Environment and Task Inference: A Survey from the Mobile Robot Perspective
Aaron Hao Tan, Goldie Nejat
Journal of Intelligent and Robotic Systems, 2022
Paper

The first extensive investigation of mobile robot inference problems in unknown environments with limited sensor and communication range and propose a new taxonomy to classify the different environment and task inference methods for single- and multi-robot systems.

A Sim-to-Real Pipeline for Deep Reinforcement Learning for Autonomous Robot Navigation in Cluttered Rough Terrain
Han Hu, Kaicheng Zhang, Aaron Hao Tan, Michael Ruan, Christopher Agia, Goldie Nejat
IEEE Robotics and Automation Letters + IROS, 2021  
Paper / Talk / Video / Baseline Demo

The development of a novel sim-to-real pipeline for a mobile robot to effectively learn how to navigate real-world 3D rough terrain environments.

Design and development of a novel autonomous scaled multiwheeled vehicle
Aaron Hao Tan, Michael Peiris, Moustafa El-Gindy, Haoxiang Lang
Robotica, 2021  
ASME IDETC/CIE, 2019  
Journal (Access) / Conference (Access) / Slides / Video

A 1:6 scale, multi-wheeled mobile robotic platform with independent suspension, steering and actuation for off-terrain operations.

Supplementary Works

These are works that I have contributed to during my free time.

Piezoresistive Sensors Array for Multijoint Motion Estimation Application
Zinan Cen, Fraser Robinson, Goldie Nejat, Hani E. Naguib
Aaron Hao Tan (Acknowledged)
IEEE/ASME Transactions on Mechatronics, 2024  
Paper

I was acknowledged in the development of a smart clothing system using low-cost, energy-efficient strain sensors to measure elbow and shoulder joint angles. A novel neural network architecture was used to enhance the accuracy of the sensor signal mapping.

Robust Face Mask Detection by a Socially Assistive Robot Using Deep Learning
Yuan Zhang, Meysam Effati, Aaron Hao Tan, Goldie Nejat
Computers, 2024  
Paper

We propose a novel two-step deep learning (DL) method based on our extended ResNet-50 model. It can detect and classify whether face masks are missing, are worn correctly or incorrectly, or the face is covered by other means (e.g., a hand or hair).

Development of a Pillow Placement Process for Robotic Bed-Making
Chi-Hong Cheung, Aaron Hao Tan, Andrew Goldenberg
IEEE/ASME MESA, 2023  
Paper (Access)

We propose a novel process for a 6-DOF static one-armed robotic manipulator to address the challenges of pillow placement on a small-scale bed.

Deep Learning Model to Identify Homonymous Defects on Automated Perimetry
Aaron Hao Tan, Laura Donaldson, Luqmaan Moolla, Austin Pereira, Edward Margolin
British Journal of Ophthalmology, 2022  
Paper / Slide (NANOS 2022)

The first application of deep learning to the classification of homonymous defects on automated perimetry.

Jeeves, the Ethically Designed Interface
Aaron Hao Tan, Angus Fung, Michael Pham-Hung, Cristina Getson
RO-MAN: Roboethics Competition, 2021  
Talk

A competition designed to answer: how can robots respond and interact in an ethical manner when delivery objects within a domestic setting? Placed First.

Image and Position based Visual Servoing (Mobile Robot and Manipulator)
Aaron Hao Tan
ASME IDETC/CIE, 2018  
IEEE CIVEMSA , 2018  
Papers: Image Based / Position Based / Docking
Videos: UR5 / Docking

Implemented image and position-based visual servoing on a Clearpath Husky and UR5 Manipulator.

Teachings
2024 F: MIE1517: Introduction to Deep Learning Tutorial TA, University of Toronto
2024 F: ROB301: Introduction to Robotics Tutorial TA, University of Toronto
2024 S: MIE1070: Intelligent Robots for Society Head TA, University of Toronto
2024 W: MIE443: Mechatronics Systems: Design & Integration Head TA, University of Toronto
2023 F: ROB301: Introduction to Robotics Tutorial TA, University of Toronto
2023 S: MIE1070: Intelligent Robots for Society Head TA, University of Toronto
2023 W: MIE443: Mechatronics Systems: Design & Integration Tutorial TA, University of Toronto
2022 F: ECE1724: Bio-inspired Algorithms for Smart Mobility, University of Toronto
2022 F: ROB301: Introduction to Robotics Tutorial TA, University of Toronto
2022 S: MIE1070: Intelligent Robots for Society Head TA, University of Toronto
2022 W: MIE443: Mechatronics Systems: Design & Integration Tutorial TA, University of Toronto
2022 W: ENH610: Parasitology and Pest Control Lab TA, Toronto Metropolitan University
2021 W: MIE443: Mechatronics Systems: Design & Integration Tutorial TA, University of Toronto
2020 W: MIE443: Mechatronics Systems: Design & Integration Lab TA, University of Toronto
2019 W: MECE3390U: Mechatronics Head TA, Ontario Tech University
2018 F: MECE2230U: Statics Head TA, Ontario Tech University
2018 W: MECE3390U: Mechatronics Head TA, Ontario Tech University
2017 F: MECE3350U Control Systems Head TA, Ontario Tech University

Course Evaluations: Ontario Tech University (Eval 1/Eval 2), University of Toronto (Eval/Certificate)
Mentoring
2024-2025: Master of Engineering Student: Sourabh Prasad, Currently working on Cross Embodiment Navigation
2023-2024: Undergraduate Thesis Student: Daniel Choi (Thesis), Currently MASc Student at MIE UofT
2022-2023: Master of Engineering Student: Yuhan Zhu , Currently PhD Student at University of California, Riverside
2022-2023: Master of Engineering Student: Haitong Wang , Currently PhD Student at UofT
2022-2023: Undergraduate Thesis Student: Yuntao Cai, (Thesis), Currently MASc Student at ECE UofT
2022-2023: Undergraduate Thesis Student: Siddarth Narasimhan (Thesis), Currently MASc Student at MIE UofT
2021-2023: Master of Applied Science Student: Fraser Robinson (Thesis), Currently at Revolve Surgical (YC S21)
2021-2022: Undergraduate Thesis Student: Yuhan Zhu (Thesis), Currently PhD Student at University of California, Riverside
2021-2022: Undergraduate Thesis Student: Richard Ren (Thesis), Currently Software Engineer at Amazon
2021-2022: Undergraduate Thesis Student: Giro Ele (Thesis)
2020-2021: Undergraduate Thesis Student: Federico Pizzaro Bejarano (Thesis), Currently PhD Student at UofT
2020-2021: Undergraduate Thesis Student: Ge Lin (Thesis) , Currently M.Eng at McGill University
Academic Services
2020-Present: Reviewer for RA-L, ICRA, CoRL, IROS, RSS, JIRS, Machine Learning, Scientific Reports
Misc. Updates
2024 S: Keynote Speaker @ The Future of Construction (Picture /Talk)
2023 S: Placed 3rd in the prestigious Shot on iPhone Photography Award hosted by IPPAWARDS (Picture)
2023 W: Won 1st place in Toronto's competitive men's basketball league (Picture)
2022 F: Won 1st place in Toronto's competitive men's basketball league (Picture)
2022 S: Organized paintball social event for Robotics Institute at the University of Toronto (Picture)
2022 S: Won 1st place in Toronto's competitive men's basketball league (Pic 1/Pic 2)
2021 F: Won 2nd place in Toronto's recreational men's basketball league (Picture)
2019 S: Photographer and member of the Local Organization Committee for the 14th IEEE ICCSE Conference
2018 S: Featured in Apple's Shot on iPhone photography campaign (Pic 1/Pic 2)

Consumer App Projects
Scholarply
Aaron Hao Tan, Angus Fung
2023 Q3-4  
Scholarply / Article / Newsletter / TikTok
Demo
  • Accelerating the scholarship application process via LLM agents to help students secure funding while focusing on their studies.
  • Selected by Microsoft Startup Hub Program, receiving grants worth $150k.
ONE800
Aaron Hao Tan, Angus Fung
2023 Q1-2  
ONE800 / Twitter / Instagram
Demo / Team (Pic1 / Pic2)
  • An all-in-one service built in to iMessage aimed at lowering the barrier of entry for LLMs and Generative AI.

8/24 Forever