Zhanxin Wu

I am a master student majoring in Computer Science at National University of Singapore (NUS) advised by Prof David Hsu. I work at the intersection of robotics and machine learning, with the goal of enabling robots to work intellectually and seamlessly in the real world. Currently, I am working on open-world object goal navigation at the NUS Adacomp.

Previously, I worked as an Undergraduate Research Assistant with Prof Junhua Zhao in the Lab of Energy Internet. After that, I was a Robotics Institute Summer Scholar (RISS) at Carnegie Mellon University advised by Prof Jean Oh. I received my B.E. in Computer Science and Engineering from the Chinese University of Hongkong, Shenzhen (CUHKSZ) in 2022.

Email  /  Google Scholar  /  Github  /  LinkedIn

profile photo

More in progress...

Open Scene Graphs for Open World Object-Goal Navigation
Joel Loo*, Zhanxin Wu*, David Hsu
ICRA Vision-Language Models for Navigation and Manipulation workshop, 2024
Paper / Website

We propose the system for Open World ObjectNav, which uses foundation models to reason and generalise. Key to it is our Open Scene Graphs representation, which captures rich, structured, open set scene information about objects and regions. We show that our system generalises zero-shot across open-set language object queries, environments and robots.

Invariance is Key to Generalization: Examining the Role of Representation in Sim-to-Real Transfer for Visual Navigation
Bo Ai, Zhanxin Wu, David Hsu
International Symposium on Experimental Robotics (ISER), 2023
To appear in Springer Proceedings in Advanced Robotics (SPAR)

This work examines, experimentally and theoretically, one representation that enables visual navigation policies solely trained in the Habitat simulator to generalize to real-world scenes, both indoor and outdoors.

Integrating Common Sense and Planning with Large Language Models for Room Tidying
Zhanxin Wu, Bo Ai, David Hsu
Robotics: Science and Systems (RSS) Learning for Task and Motion Planning Workshop, 2023
Paper / Poster

A framework that enables an agent to put misplaced objects back in place with partial map information by exploiting commonsense knowledge in large language models (LLMs).

Semantic Segmentation in Complex Scenes for Robotics Navigation
Zhanxin Wu, Xinjie Yao, Jean Oh
CMU Robotics Institute Summer Scholar’ Working Papers Journals, 2021
Paper / Video / Poster

A lightweight framework for semantic segmentation to recover information from uninformative pixels and improve 3D semantic understanding of scenes.

Real-Time Corporate Carbon Footprint Estimation Methodology Based on Appliance Identification
Guolong Liu, Jinjie Liu, Junhua Zhao, Jing Qiu, Yiru Mao, Zhanxin Wu, Fushuan Wen
IEEE Transactions on Industrial Informatics, 2022

Formulated corporate carbon footprint estimation problem and proposed the first Methodology to estimate the direct and indirect carbon emissions of factories in real time

A Temporal Convolutional Neural Network with Attention Mechanism for Industrial Non-Intrusive Load Monitoring
Guolong Liu, Gaoqi Liang, Huan Zhao, Junhua Zhao, Jinjie Liu, Zhanxin Wu
IEEE Energy Internet and Energy System Integration (EI2), 2021

A temporal convolutional neural network with attention mechanism based method is proposed for industrial non-intrusive load monitoring.

Deep End-to-end Super-resolution Perception Method for Load Data at Distribution Side
Guolong Liu, Junhua Zhao, Fushuan Wen, Zhanxin Wu, Yusheng Xue
Automation of Electric Power Systems, 2020

Developed a deep end-to-end super resolution perception, recovered nearly 89% of high-frequency information lost in low-frequency information for equipment load identification at 1/10th of the original data volume, communication, and storage requirements.

Autonomous Driving in Duckietown
Zhanxin Wu, Henrikus Theorizchy Cleven
NUS CS5478 Intelligent Robots: Algorithms and Systems, 2023

Developed a self-driving agent in the Duckietown simulation with classical planning, computer vision, and imitation learning techniques. Placed among the top-scored project in the module.

Teaching Assistant
CS5446/4246 AI Planning and Decision Making, Fall 2023, NUS
DBA5106 Foundations of Business Analytics, Fall 2023, NUS
CS5242 Neural Networks and Deep Learning, Spring 2023, NUS
DBA5106 Foundations of Business Analytics, Fall 2022, NUS
CSC4020 Fundamentals of Machine Learning, Spring 2022, CUHKSZ
ERG3010 Data and Knowledge Management, Fall 2021, CUHKSZ
Awards and Honors
2021: Dean's List, CUHKSZ School of Data Science
2021: Academic Performance Scholarship, CUHKSZ
2020: Dean's List, CUHKSZ School of Data Science
2020: Academic Performance Scholarship, CUHKSZ
2020: Undergraduate Research Award, CUHKSZ

Thank you for visiting my pawrent's website 🐾 🐾 🐾 framework

Template from Jon Barron. Last updated: Oct 2023