Hwiyeon Yoo

I am an AI/ML Researcher at Boeing AI, based in Seoul, South Korea. At Boeing, I have been working on developing vision-based AI models for aviation manufacturing automation and inspection, such as OCR, key information extraction, and anomaly detection.

I received my PhD in robotics perception at Robot Learning Laboratory in Seoul National University (SNU), Korea, in 2024, under supervision of Prof. Songhwai Oh . I received my BS in Electrical and Computer Engineering from SNU in 2017.

My research interest is Semantic Perception for Robots, including Embodied Navigation, Robot Learning, Vision-Language-Action (VLA), Key Information Extraction, and Anomaly Detection.

Email / CV / Google Scholar / Github / Linkedin

Research

	Fine-Grained Open-Vocabulary Object Recognition via User-Guided Segmentation Jinwoo Ahn, Hyeokjoon Kwon, and Hwiyeon Yoo* (Corresponding Author). arXiv preprint, 2024. Keywords:* Open-vocabulary, Object detection, VLM, Fine-grained detection, User preference arXiv / paper
	Commonsense-Aware Object Value Graph for Object Goal Navigation Hwiyeon Yoo, Yunho Choi, Jeongho Park, and Songhwai Oh. IEEE Robotics and Automation Letters (RA-L), 2024 40th Anniversary of the IEEE Conference on Robotics and Automation (ICRA@40), 2024 Keywords: Visual navigation, Embodied agent, Object goal navigation, Semantic scene understanding paper / code / video
	Local Selective Vision Transformer for Depth Estimation Using a Compound Eye Camera Wooseok Oh, Hwiyeon Yoo, Timothy Ha, and Songhwai Oh. Pattern Recognition Letters, 2023. Keywords: Depth estimation, Vision transformer, Biomimetics paper
	Topological Semantic Graph Memory for Image-Goal Navigation Nuri Kim, Obin Kwon, Hwiyeon Yoo, Yunho Choi, Jeongho Park, and Songhwai Oh. Conference on Robot Learning (CoRL), 2022. Oral presentation Keywords: Visual navigation, Embodied agent, Image goal navigation, Semantic scene understanding project page / paper / code / video
	Visual Graph Memory with Unsupervised Representation for Visual Navigation Obin Kwon, Nuri Kim, Yunho Choi, Hwiyeon Yoo, Jeongho Park, Songhwai Oh. (* equal contribution) International Conference on Computer Vision (ICCV), 2021. Keywords: Visual navigation, Embodied agent, Image goal navigation, Semantic scene understanding project page / paper / code / video
	Actualization of Deep Ego-motion Classification on Miniaturized Octagonal Compound Eye Camera Hwiyeon Yoo, Jungho Yi, Jong Mo Seo, and Songhwai Oh. International Conference on Control, Automation and Systems (ICCAS), 2021. Best Poster Paper Award Winner Keywords: Ego-motion classification, Biomimetics, Biomimetic camera paper
	Vision-Based 3D Reconstruction Using a Compound Eye Camera Wooseok Oh, Hwiyeon Yoo, Timothy Ha, and Songhwai Oh. International Conference on Control, Automation and Systems (ICCAS), 2021. Keywords: Depth estimation, 3D reconstruction, Biomimetics paper
	Localizability-based Topological Local Object Occupancy Map for Homing Navigation Hwiyeon Yoo, and Songhwai Oh. International Conference on Ubiquitous Robots (UR), 2021. Keywords: Visual navigation, Embodied agent, Homing, Topological mapping paper
	Path-Following Navigation Network Using Sparse Visual Memory Hwiyeon Yoo, Nuri Kim, Jeongho Park, and Songhwai Oh. International Conference on Control, Automation and Systems (ICCAS), 2020. Keywords: Visual navigation, Embodied agent, Path following, Visual memory paper
	Deep Ego-Motion Classifiers for Compound Eye Cameras Hwiyeon Yoo, Geonho Cha, and Songhwai Oh. Sensors, vol. 19, no. 23, Dec.2019. Keywords: Ego-motion classification, Biomimetics, Biomimetic camera paper
	Unsupervised Holistic Image Generation from Key Local Patches Donghoon Lee, Sangdoo Yun, Sungjoon Choi, Hwiyeon Yoo, Ming-Hsuan Yang, and Songhwai Oh. European Conference on Computer Vision (ECCV), 2018. Keywords: Unsupervised image generation, GAN, Image completion paper / code
	Text2Action: Generative Adversarial Synthesis from Language to Action Hyemin Ahn, Timothy Ha, Yunho Choi, Hwiyeon Yoo*, and Songhwai Oh. ( equal contribution) IEEE International Conference on Robotics and Automation (ICRA), 2018. Keywords: Action generation, GAN paper / code / video
	Estimating Objectness Using a Compound Eye Camera Hwiyeon Yoo, Donghoon Lee, Geonho Cha, and Songhwai Oh. International Conference on Multisensor Fusion and Integration for Intelligent Systems (MFI), 2017. Keywords: Objectness, Biomimetics, Biomimetic camera paper
	Light-Weight Semantic Segmentation for Compound Images Geonho Cha, Hwiyeon Yoo, Donghoon Lee, and Songhwai Oh. International Conference on Multisensor Fusion and Integration for Intelligent Systems (MFI), 2017. Keywords: Semantic segmentation, Biomimetics, Biomimetic camera paper

Projects

General-Purpose Deep Reinforcement Learning Using Metaverse for Real World Applications
National Research Foundation of Korea (NRF) funded by the Ministry of Science and ICT (MSIT), 2023-

Implementation of a vision-based object goal navigation algorithm for embodied agents in real robot navigation.

AI Technology for Guidance of a Mobile Robot to its Goal with Uncertain Maps in Indoor/Outdoor Environments
Ministry of Science and ICT (MSIT), 2019-2023

Development of a vision-based path following navigation algorithm for embodied mobile robots with sparse implicit memory.
Development of a vision-based path following and homing navigation algorithm for embodied mobile robots with building semantic map.
Development of a vision-based object goal navigation algorithm for unknown environments for embodied mobile robots using semantic graph memory.

BioMimetic Robot Research Center - Biomimetic Recognition Technology
Defense Acquisition Program Administration and Agency for Defense Development (ADD), 2016-2021

Development of an insect-like compound eye camera prototype.
Development of light-weight computer vision models on the compound eye: objectness estimation, semantic segmentation, ego-motion estimation, depth estimation, and 3D environment reconstruction.

Realistic 4D Reconstruction of Dynamic Objects
Ministry of Science and ICT (MSIT), 2017-2019

Development of a 3D point cloud matching algorithm.
Development of a 3D human motion reconstruction algorithm by using human part segmentation and tracking.

This webpage template is from Jon Barron's.