Dongsoo Han

About

Dongsoo Han is a leading researcher in indoor positioning and magnetic actuation systems, whose work bridges robotics, IoT, and deep learning. His primary research areas include indoor localization using magnetic fields and Wi-Fi signals, magnetic origami robotics, and mobile robot navigation. Han’s major contributions include pioneering a magnetic indoor positioning system that leverages deep neural networks to overcome the ambiguity of geomagnetic data in wide indoor spaces, a method that has garnered 41 citations and significantly advanced the field. He also developed a fusion approach combining SLAM with Wi-Fi-based positioning for mobile robots, enabling efficient learning data collection and tracking in indoor environments (21 citations). In a notable recent achievement, Han introduced reprogrammable, recyclable origami robots controlled by magnetic fields, creating cost-effective, biodegradable robots for wireless applications (15 citations). His work on a home indoor positioning system (HIPS) for IoT applications (9 citations) and a 2D particle filter accelerator for mobile robot pose estimation (5 citations) further demonstrates his impact. With over 90 total citations across his top papers, Han’s research is shaping the future of smart environments and sustainable robotics.

Research Focus

Key Achievements

Top Papers

1. 1
   Magnetic indoor positioning system using deep neural network

   41 citations · 2017
2. 2
   Fusion of the SLAM with Wi-Fi-Based Positioning Methods for Mobile Robot-Based Learning Data Collection, Localization, and Tracking in Indoor Spaces

   21 citations · 2020
3. 3
   Reprogrammable, Recyclable Origami Robots Controlled by Magnetic Fields

   15 citations · 2024
4. 4
   Construction of an indoor positioning system for home IoT applications

   9 citations · 2017
5. 5
   2D Particle Filter Accelerator for Mobile Robot Indoor Localization and Pose Estimation

   5 citations · 2024

Key Collaborators

Contact & Links