Challenges in Deictic Gesture-Based Spatial Referencing for Human-Robot Interaction in Construction

November 2, 2021·
Sungboo Yoon
Sungboo Yoon
,
YeSeul Kim
,
Changbum R. Ahn
,
Moonseo Park
· 0 min read
Abstract
This paper investigates the limits of deictic gesture-based spatial communication between humans and robots in construction environments. Through experiments on wall and ceiling targets, it shows that current methods can estimate pointed positions with reasonable overall performance but face larger errors in ceiling and side-panel conditions, highlighting practical challenges for spatial referencing on real job sites.
Type
Publication
In Proceedings of the 38th International Symposium on Automation and Robotics in Construction (ISARC 2021)
publications
Sungboo Yoon
Authors
Sungboo Yoon
PhD Candidate @ Seoul National University

Hello! I am a fifth-year Ph.D. candidate in the Department of Architecture & Architectural Engineering at Seoul National University. I am fortunate to be advised by Professor Changbum R. Ahn, and I am a member of the Construction Engineering & Management Lab. My research interests include construction robotics, human-robot interaction, and robot learning.

I previously completed both my bachelor’s and master’s degrees in Architectural Engineering at Seoul National University, where I conducted research on modular construction and human-robot interaction under the advisement of Professor Moonseo Park.

I am honored to be a recipient of the Basic Science Research Program (Ph.D. Fellowship) from the National Research Foundation of Korea (NRF).

Currently, I serve as a student coordinator of a joint project funded by the Ministry of Land, Infrastructure and Transport & Ministry of Trade, Industry and Energy, South Korea, on developing a multipurpose robotic platform and XR-based human–robot collaboration system for construction work at height. If you are interested, please visit this page for more details.