TY - GEN
T1 - Hierarchical Intention Tracking for Robust Human-Robot Collaboration in Industrial Assembly Tasks
AU - Huang, Zhe
AU - Mun, Ye Ji
AU - Li, Xiang
AU - Xie, Yiqing
AU - Zhong, Ninghan
AU - Liang, Weihang
AU - Geng, Junyi
AU - Chen, Tan
AU - Driggs-Campbell, Katherine
N1 - Funding Information:
Z. Huang, Y. Mun, X. Li, Y. Xie, W. Liang, and K. Driggs-Campbell are with the Department of Electrical and Computer Engineering at the University of Illinois at Urbana-Champaign. emails: {zheh4, yejimun2, xiangl5, yiqingx2, weihang2, krdc}@illinois.edu N. Zhong is with the Department of Computer Science at the University of Illinois at Urbana-Champaign. email: ninghan2@illinois.edu J. Geng is with the Department of Aerospace Engineering at Pennsylvania State University. email: jgeng@psu.edu T. Chen is with the Department of Electrical and Computer Engineering at Michigan Technological University. email: tanchen@mtu.edu This work was supported by Foxconn Interconnect Technology through the UIUC Center for Networked Intelligent Components and Environments (C-NICE).
Publisher Copyright:
© 2023 IEEE.
PY - 2023
Y1 - 2023
N2 - Collaborative robots require effective human intention estimation to safely and smoothly work with humans in less structured tasks such as industrial assembly, where human intention continuously changes. We propose the concept of intention tracking and introduce a collaborative robot system that concurrently tracks intentions at hierarchical levels. The high-level intention is tracked to estimate human's interaction pattern and enable robot to (1) avoid collision with human to minimize interruption and (2) assist human to correct failure. The low-level intention estimate provides robot with task-related information. We implement the system on a UR5e robot and demonstrate robust, seamless and ergonomic human-robot collaboration in an ablative pilot study of an assembly use case.
AB - Collaborative robots require effective human intention estimation to safely and smoothly work with humans in less structured tasks such as industrial assembly, where human intention continuously changes. We propose the concept of intention tracking and introduce a collaborative robot system that concurrently tracks intentions at hierarchical levels. The high-level intention is tracked to estimate human's interaction pattern and enable robot to (1) avoid collision with human to minimize interruption and (2) assist human to correct failure. The low-level intention estimate provides robot with task-related information. We implement the system on a UR5e robot and demonstrate robust, seamless and ergonomic human-robot collaboration in an ablative pilot study of an assembly use case.
UR - http://www.scopus.com/inward/record.url?scp=85168638956&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85168638956&partnerID=8YFLogxK
U2 - 10.1109/ICRA48891.2023.10160515
DO - 10.1109/ICRA48891.2023.10160515
M3 - Conference contribution
AN - SCOPUS:85168638956
T3 - Proceedings - IEEE International Conference on Robotics and Automation
SP - 9821
EP - 9828
BT - Proceedings - ICRA 2023
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2023 IEEE International Conference on Robotics and Automation, ICRA 2023
Y2 - 29 May 2023 through 2 June 2023
ER -