TY - GEN
T1 - A Multi-Granularity Scene Segmentation Network for Human-Robot Collaboration Environment Perception
AU - Fan, Junming
AU - Zheng, Pai
AU - Lee, Carman K.M.
N1 - Funding Information:
This research is supported by the Laboratory for Artificial Intelligence in Design (Project Code: RP2-1); and the Research Committee of The Hong Kong Polytechnic University under Collaborative Departmental General Research Fund (G-UAMS), Hong Kong SAR, China.
Publisher Copyright:
© 2022 IEEE.
PY - 2022/10
Y1 - 2022/10
N2 - Human-robot collaboration (HRC) has been considered as a promising paradigm towards futuristic human-centric smart manufacturing, to meet the thriving needs of mass personalization. In this context, existing robotic systems normally adopt a single-granularity semantic segmentation scheme for environment perception, which lacks the flexibility to be implemented to various HRC situations. To fill the gap, this study proposes a multi-granularity scene segmentation network. Inspired by some recent network designs, we construct an encoder network with two ConvNext-T backbones for RGB and depth respectively, and an decoder network consisting of multi-scale supervision and multi-granularity segmentation branches. The proposed model is demonstrated in a human-robot collaborative battery disassembly scenario and further evaluated in comparison with state-of-the-art RGB-D semantic segmentation methods on the NYU-Depth V2 dataset.
AB - Human-robot collaboration (HRC) has been considered as a promising paradigm towards futuristic human-centric smart manufacturing, to meet the thriving needs of mass personalization. In this context, existing robotic systems normally adopt a single-granularity semantic segmentation scheme for environment perception, which lacks the flexibility to be implemented to various HRC situations. To fill the gap, this study proposes a multi-granularity scene segmentation network. Inspired by some recent network designs, we construct an encoder network with two ConvNext-T backbones for RGB and depth respectively, and an decoder network consisting of multi-scale supervision and multi-granularity segmentation branches. The proposed model is demonstrated in a human-robot collaborative battery disassembly scenario and further evaluated in comparison with state-of-the-art RGB-D semantic segmentation methods on the NYU-Depth V2 dataset.
UR - http://www.scopus.com/inward/record.url?scp=85146311010&partnerID=8YFLogxK
U2 - 10.1109/IROS47612.2022.9981684
DO - 10.1109/IROS47612.2022.9981684
M3 - Conference article published in proceeding or book
AN - SCOPUS:85146311010
T3 - IEEE International Conference on Intelligent Robots and Systems
SP - 2105
EP - 2110
BT - IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2022
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2022 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2022
Y2 - 23 October 2022 through 27 October 2022
ER -