Transfer Learning Based Multi-Perception Safety Strategy for Human-Robot Collaboration

Chongyi Wei; Changcong Wang; Shaoping Bai; Yibin Li; Xincheng Tian; Lelai Zhou

doi:10.1109/RCAR58764.2023.10249759

Transfer Learning Based Multi-Perception Safety Strategy for Human-Robot Collaboration

Chongyi Wei^*, Changcong Wang, Shaoping Bai, Yibin Li, Xincheng Tian, Lelai Zhou

^*Corresponding author for this work

Research output: Contribution to book/anthology/report/conference proceeding › Article in proceeding › Research › peer-review

Abstract

Human-robot collaboration (HRC) is vital to adapt to the significant change in manufacturers' demands for automation, and safety is a primary and major challenge that must be addressed for it. In this paper, a muti-perception safety strategy and framework are introduced to ensure human safety while trying to avoid reducing the work efficiency of the robot by taking human activity intentions and human-robot distance into account. To realize the safety strategy, an LSTM-CNN based neural network is built for human activity classification. To improve the generalization ability and performance of the network with data scarcity for existing deep learning-based human activity recognition methods, transfer learning-enabled activity recognition is proposed. Based on the studies, a feasible security system is implemented in the human-robot collaboration scenario.

Original language	English
Title of host publication	Proceedings of the 2023 IEEE International Conference on Real-Time Computing and Robotics, RCAR 2023
Number of pages	6
Publisher	IEEE (Institute of Electrical and Electronics Engineers)
Publication date	2023
Pages	799-804
Article number	10249759
ISBN (Print)	979-8-3503-2719-9
ISBN (Electronic)	979-8-3503-2718-2
DOIs	https://doi.org/10.1109/RCAR58764.2023.10249759
Publication status	Published - 2023
Event	2023 IEEE International Conference on Real-Time Computing and Robotics, RCAR 2023 - Datong, China Duration: 17 Jul 2023 → 20 Jul 2023

Conference

Conference	2023 IEEE International Conference on Real-Time Computing and Robotics, RCAR 2023
Country/Territory	China
City	Datong
Period	17/07/2023 → 20/07/2023
Sponsor	Beijing NOKOV Science and Technology Co., Cyborg and Bionic Systems, Galleon (Shanghai) Consulting Co., Ltd., Shanghai Society of Aeronautics

Bibliographical note

Publisher Copyright:
© 2023 IEEE.

Access to Document

10.1109/RCAR58764.2023.10249759

AUB Link

Search for the material in Aalborg University Library's search engine

Cite this

Wei, C., Wang, C., Bai, S., Li, Y., Tian, X., & Zhou, L. (2023). Transfer Learning Based Multi-Perception Safety Strategy for Human-Robot Collaboration. In Proceedings of the 2023 IEEE International Conference on Real-Time Computing and Robotics, RCAR 2023 (pp. 799-804). Article 10249759 IEEE (Institute of Electrical and Electronics Engineers). https://doi.org/10.1109/RCAR58764.2023.10249759

@inproceedings{7689e49c04924936837fdcb2ed9bef9a,

title = "Transfer Learning Based Multi-Perception Safety Strategy for Human-Robot Collaboration",

abstract = "Human-robot collaboration (HRC) is vital to adapt to the significant change in manufacturers' demands for automation, and safety is a primary and major challenge that must be addressed for it. In this paper, a muti-perception safety strategy and framework are introduced to ensure human safety while trying to avoid reducing the work efficiency of the robot by taking human activity intentions and human-robot distance into account. To realize the safety strategy, an LSTM-CNN based neural network is built for human activity classification. To improve the generalization ability and performance of the network with data scarcity for existing deep learning-based human activity recognition methods, transfer learning-enabled activity recognition is proposed. Based on the studies, a feasible security system is implemented in the human-robot collaboration scenario.",

author = "Chongyi Wei and Changcong Wang and Shaoping Bai and Yibin Li and Xincheng Tian and Lelai Zhou",

note = "Publisher Copyright: {\textcopyright} 2023 IEEE.; 2023 IEEE International Conference on Real-Time Computing and Robotics, RCAR 2023 ; Conference date: 17-07-2023 Through 20-07-2023",

year = "2023",

doi = "10.1109/RCAR58764.2023.10249759",

language = "English",

isbn = "979-8-3503-2719-9",

pages = "799--804",

booktitle = "Proceedings of the 2023 IEEE International Conference on Real-Time Computing and Robotics, RCAR 2023",

publisher = "IEEE (Institute of Electrical and Electronics Engineers)",

address = "United States",

}

Wei, C, Wang, C, Bai, S, Li, Y, Tian, X & Zhou, L 2023, Transfer Learning Based Multi-Perception Safety Strategy for Human-Robot Collaboration. in Proceedings of the 2023 IEEE International Conference on Real-Time Computing and Robotics, RCAR 2023., 10249759, IEEE (Institute of Electrical and Electronics Engineers), pp. 799-804, 2023 IEEE International Conference on Real-Time Computing and Robotics, RCAR 2023, Datong, China, 17/07/2023. https://doi.org/10.1109/RCAR58764.2023.10249759

Transfer Learning Based Multi-Perception Safety Strategy for Human-Robot Collaboration. / Wei, Chongyi; Wang, Changcong; Bai, Shaoping et al.
Proceedings of the 2023 IEEE International Conference on Real-Time Computing and Robotics, RCAR 2023. IEEE (Institute of Electrical and Electronics Engineers), 2023. p. 799-804 10249759.

Research output: Contribution to book/anthology/report/conference proceeding › Article in proceeding › Research › peer-review

TY - GEN

T1 - Transfer Learning Based Multi-Perception Safety Strategy for Human-Robot Collaboration

AU - Wei, Chongyi

AU - Wang, Changcong

AU - Bai, Shaoping

AU - Li, Yibin

AU - Tian, Xincheng

AU - Zhou, Lelai

PY - 2023

Y1 - 2023

N2 - Human-robot collaboration (HRC) is vital to adapt to the significant change in manufacturers' demands for automation, and safety is a primary and major challenge that must be addressed for it. In this paper, a muti-perception safety strategy and framework are introduced to ensure human safety while trying to avoid reducing the work efficiency of the robot by taking human activity intentions and human-robot distance into account. To realize the safety strategy, an LSTM-CNN based neural network is built for human activity classification. To improve the generalization ability and performance of the network with data scarcity for existing deep learning-based human activity recognition methods, transfer learning-enabled activity recognition is proposed. Based on the studies, a feasible security system is implemented in the human-robot collaboration scenario.

AB - Human-robot collaboration (HRC) is vital to adapt to the significant change in manufacturers' demands for automation, and safety is a primary and major challenge that must be addressed for it. In this paper, a muti-perception safety strategy and framework are introduced to ensure human safety while trying to avoid reducing the work efficiency of the robot by taking human activity intentions and human-robot distance into account. To realize the safety strategy, an LSTM-CNN based neural network is built for human activity classification. To improve the generalization ability and performance of the network with data scarcity for existing deep learning-based human activity recognition methods, transfer learning-enabled activity recognition is proposed. Based on the studies, a feasible security system is implemented in the human-robot collaboration scenario.

UR - http://www.scopus.com/inward/record.url?scp=85173613850&partnerID=8YFLogxK

U2 - 10.1109/RCAR58764.2023.10249759

DO - 10.1109/RCAR58764.2023.10249759

M3 - Article in proceeding

AN - SCOPUS:85173613850

SN - 979-8-3503-2719-9

SP - 799

EP - 804

BT - Proceedings of the 2023 IEEE International Conference on Real-Time Computing and Robotics, RCAR 2023

PB - IEEE (Institute of Electrical and Electronics Engineers)

T2 - 2023 IEEE International Conference on Real-Time Computing and Robotics, RCAR 2023

Y2 - 17 July 2023 through 20 July 2023

ER -

Transfer Learning Based Multi-Perception Safety Strategy for Human-Robot Collaboration

Abstract

Conference

Bibliographical note

Access to Document

AUB Link

Other files and links

Fingerprint

Cite this