智慧工廠已經是現在工業的趨勢。他其中的一個重點會使用物聯網
（IoT）進行資料的蒐集和人工智能 (AI) 來進行資料的分析，藉此來大幅
提升工廠的生產效率。我們的研究會使用人工智慧來協助工廠中的組裝任
務。我們設計了一個系統來幫助人們來完成模擬製造環境中的組裝任務。
用戶需要分五個階段組裝 Meccanoid 機器人，系統會針對每個階段給予
適當的指導。我們會透過用戶手腕上的 IMU 來進行資料分析，並根據他
之前的行為來調整出更適合用戶的指導。我們的目標是讓我們的系統可以
更好的了解用戶的行為並給出指導，所以我們會先將資料進行動作辨識和
人物辨識。我們將用戶的動作分成六類並進行動作的辨識，讓我們可以了
解用戶的動作與行為。人物辨識則是用來辨別用戶的行為模式比較像新手
或是老手，藉此能更有針對性的給出建議。在本文中，我們會先將 IMU
獲取的資料先進行動作辨識與人物辨識，再根據他們的結果整理出五個特
徵，系統會根據這些特徵給出適當的指導。最後我們會比較用戶能否透過
我們系統的指導來獲得進步。

Smart factory are already the trend in the industry. One of the focuses of
smart factory the industrial Internet of Things (IIoT) for data collection
and artificial intelligence (AI) for data analysis, thereby greatly improving
productivity. In this research, we focus on artificial intelligence and assist
assembly tasks in a factory. We simulate an assembly scenario in a factory
and designed a system to assist people in the assembly task. The user needs
to assemble the Meccanoid robot in five stages, and we give appropriate
guidance for each stage. To better understand users, we analyze the data
through the IMU on the user’s wrists and adjust the guidance. Our goal
is to make our system to better understand the user’s behavior and give
guidance, so we first perform action recognition and identity recognition
on the data. We divide the user’s actions into six categories and identify the
actions so that we can understand the user’s actions and behaviors. Identity
recognition identifies whether the user’s behavior pattern is more like a
novice or a master so that more targeted suggestions can be given. In this
paper, we first perform action recognition and identity recognition on the
data obtained by the IMU, and then sort out five features based on those
results. We give appropriate guidance based on these features. Finally,
we compare whether users can make progress through the guidance of our
system.

[1] B. Chen, J. Wan, L. Shu, P. Li, M. Mukherjee, and B. Yin, “Smart factory of industry 4.0: Key
technologies, application case, and challenges,” IEEE Access, vol. 6, pp. 6505–6519, 2018.
[2] L. Lattanzi, C. Cristalli, D. Massa, S. Boria, P. Lépine, and M. Pellicciari, “Geometrical calibration of
a 6-axis robotic arm for high accuracy manufacturing task,” The International Journal of Advanced
Manufacturing Technology, vol. 111, no. 7, pp. 1813–1829, 2020.
[3] W. Shen and D. H. Norrie, “Agent-based systems for intelligent manufacturing: a state-of-the-art
survey,” Knowledge and information systems, vol. 1, no. 2, pp. 129–156, 1999.
[4] R. Y. Zhong, X. Xu, E. Klotz, and S. T. Newman, “Intelligent manufacturing in the context of industry
4.0: a review,” Engineering, vol. 3, no. 5, pp. 616–630, 2017.
[5] S. Jeschke, C. Brecher, T. Meisen, D. Özdemir, and T. Eschert, “Industrial internet of things and cyber
manufacturing systems,” in Industrial internet of things, pp. 3–19, Springer, 2017.
[6] J. Lee, H. Davari, J. Singh, and V. Pandhare, “Industrial artificial intelligence for industry 4.0-based
manufacturing systems,” Manufacturing letters, vol. 18, pp. 20–23, 2018.
[7] W. Tao, M. C. Leu, and Z. Yin, “Multi-modal recognition of worker activity for human-centered
intelligent manufacturing,” Engineering Applications of Artificial Intelligence, vol. 95, p. 103868,
2020.
[8] H. ElMaraghy and W. ElMaraghy, “Smart adaptable assembly systems,” Procedia CIRP, vol. 44,
pp. 4–13, 2016.
[9] K.-J. Wang, D. A. Rizqi, and H.-P. Nguyen, “Skill transfer support model based on deep learning,”
Journal of Intelligent Manufacturing, vol. 32, no. 4, pp. 1129–1146, 2021.
[10] T.-Y. Chen, Y.-C. Chiu, N. Bi, and R. T.-H. Tsai, “Multi-modal chatbot in intelligent manufacturing,”
IEEE Access, vol. 9, pp. 82118–82129, 2021.
[11] A. Filippeschi, N. Schmitz, M. Miezal, G. Bleser, E. Ruffaldi, and D. Stricker, “Survey of motion
tracking methods based on inertial sensors: A focus on upper limb human motion,” Sensors, vol. 17,
no. 6, p. 1257, 2017.
[12] N. Ahmad, R. A. R. Ghazilla, N. M. Khairi, and V. Kasi, “Reviews on various inertial measurement
unit (imu) sensor applications,” International Journal of Signal Processing Systems, vol. 1, no. 2,
pp. 256–262, 2013.
[13] Y. Zhang and J. Zheng, “Imu action recognition based on machine learning,” Journal of Electronic
Research and Application, vol. 3, no. 6, 2019.
[14] C. Chen, R. Jafari, and N. Kehtarnavaz, “A survey of depth and inertial sensor fusion for human action
recognition,” Multimedia Tools and Applications, vol. 76, no. 3, pp. 4405–4425, 2017.
[15] J. Carreira and A. Zisserman, “Quo vadis, action recognition? a new model and the kinetics dataset,”
in proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6299–6308,
2017.
[16] S. Ji, W. Xu, M. Yang, and K. Yu, “3d convolutional neural networks for human action recognition,”
IEEE transactions on pattern analysis and machine intelligence, vol. 35, no. 1, pp. 221–231, 2012.
[17] W. Tao, Z.-H. Lai, M. C. Leu, and Z. Yin, “Worker activity recognition in smart manufacturing us-
ing imu and semg signals with convolutional neural networks,” Procedia Manufacturing, vol. 26,
pp. 1159–1166, 2018.
[18] C. Hou, “A study on imu-based human activity recognition using deep learning and traditional machine
learning,” in 2020 5th International Conference on Computer and Communication Systems (ICCCS),
pp. 225–234, 2020.
[19] C. Shiranthika, N. Premakumara, H.-L. Chiu, H. Samani, C. Shyalika, and C.-Y. Yang, “Human ac-
tivity recognition using cnn lstm,” in 2020 5th International Conference on Information Technology
Research (ICITR), pp. 1–6, 2020.