EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Learning an Intention Projection Operator for Axis-Wise Human Control in Remote Piloted Aircraft Systems

Satoshi Miura, Yuki Kaku, Bo Zhang, Tomoyuki Miyashita, Shigeki Sugano

IEEE Transactions on Systems, Man, and Cybernetics: Systems · 2026-11 · 56 (11) · 6804-6817

DOI: 10.1109/tsmc.2026.3717276 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Systems, Man, and Cybernetics: Systems, 2026-11. Verfasst von Satoshi Miura und 4 weiteren Autor:innen. Die Arbeit nennt 55 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Council for Science, Technology, and Innovation (CSTII) Cross-Ministerial Strategic Innovation Promotion Program (SIP), New Energy and Industrial Technology Development Organization, Japan Society for the Promotion of Science (JSPS) KAKENHI.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Remote piloted aircraft systems (RPASs) are mainly operated in a Cartesian coordinate system. This coordinate system makes it easy to recognize the movement direction of the aircraft; however, with a conventional gamepad, it is difficult to understand the mapping and to manipulate the aircraft precisely. This article presents an intuitive RPAS operation method. We developed a hand-controller that considers wrist embodiment and motion in a Cartesian coordinate system. In addition, because unintended input often interferes with intended input, a recurrent neural network, namely, long short-term memory (LSTM), was used to learn the user’s large and precise input tendencies. In the first experiment, seven participants operated a UAV using the controller with and without the LSTM. The LSTM-based controller yielded 27.8% shorter test-course completion times while maintaining operating accuracy. Furthermore, in the second experiment, in which 11 participants operated a UAV, the controller yielded a 1.67 times higher success rate for beginners, a 35% shorter mean course completion time, and significantly higher brain activation related to intentional operation for all users, compared with a conventional gamepad. In conclusion, users can easily understand the mapping and intuitively adjust the input magnitude from the neutral position.

Förderung

  • Council for Science, Technology, and Innovation (CSTII) Cross-Ministerial Strategic Innovation Promotion Program (SIP)
  • New Energy and Industrial Technology Development Organization
  • Japan Society for the Promotion of Science (JSPS) KAKENHI
  • Takano Foundation
  • Suzuki Foundation
  • Nakajima Foundation

Zitieren

APA

Miura, S., Kaku, Y., Zhang, B., Miyashita, T., & Sugano, S. (2026). Learning an Intention Projection Operator for Axis-Wise Human Control in Remote Piloted Aircraft Systems. IEEE Transactions on Systems, Man, and Cybernetics: Systems, 56(11), 6804-6817. https://doi.org/10.1109/tsmc.2026.3717276

Vancouver

Miura S, Kaku Y, Zhang B, Miyashita T, Sugano S. Learning an Intention Projection Operator for Axis-Wise Human Control in Remote Piloted Aircraft Systems. IEEE Transactions on Systems, Man, and Cybernetics: Systems. 2026;56(11):6804-6817. doi:10.1109/tsmc.2026.3717276

BibTeX
@article{Miura2026,
  author = {Miura, Satoshi and Kaku, Yuki and Zhang, Bo and Miyashita, Tomoyuki and Sugano, Shigeki},
  title = {Learning an Intention Projection Operator for Axis-Wise Human Control in Remote Piloted Aircraft Systems},
  journal = {IEEE Transactions on Systems, Man, and Cybernetics: Systems},
  year = {2026},
  volume = {56},
  number = {11},
  pages = {6804--6817},
  doi = {10.1109/tsmc.2026.3717276}
}
Kostenlos starten →