EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Towards a Safe Human–Robot Collaboration Using Information on Human Worker Activity

Luka Orsag iD, Tomislav Stipancic iD, Leon Koren

Sensors · 22.01.2023 · 23 (3) · 1283

DOI: 10.3390/s23031283 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 22.01.2023. Verfasst von Luka Orsag und 2 weiteren Autor:innen. Beteiligte Einrichtung: Faculty of Mechanical Engineering and Naval Architecture, University of Zagreb, Ivana Lucica 5, 10000 Zagreb, Croatia. Hauptthemen laut MEDLINE: Robotics. Die Arbeit wurde bisher 31-mal zitiert (Crossref) und nennt 49 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Most industrial workplaces involving robots and other apparatus operate behind the fences to remove defects, hazards, or casualties. Recent advancements in machine learning can enable robots to co-operate with human co-workers while retaining safety, flexibility, and robustness. This article focuses on the computation model, which provides a collaborative environment through intuitive and adaptive human–robot interaction (HRI). In essence, one layer of the model can be expressed as a set of useful information utilized by an intelligent agent. Within this construction, a vision-sensing modality can be broken down into multiple layers. The authors propose a human-skeleton-based trainable model for the recognition of spatiotemporal human worker activity using LSTM networks, which can achieve a training accuracy of 91.365%, based on the InHARD dataset. Together with the training results, results related to aspects of the simulation environment and future improvements of the system are discussed. By combining human worker upper body positions with actions, the perceptual potential of the system is increased, and human–robot collaboration becomes context-aware. Based on the acquired information, the intelligent agent gains the ability to adapt its behavior according to its dynamic and stochastic surroundings.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

RoboticsHumansMachine LearningIntelligenceIndustryRecognition, Psychology

Stichwörter der Autor:innen

LSTMactivity recognitionadaptive manufacturing systemsdeep learninghuman–robot collaborationroboticssafe HCI

Autor:innen und Institutionen

  • Faculty of Mechanical Engineering and Naval Architecture, University of Zagreb, Ivana Lucica 5, 10000 Zagreb, Croatia.

ORCID-Profile: Luka Orsag, Tomislav Stipancic

Zitieren

APA

Orsag, L., Stipancic, T., & Koren, L. (2023). Towards a Safe Human–Robot Collaboration Using Information on Human Worker Activity. Sensors, 23(3), 1283. https://doi.org/10.3390/s23031283

Vancouver

Orsag L, Stipancic T, Koren L. Towards a Safe Human–Robot Collaboration Using Information on Human Worker Activity. Sensors. 2023;23(3):1283. doi:10.3390/s23031283

BibTeX
@article{Orsag2023,
  author = {Orsag, Luka and Stipancic, Tomislav and Koren, Leon},
  title = {Towards a Safe Human–Robot Collaboration Using Information on Human Worker Activity},
  journal = {Sensors},
  year = {2023},
  volume = {23},
  number = {3},
  pages = {1283},
  doi = {10.3390/s23031283}
}
Kostenlos starten →