Haptic-based touch detection for collaborative robots in welding applications

•A new haptic-based touch detection algorithm was proposed to detect collisions.•We have designed a special system architecture and it has worked very well.•We made tests in a real GTAW welding scenario solving touch detection issues.•Comparison between hampel and 3-Sigma approaches were done to imp...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Robotics and computer-integrated manufacturing 2020-08, Vol.64, p.101952, Article 101952
Hauptverfasser: Tannous, Michael, Miraglia, Marco, Inglese, Francesco, Giorgini, Luca, Ricciardi, Filippo, Pelliccia, Riccardo, Milazzo, Mario, Stefanini, Cesare
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:•A new haptic-based touch detection algorithm was proposed to detect collisions.•We have designed a special system architecture and it has worked very well.•We made tests in a real GTAW welding scenario solving touch detection issues.•Comparison between hampel and 3-Sigma approaches were done to improve precision.•This paper systematically designed an online algorithm for real-time applications. In the Industry 4.0 scenario, collaborative robots have been strongly employed for complex processes and customized production activities. Interaction-based technologies have characterized this approach assisting the operator in several process workflows. In this paper, a haptic-based touch detection strategy is described and tested to assist, in real-time, the operator using a collaborative system in a real industrial scenario, namely the welding process. To assess the performance, two main criteria were analyzed: the 3-Sigma rule and the Hampel identifier. Experimental results showed better performance of the 3-Sigma rule in terms of precision percentage (mean value of 99.9%) and miss rate (mean value of 10%) with respect to the Hampel identifier. Results confirmed the influence of the contamination level related to the dataset. This algorithm adds significant advances to enable the use of light and simple machine learning approaches in real-time applications.
ISSN:0736-5845
1879-2537
DOI:10.1016/j.rcim.2020.101952