Load cell torques and force data collection during tele-operated robotic gas tungsten arc welding in presence of collisions

• Main Authors: Michael Tannous, Francesco Bologna, Cesare Stefanini
• Format: Article
• Language: English
• Published: Elsevier 2020-08-01
• Series: Data in Brief
• Subjects: Load cell torques; Human-robot interaction; Haptic interface; Machine learning; Welding applications; Smart manufacturing
• Online Access: http://www.sciencedirect.com/science/article/pii/S2352340920308751
• ISSN: 2352-3409

Torque and force signals data were acquired from a load-cell sensor during a robotic welding process, in presence of collisions between the tool and the workpiece edges outlined in part in ''Haptic-based touch detection for collaborative robots in welding applications'' [1]. The dataset is composed from 15 tests captured during a tele-operated welding robot performing a 1G ASME/AWS (i.e., PA ISO) welding process. The raw data files have been provided. These data can be used to correlate torque signal features with collision events, to improve algorithms of collision detection/avoidance and to develop reliable real-time haptic feedback to the welder. This dataset can also be used to study the torque signal variation in different welding positions (e.g., 2G, 3G, 2F, etc.). Dataset is provided as raw data and in MATLAB files.