Labelled Force/Torque Time Series from Robotic Wheel Assembly Dataset
A time series dataset of forces and torques that can be used to develop and test ML models for anomaly detection in robotic assembly.
Asset Description
This dataset contains 524 recordings of 6-dimensional time series representing forces and torques during the assembly of small car model wheels using a Delta robot. The data includes labels indicating the success of each assembly and serves as a valuable resource for anomaly detection and quality control research in robotic assembly processes.
Dataset Details
Dataset Overview
The dataset comprises recordings of forces in three directions (x, y, z) and torques in three directions (x, y, z), sampled at a rate of 0.004 seconds per sample. The data is provided in a CSV file (ForceTorqueTimeSeries.csv), with additional video and documentation files. The dataset is intended for use in anomaly detection models, particularly in the context of robotic assembly processes.
Usage
Users can download the dataset and accompanying files from Zenodo to develop and test machine learning models for anomaly detection in robotic assembly. The dataset can be used in conjunction with the other provided files, which describe the data acquisition process and preliminary experiments.
Maturity
Already Implemented/Available
Licence
Open source - CC BY 4.0
Resources
- The dataset is available for download in Zenodo
- Provided by Czech Technical University in Prague - CTU
Acknowledgement
This work was co-funded partly by AI REDGIO 5.0 and partly by the European Union under the project ROBOPROX(reg. no. CZ.02.01.01/00/22_008/0004590). In the AI REDGIO 5.0 project it will be used in the Didactic Factory Pilot DFXI: AI-driven Monitoring of Robotic Assembly Process