Details
| Original language | English |
|---|---|
| Pages (from-to) | 438 - 451 |
| Number of pages | 14 |
| Journal | IEEE transactions on robotics |
| Volume | 40 |
| Early online date | 13 Nov 2023 |
| Publication status | Published - 15 Nov 2023 |
Abstract
During the operation of industrial robots, unusual events may endanger the safety of humans and the quality of production. When collecting data to detect such cases, it is not ensured that data from all potentially occurring errors is included as unforeseeable events may happen over time. Therefore, anomaly detection (AD) delivers a practical solution, using only normal data to learn to detect unusual events. We introduce a dataset that allows training and benchmarking of anomaly detection methods for robotic applications based on machine data which will be made publicly available to the research community. As a typical robot task the dataset includes a pick-and-place application which involves movement, actions of the end effector, and interactions with the objects of the environment. Since several of the contained anomalies are not task-specific but general, evaluations on our dataset are transferable to other robotics applications as well. In addition, we present multivariate time-series flow (MVT-Flow) as a new baseline method for anomaly detection: It relies on deep-learning-based density estimation with normalizing flows, tailored to the data domain by taking its structure into account for the architecture. Our evaluation shows that MVT-Flow outperforms baselines from previous work by a large margin of 6.2% in area under receiving operator characteristic.
Keywords
- Anomaly detection, Dataset for Anomaly Detection, Deep Learning in Robotics and Automation, Failure Detection and Recovery, Hidden Markov models, Probability and Statistical Models, Robots, Safety, Service robots, Time series analysis, Training, deep learning in robotics and automation, probability and statistical models, Dataset for anomaly detection (AD), failure detection and recovery
ASJC Scopus subject areas
- Engineering(all)
- Electrical and Electronic Engineering
- Engineering(all)
- Control and Systems Engineering
- Computer Science(all)
- Computer Science Applications
Cite this
- Standard
- Harvard
- Apa
- Vancouver
- BibTeX
- RIS
In: IEEE transactions on robotics, Vol. 40, 15.11.2023, p. 438 - 451.
Research output: Contribution to journal › Article › Research › peer review
}
TY - JOUR
T1 - The voraus-AD Dataset for Anomaly Detection in Robot Applications
AU - Brockmann, Jan Thies
AU - Rudolph, Marco
AU - Rosenhahn, Bodo
AU - Wandt, Bastian
N1 - Funding Information: This work was supported in part by the Federal Ministry of Education and Research (BMBF), Germany under the AI service center KISSKI under Grant 01IS22093C, in part by the Deutsche Forschungsgemeinschaft (DFG) under Germany's Excellence Strategy within the Cluster of Excellence PhoenixD under Grant EXC 2122, and in part by the German Federal Ministry of the Environment, Nature Conservation, Nuclear Safety and Consumer Protection (GreenAutoML4FASproject) under Grant 67KI32007A.
PY - 2023/11/15
Y1 - 2023/11/15
N2 - During the operation of industrial robots, unusual events may endanger the safety of humans and the quality of production. When collecting data to detect such cases, it is not ensured that data from all potentially occurring errors is included as unforeseeable events may happen over time. Therefore, anomaly detection (AD) delivers a practical solution, using only normal data to learn to detect unusual events. We introduce a dataset that allows training and benchmarking of anomaly detection methods for robotic applications based on machine data which will be made publicly available to the research community. As a typical robot task the dataset includes a pick-and-place application which involves movement, actions of the end effector, and interactions with the objects of the environment. Since several of the contained anomalies are not task-specific but general, evaluations on our dataset are transferable to other robotics applications as well. In addition, we present multivariate time-series flow (MVT-Flow) as a new baseline method for anomaly detection: It relies on deep-learning-based density estimation with normalizing flows, tailored to the data domain by taking its structure into account for the architecture. Our evaluation shows that MVT-Flow outperforms baselines from previous work by a large margin of 6.2% in area under receiving operator characteristic.
AB - During the operation of industrial robots, unusual events may endanger the safety of humans and the quality of production. When collecting data to detect such cases, it is not ensured that data from all potentially occurring errors is included as unforeseeable events may happen over time. Therefore, anomaly detection (AD) delivers a practical solution, using only normal data to learn to detect unusual events. We introduce a dataset that allows training and benchmarking of anomaly detection methods for robotic applications based on machine data which will be made publicly available to the research community. As a typical robot task the dataset includes a pick-and-place application which involves movement, actions of the end effector, and interactions with the objects of the environment. Since several of the contained anomalies are not task-specific but general, evaluations on our dataset are transferable to other robotics applications as well. In addition, we present multivariate time-series flow (MVT-Flow) as a new baseline method for anomaly detection: It relies on deep-learning-based density estimation with normalizing flows, tailored to the data domain by taking its structure into account for the architecture. Our evaluation shows that MVT-Flow outperforms baselines from previous work by a large margin of 6.2% in area under receiving operator characteristic.
KW - Anomaly detection
KW - Dataset for Anomaly Detection
KW - Deep Learning in Robotics and Automation
KW - Failure Detection and Recovery
KW - Hidden Markov models
KW - Probability and Statistical Models
KW - Robots
KW - Safety
KW - Service robots
KW - Time series analysis
KW - Training
KW - deep learning in robotics and automation
KW - probability and statistical models
KW - Dataset for anomaly detection (AD)
KW - failure detection and recovery
UR - http://www.scopus.com/inward/record.url?scp=85177031511&partnerID=8YFLogxK
U2 - 10.48550/arXiv.2311.04765
DO - 10.48550/arXiv.2311.04765
M3 - Article
AN - SCOPUS:85177031511
VL - 40
SP - 438
EP - 451
JO - IEEE transactions on robotics
JF - IEEE transactions on robotics
SN - 1552-3098
ER -