Abstract | ||
---|---|---|
The ever-increasing complexity of robots usually implies a parallel increase in the number of failures of such systems. Due to this, monitoring and anomaly detection plays a key role in the implementation of smart robotics and soft computing can significantly contribute to this task. In keeping with this idea, recently proposed Hybrid Unsupervised Exploratory Plots (HUEPs) are proposed in present paper to monitor the performance and improve anomaly detection in a component-based robotic software. Furthermore, the original HUEP formulation is extended by means of density-based clustering. Such clustering techniques are validated in conjunction with unsupervised exploratory projection ones. This novel proposal is validated on an open and up-to-date dataset containing information about the software performance of a collaborative robot. |
Year | DOI | Venue |
---|---|---|
2021 | 10.1007/978-3-030-87869-6_11 | 16TH INTERNATIONAL CONFERENCE ON SOFT COMPUTING MODELS IN INDUSTRIAL AND ENVIRONMENTAL APPLICATIONS (SOCO 2021) |
Keywords | DocType | Volume |
Smart robotics, Component-based robot software, Performance monitoring, Anomaly detection, Soft computing, Unsupervised learning, Clustering, Exploratory projection | Conference | 1401 |
ISSN | Citations | PageRank |
2194-5357 | 0 | 0.34 |
References | Authors | |
0 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Nuño Basurto | 1 | 2 | 2.75 |
Carlos Cambra | 2 | 0 | 0.34 |
ÁLvaro Herrero | 3 | 487 | 50.88 |