In this chapter, we introduce an anomaly monitoring pipeline using the Bayesian nonparametric hidden Markov models after the task representation and skill identification in previous chapter, which divided into three categories according to different thresholds definition, including (i) log-likelihood-based threshold, (ii) threshold based on the gradient of log-likelihood, and (iii) computing the threshold by mapping latent state to log-likelihood. Those method are effectively implement the anomaly monitoring during robot manipulation task. We also evaluate and analyse the performance and results for each method, respectively.
Nonparametric Bayesian Method for Robot Anomaly Monitoring
Nonparametric Bayesian Learning for Collaborative Robot Multimodal Introspection ; Kapitel : 4 ; 51-93
2020-07-22
43 pages
Aufsatz/Kapitel (Buch)
Elektronische Ressource
Englisch
Nonparametric Bayesian Learning for Collaborative Robot Multimodal Introspection
GWLB - Gottfried Wilhelm Leibniz Bibliothek | 2020
|Nonparametric Bayesian Learning for Collaborative Robot Multimodal Introspection
TIBKAT | 2020
|Nonparametric Bayesian Learning for Collaborative Robot Multimodal Introspection
Katalog Medizin | 2020
|Nonparametric Bayesian Learning for Collaborative Robot Multimodal Introspection
Katalog Medizin | 2020
|