A Multimodal Anomaly Detector for Robot-Assisted Feeding Using an LSTM-Based Variational Autoencoder

The detection of anomalous executions is valuable for reducing potential hazards in assistive manipulation. Multimodal sensory signals can be helpful for detecting a wide range of anomalies. However, the fusion of high-dimensional and heterogeneous modalities is a challenging problem for model-based...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:IEEE robotics and automation letters Ročník 3; číslo 3; s. 1544 - 1551
Hlavní autori: Daehyung Park, Hoshi, Yuuna, Kemp, Charles C.
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: Piscataway IEEE 01.07.2018
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Predmet:
Anomalies
Anomaly detection
assistive robots
Decoding
deep learning in robotics and automation
Detectors
Failure detection and recovery
Gaussian distribution
Hazards
Hidden Markov models
Robot sensing systems
Robots
Sensors
ISSN:2377-3766, 2377-3766
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Popis
Shrnutí:The detection of anomalous executions is valuable for reducing potential hazards in assistive manipulation. Multimodal sensory signals can be helpful for detecting a wide range of anomalies. However, the fusion of high-dimensional and heterogeneous modalities is a challenging problem for model-based anomaly detection. We introduce a long short-term memory-based variational autoencoder (LSTM-VAE) that fuses signals and reconstructs their expected distribution by introducing a progress-based varying prior. Our LSTM-VAE-based detector reports an anomaly when a reconstruction-based anomaly score is higher than a state-based threshold. For evaluations with 1555 robot-assisted feeding executions, including 12 representative types of anomalies, our detector had a higher area under the receiver operating characteristic curve of 0.8710 than 5 other baseline detectors from the literature. We also show the variational autoencoding and state-based thresholding are effective in detecting anomalies from 17 raw sensory signals without significant feature engineering effort.
Bibliografia:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:2377-3766
2377-3766
DOI:10.1109/LRA.2018.2801475