Multimodal Sparse Representation for Anomaly Classification in A Robot Introspection System

Robot introspection is expected to greatly aid longer-term autonomy of autonomous systems. By equipping robots with skills that allow them to assess the quality of their sensory data, robots can detect and classify anomalies and recover from them. However, the variability and complexity of multimodal sensory data exacerbates anomaly classification in practical applications. This work contributes a sparse representation for multimodal time-series for relevant features while preserving classification accuracy. We examine multivariate features in the time and frequency domains and analyze the correlation across all sensory signal dimensions. The sparse process consists of four phases: (i) preprocessing and synchronization of raw time signals; (ii) statistical formulations for each sensor, (iii) evaluation of feature significance using hypothesis testing, and (iv) raw multimodal sample representation with the concatenating feature vector. We test the performance of the sparse anomaly classification through the enactment of a kitting experiment designed to package 6 different objects from a given placement region to a specific container. Aaccuracy, precision, recall, and f-score are used to evaluate the sparse representation performance on various kinds of existing methods.

[1]  Vincent Duchaine,et al.  A highly sensitive multimodal capacitive tactile sensor , 2017, 2017 IEEE International Conference on Robotics and Automation (ICRA).

[2]  Hongmin Wu,et al.  Robust and Versatile Event Detection through Gradient-Based Scoring of HMM Models , 2017, ArXiv.

[3]  Houshang Darabi,et al.  LSTM Fully Convolutional Networks for Time Series Classification , 2017, IEEE Access.

[4]  Hongmin Wu,et al.  Robot introspection with Bayesian nonparametric vector autoregressive hidden Markov models , 2017, 2017 IEEE-RAS 17th International Conference on Humanoid Robotics (Humanoids).

[5]  Malik Ghallab,et al.  Robot introspection through learned hidden Markov models , 2006, Artif. Intell..

[6]  Pierre Geurts,et al.  Pattern Extraction for Time Series Classification , 2001, PKDD.

[7]  David M. J. Tax,et al.  Multivariate Time-Series Classification Using the Hidden-Unit Logistic Model , 2018, IEEE Transactions on Neural Networks and Learning Systems.

[8]  Wenyu Zhang,et al.  Multivariate Time Series Classification Using Dynamic Time Warping Template Selection for Human Activity Recognition , 2015, 2015 IEEE Symposium Series on Computational Intelligence.

[9]  Houshang Darabi,et al.  Multivariate LSTM-FCNs for Time Series Classification , 2018, Neural Networks.

[10]  Meinard Müller,et al.  Dynamic Time Warping , 2008 .

[11]  Hongmin Wu,et al.  Recovering from External Disturbances in Online Manipulation through State-Dependent Revertive Recovery Policies , 2017, 2018 27th IEEE International Symposium on Robot and Human Interactive Communication (RO-MAN).

[12]  Meinard Müller,et al.  Information retrieval for music and motion , 2007 .

[13]  Patrick Schäfer.  The BOSS is concerned with time series classification in the presence of noise , 2014, Data Mining and Knowledge Discovery.

[14]  Luís Nunes,et al.  Human Activity Recognition and Prediction , 2015 .

[15]  Davide Anguita,et al.  A Public Domain Dataset for Human Activity Recognition using Smartphones , 2013, ESANN.

[16]  Andreas W. Kempa-Liehr,et al.  Distributed and parallel time series feature extraction for industrial big data applications , 2016, ArXiv.

[17]  Layth C. Alwan,et al.  Time-Series Modeling for Statistical Process Control , 1988 .

[18]  Carlo Vercellis,et al.  Combining discrete SVM and fixed cardinality warping distances for multivariate time series classification , 2010, Pattern Recognit..

[19]  George C. Runger,et al.  Learning a symbolic representation for multivariate time series classification , 2015, Data Mining and Knowledge Discovery.

[20]  Patrick Schäfer,et al.  Scalable time series classification , 2016, Data Mining and Knowledge Discovery.

[21]  Jun Nakanishi,et al.  Dynamical Movement Primitives: Learning Attractor Models for Motor Behaviors , 2013, Neural Computation.

[22]  Yan Lu,et al.  Human Activity Recognition using Smartphone , 2014, ArXiv.