Statistical detection of faults in swarm robots under noisy conditions

Fault detection plays an important role in supervising the operation of robotic swarm systems. If faults are not detected, they can considerably affect the performance of the robot swarm. In this paper, we present a robust fault detection mechanism against noise and uncertainties in data, by merging the multiresolution representation of data using wavelets with the sensitivity to small changes of an exponentially weighted moving average scheme. Specifically, to monitor swarm robotics systems performing a virtual viscoelastic control model for circle formation task, the proposed mechanism is applied to the uncorrelated residuals form principal component analysis model. Monitoring results using a simulation data from ARGoS simulator demonstrate that the proposed method achieves improved fault detection performances compared with the conventional approach.

[1]  Cherif Foudil,et al.  Monitoring a robot swarm using a data-driven fault detection approach , 2017, Robotics Auton. Syst..

[2]  Age K. Smilde,et al.  Principal Component Analysis , 2003, Encyclopedia of Machine Learning.

[3]  Jonathan Timmis,et al.  A modified Dendritic Cell Algorithm for on-line error detection in robotic systems , 2009, 2009 IEEE Congress on Evolutionary Computation.

[4]  Marco Dorigo,et al.  From Fireflies to Fault-Tolerant Swarms of Robots , 2009, IEEE Transactions on Evolutionary Computation.

[5]  Mauro Birattari,et al.  Fault detection in autonomous robots based on fault injection and learning , 2008, Auton. Robots.

[6]  Fouzi Harrou,et al.  Improved anomaly detection using multi-scale PLS and generalized likelihood ratio test , 2016, 2016 IEEE Symposium Series on Computational Intelligence (SSCI).

[7]  Ruqiang Yan,et al.  Wavelets: Theory and Applications for Manufacturing , 2010 .

[8]  J. E. Jackson,et al.  Control Procedures for Residuals Associated With Principal Component Analysis , 1979 .

[9]  Eliseo Ferrante,et al.  ARGoS: a modular, parallel, multi-engine simulator for multi-robot systems , 2012, Swarm Intelligence.

[10]  Mohamed N. Nounou,et al.  Univariate process monitoring using multiscale Shewhart charts , 2014, 2014 International Conference on Control, Decision and Information Technologies (CoDIT).

[11]  Yongsheng Ding,et al.  Self-organized swarm robot for target search and trapping inspired by bacterial chemotaxis , 2015, Robotics Auton. Syst..

[12]  Zhongyang Zheng,et al.  Research Advance in Swarm Robotics , 2013 .

[13]  Hazem N. Nounou,et al.  A statistical fault detection strategy using PCA based EWMA control schemes , 2013, 2013 9th Asian Control Conference (ASCC).

[14]  Anders Lyhne Christensen,et al.  To err is robotic, to tolerate immunological: fault detection in multirobot systems. , 2015, Bioinspiration & biomimetics.

[15]  Belkacem Khaldi,et al.  An Overview of Swarm Robotics: Swarm Intelligence Applied to Multi-robotics , 2015 .

[16]  Spyros G. Tzafestas,et al.  Finding fault - fault diagnosis on the wheels of a mobile robot using local model neural networks , 2004, IEEE Robotics & Automation Magazine.

[17]  Richard M. Crowder,et al.  Exogenous Fault Detection and Recovery for Swarm Robotics , 2015 .

[18]  Alan F. T. Winfield,et al.  On Fault Tolerance and Scalability of Swarm Robotic Systems , 2010, DARS.

[19]  Hazem N. Nounou,et al.  Enhanced monitoring using PCA-based GLR fault detection and multiscale filtering , 2013, 2013 IEEE Symposium on Computational Intelligence in Control and Automation (CICA).

[20]  Fred Spiring,et al.  Introduction to Statistical Quality Control , 2007, Technometrics.

[21]  Jonathan Timmis,et al.  Run-time detection of faults in autonomous mobile robots based on the comparison of simulated and real robot behaviour , 2014, 2014 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[22]  Hui Keng Lau,et al.  Error detection in swarm robotics : a focus on adaptivity to dynamic environments , 2012 .

[23]  Bojan Jakimovski,et al.  Artificial Immune System Based Robot Anomaly Detection Engine for Fault Tolerant Robots , 2008, ATC.

[24]  Ying Sun,et al.  Reliable fault detection and diagnosis of photovoltaic systems based on statistical monitoring approaches , 2018 .

[25]  Foudil Cherif,et al.  Swarm robots circle formation via a virtual viscoelastic control model , 2016, 2016 8th International Conference on Modelling, Identification and Control (ICMIC).

[26]  Nabil Zerrouki,et al.  Accelerometer and Camera-Based Strategy for Improved Human Fall Detection , 2016, Journal of Medical Systems.

[27]  Raghunathan Rengaswamy,et al.  A review of process fault detection and diagnosis: Part III: Process history based methods , 2003, Comput. Chem. Eng..

[28]  Ying Sun,et al.  An Improved Wavelet‐Based Multivariable Fault Detection Scheme , 2017 .

[29]  Si-Zhao Joe Qin,et al.  Survey on data-driven industrial process monitoring and diagnosis , 2012, Annu. Rev. Control..

[30]  Fouzi Harrou,et al.  Anomaly detection/detectability for a linear model with a bounded nuisance parameter , 2014, Annu. Rev. Control..

[31]  Mauro Birattari,et al.  Automatic Synthesis of Fault Detection Modules for Mobile Robots , 2007, Second NASA/ESA Conference on Adaptive Hardware and Systems (AHS 2007).

[32]  Steven X. Ding,et al.  A Review on Basic Data-Driven Approaches for Industrial Process Monitoring , 2014, IEEE Transactions on Industrial Electronics.