Online fault detection of a mobile robot with a parallelized particle filter

Fault diagnosis is one of the most challenging problems, which have to be solved if one considers real-life applications of mobile robots. In this paper, we present a particle filtering-based approach combined with the negative log-likelihood test to address the fault detection task. The major disadvantage of the method is its high computational burden closely related to the number of particles used, which can be computationally too expensive to be processed online by the onboard computer of the robot. In order to address this problem, a solution, in which a part of computations are delegated to an external parallel computing environment such as a computer cluster, is presented. The proposed methods of parallelizing particle filters are aimed at improving their performance in terms of efficiency, estimation error and execution time, which are vital factors in an online setup. To depict the performance benefits of the presented methods, they are confronted with some other existing approaches in a series of experiments.

[1]  Mónica F. Bugallo,et al.  A New Class of Particle Filters for Random Dynamic Systems with Unknown Statistics , 2004, EURASIP J. Adv. Signal Process..

[2]  Jinxia Yu,et al.  An adaptive particle filter for mobile robot fault diagnosis , 2006 .

[3]  Ondřej Straka,et al.  A Survey of Sample Size Adaptation Techniques for Particle Filters , 2009 .

[4]  Neil J. Gordon,et al.  A tutorial on particle filters for online nonlinear/non-Gaussian Bayesian tracking , 2002, IEEE Trans. Signal Process..

[5]  Visakan Kadirkamanathan,et al.  Particle filtering-based fault detection in non-linear stochastic systems , 2002, Int. J. Syst. Sci..

[6]  N. Gordon,et al.  Novel approach to nonlinear/non-Gaussian Bayesian state estimation , 1993 .

[7]  Christophe Andrieu,et al.  Particle methods for change detection, system identification, and control , 2004, Proceedings of the IEEE.

[8]  Marek Kowal,et al.  Neuro-fuzzy networks and their application to fault detection of dynamical systems , 2007, Eng. Appl. Artif. Intell..

[9]  Nando de Freitas,et al.  Diagnosis by a waiter and a Mars explorer , 2004, Proceedings of the IEEE.

[10]  Ron John Patton,et al.  Robustness in Model-Based Fault Diagnosis , 1992, Concise Encyclopedia of Modelling & Simulation.

[11]  Marios M. Polycarpou,et al.  Design and analysis of a fault isolation scheme for a class of uncertain nonlinear systems , 2008, Annu. Rev. Control..

[12]  Petar M. Djuric,et al.  Resampling Algorithms for Particle Filters: A Computational Complexity Perspective , 2004, EURASIP J. Adv. Signal Process..

[13]  An-Yeu Wu,et al.  Efficient parallelized particle filter design on CUDA , 2010, 2010 IEEE Workshop On Signal Processing Systems.

[14]  Olivier Brun,et al.  Parallelisation of the particle filtering technique and application to Doppler-bearing tracking of maneuvering sources , 2003, Parallel Comput..

[15]  Sebastian Thrun,et al.  Real-time fault diagnosis [robot fault diagnosis] , 2004, IEEE Robotics & Automation Magazine.

[16]  Frank Hutter,et al.  The Gaussian Particle Filter for Diagnosis of Non-Linear Systems , 2003 .

[17]  P. Frank,et al.  Survey of robust residual generation and evaluation methods in observer-based fault detection systems , 1997 .

[18]  Sebastian Thrun,et al.  Probabilistic robotics , 2002, CACM.

[19]  Belkacem Athamena,et al.  ON-LINE FAULT DIAGNOSIS TECHNIQUE OF THE MAGNETIC LEVITATION VEHICLE SYSTEM , 2001 .

[20]  Michal Zajac.  Mobile Robot Self-diagnosis with a Bank of Adaptive Particle Filters , 2011, ICAIS.

[21]  Silvio Simani,et al.  Model-based robust fault detection and isolation of an industrial gas turbine prototype using soft computing techniques , 2012, Neurocomputing.

[22]  Michèle Basseville,et al.  Detection of abrupt changes: theory and application , 1993 .

[23]  Steven X. Ding,et al.  Frequency domain approach to optimally robust residual generation and evaluation for model-based fault diagnosis , 1994, Autom..

[24]  Marco Platzner,et al.  A Multithreaded Framework for Sequential Monte Carlo Methods on CPU/FPGA Platforms , 2009, ARC.

[25]  Simon J. Godsill,et al.  On sequential Monte Carlo sampling methods for Bayesian filtering , 2000, Stat. Comput..

[26]  P. Djurić,et al.  Particle filtering , 2003, IEEE Signal Process. Mag..

[27]  Visakan Kadirkamanathan,et al.  Fault detection and isolation in non-linear stochastic systems—A combined adaptive Monte Carlo filtering and likelihood ratio approach , 2004 .

[28]  Ondřej Straka,et al.  PARTICLE FILTER ADAPTATION BASED ON EFFICIENT SAMPLE SIZE , 2006 .

[29]  HongSangjin,et al.  Resampling algorithms for particle filters , 2004 .

[30]  Olli Yli-Harja,et al.  Novel Data Fusion Method and Exploration of Multiple Information Sources for Transcription Factor Target Gene Prediction , 2010, EURASIP J. Adv. Signal Process..

[31]  Fredrik Gustafsson,et al.  Particle Filtering: The Need for Speed , 2010, EURASIP J. Adv. Signal Process..

[32]  W. Cholewa,et al.  Fault Diagnosis: Models, Artificial Intelligence, Applications , 2004 .

[33]  Jie Chen,et al.  Robust Model-Based Fault Diagnosis for Dynamic Systems , 1998, The International Series on Asian Studies in Computer and Information Science.

[34]  Alkan Alkaya,et al.  Variance sensitive adaptive threshold-based PCA method for fault detection with experimental application. , 2011, ISA transactions.

[35]  S. Thrun,et al.  Particle Filters for Rover Fault Diagnosis , 2004 .

[36]  Zixing Cai,et al.  An adaptive particle filter for soft fault compensation of mobile robots , 2008, Science in China Series F: Information Sciences.

[37]  Petar M. Djuric,et al.  Architectures for efficient implementation of particle filters , 2004 .

[38]  Zixing Cai,et al.  A multiple particle filters method for fault diagnosis of mobile robot dead-reckoning system , 2005, 2005 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[39]  Agostino Martinelli,et al.  The odometry error of a mobile robot with a synchronous drive system , 2002, IEEE Trans. Robotics Autom..

[40]  Joaquín Míguez,et al.  Analysis of parallelizable resampling algorithms for particle filtering , 2007, Signal Process..

[41]  Ron J. Patton,et al.  Robustness in Model-Based Fault Diagnosis: The 1995 Situation , 1995 .

[42]  Visakan Kadirkamanathan,et al.  Particle filtering based likelihood ratio approach to fault diagnosis in nonlinear stochastic systems , 2001, IEEE Trans. Syst. Man Cybern. Part C.

[43]  Wolfram Burgard,et al.  Efficient Failure Detection for Mobile Robots Using Mixed-Abstraction Particle Filters , 2006, EUROS.

[44]  Andrew Ball,et al.  The development of an adaptive threshold for model-based fault detection of a nonlinear electro-hydraulic system , 2005 .

[45]  Sven Zenker.  Parallel particle filters for online identification of mechanistic mathematical models of physiology from monitoring data: performance and real-time scalability in simulation scenarios , 2010, Journal of Clinical Monitoring and Computing.

[46]  Vicenç Puig,et al.  Passive robust fault detection using fuzzy parity equations , 2002, Math. Comput. Simul..

[47]  Peter J Seiler,et al.  Wind Turbine Fault Detection Using Counter-Based Residual Thresholding , 2011 .

[48]  Donghua Zhou,et al.  FAST LEAK DETECTION AND LOCATION OF GAS PIPELINES BASED ON AN ADAPTIVE PARTICLE FILTER , 2005 .

[49]  Jean-Pierre Vila,et al.  Adaptive threshold computation for CUSUM-type procedures in change detection and isolation problems , 2008, Comput. Stat. Data Anal..

[50]  Petar M. Djuric,et al.  Resampling algorithms and architectures for distributed particle filters , 2005, IEEE Transactions on Signal Processing.