A Bayesian network for diagnosis of networked mobile robots

The network of communicating mobile vehicles is a subclass of Wireless Networked Control Systems (WNCS) characterized by wireless communications and mobile nodes. The integration of the wireless network into control loop, given the stochastic aspects of wireless communication and mobility of its communicating entities, can lead to problems that affect system performances. In other words, the system quality of control QoC depends on the wireless network quality of service QoS state. A diagnosis method is essential to monitor, diagnose and maintain the system in an operational state. The present paper proposes a modular multi-layer Bayesian network model for diagnosis taking into account the network failures. Results regarding the system performance are presented to illustrate the relevance of the developed Bayesian Network BN to decisions making in order to lead the system to its final goal.

[1]  Zeashan Hameed Khan,et al.  Effect of Packet Loss on the Quality of Control of a Networked Mobile Robot , 2009 .

[2]  Niels Lohse,et al.  Distributed Bayesian diagnosis for modular assembly systems—A case study , 2013 .

[3]  Marco Valtorta,et al.  Agent-encapsulated Bayesian networks and the rumor problem , 2010, AAMAS.

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

[5]  Kevin Murphy,et al.  Bayes net toolbox for Matlab , 1999 .

[6]  Sylviane Gentil,et al.  A Co-design Distributed Bayesian Approach for Decision and Scheduling of WNCS , 2011 .

[7]  Ole J. Mengshoel,et al.  Software and System Health Management for Autonomous Robotics Missions , 2012 .

[8]  Sung-Bae Cho,et al.  Landmark detection from mobile life log using a modular Bayesian network model , 2009, Expert Syst. Appl..

[9]  Christophe Aubrun,et al.  Co-design Approaches to Dependable Networked Control Systems , 2010 .

[10]  João Pedro Hespanha,et al.  A Survey of Recent Results in Networked Control Systems , 2007, Proceedings of the IEEE.

[11]  Scott Langevin,et al.  Knowledge representation, communication, and update in probability-based multiagent systems , 2010, AAMAS.

[12]  Judea Pearl,et al.  Probabilistic reasoning in intelligent systems - networks of plausible inference , 1991, Morgan Kaufmann series in representation and reasoning.

[13]  Sung-Bae Cho,et al.  Modular Bayesian Networks for Inferring Landmarks on Mobile Daily Life , 2006, Australian Conference on Artificial Intelligence.

[14]  Dawn M. Tilbury,et al.  The Emergence of Industrial Control Networks for Manufacturing Control, Diagnostics, and Safety Data , 2007, Proceedings of the IEEE.

[15]  Jean-Marc Thiriet,et al.  CO-DESIGN OF A SAFE NETWORK CONTROL QUADROTOR , 2008 .

[16]  K.W. Przytula,et al.  Reasoning Framework for Diagnosis and Prognosis , 2007, 2007 IEEE Aerospace Conference.

[17]  Kazuya Yoshida,et al.  Emergency response to the nuclear accident at the Fukushima Daiichi Nuclear Power Plants using mobile rescue robots , 2013, J. Field Robotics.

[18]  Victor R. Lesser,et al.  Justifying multiply sectioned Bayesian networks , 2000, Proceedings Fourth International Conference on MultiAgent Systems.

[19]  Y. Tipsuwan,et al.  Control methodologies in networked control systems , 2003 .

[20]  Tianhua Xu,et al.  Bayesian network based fault diagnosis and maintenance for high-speed train control systems , 2013, 2013 International Conference on Quality, Reliability, Risk, Maintenance, and Safety Engineering (QR2MSE).

[21]  Feng-Li Lian,et al.  Network design consideration for distributed control systems , 2002, IEEE Trans. Control. Syst. Technol..

[22]  D. Lee,et al.  Failure prediction and diagnosis for satellite monitoring systems using Bayesian networks , 2008, MILCOM 2008 - 2008 IEEE Military Communications Conference.