Autonomous fault detection for performance bugs in component-based robotic systems

We present a novel fault detection method for application in component-based robotic systems. In contrast to existing work, our method specifically addresses faults in the software system of the robot using a data-driven methodology which exploits the inter-process communication of the system. This enables an application of the approach without expert knowledge or availability of complex software models. We specifically focus on performance bugs, which slowly degrade the performance of the system and are thereby harder to detect but also most valuable for automatic recovery. Using a data set recorded on a RoboCup@Home platform we demonstrate the performance and applicability of our method and analyze the types of faults that can be detected by the method.

[1]  Shan Lu,et al.  Understanding and detecting real-world performance bugs , 2012, PLDI.

[2]  Morgan Quigley,et al.  ROS: an open-source Robot Operating System , 2009, ICRA 2009.

[3]  Franz Wotawa,et al.  Detecting and locating faults in the control software of autonomous mobile robots , 2005, IJCAI.

[4]  Franz Wotawa,et al.  Real-Time Diagnosis and Repair of Faults of Robot Control Software , 2005, RoboCup.

[5]  Michael J. Sydor.  APM Best Practices: Realizing Application Performance Management , 2010 .

[6]  Sebastian Wrede,et al.  A Data Set for Fault Detection Research on Component-Based Robotic Systems , 2016, TAROS.

[7]  Gerald Steinbauer,et al.  An integrated model-based diagnosis and repair architecture for ROS-based robot systems , 2013, 2013 IEEE International Conference on Robotics and Automation.

[8]  Meir Kalech,et al.  Online data-driven anomaly detection in autonomous robots , 2014, Knowledge and Information Systems.

[9]  Dubravko Miljkovic,et al.  Fault detection methods: A literature survey , 2011, 2011 Proceedings of the 34th International Convention MIPRO.

[10]  Bernhard Schölkopf,et al.  Support Vector Method for Novelty Detection , 1999, NIPS.

[11]  Franz Wotawa,et al.  Towards Automated Online Diagnosis of Robot Navigation Software , 2008, SIMPAR.

[12]  VARUN CHANDOLA,et al.  Anomaly detection: A survey , 2009, CSUR.

[13]  J-C. Laprie,et al.  DEPENDABLE COMPUTING AND FAULT TOLERANCE : CONCEPTS AND TERMINOLOGY , 1995, Twenty-Fifth International Symposium on Fault-Tolerant Computing, 1995, ' Highlights from Twenty-Five Years'..

[14]  Xin Li,et al.  Reference-driven performance anomaly identification , 2009, SIGMETRICS '09.

[15]  Franz Wotawa,et al.  Using AI Techniques for Fault Localization in Component-Oriented Software Systems , 2006, MICAI.

[16]  Sebastian Wrede,et al.  A middleware for collaborative research in experimental robotics , 2011, 2011 IEEE/SICE International Symposium on System Integration (SII).

[17]  H. Zou,et al.  Regularization and variable selection via the elastic net , 2005 .

[18]  Valiallah Monajjemi,et al.  Drums: A Middleware-Aware Distributed Robot Monitoring System , 2014, 2014 Canadian Conference on Computer and Robot Vision.

[19]  Sebastian G. Elbaum,et al.  Inferring and monitoring invariants in robotic systems , 2017, Auton. Robots.

[20]  Gerald Steinbauer,et al.  A Survey about Faults of Robots Used in RoboCup , 2012, RoboCup.

[21]  Martin Heckmann,et al.  Online data-driven fault detection for robotic systems , 2011, 2011 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[22]  Ola Pettersson,et al.  Execution monitoring in robotics: A survey , 2005, Robotics Auton. Syst..

[23]  D.J. Leith,et al.  Adaptive Kalman Filtering for anomaly detection in software appliances , 2008, IEEE INFOCOM Workshops 2008.