Adaptive data-driven error detection in swarm robotics with statistical classifiers

Swarm robotics is an example of a complex system with interactions among distributed autonomous robots as well with the environment. Within the swarm there is no centralised control, behaviour emerges from interactions between agents within the swarm. Agents within the swarm exhibit time varying behaviour in dynamic environments, and are subject to a variety of possible anomalies. The focus within our work is on specific faults in individual robots that can affect the global performance of the robotic swarm. We argue that classical approaches for achieving tolerance through implicit redundancy is insufficient in some cases and additional measures should be explored. Our contribution is to demonstrate that tolerance through explicit detection with statistical techniques works well and is suitable due to its lightweight computation.

[1]  Jonathan Timmis,et al.  Modelling the Tunability of Early T Cell Signalling Events , 2008, ICARIS.

[2]  Richard T. Vaughan,et al.  The Player/Stage Project: Tools for Multi-Robot and Distributed Sensor Systems , 2003 .

[3]  Amanda J. C. Sharkey,et al.  Swarm robotics , 2014, Scholarpedia.

[4]  L. Festinger.  A Theory of Social Comparison Processes , 1954 .

[5]  B. Matthews.  Comparison of the predicted and observed secondary structure of T4 phage lysozyme. , 1975, Biochimica et biophysica acta.

[6]  Nick D.L. Owens,et al.  From Biology to Algorithms , 2010 .

[7]  Alexander H. Jackson,et al.  Robot fault-tolerance using an embryonic array , 2003, NASA/DoD Conference on Evolvable Hardware, 2003. Proceedings..

[8]  Alan F. T. Winfield,et al.  Safety in numbers: fault-tolerance in robot swarms , 2006, Int. J. Model. Identif. Control..

[9]  F. E. Grubbs.  Procedures for Detecting Outlying Observations in Samples , 1969 .

[10]  Erol Sahin,et al.  Swarm Robotics: From Sources of Inspiration to Domains of Application , 2004, Swarm Robotics.

[11]  William M. K. Trochim,et al.  Research methods knowledge base , 2001 .

[12]  Jonathan Timmis,et al.  T Cell Receptor Signalling Inspired Kernel Density Estimation and Anomaly Detection , 2009, ICARIS.

[13]  Jonathan Timmis,et al.  The Diagnostic Dendritic Cell Algorithm for robotic systems , 2010, IEEE Congress on Evolutionary Computation.

[14]  Erol Şahin,et al.  A review of studies in swarm robotics , 2007 .

[15]  Algirdas Avizienis,et al.  Design of fault-tolerant computers , 1967, AFIPS '67 (Fall).

[16]  Julie Greensmith,et al.  The Application of a Dendritic Cell Algorithm to a Robotic Classifier , 2007, ICARIS.

[17]  Rodney A. Brooks,et al.  A Robust Layered Control Syste For A Mobile Robot , 2022 .

[18]  Anders Lyhne Christensen,et al.  Fault detection in autonomous robots , 2008 .

[19]  M. Braga,et al.  Exploratory Data Analysis , 2018, Encyclopedia of Social Network Analysis and Mining. 2nd Ed..

[20]  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).

[21]  Jon Timmis,et al.  Elucidation of T cell signalling models. , 2010, Journal of theoretical biology.

[22]  Victoria J. Hodge,et al.  A Survey of Outlier Detection Methodologies , 2004, Artificial Intelligence Review.

[23]  Jonathan Timmis,et al.  Parameter Optimisation in the Receptor Density Algorithm , 2011, ICARIS.

[24]  Dulal K. Bhaumik,et al.  Statistical Methods for Groundwater Monitoring , 1994 .

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

[26]  Andrew M. Tyrrell,et al.  Robot error detection using an artificial immune system , 2003, NASA/DoD Conference on Evolvable Hardware, 2003. Proceedings..