On-Board Evolutionary Algorithm and Off-Line Rule Discovery for Column Formation in Swarm Robotics

This paper aims at building autonomous controllers for swarm robots, specifically aimed at enforcing a given shape formation, here a column formation. The proposed approach features two main characteristics. Firstly, a state-of-the-art evolutionary setting is used to achieve the on-board optimization of the controller, avoiding any simulator-based approach. Secondly, as the cost of physical experiments might be prohibitively high for plain evolutionary approaches, a data mining approach is achieved on the top of evolution, rule discovery is used to discover the most promising regions in the controller search space. The merits of the approach are experimentally validated using a 5 robot formation, showing that the hybrid evolutionary learning process outperforms evolution alone in terms of swarm speed and shape quality.

[1]  Guy Theraulaz,et al.  Key Behavioural Factors in a Self-Organised Fish School Model , 2008 .

[2]  Iñaki Navarro,et al.  A Proposal of a Set of Metrics for Collective Movement of Robots , 2009 .

[3]  Peter Stone,et al.  Learning and Multiagent Reasoning for Autonomous Agents , 2007, IJCAI.

[4]  Ashraf Saad,et al.  Evolving an artificial neural network classifier for condition monitoring of rotating mechanical systems , 2007, Appl. Soft Comput..

[5]  A. E. Eiben,et al.  Embodied, On-line, On-board Evolution for Autonomous Robotics , 2010 .

[6]  Ian Witten,et al.  Data Mining , 2000 .

[7]  Maja J. Mataric,et al.  Reinforcement Learning in the Multi-Robot Domain , 1997, Auton. Robots.

[8]  William W. Cohen.  Fast Effective Rule Induction , 1995, ICML.

[9]  Nicolas Bredeche,et al.  Embedded Evolutionary Robotics: The (1+1)-Restart-Online Adaptation Algorithm , 2011 .

[10]  Heikki Mannila,et al.  Principles of Data Mining , 2001, Undergraduate Topics in Computer Science.

[11]  Hod Lipson,et al.  Evolutionary Robotics: Emergence of Communication , 2007, Current Biology.

[12]  Hitoshi Iba,et al.  Evolutionary Learning Strategy using Bug-Based Search , 1993, IJCAI.

[13]  Nikolaus Hansen,et al.  A restart CMA evolution strategy with increasing population size , 2005, 2005 IEEE Congress on Evolutionary Computation.

[14]  Marco Dorigo,et al.  Evolution, Self-organization and Swarm Robotics , 2008, Swarm Intelligence.

[15]  Dario Floreano,et al.  Evolved swarming without positioning information: an application in aerial communication relay , 2009, Auton. Robots.

[16]  Simon Parsons,et al.  Principles of Data Mining by David J. Hand, Heikki Mannila and Padhraic Smyth, MIT Press, 546 pp., £34.50, ISBN 0-262-08290-X , 2004, The Knowledge Engineering Review.

[17]  Hans-Paul Schwefel,et al.  Evolution strategies – A comprehensive introduction , 2002, Natural Computing.

[18]  Brent Martin,et al.  INSTANCE-B ASED LEARNING: Nearest Neighbour with Generalisation , 1995 .

[19]  Einoshin Suzuki,et al.  Autonomous Discovery of Reliable Exception Rules , 1997, KDD.

[20]  Einoshin Suzuki,et al.  Constructing Low-Cost Swarm Robots That March in Column Formation , 2010, ANTS Conference.

[21]  Mac Schwager,et al.  Distributed Coverage Control with Sensory Feedback for Networked Robots , 2006, Robotics: Science and Systems.

[22]  Wenguo Liu,et al.  Environment-driven distributed evolutionary adaptation in a population of autonomous robotic agents , 2012 .

[23]  Alan F. T. Winfield,et al.  Foraging Robots , 2009, Encyclopedia of Complexity and Systems Science.

[24]  Jordan B. Pollack,et al.  Embodied Evolution: Distributing an evolutionary algorithm in a population of robots , 2002, Robotics Auton. Syst..

[25]  Inman Harvey,et al.  Noise and the Reality Gap: The Use of Simulation in Evolutionary Robotics , 1995, ECAL.

[26]  A. E. Eiben,et al.  On-Line, On-Board Evolution of Robot Controllers , 2009, Artificial Evolution.

[27]  S. Salzberg,et al.  INSTANCE-BASED LEARNING : Nearest Neighbour with Generalisation , 1995 .