Iterative improvement in the automatic modular design of robot swarms

Iterative improvement is an optimization technique that finds frequent application in heuristic optimization, but, to the best of our knowledge, has not yet been adopted in the automatic design of control software for robots. In this work, we investigate iterative improvement in the context of the automatic modular design of control software for robot swarms. In particular, we investigate the optimization of two control architectures: finite-state machines and behavior trees. Finite state machines are a common choice for the control architecture in swarm robotics whereas behavior trees have received less attention so far. We compare three different optimization techniques: iterative improvement, Iterated F-race, and a hybridization of Iterated F-race and iterative improvement. For reference, we include in our study also (i) a design method in which behavior trees are optimized via genetic programming and (ii) EvoStick, a yardstick implementation of the neuro-evolutionary swarm robotics approach. The results indicate that iterative improvement is a viable optimization algorithm in the automatic modular design of control software for robot swarms.

[1]  C. D. Gelatt,et al.  Optimization by Simulated Annealing , 1983, Science.

[2]  Andrew W. Moore,et al.  Reinforcement Learning: A Survey , 1996, J. Artif. Intell. Res..

[3]  Jeffrey Horn,et al.  Handbook of evolutionary computation , 1997 .

[4]  Thomas Stützle,et al.  Iterated Local Search , 2003, Handbook of Metaheuristics.

[5]  M. O'Neill,et al.  Grammatical evolution , 2001, GECCO '09.

[6]  Lincoln Smith,et al.  Evolving controllers for a homogeneous system of physical robots: structured cooperation with minimal sensors , 2003, Philosophical Transactions of the Royal Society of London. Series A: Mathematical, Physical and Engineering Sciences.

[7]  Hod Lipson.  Evolutionary Robotics and Open-Ended Design Automation , 2005 .

[8]  Luis Mateus Rocha,et al.  Evolving an Integrated Phototaxis and Hole-avoidance Behavior for a Swarm-bot , 2006 .

[9]  Thomas Stützle,et al.  Improvement Strategies for the F-Race Algorithm: Sampling Design and Iterative Refinement , 2007, Hybrid Metaheuristics.

[10]  Stefano Nolfi,et al.  Evolutionary robotics , 2014, Evolutionary Intelligence.

[11]  Vito Trianni,et al.  Evolutionary Swarm Robotics - Evolving Self-Organising Behaviours in Groups of Autonomous Robots , 2008, Studies in Computational Intelligence.

[12]  Stefano Nolfi,et al.  Self-Organizing Sync in a Robotic Swarm: A Dynamical System View , 2009, IEEE Transactions on Evolutionary Computation.

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

[14]  Thomas Stützle,et al.  F-Race and Iterated F-Race: An Overview , 2010, Experimental Methods for the Analysis of Optimization Algorithms.

[15]  Michel Gendreau,et al.  Handbook of Metaheuristics , 2010 .

[16]  Eliseo Ferrante,et al.  Swarm robotics: a review from the swarm engineering perspective , 2013, Swarm Intelligence.

[17]  Marc Parizeau,et al.  DEAP: evolutionary algorithms made easy , 2012, J. Mach. Learn. Res..

[18]  Eliseo Ferrante,et al.  ARGoS: a modular, parallel, multi-engine simulator for multi-robot systems , 2012, Swarm Intelligence.

[19]  Mauro Birattari,et al.  Swarm robotics , 2014, Scholarpedia.

[20]  Mauro Birattari,et al.  AutoMoDe: A novel approach to the automatic design of control software for robot swarms , 2014, Swarm Intelligence.

[21]  Vito Trianni,et al.  Evolutionary Robotics: Model or Design? , 2014, Front. Robot. AI.

[22]  Mauro Birattari,et al.  AutoMoDe-Chocolate: automatic design of control software for robot swarms , 2015, Swarm Intelligence.

[23]  Matthew Studley,et al.  Evolving Behaviour Trees for Swarm Robotics , 2018, DARS.

[24]  Leslie Pérez Cáceres,et al.  The irace package: Iterated racing for automatic algorithm configuration , 2016 .

[25]  Anders Lyhne Christensen,et al.  Open Issues in Evolutionary Robotics , 2016, Evolutionary Computation.

[26]  G.,et al.  Software Infrastructure for E-puck ( and TAM ) , 2016 .

[27]  Anders Lyhne Christensen,et al.  Hybrid Control for a Real Swarm Robotics System in an Intruder Detection Task , 2016, EvoApplications.

[28]  Mauro Birattari,et al.  Automatic Design of Robot Swarms: Achievements and Challenges , 2016, Front. Robot. AI.

[29]  Petter Ögren,et al.  Behavior Trees in Robotics and AI: An Introduction , 2017, ArXiv.

[30]  Mauro Birattari,et al.  On Mimicking the Effects of the Reality Gap with Simulation-Only Experiments , 2018, ANTS Conference.

[31]  D.,et al.  Search space for AutoMoDe-Chocolate and AutoMoDe-Maple , 2018 .

[32]  K.,et al.  Reference Models for AutoMoDe , 2018 .

[33]  Mauro Birattari,et al.  Behavior Trees as a Control Architecture in the Automatic Modular Design of Robot Swarms , 2018, ANTS Conference.

[34]  Mauro Birattari,et al.  Automatic Design of Communication-Based Behaviors for Robot Swarms , 2018, ANTS Conference.

[35]  Thomas Stützle,et al.  Automatic Off-Line Design of Robot Swarms: A Manifesto , 2019, Front. Robot. AI.

[36]  Mauro Birattari,et al.  Simulation-only experiments to mimic the effects of the reality gap in the automatic design of robot swarms , 2019, Swarm Intelligence.