000210589 001__ 210589
000210589 005__ 20190118052841.0
000210589 0247_ $$2doi$$a10.5075/epfl-thesis-6707
000210589 02470 $$2urn$$aurn:nbn:ch:bel-epfl-thesis6707-2
000210589 02471 $$2nebis$$a10494713
000210589 037__ $$aTHESIS
000210589 041__ $$aeng
000210589 088__ $$a6707
000210589 245__ $$aDistributed Multi-Robot Learning using Particle Swarm Optimization
000210589 260__ $$aLausanne$$bEPFL$$c2015
000210589 269__ $$a2015
000210589 300__ $$a167
000210589 336__ $$aTheses
000210589 502__ $$aProf. Colin Neil Jones (président) ; Prof. Alcherio Martinoli (directeur de thèse) ; Prof. Auke Ijspeert, Prof. Luca Gambardella, Dr Roderich Gross (rapporteurs)
000210589 520__ $$aThis thesis studies the automatic design and optimization of high-performing robust controllers for mobile robots using exclusively on-board resources. Due to the often large parameter space and noisy performance metrics, this constitutes an expensive optimization problem. Population-based learning techniques have been proven to be effective in dealing with noise and are thus promising tools to approach this problem. We focus this research on the Particle Swarm Optimization (PSO) algorithm, which, in addition to dealing with noise, allows a distributed implementation, speeding up the optimization process and adding robustness to failure of individual agents. In this thesis, we systematically analyze the different variables that affect the learning process for a multi-robot obstacle avoidance benchmark. These variables include algorithmic parameters, controller architecture, and learning and testing environments. The analysis is performed on experimental setups of increasing evaluation time and complexity: numerical benchmark functions, high-fidelity simulations, and experiments with real robots. Based on this analysis, we apply the distributed PSO framework to learn a more complex, collaborative task: flocking. This attempt to learn a collaborative task in a distributed manner on a large parameter space is, to our knowledge, the first of such kind. In addition, we address the problem of noisy performance evaluations encountered in these robotic tasks and present a %new distributed PSO algorithm for dealing with noise suitable for resource-constrained mobile robots due to its low requirements in terms of memory and limited local communication.
000210589 6531_ $$aDistributed Learning
000210589 6531_ $$aMulti-Robot Systems
000210589 6531_ $$aParticle Swarm Optimization
000210589 700__ $$0244279$$aDi Mario, Ezequiel Leonardo$$g194716
000210589 720_2 $$0241071$$aMartinoli, Alcherio$$edir.$$g105782
000210589 8564_ $$s4111327$$uhttps://infoscience.epfl.ch/record/210589/files/EPFL_TH6707.pdf$$yn/a$$zn/a
000210589 909C0 $$0252151$$pDISAL$$xU11904
000210589 909CO $$ooai:infoscience.tind.io:210589$$pDOI$$pENAC$$pthesis$$pthesis-bn2018$$qDOI2
000210589 917Z8 $$x108898
000210589 917Z8 $$x108898
000210589 917Z8 $$x108898
000210589 918__ $$aENAC$$cIIE$$dEDEE
000210589 919__ $$aDISAL
000210589 920__ $$a2015-8-21$$b2015
000210589 970__ $$a6707/THESES
000210589 973__ $$aEPFL$$sPUBLISHED
000210589 980__ $$aTHESIS