Literature DB >> 33500898

A Two Teraflop Swarm.

Simon Jones1,2,3, Matthew Studley2,3, Sabine Hauert1,3, Alan Frank Thomas Winfield2,3.   

Abstract

We introduce the Xpuck swarm, a research platform with an aggregate raw processing power in excess of two teraflops. The swarm uses 16 e-puck robots augmented with custom hardware that uses the substantial CPU and GPU processing power available from modern mobile system-on-chip devices. The augmented robots, called Xpucks, have at least an order of magnitude greater performance than previous swarm robotics platforms. The platform enables new experiments that require high individual robot computation and multiple robots. Uses include online evolution or learning of swarm controllers, simulation for answering what-if questions about possible actions, distributed super-computing for mobile platforms, and real-world applications of swarm robotics that requires image processing, or SLAM. The teraflop swarm could also be used to explore swarming in nature by providing platforms with similar computational power as simple insects. We demonstrate the computational capability of the swarm by implementing a fast physics-based robot simulator and using this within a distributed island model evolutionary system, all hosted on the Xpucks.
Copyright © 2018 Jones, Studley, Hauert and Winfield.

Entities:  

Keywords:  GPGPU; behavior trees; distributed evolutionary algorithm; embodied reality modelling; evolutionary robotics; robot hardware; simulation; swarm robotics

Year:  2018        PMID: 33500898      PMCID: PMC7805610          DOI: 10.3389/frobt.2018.00011

Source DB:  PubMed          Journal:  Front Robot AI        ISSN: 2296-9144


  11 in total

1.  Evolving mobile robots able to display collective behaviors.

Authors:  Gianluca Baldassarre; Stefano Nolfi; Domenico Parisi
Journal:  Artif Life       Date:  2003       Impact factor: 0.667

2.  The smallest insects evolve anucleate neurons.

Authors:  Alexey A Polilov
Journal:  Arthropod Struct Dev       Date:  2011-11-09       Impact factor: 2.010

3.  The structure of the nervous system of the nematode Caenorhabditis elegans.

Authors:  J G White; E Southgate; J N Thomson; S Brenner
Journal:  Philos Trans R Soc Lond B Biol Sci       Date:  1986-11-12       Impact factor: 6.237

4.  Behavior Trees for Evolutionary Robotics.

Authors:  Kirk Y W Scheper; Sjoerd Tijmons; Cornelis C de Visser; Guido C H E de Croon
Journal:  Artif Life       Date:  2015-11-25       Impact factor: 0.667

5.  Resilient machines through continuous self-modeling.

Authors:  Josh Bongard; Victor Zykov; Hod Lipson
Journal:  Science       Date:  2006-11-17       Impact factor: 47.728

6.  Evolutionary conditions for the emergence of communication in robots.

Authors:  Dario Floreano; Sara Mitri; Stéphane Magnenat; Laurent Keller
Journal:  Curr Biol       Date:  2007-02-22       Impact factor: 10.834

7.  Simple model of spiking neurons.

Authors:  E M Izhikevich
Journal:  IEEE Trans Neural Netw       Date:  2003

8.  The evolution of information suppression in communicating robots with conflicting interests.

Authors:  Sara Mitri; Dario Floreano; Laurent Keller
Journal:  Proc Natl Acad Sci U S A       Date:  2009-09-03       Impact factor: 11.205

9.  Engineering the evolution of self-organizing behaviors in swarm robotics: a case study.

Authors:  Vito Trianni; Stefano Nolfi
Journal:  Artif Life       Date:  2011-05-09       Impact factor: 0.667

10.  HRLSim: a high performance spiking neural network simulator for GPGPU clusters.

Authors:  Kirill Minkovich; Corey M Thibeault; Michael John O'Brien; Aleksey Nogin; Youngkwan Cho; Narayan Srinivasa
Journal:  IEEE Trans Neural Netw Learn Syst       Date:  2014-02       Impact factor: 10.451

View more

北京卡尤迪生物科技股份有限公司 © 2022-2023.