research-article

An investigation of environmental influence on the benefits of adaptation mechanisms in evolutionary swarm robotics

Authors:

Andreas Steyven,

Ben PaechterAuthors Info & Claims

GECCO '17: Proceedings of the Genetic and Evolutionary Computation Conference

Pages 155 - 162

https://doi.org/10.1145/3071178.3071232

Published: 01 July 2017 Publication History

Abstract

A robotic swarm that is required to operate for long periods in a potentially unknown environment can use both evolution and individual learning methods in order to adapt. However, the role played by the environment in influencing the effectiveness of each type of learning is not well understood. In this paper, we address this question by analysing the performance of a swarm in a range of simulated, dynamic environments where a distributed evolutionary algorithm for evolving a controller is augmented with a number of different individual learning mechanisms. The learning mechanisms themselves are defined by parameters which can be either fixed or inherited. We conduct experiments in a range of dynamic environments whose characteristics are varied so as to present different opportunities for learning. Results enable us to map environmental characteristics to the most effective learning algorithm.

Supplementary Material

ZIP File (p155-steyven.zip)

Supplemental material.

Download
4.60 MB

References

[1]

Nicolas Bredeche and Jean-Marc Montanier. 2010. Environment-driven embodied evolution in a population of autonomous agents. In Parallel Problem Solving from Nature, PPSN XI, Robert Schaefer, Carlos Cotta, Joanna Kołodziej, and Günter Rudolph (Eds.), Vol. 6239. Springer Berlin Heidelberg, Krakov, Poland, 290--299.

Digital Library

[2]

Nicolas Bredeche, Jean-Marc Montanier, Berend Weel, and Evert Haasdijk. 2013. Roborobo! a Fast Robot Simulator for Swarm and Collective Robotics. CoRR abs/1304.2 (apr 2013). arXiv:1304.2888

[3]

Kai Ellefsen. 2013. Balancing the Costs and Benefits of Learning Ability. In Advances in Artificial Life, ECAL 2013, Pietro Liò, Orazio Miglino, Giuseppe Nicosia, Stefano Nolfi, and Mario Pavone (Eds.). MIT Press, Taomina, 292--299.

[4]

Jorge Gomes, Miguel Duarte, Pedro Mariano, and Anders Lyhne Christensen. 2016. Cooperative Coevolution of Control for a Real Multirobot System. Springer International Publishing, Cham, 591--601.

[5]

Evert Haasdijk. 2015. Combining Conflicting Environmental and Task Requirements in Evolutionary Robotics. In 2015 IEEE 9th International Conference on Self-Adaptive and Self-Organizing Systems. IEEE, 131--137.

Digital Library

[6]

Evert Haasdijk, Agoston Endre Eiben, and Alan Frank Thomas Winfield. 2013. Individual, Social and Evolutionary Adaptation in Collective Systems. In Handbook of Collective Robotics - Fundamentals and Challenges (2013 ed.), Serge Kernbach (Ed.). Pan Stanford, Germany, Chapter 12, 411--469.

[7]

Evert Haasdijk, P. A. Vogt, and Agoston Endre Eiben. 2008. Social learning in Population-based Adaptive Systems. In 2008 IEEE Congress on Evolutionary Computation (IEEE World Congress on Computational Intelligence). IEEE, 1386--1392.

[8]

Evert Haasdijk, Berend Weel, and Agoston Endre Eiben. 2013. Right on the MONEE. In Proceeding of the fifteenth annual conference on Genetic and evolutionary computation conference, Christian Blum (Ed.). ACM New York, NY, USA, Amsterdam, The Netherlands, 207--214.

Digital Library

[9]

Emma Hart, Andreas Steyven, and Ben Paechter. 2015. Improving Survivability in Environment-driven Distributed Evolutionary Algorithms through Explicit Relative Fitness and Fitness Proportionate Communication. In Proceedings of the 2015 on Genetic and Evolutionary Computation Conference - GECCO '15, Sara Silva (Ed.). ACM Press, New York, New York, USA, 169--176.

Digital Library

[10]

Jacqueline Heinerman, Dexter Drupsteen, and Agoston Endre Eiben. 2015. Three-fold Adaptivity in Groups of Robots: The Effect of Social Learning. In Proceedings of the 17th annual conference on Genetic and evolutionary computation. ACM Press, New York, New York, USA, 177--183.

Digital Library

[11]

Jacqueline Heinerman, Massimiliano Rango, and Agoston Endre Eiben. 2015. Evolution, Individual Learning, and Social Learning in a Swarm of Real Robots. In 2015 IEEE Symposium Series on Computational Intelligence. IEEE, 1055--1062.

[12]

Jacqueline Heinerman, Alessandro Zonta, Evert Haasdijk, and Agoston Endre Eiben. 2016. On-line Evolution of Foraging Behaviour in a Population of Real Robots. Springer, Cham, 198--212.

[13]

Giles Mayley. 1996. Landscapes, Learning Costs, and Genetic Assimilation. Evolutionary Computation 4, 3 (sep 1996), 213--234.

Digital Library

[14]

Stefano Nolfi and Dario Floreano. 1999. Learning and evolution. Autonomous robots 7, 1 (1999), 89--113.

Digital Library

[15]

Nikita Noskov, Evert Haasdijk, Berend Weel, and Agoston Endre Eiben. 2013. MONEE: Using Parental Investment to Combine Open-Ended and Task-Driven Evolution. In Applications of Evolutionary Computation, A. I. Esparcia-Alcázar (Ed.), Vol. 7835. Springer, Berlin Heidelberg, 569--578.

Digital Library

[16]

Carlos Segura, Carlos A. Coello Coello, Eduardo Segredo, and Arturo Hernandez Aguirre. 2016. A Novel Diversity-Based Replacement Strategy for Evolutionary Algorithms. IEEE Transactions on Cybernetics 46, 12 (dec 2016), 3233--3246.

[17]

Andreas Steyven, Emma Hart, and Ben Paechter. 2016. Understanding Environmental Influence in an Open-Ended Evolutionary Algorithm. In Parallel Problem Solving from Nature PPSN XIV, Julia Handl et al. (Eds.). Vol. 9921 LNCS. Springer International Publishing AG, Chapter 86, 921--931.

[18]

Andreas Steyven, Emma Hart, and Ben Paechter. 2015. The Cost of Communication: Environmental Pressure and Survivability in mEDEA. In Proceedings of the Companion Publication of the 2015 on Genetic and Evolutionary Computation Conference - GECCO Companion '15, Sara Silva (Ed.). ACM Press, New York, New York, USA, 1239--1240.

Digital Library

[19]

R.S. Sutton and A.G. Barto. 1998. Reinforcement Learning: An Introduction. IEEE Transactions on Neural Networks 9, 5 (sep 1998), 1054--1054.

Digital Library

[20]

Joanne H. Walker, Simon M. Garrett, and Myra S. Wilson. 2006. The balance between initial training and lifelong adaptation in evolving robot controllers. IEEE transactions on systems, man, and cybernetics. Part B, Cybernetics : a publication of the IEEE Systems, Man, and Cybernetics Society 36, 2 (apr 2006), 423--32.

Digital Library

Cited By

Mathias HWu ADang D(2022)Analysis of Evolved Response Thresholds for Decentralized Dynamic Task AllocationACM Transactions on Evolutionary Learning and Optimization10.1145/35308212:2(1-30)Online publication date: 16-Aug-2022
https://dl.acm.org/doi/10.1145/3530821
Khorrami BHeidarlou HFeizizadeh B(2021)Evaluation of the environmental impacts of urbanization from the viewpoint of increased skin temperatures: a case study from Istanbul, TurkeyApplied Geomatics10.1007/s12518-020-00350-3Online publication date: 6-Jan-2021
https://doi.org/10.1007/s12518-020-00350-3
Liu RJia FLuo WChandarana MNam CLewis MSycara KElkind EVeloso MAgmon NTaylor M(2019)Trust-Aware Behavior Reflection for Robot Swarm Self-HealingProceedings of the 18th International Conference on Autonomous Agents and MultiAgent Systems10.5555/3306127.3331683(122-130)Online publication date: 8-May-2019
https://dl.acm.org/doi/10.5555/3306127.3331683
Show More Cited By

Index Terms

An investigation of environmental influence on the benefits of adaptation mechanisms in evolutionary swarm robotics
1. Computing methodologies
  1. Artificial intelligence
    1. Distributed artificial intelligence
      1. Mobile agents

Recommendations

Evolutionary swarm cooperative optimization in dynamic environments

A hybrid approach called Evolutionary Swarm Cooperative Algorithm (ESCA) based on the collaboration between a particle swarm optimization algorithm and an evolutionary algorithm is presented. ESCA is designed to deal with moving optima of optimization ...
Adaptation of a multiagent evolutionary algorithm to NK landscapes
GECCO '13 Companion: Proceedings of the 15th annual conference companion on Genetic and evolutionary computation

Multiagent evolutionary algorithm (MEA) is a relatively new optimization technique, where a life cycle of a population of agents, which perform local search, is simulated. The algorithm was originally intended as a method for solving the graph coloring ...
The influence of learning on evolution: A mathematical framework

The Baldwin effect can be observed if phenotypic learning influences the evolutionary fitness of individuals, which can in turn accelerate or decelerate evolutionary change. Evidence for both learning-induced acceleration and deceleration can be found ...

Comments

Information & Contributors

Information

Published In

cover image ACM Conferences

GECCO '17: Proceedings of the Genetic and Evolutionary Computation Conference

July 2017

1427 pages

ISBN:9781450349208

DOI:10.1145/3071178

General Chair:
Peter A. N. Bosman
Centrum Wiskunde & Informatica (CWI)

Copyright © 2017 ACM.

Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]

Sponsors

SIGEVO: ACM Special Interest Group on Genetic and Evolutionary Computation

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 01 July 2017

Permissions

Request permissions for this article.

Request Permissions

Check for updates

Author Tags

Qualifiers

Research-article

Conference

GECCO '17

Sponsor:

SIGEVO

GECCO '17: Genetic and Evolutionary Computation Conference

July 15 - 19, 2017

Berlin, Germany

Acceptance Rates

GECCO '17 Paper Acceptance Rate 178 of 462 submissions, 39%;

Overall Acceptance Rate 1,669 of 4,410 submissions, 38%

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

5
Total Citations
View Citations
169
Total Downloads

Downloads (Last 12 months)6
Downloads (Last 6 weeks)1

Reflects downloads up to 09 Nov 2024

Other Metrics

View Author Metrics

Citations

Cited By

Mathias HWu ADang D(2022)Analysis of Evolved Response Thresholds for Decentralized Dynamic Task AllocationACM Transactions on Evolutionary Learning and Optimization10.1145/35308212:2(1-30)Online publication date: 16-Aug-2022
https://dl.acm.org/doi/10.1145/3530821
Khorrami BHeidarlou HFeizizadeh B(2021)Evaluation of the environmental impacts of urbanization from the viewpoint of increased skin temperatures: a case study from Istanbul, TurkeyApplied Geomatics10.1007/s12518-020-00350-3Online publication date: 6-Jan-2021
https://doi.org/10.1007/s12518-020-00350-3
Liu RJia FLuo WChandarana MNam CLewis MSycara KElkind EVeloso MAgmon NTaylor M(2019)Trust-Aware Behavior Reflection for Robot Swarm Self-HealingProceedings of the 18th International Conference on Autonomous Agents and MultiAgent Systems10.5555/3306127.3331683(122-130)Online publication date: 8-May-2019
https://dl.acm.org/doi/10.5555/3306127.3331683
Hart ESteyven APaechter BTakadama K(2018)Evolution of a functionally diverse swarm via a novel decentralised quality-diversity algorithmProceedings of the Genetic and Evolutionary Computation Conference10.1145/3205455.3205481(101-108)Online publication date: 2-Jul-2018
https://dl.acm.org/doi/10.1145/3205455.3205481
Pitt JHart E(2017)For Flux Sake: The Confluence of Socially- and Biologically-Inspired Computing for Engineering Change in Open Systems2017 IEEE 2nd International Workshops on Foundations and Applications of Self* Systems (FAS*W)10.1109/FAS-W.2017.119(45-50)Online publication date: Sep-2017
https://doi.org/10.1109/FAS-W.2017.119

View Options

Get Access

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Full Access

Get this Publication

View options

PDF

View or Download as a PDF file.

eReader

View online with eReader.

Media

Figures

Other

Tables

View Table of Contents