Skip to main content
Top
Published in: Artificial Life and Robotics 2/2022

25-11-2021 | Original Article

Topology and weight evolving artificial neural networks in cooperative transport by a robotic swarm

Authors: Motoaki Hiraga, Kazuhiro Ohkura

Published in: Artificial Life and Robotics | Issue 2/2022

Log in

Activate our intelligent search to find suitable subject content or patents.

search-config
loading …

Abstract

This paper applies Topology and Weight Evolving Artificial Neural Networks (TWEANNs) to design controllers for a robotic swarm. A typical method of designing controllers by an evolutionary robotics approach uses neural networks as the robot controllers with only optimizing the weight values of the neural network. However, this approach might restrict the behavior of robots or might have unsuitable structures within the controller. In this paper, we applied Mutation-Based Evolving Artificial Neural Network (MBEANN), which is a TWEANN algorithm that only employs mutations to evolve neural networks, to design the controller for a robotic swarm. For comparison with the MBEANN approach, we used NeuroEvolution of Augmenting Topologies (NEAT), which is a widely used TWEANN algorithm. The controllers are evaluated in cooperative transport performed by a robotic swarm using computer simulations. The results show that the robot controller evolved with MBEANN outperformed the NEAT controller in the cooperative transportation task.

Dont have a licence yet? Then find out more about our products and how to get one now:

Springer Professional "Wirtschaft+Technik"

Online-Abonnement

Mit Springer Professional "Wirtschaft+Technik" erhalten Sie Zugriff auf:

  • über 102.000 Bücher
  • über 537 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Maschinenbau + Werkstoffe
  • Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

Springer Professional "Technik"

Online-Abonnement

Mit Springer Professional "Technik" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 390 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Maschinenbau + Werkstoffe




 

Jetzt Wissensvorsprung sichern!

Footnotes
1
The experiments are conducted using pybox2d, a Python library for simulating 2D physics based on the Box2D physics engine. Available at https://​github.​com/​pybox2d/​pybox2d.
 
2
Box2D is tuned to work well with meter-kilogram-second (MKS) units with simulating 60 time steps per second. Hence, the object has a mass of 20 kg in the simulation.
 
Literature
1.
go back to reference Şahin E (2005) Swarm robotics: from sources of inspiration to domains of application. In: Şahin E, Spears WM (eds) Swarm robotics, Springer. Lecture notes in computer science, 3342nd edn. Springer, Berlin, pp 10–20 Şahin E (2005) Swarm robotics: from sources of inspiration to domains of application. In: Şahin E, Spears WM (eds) Swarm robotics, Springer. Lecture notes in computer science, 3342nd edn. Springer, Berlin, pp 10–20
2.
go back to reference Dorigo M, Birattari M, Brambilla M (2014) Swarm robotics. Scholarpedia 9(1):1463CrossRef Dorigo M, Birattari M, Brambilla M (2014) Swarm robotics. Scholarpedia 9(1):1463CrossRef
3.
4.
go back to reference Brambilla M, Ferrante E, Birattari M, Dorigo M (2013) Swarm robotics: a review from the swarm engineering perspective. Swarm Intell 7(1):1–41CrossRef Brambilla M, Ferrante E, Birattari M, Dorigo M (2013) Swarm robotics: a review from the swarm engineering perspective. Swarm Intell 7(1):1–41CrossRef
5.
go back to reference Francesca G, Birattari M (2016) Automatic design of robot swarms: achievements and challenges. Front Robot AI 3:29CrossRef Francesca G, Birattari M (2016) Automatic design of robot swarms: achievements and challenges. Front Robot AI 3:29CrossRef
6.
go back to reference Nolfi S, Floreano D (2000) Evolutionary robotics: the biology, intelligence, and technology of self-organizing machines. MIT Press, London Nolfi S, Floreano D (2000) Evolutionary robotics: the biology, intelligence, and technology of self-organizing machines. MIT Press, London
7.
go back to reference Trianni V (2008) Evolutionary swarm robotics: evolving self-organising behaviours in groups of autonomous robots, Studies in Computational Intelligence, vol 108. Springer, BerlinCrossRef Trianni V (2008) Evolutionary swarm robotics: evolving self-organising behaviours in groups of autonomous robots, Studies in Computational Intelligence, vol 108. Springer, BerlinCrossRef
8.
go back to reference Yao X (1999) Evolving artificial neural networks. Proc IEEE 87(9):1423–1447CrossRef Yao X (1999) Evolving artificial neural networks. Proc IEEE 87(9):1423–1447CrossRef
9.
go back to reference Floreano D, Dürr P, Mattiussi C (2008) Neuroevolution: from architectures to learning. Evol Intell 1(1):47–62CrossRef Floreano D, Dürr P, Mattiussi C (2008) Neuroevolution: from architectures to learning. Evol Intell 1(1):47–62CrossRef
10.
go back to reference Trianni V, Groß R, Labella TH, Şahin E, Dorigo M (2003) Evolving aggregation behaviors in a swarm of robots. Eur Conf Artif Life 2801:865–874CrossRef Trianni V, Groß R, Labella TH, Şahin E, Dorigo M (2003) Evolving aggregation behaviors in a swarm of robots. Eur Conf Artif Life 2801:865–874CrossRef
11.
go back to reference Soysal O, Bahçeci E, Şahin E (2007) Aggregation in swarm robotic systems: evolution and probabilistic control. Turk J Electr Eng Comput Sci 15(2):199–225 Soysal O, Bahçeci E, Şahin E (2007) Aggregation in swarm robotic systems: evolution and probabilistic control. Turk J Electr Eng Comput Sci 15(2):199–225
12.
go back to reference Baldassarre G, Nolfi S, Parisi D (2003) Evolving mobile robots able to display collective behaviors. Artif Life 9(3):255–267CrossRef Baldassarre G, Nolfi S, Parisi D (2003) Evolving mobile robots able to display collective behaviors. Artif Life 9(3):255–267CrossRef
13.
go back to reference Sperati V, Trianni V, Nolfi S (2011) Self-organised path formation in a swarm of robots. Swarm Intell 5(2):97–119CrossRef Sperati V, Trianni V, Nolfi S (2011) Self-organised path formation in a swarm of robots. Swarm Intell 5(2):97–119CrossRef
14.
go back to reference Hiraga M, Wei Y, Yasuda T, Ohkura K (2018) Evolving autonomous specialization in congested path formation task of robotic swarms. Artif Life Robot 23(4):547–554CrossRef Hiraga M, Wei Y, Yasuda T, Ohkura K (2018) Evolving autonomous specialization in congested path formation task of robotic swarms. Artif Life Robot 23(4):547–554CrossRef
15.
go back to reference Groß R, Dorigo M (2009) Towards group transport by swarms of robots. Int J Bio-Inspir Comput 1(1–2):1–13CrossRef Groß R, Dorigo M (2009) Towards group transport by swarms of robots. Int J Bio-Inspir Comput 1(1–2):1–13CrossRef
16.
go back to reference Alkilabi MHM, Narayan A, Tuci E (2017) Cooperative object transport with a swarm of e-puck robots: robustness and scalability of evolved collective strategies. Swarm Intell 11(3–4):185–209CrossRef Alkilabi MHM, Narayan A, Tuci E (2017) Cooperative object transport with a swarm of e-puck robots: robustness and scalability of evolved collective strategies. Swarm Intell 11(3–4):185–209CrossRef
17.
go back to reference Wei Y, Hiraga M, Ohkura K, Car Z (2019) Autonomous task allocation by artificial evolution for robotic swarms in complex tasks. Artif Life Robot 24(1):127–134CrossRef Wei Y, Hiraga M, Ohkura K, Car Z (2019) Autonomous task allocation by artificial evolution for robotic swarms in complex tasks. Artif Life Robot 24(1):127–134CrossRef
18.
go back to reference Duarte M, Costa V, Gomes J, Rodrigues T, Silva F, Oliveira SM, Christensen AL (2016) Evolution of collective behaviors for a real swarm of aquatic surface robots. PLOS ONE 11(3):e0151834CrossRef Duarte M, Costa V, Gomes J, Rodrigues T, Silva F, Oliveira SM, Christensen AL (2016) Evolution of collective behaviors for a real swarm of aquatic surface robots. PLOS ONE 11(3):e0151834CrossRef
19.
go back to reference Gomes J, Urbano P, Christensen AL (2013) Evolution of swarm robotics systems with novelty search. Swarm Intell 7(2–3):115–144CrossRef Gomes J, Urbano P, Christensen AL (2013) Evolution of swarm robotics systems with novelty search. Swarm Intell 7(2–3):115–144CrossRef
20.
go back to reference Ohkura K, Yasuda T, Kawamatsu Y, Matsumura Y, Ueda K (2007) MBEANN: mutation-based evolving artificial neural networks. European conference on artificial life. Springer, Berlin, pp 936–945 Ohkura K, Yasuda T, Kawamatsu Y, Matsumura Y, Ueda K (2007) MBEANN: mutation-based evolving artificial neural networks. European conference on artificial life. Springer, Berlin, pp 936–945
21.
go back to reference Stanley KO, Miikkulainen R (2002) Evolving neural networks through augmenting topologies. Evol Comput 10(2):99–127CrossRef Stanley KO, Miikkulainen R (2002) Evolving neural networks through augmenting topologies. Evol Comput 10(2):99–127CrossRef
22.
go back to reference Tuci E, Alkilabi MHM, Akanyeti O (2018) Cooperative object transport in multi-robot systems: a review of the state-of-the-art. Front Robot AI 5:59CrossRef Tuci E, Alkilabi MHM, Akanyeti O (2018) Cooperative object transport in multi-robot systems: a review of the state-of-the-art. Front Robot AI 5:59CrossRef
23.
go back to reference Bayındır L (2016) A review of swarm robotics tasks. Neurocomputing 172:292–321CrossRef Bayındır L (2016) A review of swarm robotics tasks. Neurocomputing 172:292–321CrossRef
Metadata
Title
Topology and weight evolving artificial neural networks in cooperative transport by a robotic swarm
Authors
Motoaki Hiraga
Kazuhiro Ohkura
Publication date
25-11-2021
Publisher
Springer Japan
Published in
Artificial Life and Robotics / Issue 2/2022
Print ISSN: 1433-5298
Electronic ISSN: 1614-7456
DOI
https://doi.org/10.1007/s10015-021-00716-9

Other articles of this Issue 2/2022

Artificial Life and Robotics 2/2022 Go to the issue