Top

Artificial Life and Robotics

Published in:

26-11-2021 | Original Article

A hierarchical training method of generating collective foraging behavior for a robotic swarm

Authors: Boyin Jin, Yupeng Liang, Ziyao Han, Motoaki Hiraga, Kazuhiro Ohkura

Published in: Artificial Life and Robotics | Issue 1/2022

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

search-config

AI-assisted search

Off

Abstract

Swarm robotics is a field in which multiple robots coordinate their collective behavior autonomously to accomplish a given task without any form of centralized control. Training a robotic swarm to complete a multi-objective task under sparse rewards is a challenging task in reinforcement learning (RL). This research has applied a hierarchical training method for the RL training process to address the multi-objective task with sparse rewards. We conduct experiments where a robotic swarm has to accomplish a complex collective foraging problem using computer simulations. The results show that the proposed approach leads to perform more effectively than a conventional RL approach.

previous article Using sim-to-real transfer learning to close gaps between simulation and real environments through reinforcement learning

next article Optimization of urban logistics terminal distribution based on cellular automaton model

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!

inform now

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!

inform now

Şahin E (2005) Swarm robotics: from sources of inspiration to domains of application. Swarm Robot Springer Lect Notes Comput Sci 3342:10–20CrossRef

Kennedy J (2006) Swarm intelligence. Handbook of nature-inspired and innovative computing. Springer, Berlin, pp 187–219CrossRef

Bayındır L (2016) A review of swarm robotics tasks. Neurocomputing 172:292–321CrossRef

Sutton RS, Barto AG (2018) Reinforcement learning: an introduction. MIT Press, LondonMATH

Mnih V, Kavukcuoglu K, Silver D, Rusu AA, Veness J, Bellemare MG, Graves A, Riedmiller M, Fidjeland AK, Ostrovski G et al (2015) Human-level control through deep reinforcement learning. Nature 518 7540:529–533CrossRef

Kober J, Bagnell JA, Peters J (2013) Reinforcement learning in robotics: a survey. Int J Robot Res 32(11):1238–1274CrossRef

Riedmiller M, Hafner R, Lampe T, Neunert M, Degrave J, Wiele T, Mnih V, Heess N, Springenberg JT (2018) Learning by playing solving sparse reward tasks from scratch. In: International Conference on Machine Learning, PMLR, pp 4344–4353

Laud AD (2004) Theory and application of reward shaping in reinforcement learning. University of Illinois at Urbana-Champaign, Champaign

Hüttenrauch M, Adrian S, Neumann G et al (2019) Deep reinforcement learning for swarm systems. J Mach Learn Res 20(54):1–31MathSciNetMATH

10.

Schulman J, Wolski F, Dhariwal P, Radford A, Klimov O (2017) Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347

11.

Konda VR, Tsitsiklis JN (2000) Actor-critic algorithms. Advances in neural information processing systems. Springer, Berlin, pp 1008–1014

Title: A hierarchical training method of generating collective foraging behavior for a robotic swarm
Authors: Boyin Jin
Yupeng Liang
Ziyao Han
Motoaki Hiraga
Kazuhiro Ohkura
Publication date: 26-11-2021
Publisher: Springer Japan
Published in: Artificial Life and Robotics / Issue 1/2022
Print ISSN: 1433-5298
Electronic ISSN: 1614-7456
DOI: https://doi.org/10.1007/s10015-021-00714-x

Springer Professional

Abstract

Please log in to get access to your license.

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

Springer Professional "Wirtschaft+Technik"

Springer Professional "Technik"

Other articles of this Issue 1/2022

Assessing the effects of Kampo medicine on human skin texture and microcirculation

Correction to: Proposal and evaluation for color constancy CAPTCHA

Comparison of noncontact camera-based methods for measuring pulse-rate of awake infants

A new method to estimate the pose of an arbitrary 3D object without prerequisite knowledge: projection-based 3D perception

Radiodermatitis grade estimation by RGB color imaging

Using sim-to-real transfer learning to close gaps between simulation and real environments through reinforcement learning