Evolutionary hexapod robot gait control using a new recurrent neural network learned through group-based hybrid metaheuristic algorithm

Chia Feng Juang, Yu Cheng Chang, I. Fang Chung

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

2 Scopus citations

Abstract

This paper proposes a new recurrent neural network (RNN) structure evolved to control the gait of a hexapod robot for fast forward walking. In this evolutionary robot, the gait control problem is formulated as an optimization problem with the objective of a fast forward walking speed and a small deviation in the forward walking direction. Evolutionary optimization of the RNNs through a group-based hybrid metaheuristic algorithm is proposed to find the optimal RNN controller. Preliminary simulation results with comparisons show the advantage of the proposed approach1.

Original languageEnglish
Title of host publicationGECCO 2018 Companion - Proceedings of the 2018 Genetic and Evolutionary Computation Conference Companion
PublisherAssociation for Computing Machinery, Inc
Pages111-112
Number of pages2
ISBN (Electronic)9781450357647
DOIs
StatePublished - 6 Jul 2018
Event2018 Genetic and Evolutionary Computation Conference, GECCO 2018 - Kyoto, Japan
Duration: 15 Jul 201819 Jul 2018

Publication series

NameGECCO 2018 Companion - Proceedings of the 2018 Genetic and Evolutionary Computation Conference Companion

Conference

Conference2018 Genetic and Evolutionary Computation Conference, GECCO 2018
Country/TerritoryJapan
CityKyoto
Period15/07/1819/07/18

Keywords

  • Evolutionary robots
  • Genetic algorithms
  • Hexapod robots
  • Particle swarm optimization

Fingerprint

Dive into the research topics of 'Evolutionary hexapod robot gait control using a new recurrent neural network learned through group-based hybrid metaheuristic algorithm'. Together they form a unique fingerprint.

Cite this