Online Gait Learning for Modular Robots with Arbitrary Shapes and Sizes

Berend Weel*, M. D'Angelo, Evert Haasdijk, A. E. Eiben

*Corresponding author for this work

Research output: Contribution to JournalArticleAcademicpeer-review

Abstract

Evolutionary robotics using real hardware is currently restricted to evolving robot controllers, but the technology for evolvable morphologies is advancing quickly. Rapid prototyping (3D printing) and automated assembly are the main enablers of robotic systems where robot offspring can be produced based on a blueprint that specifies the morphologies and the controllers of the parents. This article addresses the problem of gait learning in newborn robots whose morphology is unknown in advance. We investigate a reinforcement learning method and conduct simulation experiments using robot morphologies with different size and complexity. We establish that reinforcement learning does the job well and that it outperforms two alternative algorithms. The experiments also give insights into the online dynamics of gait learning and into the influence of the size, shape, and morphological complexity of the modular robots. These insights can potentially be used to predict the viability of modular robotic organisms before they are constructed.

Original languageEnglish
Pages (from-to)80-104
Number of pages25
JournalArtificial life
Volume23
Issue number1
DOIs
Publication statusPublished - 1 Feb 2017

Keywords

  • Artificial life
  • Embodied evolution
  • Evolutionary robotics
  • Modular robots
  • Online gait learning
  • Reinforcement learning

Fingerprint Dive into the research topics of 'Online Gait Learning for Modular Robots with Arbitrary Shapes and Sizes'. Together they form a unique fingerprint.

  • Cite this