Skip to content

Learning in Growing Robots: Knowledge Transfer from Tadpole to Frog Robot

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Original languageEnglish
Title of host publicationConference on Biomimetic and Biohybrid Systems
Subtitle of host publicationLiving Machines 2019: Biomimetic and Biohybrid Systems
Publisher or commissioning bodySpringer, Cham
Pages378-382
Number of pages5
ISBN (Print)9783030247409
DOIs
DateAccepted/In press - 4 Jun 2019
DatePublished (current) - 6 Jul 2019
Event2019 Living Machines - Kasugano International Forum, Nara, Japan
Duration: 9 Jul 201912 Jul 2019
Conference number: 8
http://livingmachinesconference.eu/2019

Publication series

NameLecture Notes in Computer Science
PublisherSpringer Cham
Volume11556

Conference

Conference2019 Living Machines
CountryJapan
CityNara
Period9/07/1912/07/19
Internet address

Abstract

Inspired by natural growing processes, we investigate how morphological changes can potentially help to lead and facilitate the task of learning to control a robot. We use the model of a tadpole that grows in four discrete stages into a frog. The control task to learn is to locomote to food positions that occur at random positions. We employ reinforcement learning, which is able to find a tail-driven swimming strategy for the tadpole stage that transitions into a leg-driven strategy for the frog. Furthermore, by using knowledge transferred from one growing stage to the next one, we were able to show that growing can benefit from guiding the controller optimization through morphological changes. The results suggest that learning time can be reduced compared to the cases when learning each stage individually from scratch.

    Research areas

  • morphological computation, reinforcement learning, knowledge transfer, biomimetic robotics

    Structured keywords

  • Tactile Action Perception

Event

2019 Living Machines

Conference number8
Duration9 Jul 201912 Jul 2019
Location of eventKasugano International Forum
CityNara
CountryJapan
Web address (URL)

Event: Conference

Documents

Documents

  • Full-text PDF (accepted author manuscript)

    Rights statement: This is the accepted author manuscript (AAM). The final published version (version of record) is available online via Springer Cham at https://doi.org/10.1007/978-3-030-24741-6_42 . Please refer to any applicable terms of use of the publisher.

    Accepted author manuscript, 1 MB, PDF document

    Embargo ends: 6/07/20

    Request copy

    Licence: Other

DOI

View research connections

Related faculties, schools or groups