Fitness Shaping on SLIP Locomotion Optimization

Claudio S. Ravasio*, Fumiya Iida, Andre Rosendo

*Corresponding author for this work

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

1 Citation (Scopus)

Abstract

Walking robots have been a thriving topic for years, and their impact in our future is undeniable. Through different walking techniques machines match their control parameters to environmental conditions, and in both simulation and real-world this control optimization always requires many iterations to find the best parameter. We benchmark four optimization methods and two fitness shaping methods to assess how fast a locomotion model, with two control parameters, can converge to stability. We find that a best overall solution does not exist, with inference-based methods such as Bayesian Optimization in some cases being as inefficient as Random Search. Fitness Shaping using additional information provided by the simulation after termination is shown to improve optimization speed in the presence of running gaits. Additionally, our results validate Bayesian Optimization as the fastest optimization method for walking gaits, and present Neural Networks as the fastest for running gaits and. In the presence of so many methods and models, this comparative study aims to clarify the potential gains for optimization methods in bipedal locomotion.

Original languageEnglish
Title of host publication2020 10th IEEE-RAS International Conference on Humanoid Robots, Humanoids 2020
EditorsTamim Asfour, Dongheui Lee, Mombaur Katja, Katsu Yamane, Kensuke Harada, Ludovic Righetti, Nikos Tsagarakis, Tomomichi Sugihara
PublisherIEEE Computer Society
Pages341-348
Number of pages8
ISBN (Electronic)9781728193724
DOIs
Publication statusPublished - 2021
Event20th IEEE-RAS International Conference on Humanoid Robots, Humanoids 2020 - Munich, Germany
Duration: 19 Jul 202121 Jul 2021

Publication series

NameIEEE-RAS International Conference on Humanoid Robots
Volume2021-July
ISSN (Print)2164-0572
ISSN (Electronic)2164-0580

Conference

Conference20th IEEE-RAS International Conference on Humanoid Robots, Humanoids 2020
Country/TerritoryGermany
CityMunich
Period19/07/202121/07/2021

Fingerprint

Dive into the research topics of 'Fitness Shaping on SLIP Locomotion Optimization'. Together they form a unique fingerprint.

Cite this