A method for co-evolving morphology and walking pattern of biped humanoid robot

Ken Endo, Fuminori Yamasaki, Takashi Maeno, Hiroaki Kitano

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

18 Citations (Scopus)

Abstract

In this paper, we present a method for co-evolving structures and controller of biped walking robots. Currently, biped walking humanoid robots are designed manually on trial-and-error basis. Although certain control theory exists, such as zero moment point (ZMP) compensation, these theories assume humanoid robot morphology is given in advance. Thus, engineers have to design control program for apriori designed morphology. If morphology and locomotion are considered simultaneously, we do not have to spare time with trial-and-error. Therefore a method useful for designing the robot is proposed. At first, the simple models of both morphology and controller are used for the dynamic simulation, which are multi-link model as morphology and two kinds of controllers. One is a layered neural network and the other is neural oscillator. The robots with the optimal energy efficiency of walking are designed with Genetic Algorithm. As a result, various combinations of morphologies and gaits are generated, and obtained relationship between length of each link and moving distance which gives the optimal energy efficiency. Moreover, the robots are encoded from limited size of chromosomes.

Original languageEnglish
Title of host publicationProceedings - IEEE International Conference on Robotics and Automation
Pages2775-2780
Number of pages6
Volume3
Publication statusPublished - 2002
Event2002 IEEE International Conference on Robotics adn Automation - Washington, DC, United States
Duration: 2002 May 112002 May 15

Other

Other2002 IEEE International Conference on Robotics adn Automation
CountryUnited States
CityWashington, DC
Period02/5/1102/5/15

Fingerprint

Robots
Controllers
Energy efficiency
Chromosomes
Control theory
Genetic algorithms
Neural networks
Engineers
Computer simulation

Keywords

  • Biped walking
  • Genetic algorithm
  • Neural network
  • Oscillator

ASJC Scopus subject areas

  • Software
  • Control and Systems Engineering

Cite this

Endo, K., Yamasaki, F., Maeno, T., & Kitano, H. (2002). A method for co-evolving morphology and walking pattern of biped humanoid robot. In Proceedings - IEEE International Conference on Robotics and Automation (Vol. 3, pp. 2775-2780)

A method for co-evolving morphology and walking pattern of biped humanoid robot. / Endo, Ken; Yamasaki, Fuminori; Maeno, Takashi; Kitano, Hiroaki.

Proceedings - IEEE International Conference on Robotics and Automation. Vol. 3 2002. p. 2775-2780.

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

Endo, K, Yamasaki, F, Maeno, T & Kitano, H 2002, A method for co-evolving morphology and walking pattern of biped humanoid robot. in Proceedings - IEEE International Conference on Robotics and Automation. vol. 3, pp. 2775-2780, 2002 IEEE International Conference on Robotics adn Automation, Washington, DC, United States, 02/5/11.
Endo K, Yamasaki F, Maeno T, Kitano H. A method for co-evolving morphology and walking pattern of biped humanoid robot. In Proceedings - IEEE International Conference on Robotics and Automation. Vol. 3. 2002. p. 2775-2780
Endo, Ken ; Yamasaki, Fuminori ; Maeno, Takashi ; Kitano, Hiroaki. / A method for co-evolving morphology and walking pattern of biped humanoid robot. Proceedings - IEEE International Conference on Robotics and Automation. Vol. 3 2002. pp. 2775-2780
@inproceedings{c8b06789cf794e1e9b4e1de0e106e7ff,
title = "A method for co-evolving morphology and walking pattern of biped humanoid robot",
abstract = "In this paper, we present a method for co-evolving structures and controller of biped walking robots. Currently, biped walking humanoid robots are designed manually on trial-and-error basis. Although certain control theory exists, such as zero moment point (ZMP) compensation, these theories assume humanoid robot morphology is given in advance. Thus, engineers have to design control program for apriori designed morphology. If morphology and locomotion are considered simultaneously, we do not have to spare time with trial-and-error. Therefore a method useful for designing the robot is proposed. At first, the simple models of both morphology and controller are used for the dynamic simulation, which are multi-link model as morphology and two kinds of controllers. One is a layered neural network and the other is neural oscillator. The robots with the optimal energy efficiency of walking are designed with Genetic Algorithm. As a result, various combinations of morphologies and gaits are generated, and obtained relationship between length of each link and moving distance which gives the optimal energy efficiency. Moreover, the robots are encoded from limited size of chromosomes.",
keywords = "Biped walking, Genetic algorithm, Neural network, Oscillator",
author = "Ken Endo and Fuminori Yamasaki and Takashi Maeno and Hiroaki Kitano",
year = "2002",
language = "English",
volume = "3",
pages = "2775--2780",
booktitle = "Proceedings - IEEE International Conference on Robotics and Automation",

}

TY - GEN

T1 - A method for co-evolving morphology and walking pattern of biped humanoid robot

AU - Endo, Ken

AU - Yamasaki, Fuminori

AU - Maeno, Takashi

AU - Kitano, Hiroaki

PY - 2002

Y1 - 2002

N2 - In this paper, we present a method for co-evolving structures and controller of biped walking robots. Currently, biped walking humanoid robots are designed manually on trial-and-error basis. Although certain control theory exists, such as zero moment point (ZMP) compensation, these theories assume humanoid robot morphology is given in advance. Thus, engineers have to design control program for apriori designed morphology. If morphology and locomotion are considered simultaneously, we do not have to spare time with trial-and-error. Therefore a method useful for designing the robot is proposed. At first, the simple models of both morphology and controller are used for the dynamic simulation, which are multi-link model as morphology and two kinds of controllers. One is a layered neural network and the other is neural oscillator. The robots with the optimal energy efficiency of walking are designed with Genetic Algorithm. As a result, various combinations of morphologies and gaits are generated, and obtained relationship between length of each link and moving distance which gives the optimal energy efficiency. Moreover, the robots are encoded from limited size of chromosomes.

AB - In this paper, we present a method for co-evolving structures and controller of biped walking robots. Currently, biped walking humanoid robots are designed manually on trial-and-error basis. Although certain control theory exists, such as zero moment point (ZMP) compensation, these theories assume humanoid robot morphology is given in advance. Thus, engineers have to design control program for apriori designed morphology. If morphology and locomotion are considered simultaneously, we do not have to spare time with trial-and-error. Therefore a method useful for designing the robot is proposed. At first, the simple models of both morphology and controller are used for the dynamic simulation, which are multi-link model as morphology and two kinds of controllers. One is a layered neural network and the other is neural oscillator. The robots with the optimal energy efficiency of walking are designed with Genetic Algorithm. As a result, various combinations of morphologies and gaits are generated, and obtained relationship between length of each link and moving distance which gives the optimal energy efficiency. Moreover, the robots are encoded from limited size of chromosomes.

KW - Biped walking

KW - Genetic algorithm

KW - Neural network

KW - Oscillator

UR - http://www.scopus.com/inward/record.url?scp=0036057580&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0036057580&partnerID=8YFLogxK

M3 - Conference contribution

VL - 3

SP - 2775

EP - 2780

BT - Proceedings - IEEE International Conference on Robotics and Automation

ER -