An energy efficient dynamic gait for a Nao robot

Zhenglong Sun, Nico Roos

Research output: Chapter in Book/Report/Conference proceedingChapterAcademic

2 Citations (Scopus)

Abstract

This paper presents a framework to generate energy efficient dynamic human-like walk for a Nao humanoid robot. We first extend the inverted pendulum model with the goal of finding an energy efficient and stable walking gait. In this model, we propose a leg control policy which utilizes joint stiffness control. We use policy gradient reinforcement learning to identify the optimal parameters of the new gait for a Nao humanoid robot. We successfully test the control policy in a simulator and on a real Nao robot. The test results show that the new control policy realizes a dynamic walk that is more energy efficient than the standard walk of Nao robot.
Original languageEnglish
Title of host publication2014 IEEE International Conference on Autonomous Robot Systems and Competitions, ICARSC 2014
PublisherIEEE Computer Society
Pages267-272
Number of pages6
ISBN (Print)978-1-4799-4254-1
DOIs
Publication statusPublished - 2014

Publication series

Series2014 IEEE International Conference on Autonomous Robot Systems and Competitions, ICARSC 2014

Keywords

  • Energy-efficient
  • Humanoid Robot
  • Learning Control

Cite this

Sun, Z., & Roos, N. (2014). An energy efficient dynamic gait for a Nao robot. In 2014 IEEE International Conference on Autonomous Robot Systems and Competitions, ICARSC 2014 (pp. 267-272). IEEE Computer Society. 2014 IEEE International Conference on Autonomous Robot Systems and Competitions, ICARSC 2014 https://doi.org/10.1109/ICARSC.2014.6849797
Sun, Zhenglong ; Roos, Nico. / An energy efficient dynamic gait for a Nao robot. 2014 IEEE International Conference on Autonomous Robot Systems and Competitions, ICARSC 2014. IEEE Computer Society, 2014. pp. 267-272 (2014 IEEE International Conference on Autonomous Robot Systems and Competitions, ICARSC 2014).
@inbook{27616de3cd37431aab53f563608d1683,
title = "An energy efficient dynamic gait for a Nao robot",
abstract = "This paper presents a framework to generate energy efficient dynamic human-like walk for a Nao humanoid robot. We first extend the inverted pendulum model with the goal of finding an energy efficient and stable walking gait. In this model, we propose a leg control policy which utilizes joint stiffness control. We use policy gradient reinforcement learning to identify the optimal parameters of the new gait for a Nao humanoid robot. We successfully test the control policy in a simulator and on a real Nao robot. The test results show that the new control policy realizes a dynamic walk that is more energy efficient than the standard walk of Nao robot.",
keywords = "Energy-efficient, Humanoid Robot, Learning Control",
author = "Zhenglong Sun and Nico Roos",
year = "2014",
doi = "10.1109/ICARSC.2014.6849797",
language = "English",
isbn = "978-1-4799-4254-1",
series = "2014 IEEE International Conference on Autonomous Robot Systems and Competitions, ICARSC 2014",
pages = "267--272",
booktitle = "2014 IEEE International Conference on Autonomous Robot Systems and Competitions, ICARSC 2014",
publisher = "IEEE Computer Society",
address = "United States",

}

Sun, Z & Roos, N 2014, An energy efficient dynamic gait for a Nao robot. in 2014 IEEE International Conference on Autonomous Robot Systems and Competitions, ICARSC 2014. IEEE Computer Society, 2014 IEEE International Conference on Autonomous Robot Systems and Competitions, ICARSC 2014, pp. 267-272. https://doi.org/10.1109/ICARSC.2014.6849797

An energy efficient dynamic gait for a Nao robot. / Sun, Zhenglong; Roos, Nico.

2014 IEEE International Conference on Autonomous Robot Systems and Competitions, ICARSC 2014. IEEE Computer Society, 2014. p. 267-272 (2014 IEEE International Conference on Autonomous Robot Systems and Competitions, ICARSC 2014).

Research output: Chapter in Book/Report/Conference proceedingChapterAcademic

TY - CHAP

T1 - An energy efficient dynamic gait for a Nao robot

AU - Sun, Zhenglong

AU - Roos, Nico

PY - 2014

Y1 - 2014

N2 - This paper presents a framework to generate energy efficient dynamic human-like walk for a Nao humanoid robot. We first extend the inverted pendulum model with the goal of finding an energy efficient and stable walking gait. In this model, we propose a leg control policy which utilizes joint stiffness control. We use policy gradient reinforcement learning to identify the optimal parameters of the new gait for a Nao humanoid robot. We successfully test the control policy in a simulator and on a real Nao robot. The test results show that the new control policy realizes a dynamic walk that is more energy efficient than the standard walk of Nao robot.

AB - This paper presents a framework to generate energy efficient dynamic human-like walk for a Nao humanoid robot. We first extend the inverted pendulum model with the goal of finding an energy efficient and stable walking gait. In this model, we propose a leg control policy which utilizes joint stiffness control. We use policy gradient reinforcement learning to identify the optimal parameters of the new gait for a Nao humanoid robot. We successfully test the control policy in a simulator and on a real Nao robot. The test results show that the new control policy realizes a dynamic walk that is more energy efficient than the standard walk of Nao robot.

KW - Energy-efficient

KW - Humanoid Robot

KW - Learning Control

U2 - 10.1109/ICARSC.2014.6849797

DO - 10.1109/ICARSC.2014.6849797

M3 - Chapter

SN - 978-1-4799-4254-1

T3 - 2014 IEEE International Conference on Autonomous Robot Systems and Competitions, ICARSC 2014

SP - 267

EP - 272

BT - 2014 IEEE International Conference on Autonomous Robot Systems and Competitions, ICARSC 2014

PB - IEEE Computer Society

ER -

Sun Z, Roos N. An energy efficient dynamic gait for a Nao robot. In 2014 IEEE International Conference on Autonomous Robot Systems and Competitions, ICARSC 2014. IEEE Computer Society. 2014. p. 267-272. (2014 IEEE International Conference on Autonomous Robot Systems and Competitions, ICARSC 2014). https://doi.org/10.1109/ICARSC.2014.6849797