Optimized central pattern generator network for NAO humanoid walking control

Qing Zhang; Te Tang; Dingguo Zhang; Shichao Yang; Yunli Shao

doi:10.1109/ROBIO.2013.6739676

Optimized central pattern generator network for NAO humanoid walking control

Qing Zhang, Te Tang, Dingguo Zhang, Shichao Yang, Yunli Shao

Research output: Contribution to conference › Paper › peer-review

3 Scopus citations

Abstract

In this paper, an optimized central pattern generator (CPG) network is proposed for humanoid walking control. The CPG controller targets three joints (hip, knee and ankle) of each leg including 4 degrees of freedom (DOFs). The connections for CPG units of related joints are simplified and optimized hierarchically. The total number of CPG parameters is greatly decreased in this way. Moreover, the genetic algorithm (GA) is adopted to acquire the optimal parameters in batch and the complexity of the algorithm is decreased greatly. Finally, the proposed CPG controller is applied to the straight and circular walking on a commercial humanoid robot NAO, both in simulations and practices.

Original language	English
Pages	1486-1490
Number of pages	5
DOIs	https://doi.org/10.1109/ROBIO.2013.6739676
State	Published - 2013
Externally published	Yes
Event	2013 IEEE International Conference on Robotics and Biomimetics, ROBIO 2013 - Shenzhen, China Duration: Dec 12 2013 → Dec 14 2013

Conference

Conference	2013 IEEE International Conference on Robotics and Biomimetics, ROBIO 2013
Country/Territory	China
City	Shenzhen
Period	12/12/13 → 12/14/13

Keywords

Central pattern generator
NAO
bipedal walking
genetic algorithm
humanoid robot

Access to Document

10.1109/ROBIO.2013.6739676

Cite this

@conference{170caafa50db46c982958713a0552d98,

title = "Optimized central pattern generator network for NAO humanoid walking control",

abstract = "In this paper, an optimized central pattern generator (CPG) network is proposed for humanoid walking control. The CPG controller targets three joints (hip, knee and ankle) of each leg including 4 degrees of freedom (DOFs). The connections for CPG units of related joints are simplified and optimized hierarchically. The total number of CPG parameters is greatly decreased in this way. Moreover, the genetic algorithm (GA) is adopted to acquire the optimal parameters in batch and the complexity of the algorithm is decreased greatly. Finally, the proposed CPG controller is applied to the straight and circular walking on a commercial humanoid robot NAO, both in simulations and practices.",

keywords = "Central pattern generator, NAO, bipedal walking, genetic algorithm, humanoid robot",

author = "Qing Zhang and Te Tang and Dingguo Zhang and Shichao Yang and Yunli Shao",

year = "2013",

doi = "10.1109/ROBIO.2013.6739676",

language = "English",

pages = "1486--1490",

note = "2013 IEEE International Conference on Robotics and Biomimetics, ROBIO 2013 ; Conference date: 12-12-2013 Through 14-12-2013",

}

TY - CONF

T1 - Optimized central pattern generator network for NAO humanoid walking control

AU - Zhang, Qing

AU - Tang, Te

AU - Zhang, Dingguo

AU - Yang, Shichao

AU - Shao, Yunli

PY - 2013

Y1 - 2013

N2 - In this paper, an optimized central pattern generator (CPG) network is proposed for humanoid walking control. The CPG controller targets three joints (hip, knee and ankle) of each leg including 4 degrees of freedom (DOFs). The connections for CPG units of related joints are simplified and optimized hierarchically. The total number of CPG parameters is greatly decreased in this way. Moreover, the genetic algorithm (GA) is adopted to acquire the optimal parameters in batch and the complexity of the algorithm is decreased greatly. Finally, the proposed CPG controller is applied to the straight and circular walking on a commercial humanoid robot NAO, both in simulations and practices.

AB - In this paper, an optimized central pattern generator (CPG) network is proposed for humanoid walking control. The CPG controller targets three joints (hip, knee and ankle) of each leg including 4 degrees of freedom (DOFs). The connections for CPG units of related joints are simplified and optimized hierarchically. The total number of CPG parameters is greatly decreased in this way. Moreover, the genetic algorithm (GA) is adopted to acquire the optimal parameters in batch and the complexity of the algorithm is decreased greatly. Finally, the proposed CPG controller is applied to the straight and circular walking on a commercial humanoid robot NAO, both in simulations and practices.

KW - Central pattern generator

KW - NAO

KW - bipedal walking

KW - genetic algorithm

KW - humanoid robot

UR - https://www.scopus.com/pages/publications/84898820711

U2 - 10.1109/ROBIO.2013.6739676

DO - 10.1109/ROBIO.2013.6739676

M3 - Paper

AN - SCOPUS:84898820711

SP - 1486

EP - 1490

T2 - 2013 IEEE International Conference on Robotics and Biomimetics, ROBIO 2013

Y2 - 12 December 2013 through 14 December 2013

ER -

Optimized central pattern generator network for NAO humanoid walking control

Abstract

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this