Biologically-Inspired Neural Network for Walking Stabilization of Humanoid Robots

Guilherme Barros Castro, Kazuya Tamura, Atsuo Kawamura, André Hirakawa

2017

Abstract

In order to accomplish desired tasks, humanoid robots may have to deal with unpredicted disturbances, generated by objects, people and even ground imperfections. In some of these cases, foot placement is critical and cannot be changed. Furthermore, the robot has to conduct the actions planned meanwhile stabilizing its walking motion. Therefore, we propose a Biologically-inspired Neural Network (BiNN) to stabilize the walking motion of humanoid robots by ankle joint control, which minimally affects the current movements of the robot. In contrast to other neural networks, which only generate walking patterns, the BiNN is adaptive, as it compensates disturbances during the robot motion. Moreover, the BiNN has a low computational time and can be used as a module of other control methods. This approach was evaluated with Webots simulator, presenting improvements in the compensation of an external force in regard to its magnitude and duration.

Paper Citation

in Harvard Style

Castro G., Tamura K., Kawamura A. and Hirakawa A. (2017). Biologically-Inspired Neural Network for Walking Stabilization of Humanoid Robots . In Proceedings of the 9th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART, ISBN 978-989-758-220-2, pages 96-104. DOI: 10.5220/0006138700960104

in Bibtex Style

@conference{icaart17,
author={Guilherme Barros Castro and Kazuya Tamura and Atsuo Kawamura and André Hirakawa},
title={Biologically-Inspired Neural Network for Walking Stabilization of Humanoid Robots},
booktitle={Proceedings of the 9th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART,},
year={2017},
pages={96-104},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0006138700960104},
isbn={978-989-758-220-2},
}

in EndNote Style

TY - CONF
JO - Proceedings of the 9th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART,
TI - Biologically-Inspired Neural Network for Walking Stabilization of Humanoid Robots
SN - 978-989-758-220-2
AU - Castro G.
AU - Tamura K.
AU - Kawamura A.
AU - Hirakawa A.
PY - 2017
SP - 96
EP - 104
DO - 10.5220/0006138700960104