Adaptive Neuromechanical Control for Robust Behaviors of Bio-Inspired Walking Robots

Carlos Viescas Huerta; Xiaofeng Xiong; Peter Billeschou; Poramate Manoonpong

doi:10.1007/978-3-030-63833-7_65

Adaptive Neuromechanical Control for Robust Behaviors of Bio-Inspired Walking Robots

Carlos Viescas Huerta, Xiaofeng Xiong, Peter Billeschou, Poramate Manoonpong^*

^*Corresponding author for this work

Tecnalia Research & Innovation

Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review

Abstract

Walking animals show impressive locomotion. They can also online adapt their joint compliance to deal with unexpected perturbation for their robust locomotion. To emulate such ability for walking robots, we propose here adaptive neuromechanical control. It consists of two main components: Modular neural locomotion control and online adaptive compliance control. While the modular neural control based on a central pattern generator can generate basic locomotion, the online adaptive compliance control can perform online adaptation for joint compliance. The control approach was applied to a dung beetle-like robot called ALPHA. We tested the control performance on the real robot under different conditions, including impact force absorption when dropping the robot from a certain height, payload compensation during standing, and disturbance rejection during walking. We also compared our online adaptive compliance control with conventional non-adaptive one. Experimental results show that our control approach allows the robot to effectively deal with all these unexpected conditions by adapting its joint compliance online.

Original language	English
Title of host publication	Neural Information Processing - 27th International Conference, ICONIP 2020, Proceedings : 27th International Conference, ICONIP 2020
Editors	Haiqin Yang, Kitsuchart Pasupa, Andrew Chi-Sing Leung, James T. Kwok, Jonathan H. Chan, Irwin King
Volume	2
Publisher	Springer
Publication date	2020
Pages	775-786
ISBN (Print)	9783030638320
ISBN (Electronic)	978-3-030-63833-7
DOIs	https://doi.org/10.1007/978-3-030-63833-7_65
Publication status	Published - 2020
Event	27th International Conference on Neural Information Processing, ICONIP 2020 - Bangkok, Thailand Duration: 18. Nov 2020 → 22. Nov 2020

Conference

Conference	27th International Conference on Neural Information Processing, ICONIP 2020
Country/Territory	Thailand
City	Bangkok
Period	18/11/2020 → 22/11/2020

Series	Lecture Notes in Computer Science
Volume	12533 LNCS
ISSN	0302-9743

Keywords

Adaptive locomotion
Bio-inspired robotics
Computational intelligence
Muscle models
Robot control
Walking robots

Documents & Links

10.1007/978-3-030-63833-7_65

Cite this

Huerta, C. V., Xiong, X., Billeschou, P., & Manoonpong, P. (2020). Adaptive Neuromechanical Control for Robust Behaviors of Bio-Inspired Walking Robots. In H. Yang, K. Pasupa, A. C.-S. Leung, J. T. Kwok, J. H. Chan, & I. King (Eds.), Neural Information Processing - 27th International Conference, ICONIP 2020, Proceedings: 27th International Conference, ICONIP 2020 (Vol. 2, pp. 775-786). Springer. https://doi.org/10.1007/978-3-030-63833-7_65

Huerta, Carlos Viescas ; Xiong, Xiaofeng ; Billeschou, Peter et al. / Adaptive Neuromechanical Control for Robust Behaviors of Bio-Inspired Walking Robots. Neural Information Processing - 27th International Conference, ICONIP 2020, Proceedings: 27th International Conference, ICONIP 2020. editor / Haiqin Yang ; Kitsuchart Pasupa ; Andrew Chi-Sing Leung ; James T. Kwok ; Jonathan H. Chan ; Irwin King. Vol. 2 Springer, 2020. pp. 775-786 (Lecture Notes in Computer Science, Vol. 12533 LNCS).

@inproceedings{228a0cc1ed5c40c08dfd815da09e9f5a,

title = "Adaptive Neuromechanical Control for Robust Behaviors of Bio-Inspired Walking Robots",

abstract = "Walking animals show impressive locomotion. They can also online adapt their joint compliance to deal with unexpected perturbation for their robust locomotion. To emulate such ability for walking robots, we propose here adaptive neuromechanical control. It consists of two main components: Modular neural locomotion control and online adaptive compliance control. While the modular neural control based on a central pattern generator can generate basic locomotion, the online adaptive compliance control can perform online adaptation for joint compliance. The control approach was applied to a dung beetle-like robot called ALPHA. We tested the control performance on the real robot under different conditions, including impact force absorption when dropping the robot from a certain height, payload compensation during standing, and disturbance rejection during walking. We also compared our online adaptive compliance control with conventional non-adaptive one. Experimental results show that our control approach allows the robot to effectively deal with all these unexpected conditions by adapting its joint compliance online.",

keywords = "Adaptive locomotion, Bio-inspired robotics, Computational intelligence, Muscle models, Robot control, Walking robots",

author = "Huerta, {Carlos Viescas} and Xiaofeng Xiong and Peter Billeschou and Poramate Manoonpong",

year = "2020",

doi = "10.1007/978-3-030-63833-7_65",

language = "English",

isbn = "9783030638320",

volume = "2",

series = "Lecture Notes in Computer Science",

publisher = "Springer",

pages = "775--786",

editor = "Haiqin Yang and Kitsuchart Pasupa and Leung, {Andrew Chi-Sing} and Kwok, {James T.} and Chan, {Jonathan H.} and Irwin King",

booktitle = "Neural Information Processing - 27th International Conference, ICONIP 2020, Proceedings",

address = "Germany",

note = "27th International Conference on Neural Information Processing, ICONIP 2020 ; Conference date: 18-11-2020 Through 22-11-2020",

}

Huerta, CV, Xiong, X, Billeschou, P & Manoonpong, P 2020, Adaptive Neuromechanical Control for Robust Behaviors of Bio-Inspired Walking Robots. in H Yang, K Pasupa, AC-S Leung, JT Kwok, JH Chan & I King (eds), Neural Information Processing - 27th International Conference, ICONIP 2020, Proceedings: 27th International Conference, ICONIP 2020. vol. 2, Springer, Lecture Notes in Computer Science, vol. 12533 LNCS, pp. 775-786, 27th International Conference on Neural Information Processing, ICONIP 2020, Bangkok, Thailand, 18/11/2020. https://doi.org/10.1007/978-3-030-63833-7_65

Adaptive Neuromechanical Control for Robust Behaviors of Bio-Inspired Walking Robots. / Huerta, Carlos Viescas; Xiong, Xiaofeng; Billeschou, Peter et al.
Neural Information Processing - 27th International Conference, ICONIP 2020, Proceedings: 27th International Conference, ICONIP 2020. ed. / Haiqin Yang; Kitsuchart Pasupa; Andrew Chi-Sing Leung; James T. Kwok; Jonathan H. Chan; Irwin King. Vol. 2 Springer, 2020. p. 775-786 (Lecture Notes in Computer Science, Vol. 12533 LNCS).

Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review

TY - GEN

T1 - Adaptive Neuromechanical Control for Robust Behaviors of Bio-Inspired Walking Robots

AU - Huerta, Carlos Viescas

AU - Xiong, Xiaofeng

AU - Billeschou, Peter

AU - Manoonpong, Poramate

PY - 2020

Y1 - 2020

N2 - Walking animals show impressive locomotion. They can also online adapt their joint compliance to deal with unexpected perturbation for their robust locomotion. To emulate such ability for walking robots, we propose here adaptive neuromechanical control. It consists of two main components: Modular neural locomotion control and online adaptive compliance control. While the modular neural control based on a central pattern generator can generate basic locomotion, the online adaptive compliance control can perform online adaptation for joint compliance. The control approach was applied to a dung beetle-like robot called ALPHA. We tested the control performance on the real robot under different conditions, including impact force absorption when dropping the robot from a certain height, payload compensation during standing, and disturbance rejection during walking. We also compared our online adaptive compliance control with conventional non-adaptive one. Experimental results show that our control approach allows the robot to effectively deal with all these unexpected conditions by adapting its joint compliance online.

AB - Walking animals show impressive locomotion. They can also online adapt their joint compliance to deal with unexpected perturbation for their robust locomotion. To emulate such ability for walking robots, we propose here adaptive neuromechanical control. It consists of two main components: Modular neural locomotion control and online adaptive compliance control. While the modular neural control based on a central pattern generator can generate basic locomotion, the online adaptive compliance control can perform online adaptation for joint compliance. The control approach was applied to a dung beetle-like robot called ALPHA. We tested the control performance on the real robot under different conditions, including impact force absorption when dropping the robot from a certain height, payload compensation during standing, and disturbance rejection during walking. We also compared our online adaptive compliance control with conventional non-adaptive one. Experimental results show that our control approach allows the robot to effectively deal with all these unexpected conditions by adapting its joint compliance online.

KW - Adaptive locomotion

KW - Bio-inspired robotics

KW - Computational intelligence

KW - Muscle models

KW - Robot control

KW - Walking robots

U2 - 10.1007/978-3-030-63833-7_65

DO - 10.1007/978-3-030-63833-7_65

M3 - Article in proceedings

SN - 9783030638320

VL - 2

T3 - Lecture Notes in Computer Science

SP - 775

EP - 786

BT - Neural Information Processing - 27th International Conference, ICONIP 2020, Proceedings

A2 - Yang, Haiqin

A2 - Pasupa, Kitsuchart

A2 - Leung, Andrew Chi-Sing

A2 - Kwok, James T.

A2 - Chan, Jonathan H.

A2 - King, Irwin

PB - Springer

T2 - 27th International Conference on Neural Information Processing, ICONIP 2020

Y2 - 18 November 2020 through 22 November 2020

ER -