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

Research output: Chapter in Book/Report/Conference proceedingArticle in proceedingsResearchpeer-review


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 languageEnglish
Title of host publicationNeural Information Processing - 27th International Conference, ICONIP 2020, Proceedings : 27th International Conference, ICONIP 2020
EditorsHaiqin Yang, Kitsuchart Pasupa, Andrew Chi-Sing Leung, James T. Kwok, Jonathan H. Chan, Irwin King
Publication date2020
ISBN (Print)9783030638320
ISBN (Electronic)978-3-030-63833-7
Publication statusPublished - 2020
Event27th International Conference on Neural Information Processing, ICONIP 2020 - Bangkok, Thailand
Duration: 18. Nov 202022. Nov 2020


Conference27th International Conference on Neural Information Processing, ICONIP 2020
SeriesLecture Notes in Computer Science
Volume12533 LNCS


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


Dive into the research topics of 'Adaptive Neuromechanical Control for Robust Behaviors of Bio-Inspired Walking Robots'. Together they form a unique fingerprint.

Cite this