Advanced search
1 file | 3.21 MB Add to list

Effect of compliance on morphological control of dynamic locomotion with HyQ

(2021) AUTONOMOUS ROBOTS. 45(3). p.421-434
Author
Organization
Abstract
Classic control theory applied to compliant and soft robots generally involves an increment of computation that has no equivalent in biology. To tackle this, morphological computation describes a theoretical framework that takes advantage of the computational capabilities of physical bodies. However, concrete applications in robotic locomotion control are still rare. Also, the trade-off between compliance and the capacity of a physical body to facilitate its own control has not been thoroughly studied in a real locomotion task. In this paper, we address these two problems on the state-of-the-art hydraulic robot HyQ. An end-to-end neural network is trained to control HyQ's joints positions and velocities using only Ground Reaction Forces (GRF). Our simulations and experiments demonstrate better controllability using less memory and computational resources when increasing compliance. However, we show empirically that this effect cannot be attributed to the ability of the body to perform intrinsic computation. It invites to give an increased emphasis on compliance and co-design of the controller and the robot to facilitate attempts in machine learning locomotion.
Keywords
Quadruped Locomotion, Embodiment, Morphological Computation, Morphological Control, Reflex-based Locomotion

Downloads

  • (...).pdf
    • full text (Published version)
    • |
    • UGent only
    • |
    • PDF
    • |
    • 3.21 MB

Citation

Please use this url to cite or link to this publication:

MLA
Urbain, Gabriel, et al. “Effect of Compliance on Morphological Control of Dynamic Locomotion with HyQ.” AUTONOMOUS ROBOTS, vol. 45, no. 3, 2021, pp. 421–34, doi:10.1007/s10514-021-09974-9.
APA
Urbain, G., Barasuol, V., Semini, C., Dambre, J., & wyffels, F. (2021). Effect of compliance on morphological control of dynamic locomotion with HyQ. AUTONOMOUS ROBOTS, 45(3), 421–434. https://doi.org/10.1007/s10514-021-09974-9
Chicago author-date
Urbain, Gabriel, Victor Barasuol, Claudio Semini, Joni Dambre, and Francis wyffels. 2021. “Effect of Compliance on Morphological Control of Dynamic Locomotion with HyQ.” AUTONOMOUS ROBOTS 45 (3): 421–34. https://doi.org/10.1007/s10514-021-09974-9.
Chicago author-date (all authors)
Urbain, Gabriel, Victor Barasuol, Claudio Semini, Joni Dambre, and Francis wyffels. 2021. “Effect of Compliance on Morphological Control of Dynamic Locomotion with HyQ.” AUTONOMOUS ROBOTS 45 (3): 421–434. doi:10.1007/s10514-021-09974-9.
Vancouver
1.
Urbain G, Barasuol V, Semini C, Dambre J, wyffels F. Effect of compliance on morphological control of dynamic locomotion with HyQ. AUTONOMOUS ROBOTS. 2021;45(3):421–34.
IEEE
[1]
G. Urbain, V. Barasuol, C. Semini, J. Dambre, and F. wyffels, “Effect of compliance on morphological control of dynamic locomotion with HyQ,” AUTONOMOUS ROBOTS, vol. 45, no. 3, pp. 421–434, 2021.
@article{8698429,
  abstract     = {Classic control theory applied to compliant and soft robots generally involves an increment of computation that has no equivalent in biology. To tackle this, morphological computation describes a theoretical framework that takes advantage of the computational capabilities of physical bodies. However, concrete applications in robotic locomotion control are still rare. Also, the trade-off between compliance and the capacity of a physical body to facilitate its own control has not been thoroughly studied in a real locomotion task. In this paper, we address these two problems on the state-of-the-art hydraulic robot HyQ. An end-to-end neural network is trained to control HyQ's joints positions and velocities using only Ground Reaction Forces (GRF). Our simulations and experiments demonstrate better controllability using less memory and computational resources when increasing compliance. However, we show empirically that this effect cannot be attributed to the ability of the body to perform intrinsic computation. It invites to give an increased emphasis on compliance and co-design of the controller and the robot to facilitate attempts in machine learning locomotion.},
  author       = {Urbain, Gabriel and Barasuol, Victor and Semini, Claudio and Dambre, Joni and wyffels, Francis},
  issn         = {0929-5593},
  journal      = {AUTONOMOUS ROBOTS},
  keywords     = {Quadruped Locomotion,Embodiment,Morphological Computation,Morphological Control,Reflex-based Locomotion},
  language     = {eng},
  number       = {3},
  pages        = {421--434},
  title        = {Effect of compliance on morphological control of dynamic locomotion with HyQ},
  url          = {http://dx.doi.org/10.1007/s10514-021-09974-9},
  volume       = {45},
  year         = {2021},
}

Altmetric
View in Altmetric