Advanced search
1 file | 2.47 MB Add to list

Combining evolutionary and adaptive control strategies for quadruped robotic locomotion

Author
Organization
Abstract
In traditional robotics, model-based controllers are usually needed in order to bring a robotic plant to the next desired state, but they present critical issues when the dimensionality of the control problem increases and disturbances from the external environment affect the system behavior, in particular during locomotion tasks. It is generally accepted that the motion control of quadruped animals is performed by neural circuits located in the spinal cord that act as a Central Pattern Generator and can generate appropriate locomotion patterns. This is thought to be the result of evolutionary processes that have optimized this network. On top of this, fine motor control is learned during the lifetime of the animal thanks to the plastic connections of the cerebellum that provide descending corrective inputs. This research aims at understanding and identifying the possible advantages of using learning during an evolution-inspired optimization for finding the best locomotion patterns in a robotic locomotion task. Accordingly, we propose a comparative study between two bio-inspired control architectures for quadruped legged robots where learning takes place either during the evolutionary search or only after that. The evolutionary process is carried out in a simulated environment, on a quadruped legged robot. To verify the possibility of overcoming the reality gap, the performance of both systems has been analyzed by changing the robot dynamics and its interaction with the external environment. Results show better performance metrics for the robotic agent whose locomotion method has been discovered by applying the adaptive module during the evolutionary exploration for the locomotion trajectories. Even when the motion dynamics and the interaction with the environment is altered, the locomotion patterns found on the learning robotic system are more stable, both in the joint and in the task space.
Keywords
Artificial Intelligence, Biomedical Engineering, evolutionary algorithm, bio-inspired controller, cerebellum-inspired algorithm, robotic locomotion, neurorobotics, central pattern generator, INTERNAL-MODELS, SPINAL-CORD

Downloads

  • fnbot-13-00071.pdf
    • full text (Published version)
    • |
    • open access
    • |
    • PDF
    • |
    • 2.47 MB

Citation

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

MLA
Massi, Elisa, et al. “Combining Evolutionary and Adaptive Control Strategies for Quadruped Robotic Locomotion.” FRONTIERS IN NEUROROBOTICS, vol. 13, 2019.
APA
Massi, E., Vannucci, L., Albanese, U., Capolei, M. C., Vandesompele, A., Urbain, G., … Falotico, E. (2019). Combining evolutionary and adaptive control strategies for quadruped robotic locomotion. FRONTIERS IN NEUROROBOTICS, 13.
Chicago author-date
Massi, Elisa, Lorenzo Vannucci, Ugo Albanese, Marie Claire Capolei, Alexander Vandesompele, Gabriel Urbain, Angelo Maria Sabatini, et al. 2019. “Combining Evolutionary and Adaptive Control Strategies for Quadruped Robotic Locomotion.” FRONTIERS IN NEUROROBOTICS 13.
Chicago author-date (all authors)
Massi, Elisa, Lorenzo Vannucci, Ugo Albanese, Marie Claire Capolei, Alexander Vandesompele, Gabriel Urbain, Angelo Maria Sabatini, Joni Dambre, Cecilia Laschi, Silvia Tolu, and Egidio Falotico. 2019. “Combining Evolutionary and Adaptive Control Strategies for Quadruped Robotic Locomotion.” FRONTIERS IN NEUROROBOTICS 13.
Vancouver
1.
Massi E, Vannucci L, Albanese U, Capolei MC, Vandesompele A, Urbain G, et al. Combining evolutionary and adaptive control strategies for quadruped robotic locomotion. FRONTIERS IN NEUROROBOTICS. 2019;13.
IEEE
[1]
E. Massi et al., “Combining evolutionary and adaptive control strategies for quadruped robotic locomotion,” FRONTIERS IN NEUROROBOTICS, vol. 13, 2019.
@article{8627973,
  abstract     = {In traditional robotics, model-based controllers are usually needed in order to bring a robotic plant to the next desired state, but they present critical issues when the dimensionality of the control problem increases and disturbances from the external environment affect the system behavior, in particular during locomotion tasks. It is generally accepted that the motion control of quadruped animals is performed by neural circuits located in the spinal cord that act as a Central Pattern Generator and can generate appropriate locomotion patterns. This is thought to be the result of evolutionary processes that have optimized this network. On top of this, fine motor control is learned during the lifetime of the animal thanks to the plastic connections of the cerebellum that provide descending corrective inputs. This research aims at understanding and identifying the possible advantages of using learning during an evolution-inspired optimization for finding the best locomotion patterns in a robotic locomotion task. Accordingly, we propose a comparative study between two bio-inspired control architectures for quadruped legged robots where learning takes place either during the evolutionary search or only after that. The evolutionary process is carried out in a simulated environment, on a quadruped legged robot. To verify the possibility of overcoming the reality gap, the performance of both systems has been analyzed by changing the robot dynamics and its interaction with the external environment. Results show better performance metrics for the robotic agent whose locomotion method has been discovered by applying the adaptive module during the evolutionary exploration for the locomotion trajectories. Even when the motion dynamics and the interaction with the environment is altered, the locomotion patterns found on the learning robotic system are more stable, both in the joint and in the task space.},
  articleno    = {71},
  author       = {Massi, Elisa and Vannucci, Lorenzo and Albanese, Ugo and Capolei, Marie Claire and Vandesompele, Alexander and Urbain, Gabriel and Sabatini, Angelo Maria and Dambre, Joni and Laschi, Cecilia and Tolu, Silvia and Falotico, Egidio},
  issn         = {1662-5218},
  journal      = {FRONTIERS IN NEUROROBOTICS},
  keywords     = {Artificial Intelligence,Biomedical Engineering,evolutionary algorithm,bio-inspired controller,cerebellum-inspired algorithm,robotic locomotion,neurorobotics,central pattern generator,INTERNAL-MODELS,SPINAL-CORD},
  language     = {eng},
  pages        = {19},
  title        = {Combining evolutionary and adaptive control strategies for quadruped robotic locomotion},
  url          = {http://dx.doi.org/10.3389/fnbot.2019.00071},
  volume       = {13},
  year         = {2019},
}

Altmetric
View in Altmetric
Web of Science
Times cited: