Spiking Neural Network implementation of LQR control on underactuated system

  • J. A. Juárez-Lora Instituto Politécnico Nacional, Centro de Investigación en Computación
  • Juan Humberto Sossa Azuela Instituto Politécnico Nacional
  • Victor H. Ponce-Ponce Instituto Politécnico Nacional, Centro de Investigación en Computación
  • Elsa Rubio-Espino Instituto Politécnico Nacional, Centro de Investigación en Computación
  • Ricardo Barrón Fernández Instituto Politécnico Nacional, Centro de Investigación en Computación
Keywords: Robotics, Neural Networks, Spiking Neural Networks, Machine Learning, Neurorobotics, Neurocomputing

Abstract

Adaptability, learning capabilities, and space-energy efficient hardware are required in robotic architectures, which must deal with changing dynamic environments. Nowadays, learning algorithms are implemented in Von Neumann Architectures, which separate storage from processing units, making them not appropriate for artificial neural networks (ANN), resulting in inefficient implementations. This writing presents a neural architecture proposal designed to implement a control loop in a mobile wheeled under-actuated inverted pendulum system, using spiking neural networks, linear quadratic regulator control technique, and a neural framework that allows us to define the neuron ensembles specification to represent specific control signals. The intention is to study how typical control theory algorithms can be translated into neural structures, aiming for neuromorphic implementation.

Published
2022-08-30
How to Cite
Juárez-Lora, J. A., Sossa Azuela, J. H., Ponce-Ponce, V. H., Rubio-Espino, E., & Barrón Fernández, R. (2022). Spiking Neural Network implementation of LQR control on underactuated system. International Journal of Combinatorial Optimization Problems and Informatics, 13(4), 36-46. Retrieved from https://ijcopi.org/ojs/article/view/320
Section
Articles