Evolutionary function approximation for gait generation on legged robots

Oscar A. Silva, Miguel A. Solis

Resultado de la investigación: Contribución a los tipos de informe/libroCapítulorevisión exhaustiva

Resumen

Reinforcement learning methods can be computationally expensive. Their cost is prone to be higher when the cardinality of the state space representation becomes larger. This curse of dimensionality plays an important role on our work, since gait generation by using more degrees of freedom at each leg, implies a bigger state space after discretization, and look-up tables become impractical. Thus, appropriate function approximators are needed for such kind of tasks on robotics. This chapter shows the advantage of using reinforcement learning, specifically within the batch framework. A neuroevolution of augmenting topologies scheme is used as function approximator, a particular case of a topology and weight evolving artificial neural network which has proved to outperform a fixed-topology network for certain tasks. A comparison between function approximators within the batch reinforcement learning approach is tested on a simulated version of an hexapod robot designed and already built at our undergraduate and graduate students group.

Idioma originalInglés
Título de la publicación alojadaStudies in Systems, Decision and Control
EditorialSpringer International Publishing
Páginas265-289
Número de páginas25
DOI
EstadoPublicada - 1 ene. 2016
Publicado de forma externa

Serie de la publicación

NombreStudies in Systems, Decision and Control
Volumen40
ISSN (versión impresa)2198-4182
ISSN (versión digital)2198-4190

Áreas temáticas de ASJC Scopus

  • Informática (miscelánea)
  • Ingeniería de control y sistemas
  • Ingeniería automovilística
  • Ciencias sociales (miscelánea)
  • Economía, econometría y finanzas (miscelánea)
  • Control y optimización
  • Teoría de la decisión (miscelánea)

Huella

Profundice en los temas de investigación de 'Evolutionary function approximation for gait generation on legged robots'. En conjunto forman una huella única.

Citar esto