Learning robot gait stability using neural networks as sensory feedback function for Central Pattern Generators

Sébastien Gay, José Santos-Victor, Auke Jan Ijspeert

Abstract

In this paper we present a framework to learn a model-free feedback controller for locomotion and balance control of a compliant quadruped robot walking on rough terrain. Having designed an open-loop gait encoded in a Central Pattern Generator (CPG), we use a neural network to represent sensory feedback inside the CPG dynamics. This neural network accepts sensory inputs from a gyroscope or a camera, and its weights are learned using Particle Swarm Optimization (unsupervised learning). We show with a simulated compliant quadruped robot that our controller can perform significantly better than the open-loop one on slopes and randomized height maps.
BibTeX
@inproceedings{gay2013learning,
  author = {Sébastien Gay and José Santos-Victor and Auke Jan Ijspeert},
  title = {{Learning robot gait stability using neural networks as sensory feedback function for Central Pattern Generators}},
  booktitle = {IEEE/RSJ International Conference on Intelligent Robots and Systems},
  year = {2013},
  doi = {10.1109/iros.2013.6696353},
}

Loading related content...

Figure