From Animals to Animats 11

Volume 6226 of the series Lecture Notes in Computer Science pp 402-412

Distributed Online Learning of Central Pattern Generators in Modular Robots

  • David Johan ChristensenAffiliated withThe Maersk Mc-Kinney Moller Institute, University of Southern Denmark
  • , Alexander SpröwitzAffiliated withBiorobotics Laboratory, Ecole Polytechnique Fédérale de Lausanne
  • , Auke Jan IjspeertAffiliated withBiorobotics Laboratory, Ecole Polytechnique Fédérale de Lausanne


In this paper we study distributed online learning of locomotion gaits for modular robots. The learning is based on a stochastic approximation method, SPSA, which optimizes the parameters of coupled oscillators used to generate periodic actuation patterns. The strategy is implemented in a distributed fashion, based on a globally shared reward signal, but otherwise utilizing local communication only. In a physics-based simulation of modular Roombots robots we experiment with online learning of gaits and study the effects of: module failures, different robot morphologies, and rough terrains. The experiments demonstrate fast online learning, typically 5-30 min. for convergence to high performing gaits (≈ 30 cm/sec), despite high numbers of open parameters (45-54). We conclude that the proposed approach is efficient, effective and a promising candidate for online learning on many other robotic platforms.