A robot behavior-learning experiment using Particle Swarm Optimization for training a neural-based Animat

Abstract : We investigate the use of Particle Swarm Optimization (PSO), and compare with Genetic Algorithms (GA), for a particular robot behavior-learning task: the training of an animat behavior totally determined by a fully-recurrent neural network, and with which we try to fulfill a simple exploration and food foraging task. The target behavior is simple, but the learning task is challenging because of the dynamic complexity of fully-recurrent neural networks. We show that standard PSO yield very good results for this learning problem, and appears to be much more effective than simple GA.
Complete list of metadatas

Cited literature [13 references]  Display  Hide  Download

https://hal.inria.fr/inria-00332104
Contributor : Fabien Moutarde <>
Submitted on : Monday, October 20, 2008 - 2:05:14 PM
Last modification on : Monday, November 12, 2018 - 11:03:00 AM
Long-term archiving on: Monday, June 7, 2010 - 8:53:28 PM

File

MinesParisTech_PSOrobotBehavio...
Files produced by the author(s)

Identifiers

  • HAL Id : inria-00332104, version 1

Citation

Fabien Moutarde. A robot behavior-learning experiment using Particle Swarm Optimization for training a neural-based Animat. 10th International Conference on Control, Automation, Robotics and Vision (ICARCV 2008), Dec 2008, Hanoï, Vietnam. ⟨inria-00332104⟩

Share

Metrics

Record views

215

Files downloads

294