De Nardi, R; Togelius, J; Holland, OE; Lucas, SM; (2006) Evolution of neural networks for helicopter control: Why modularity matters. In: 2006 IEEE CONGRESS ON EVOLUTIONARY COMPUTATION, VOLS 1-6. (pp. 1784 - 1791). IEEE
Full text not available from this repository.
The problem of the automatic development of controllers for vehicles for which the exact characteristics are not known is considered in the context of miniature helicopter flocking. A methodology is proposed in which neural network based controllers are evolved in a simulation using a dynamic model qualitatively similar to the physical helicopter. Several network architectures and evolutionary sequences are investigated, and two approaches are found that can evolve very competitive controllers. The division of the neural network into modules and of the task into incremental steps seems to be a precondition for success, and we analyse why this might be so.
|Title:||Evolution of neural networks for helicopter control: Why modularity matters|
|Event:||IEEE Congress on Evolutionary Computation|
|Dates:||2006-07-16 - 2006-07-21|
|UCL classification:||UCL > School of BEAMS > Faculty of Engineering Science > Computer Science|
Archive Staff Only: edit this record