Neuro-Genetic Truck Backer-Upper Controller - Archive ouverte HAL Access content directly
Conference Papers Year :

Neuro-Genetic Truck Backer-Upper Controller

(1) , (1)
1

Abstract

The precise docking of a truck at a loading dock has been proposed in Nguyen & Widrow 90] as a benchmark problem for non-linear control by neural-nets. The main difficulty is that back-propagation is not a priori suitable as a learning paradigm, because no set of training vectors is available: It is non-trivial to find solution trajectories that dock the truck from anywhere in the loading yard. In this paper we show how a genetic algorithm can evolve the weights of a feed-forward 3-layer neural net that solves the control problem for a given starting state, achieving a short trajectory from starting point to goal. The fitness of a net in the population is a function of both the nearest position from the goal and the distance traveled. The influence of input data renormalisation on trajectory precision is also discussed.
Fichier principal
Vignette du fichier
ronaldSchoenauerICEC94.pdf (256.11 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-02985436 , version 1 (02-11-2020)

Identifiers

  • HAL Id : hal-02985436 , version 1

Cite

Marc Schoenauer, Edmund Ronald. Neuro-Genetic Truck Backer-Upper Controller. Proc. First IEEE International Conference on Evolutionary Computation, Jun 1994, Orlando, United States. ⟨hal-02985436⟩
31 View
89 Download

Share

Gmail Facebook Twitter LinkedIn More