Title :
Neuro-genetic truck backer-upper controller
Author :
Schoenauer, Marc ; Ronald, Edmund
Author_Institution :
Centre de Math. Appliquees, Ecole Polytech., Palaiseau, France
Abstract :
The precise docking of a truck at a loading dock has been proposed in (Nguyen and Widrow, 1990) as a benchmark problem for non-linear control by neural-nets. The main difficulty is that backpropagation 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 feedforward 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 travelled. The influence of input data renormalisation on trajectory precision is also discussed
Keywords :
backpropagation; feedforward neural nets; genetic algorithms; nonlinear control systems; optimisation; position control; road vehicles; backpropagation; benchmark problem; control problem; feedforward 3-layer neural net; genetic algorithm; input data renormalisation; learning paradigm; loading dock; loading yard; neural-network; neuro-genetic truck backer-upper controller; nonlinear control; solution trajectories; training vectors; trajectory precision; truck; Axles; Control systems; Differential equations; Electrostatic precipitators; Feedforward neural networks; Genetic algorithms; Motion control; Neural networks; Wheels;
Conference_Titel :
Evolutionary Computation, 1994. IEEE World Congress on Computational Intelligence., Proceedings of the First IEEE Conference on
Conference_Location :
Orlando, FL
Print_ISBN :
0-7803-1899-4
DOI :
10.1109/ICEC.1994.349969
