Neural networks for automated vehicle dispatching

Decision making with respect to the dispatching of vehicles and crews is still mainly in the realm of human expertise. From the authors’ own experience, it seems very difficult to explicitly model that expertise via a symbolic approach. In this paper, they thus propose an alternative neural network model as a sub-symbolic and empirical alternative for modeling the decision process of expert dispatchers. Preliminary results about the ability of the network to reproduce various decision rules are reported.