This paper deals with a fuzzy-based system to solve the capacitated vehicle routing problem. The proposed method makes use of a neural network employing unsupervised learning guided by a fuzzy rule base. The algorithm implements a policy of penalties and rewards, a strategy of neuron inhibition, insertion and pruning, and also takes into account certain statistical characteristics of the input space. Fuzzy theory is considered to minimize drawbacks related to uncertainty and availability of partial information, guiding to an adaptive process of constraint relaxation. The effectiveness of the proposed method is attested by means of a series of computational simulations. As the proposed approach has no adaptation to any particular instance, it represents a good candidate to provide the initial condition for more dedicated approaches, like tabu search.