Decisions taken by automated vehicles are largely dependent on the input parameters. Here input parameters refer to the data being provided to support the decision-making capability of a moving vehicle. Exploration and analysis of data are an important task. A decision is taken only after evaluating all the available data for a particular problem. If the set of available data is limited and can be analyzed easily then the required decision can be easily made. However, we need to use machine learning techniques to mine the database if the data is quite big. These techniques can be used to cut down the number of input parameters on the basis of some constraints. The data set which results in a conclusion or goal under given constraints optimally is chosen to solve the underlying problem. For the navigation models, a proper feature extraction and selection model has to be created. In this work, two Hybrid Models have been proposed that can visualize and explore navigation data and handle the uncertainties in a better way.