Clustering-Based Decision Tree for Vehicle Routing Spatio-Temporal Selection

Abstract

The algorithm of the clustering-based decision tree, which is a methodology of multimodal fusion, has made many achievements in many fields. However, it is not common in the field of transportation, especially in the application of automobile navigation. Meanwhile, the concept of Spatio-temporal data is now widely used. Therefore, we proposed a vehicle routing Spatio-temporal selection system based on a clustering-based decision tree. By screening and clustering Spatio-temporal data, which is a collection of individual point data based on historical driving data, we can identify the routes and many other features. Through the decision tree modeling of the state information of Spatio-temporal data, which includes the features of the historical data and route selection, we can obtain an optimal result, that is, the route selection made by the system. Moreover, all the above calculations and operations are done on the edge, which is different from the vast majority of current cloud computing vehicle navigation. We have also experimented with our system using real vehicle data. The experiments show that it can output path decision results for a given situation, which takes little time and is the same as the approximated case of networked navigation. The experiments yielded satisfactory results. Our system could save a lot of cloud computing power, which might change the current navigation systems.