The Development of the Method to Analyze User Preference of Routing from the Probe Data in Cloud

Routing quality always dominates the top percentage which is around 20% of the complaints of in-vehicle navigation. It is because that the routing algorithm is common which is not adaptive to individual user’s preference. For example, some users prefer the quickest route while some prefer the routes quick and comfort. The reason is that the legacy in-vehicle navigation is an embedded system which has the common navigation software. As the connected vehicles rapidly spread, in the case of Toyota it is announced that all the new model vehicles in JP, CN, US will be connected, routing function switches from the embedded device to the cloud in which there are plenty of probe data uploaded from the vehicles. These probe data make it possible to analyze user preference and customized routing profile adaptive to each single user. This paper describes the method to analyze the user preference from the probe data uploaded to the cloud. The method includes data collection, the analysis model of routes scoring and user preference. As well the evaluation of the model will be introduced in the end of the paper. The analysis not only focuses on the routes chosen by the user but also compares with the ones not chosen for the same ODs (origin and destination) using multivariate analysis on the preference of each user with the routing parameters such as time, toll, distance, etc. Moreover, in the paper it will introduce the method to project the preference of each user to the entire distribution composed from all users to estimate the preference including the ODs that users have not experienced.