Personalized route recommendation for ride-hailing with deep inverse reinforcement learning and real-time traffic conditions

Personalized route recommendation aims to recommend routes based on users' route preference.The vast amount of GPS trajectories tracking driving behavior has made deep learning,especially inverse reinforcement learning (IRL), a popular choice for personalized route rec-ommendation. However, current IRL studies assume that the traffic condition is static andapproximate the expected state visitation frequencies to update the neural network. This studyimproves the IRL to recommend personalized routes considering real-time traffic conditions.We also improve the expected state visitation frequency calculation based on characteristics ofride-hailing and taxi trajectories to calculate the gradient of the neural network. In addition,the graph attention network is employed to capture the spatial dependencies between roadsegments. Numerical experiments using real ride-hailing trajectories in Chengdu, China validateour model. At last, a statistical test is conducted, and route preferences reflected by the samedriver's empty trajectories and occupied trajectories are found to have significant differences.