Cross-Regional Customized Bus Route Planning Considering Staggered Commuting During the COVID-19.

Ange Wang,Hongzhi Guan,Yunqiang Xue,Liqun Peng,Pengfei Wang

doi:10.1109/access.2021.3053351

Abstract

In order to solve the problem of cross-regional customized bus (CB) route planning during the COVID-19, we develop a CB route planning method based on an improved Q-learning algorithm. First, we design a sub-regional route planning approach considering commuters’ time windows of pick-up stops and drop-off stops. Second, for the CB route with the optimal social total travel cost, we improve the traditional Q-learning algorithm, including state-action pair, reward function and update rule of Q value table. Then, a setup method of CB stops is designed and the path impedance function is constructed to obtain the optimal operating path between each of the two stops. Finally, we take three CB lines in Beijing as examples for numerical experiment, the theoretical and numerical results show that (i) compared with the current situation, although the actual operating cost of optimized route increases slightly, it is covered by the reduction of travel cost of passengers and the transmission risk of COVID-19 has also dropped significantly; (ii) the improved Q-learning algorithm can solve the problem of data transmission lag effectively and reduce the social total travel cost obviously.

Highlights

In recent years, with the rapid growth of the economy and society, the traffic congestion become more and more serious
Different from the above studies, Considering the time window restrictions of pick-up stops and drop-off stops, this paper will focus on the customized bus (CB) route planning based on improved Q-learning algorithm which has the advantages of fast convergence speed and global optimal solution
The contributions of this study include: (i) we designed a route planning method for sub-regions, which can achieve the optimization of time windows of drop-off stops; (ii) the improved Q-learning algorithm where the Q value update strategy is improved to promote the algorithm efficiency is designed to solve the CB operation route with the optimal total travel cost; (iii) based on historical data, a path impedance function is constructed to determine the optimal operation path between two stops

Summary

INTRODUCTION

With the rapid growth of the economy and society, the traffic congestion become more and more serious. How to plan a reasonable CB operation route according to the passenger’s travel time window Different from the above studies, Considering the time window restrictions of pick-up stops and drop-off stops, this paper will focus on the CB route planning based on improved Q-learning algorithm which has the advantages of fast convergence speed and global optimal solution. In order to optimize the total time costs of passengers, we design a sub-regional route planning approach considering commuters’ time windows of pick-up stops and drop-off stops. We take three cross-regional CB lines in Beijing as examples for numerical experiment, the results show that the social total travel cost of the route planned by our method is greatly reduced.

LITERATURE REVIEW

PATH IMPEDANCE

ALGORITHM IMPROVEMENT

Findings

DISCUSSIONS AND CONCLUSION