Relay Carpool Method Based on Location Data Matching

Abstract

The reasonable carpool algorithm can alleviate the traffic congestion greatly, optimize passenger’s experience, and reduce carbon emissions. In this paper, we propose a two-stage relay carpool algorithm. In the first phase, the carpooling requirements are assigned to each vehicle based on passenger assignation algorithm of improved Hausdorff distance, so the multiple vehicles demand problem is transferred to the single vehicle requirement question. Then in the second phase, based matching degree the clustering results chooses the best matching vehicle as the candidate. The experiments show that this method has achieved the goal to make recommendations for both single vehicle carpooling and multi- vehicle carpooling.