Spatio-temporal network databases and routing algorithms: a summary of results
SSTD'07 Proceedings of the 10th international conference on Advances in spatial and temporal databases
T-drive: driving directions based on taxi trajectories
Proceedings of the 18th SIGSPATIAL International Conference on Advances in Geographic Information Systems
| Hi-index | 0.00 |
Our proposed system CrowdPath is based on the hypothesis that people know their commute area better than conventional routing services that use traditional digital roadmaps and shortest path algorithms. The knowledge and experiences of drivers reflected in volunteered commute routes may provide better routes. By leveraging such available volunteered geographic information (VGI), our goal is to investigate next-generation routing services to further reduce travel time, fuel consumption, and improve navigation. Previous related work summarizes GPS tracks into a landmark graph which is used for answering routing queries. In contrast, CrowdPath directly queries a collection of map-matched GPS tracks to recommend paths from a source location to a destination. Our evaluation using real GPS tracks illustrates the promise of CrowdPath in significantly reducing travel time compared to routes from common routing providers. In the future, CrowdPath may be extended to adapt route recommendations by start time and provide safe paths using volunteered crime and accident reports.