Mining GPS Traces to Improve Digital Maps

Digital maps are an essential component of any automobile navigation system, but existing maps are both inaccurate and incomplete. However, the availability of accurate global positioning systems suggests an approach to improving them. This project focuses on collecting time-tagged position traces from driven vehicles and using these traces to discover useful knowledge about the road network and driving habits.

Applications include revising estimates for the centerline of a road segment, inferring the number and locations of lanes on that segment, finding lane merges and splits, predicting a driver's travel time for the segment, calculating stopping distance estimates, and determining the presence and type of traffic controls at an intersection. Initial results suggest that data mining of vehicle traces can substantially improve the accuracy and completeness of digital maps, and that it can provide personalized models of driver behavior. Further work with real-time data for dynamic map updates is planned.

This research was funded by DaimlerChrysler Research and Technology.

Contributors to the Project

Professor Pat Langley

Dr. Seth Rogers

Dr. Stefan Schroedl

Vikas Taliwal

Dr. Kiri Wagstaff

Wenbing Zhang

Related Papers

Schroedl, S., Wagstaff, K., Rogers, S., Langley, P., & Wilson, C. (2004). Mining GPS traces for map refinement. Knowledge Discovery and Data Mining, 9, 59-87.

Wagstaff, K., Cardie, C., Rogers, S., & Schroedl, S. (2001). Constrained k-means clustering with background knowledge. Proceedings of the Eighteenth International Conference on Machine Learning (pp. 577-584). Williams College, MA: Morgan Kaufmann.

Rogers, S. (2000). Creating and evaluating highly accurate maps with probe vehicles. Proceedings of the IEEE Conference on Intelligent Transportation Systems. Dearborn, MI.

Pribe, C., & Rogers, S. (1999). Learning to associate driver behavior with traffic controls. Transportation Research Record, No. 1679, 95-100.

Rogers, S., Langley, P., & Wilson, C. (1999). Mining GPS data to augment road models. Proceedings of the Fifth International Conference on Knowledge Discovery and Data Mining (pp. 104-113). San Diego, CA: ACM Press.

Handley, S., Langley, P., & Rauscher, F. A. (1998). Learning to predict the duration of an automobile trip. Proceedings of the Fourth International Conference on Knowledge Discovery and Data Mining (pp. 219-223). New York: AAAI Press.

Wilson, C., Rogers, S., & Weisenburger, S. (1998). The potential of precision maps in intelligent vehicles. Proceedings of the 1998 IEEE International Conference on Intelligent Vehicles (pp. 419-422). Stuttgart, Germany