Mining Driving Preferences in Multi-cost Networks
When analyzing the trajectories of cars, it often occurs that the selected route differs from the route a navigation system would propose. Thus, to predict routes actually being selected by real drivers, trajectory mining techniques predict routes based on observations rather than calculated paths. Most approaches to this task build statistical models for the likelihood that a user travels along certain segments of a road network. However, these models neglect the motivation of a user to prefer one route over its alternatives. Another shortcoming is that these models are only applicable if there is sufficient data for the given area and driver. In this paper, we propose a novel approach which models the motivation of a driver as a preference distribution in a multi-dimensional space of traversal costs, such as distance, traffic lights, left turns, congestion probability etc.. Given this preference distribution, it is possible to compute a shortest path which better reflects actual driving decisions. We propose an efficient algorithm for deriving a distribution function of the preference weightings of a user by comparing observed routes to a set of pareto-optimal paths. In our experiments, we show the efficiency of our new algorithm compared to a naive solution of the problem and derive example weighting distributions for real world trajectories.
KeywordsRoad Segment Preference Distribution Driving Behavior Taxi Driver Skyline Query
Unable to display preview. Download preview PDF.
- 1.Simmons, R., Browning, B., Zhang, Y., Sadekar, V.: Learning to predict driver route and destination intent. In: Proc. of IEEE Intelligent Transportation Systems Conference (ITSC 2006), pp. 127–132 (2006)Google Scholar
- 2.Froehlich, J., Krumm, J.: Route prediction from trip observations. In: Society of Automotive Engineers (SAE) 2008 World Congress (2008)Google Scholar
- 4.Kriegel, H.P., Renz, M., Schubert, M.: Route skyline queries: a multi-preference path planning approach. In: Proc. of the 26th International Conference on Data Engineering (ICDE), Long Beach, CA (2010)Google Scholar
- 5.Karbassi, A., Barth, M.: Vehicle route prediction and time of arrival estimation techniques for improved transportation system management. In: Proceedings of the Intelligent Vehicles Symposium 2003, pp. 511–516. IEEE (2003)Google Scholar
- 6.Yuan, J., Zheng, Y., Zhang, C., Xie, W., Xie, X., Sun, G., Huang, Y.: T-drive: driving directions based on taxi trajectories. In: Proc. of the 18th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems (ACM GIS), San Jose, CA, pp. 99–108 (2010)Google Scholar
- 7.Yuan, J., Zheng, Y., Xie, X., Sun, G.: Driving with knowledge from the physical world. In: Proc. of the 17th ACM International Conference on Knowledge Discovery and Data Mining (SIGKDD), San Diego, CA, pp. 316–324 (2011)Google Scholar
- 8.Letchner, J., Krumm, J., Horvitz, E.: Trip router with individualized preferences (trip): Incorporating personalization into route planning. In: Proc. of 8th Conference on Innovative Applications of Artificial Intelligence, AAAI 2006. The AAAI Press (2006)Google Scholar
- 9.Mouratidis, K., Lin, Y., Yiu, M.: Preference queries in large multi-cost transportation networks. In: Proc. of the 26th International Conference on Data Engineering (ICDE), Long Beach, CA, pp. 533–544 (2010)Google Scholar
- 10.Graf, F., Kriegel, H.P., Renz, M., Schubert, M.: Mario: Multi attribute routing in open street map. In: Proc. of the 12th International Symposium on Spatial and Temporal Databases (SSTD), Minneapolis, MN (2011)Google Scholar
- 11.Zheng, Y., Zhou, X. (eds.): Computing with Spatial Trajectories. Springer (2011)Google Scholar