UPTP Vehicle Trajectory Prediction Based on User Preference Under Complexity Environment
- 188 Downloads
Accurate and reliable vehicle trajectory prediction is a vital component of any intelligent transportation system, which can improve the traffic safety and facilitate effective urban road planning. Because vehicle trajectories are uncertain and are characterized by vulnerability to environmental and user behaviors, they are exceedingly difficult to accurate via modern trajectory prediction technology. This paper proposes a vehicle trajectory prediction method that integrates environmental awareness and user preferences. First,the disutility function value is applied to the logarithmic model to calculate the user path selection probability. Secondly, the SSEM algorithm is used to process the user preferences and obtain a user type distribution. Finally, the optimal variational Gaussian mixture model is used to represent the complex environment, and the obtained user-type distribution is used to implement on-line prediction. The results of a comprehensive evaluation experiment indicate that the proposed method is more accurate than other existing prediction methods.
KeywordsEnvironment awareness Users preference Disutility function Vehicle trajectory prediction
The author would like to thank Hunan Provincial Key Laboratory of Intelligent Processing of Big Data on Transportation, Changsha University of Science and Technology, Changsha for support.The funding was given by the National Natural Science Foundation of China Grant (61572514), the Hunan Province Natural Science Foundation of China Grant (14JJ7043), the Hunan Province Transportation Department Technological Progress and Innovation Fund of China Grant (201405).
- 1.Yoon, H., & Shahabi, C. (2008). Rubst time-referenced segmentation of moving object trajectories. In Eighth IEEE International Conference on Data Miniing (pp. 1121–1126). doi: 10.1109/ICDM.2008.133.
- 3.Andrienko, G., & Andrienko, N. (2008). Spatio-temporal aggregation for visual analysis of movements. In Proceedings of IEEE VAST (Vol. 1, pp. 51–58).Google Scholar
- 4.Deb, S., Jia, C., & Fong, S. (2013). On-road direction trajectory prediction by junction-based pattern mining from GPS data. International Conference on Machine Intelligent and Research Advancement (pp. 253–257). doi: 10.1109/ICMIRA.2013.54.
- 5.Ying, J. J. C., Lee, W. C., Weng, T. C., & Tseng, V. S. (2011). Semantic trajectory mining for location prediction. ACM SIGSPATIAL GIS11 (pp. 34–43). November 1–4, 2011, Chicago, IL, USA. doi: 10.1145/2093973.2093980.
- 6.Mogelmose, A., Trivedi, M. M., & Moeslund, T. B. (2015). Trajectory analysis and prediction for improved pedestrian safety: Integrated framework and evaluations. In Intelligent Vehicles Symposium (IV) (pp. 330–335). June 28–July 1, 2015. COEX, Seoul, Korea. doi: 10.1109/IVS.2015.7225707.
- 7.Horvitz, E., & Krumm, J. (2012). Some help on the way: Opportunistic routing under uncertainty. In Proceedings of the 2012 ACM Conference on Ubiquitous Computing (pp. 371–380). September 5–8, 2012, Pittsburgh, USA. doi: 10.1145/2370216.2370273.
- 9.Assam, R., & Thomas, S. (2013). Bodygaurds: A clairvoyant location prediction using frequent neighbors and Markov model. In IEEE 10th Internet Conference on Ubiquitous Intelligent Computing and 2013 10th Internet Conference on Autonomic Trust Computing (pp. 25–32). doi: 10.1109/UIC-ATC.2013.18.
- 14.Wiest, J., Hoffken, M., Krebel, U., & Dietmayer, K. (2012). Probabilistic trajectory prediction with Gaussian mixture models. In 2012 Intelligent Vehicle Symposium Alcal de Henares, Spain (pp. 141–146). June 3–7. doi: 10.1109/IVS.2012.6232277
- 15.Fu, X. X., Jiang, Y. H., & Lu, G. (2014). Probabilistic trajectory prediction in intelligent driving. In IFAC Proceeding of the 19th World Congress the International Federation of Automatic Control, Cape Town, South Africa (Vol. 47, pp. 24–29).Google Scholar
- 19.Xia, Z.-Q., Hu, Z.-Z., & Luo, J. P. (2016). EAVTP: An environment adaptive vehicle trajectory prediction method. Journal of Chinese Computer System, 37(10), 2375–2379.Google Scholar
- 22.Ziebart, B. D., Maas, A. L., Dey, A. K., & Bagnell, J. A. (2008). Navigate like a cabbie: Probabilistic reasoning from observed context-aware behavior. In UbiComp08, September 21–24, 2008, Seoul Korea (pp. 322–331). doi: 10.1145/1409635.1409678.
- 23.Cheu, R. L., & Kreinovich, V. (2007). Use of deterministic assignment algorithms in stochastic networks analysis of equivalent link disutility function. Submitted to Transportmetriac for Review and Publication, University of Texas, Engineering Paso.Google Scholar
- 25.Chulyadyo, R., & Leray, P. (2014). A personalized recommender system from probabilistic relational model and users preference. In Procedia Computer Science, 18th International Conference on Knowledge-Based and Intelligent Information Engineering System CKES 2014 (Vol. 35, pp. 1063–1072).Google Scholar
- 26.Yap, M. D., Correia, G., & Van Arem, B. (2016). Preference of travellers for using automated vehicles as last mile public transport of multimodal train trips. Transportation Research Part A, 94, 1–16.Google Scholar
- 27.Mishra, H. K., & Chanda Sekhar, C. (2009). Variational Gaussian mixture models for speech emotion recognition. In 2009 Seventh International Conference on Advances in Pattern Recognition (pp. 183–186). IEEE. doi: 10.1109/ICAPR.2009.89.