计算机科学 ›› 2018, Vol. 45 ›› Issue (3): 235-240.doi: 10.11896/j.issn.1002-137X.2018.03.037

• 人工智能 • 上一篇    下一篇

不确定性车辆路口的轨迹预测

毛莺池,陈杨   

  1. 河海大学计算机与信息学院 南京211100,河海大学计算机与信息学院 南京211100
  • 出版日期:2018-03-15 发布日期:2018-11-13
  • 基金资助:
    本文受国家重点研发计划项目(2016YFC0400910),重大科技专项(2017ZX07104001),中央高校基本科研业务费专项资金(2015B22214,7B16814,7B20914)资助

Uncertain Vehicle Intersection Trajectory Prediction

MAO Ying-chi and CHEN Yang   

  • Online:2018-03-15 Published:2018-11-13

摘要: 在城市道路中,实时、准确、可靠地对移动车辆进行轨迹预测具有极高的应用价值,不仅可以提供准确的基于位置的服务,而且可以帮助过往车辆预知前方的交通状况。目前,移动车辆的轨迹预测方法主要基于历史轨迹的欧氏空间进行,并未考虑在受限路网中采用不确定性历史数据的车辆轨迹预测。针对这一问题,提出一种补全路径的基于马尔科夫链的轨迹预测方法,其优势在于:重新定义了补全路径算法,弥补了不确定性历史数据的不完整性,利用马尔科夫链低时间复杂度、高预测准确度的优势实现预测,避免了因频繁模式挖掘带来的查询时间过长而影响预测效率以及存在多余噪声影响轨迹预测准确率的问题。通过真实数据和实验分析表明:在参数设置相同的情况下,该方法比挖掘频繁轨迹模式算法的预测准确率平均提高了18.8%,预测时间平均缩减了80.4%。因此,该方法对于车辆路口的轨迹预测具有较高的预测准确率,并且能预测一系列的车辆未来轨迹。

关键词: 受限路网,车辆轨迹预测,不确定性历史数据,补全路径,马尔科夫链

Abstract: In the city road,real-time,accurate and reliable trajectory prediction of mobile vehicles can bring very high application value,which can not only provide accurate location-based services,but also can help the vehicle to predict the traffic situation.At present,the trajectory prediction method of moving vehicles is mainly based on the precise historical trajectory in Euclidean space,and does not consider the vehicle trajectory prediction with uncertain historical data in restricted road network.A trajectory prediction method based on Markov chain was proposed to solve this problem.Its advantages include redefining the path algorithm of completion,making up for the incompleteness of uncertain historical data,and achieving prediction by using the characteristics of low time complexity and high prediction accuracy with Markov chain.This method avoids the problem of low prediction accuracy caused by too much query time due to the frequent pattern mining and the excess noise.The results show that under the same parameter setting,the prediction accuracy of the method is 18.8% higher than that of the mining frequent trajectory model,and the prediction time is reduced by 80.4% on average.Therefore,the method has high prediction accuracy for the trajectory prediction of the vehicle intersection,and achieves the prediction of a series of vehicle future trajectories.

Key words: Restricted road network,Vehicle trajectory prediction,Uncertainty historical data,Completion path,Markov chain

[1] QIAO S J,JIN K,HAN N,et al.Trajectory Prediction Algorithm Based on Gaussian Mixture Model[J].Journal of Software,2015,26(5):1048-1063.(in Chinese) 乔少杰,金琨,韩楠,等.一种基于高斯混合模型的轨迹预测算法[J].软件学报,2015,6(5):1048-1063.
[2] ZHENG Y.Trajectory Data Mining:An Overview[J].ACMTransactions on Intelligent Systems & Technology,2015,6(3):1-41.
[3] BAO J,ZHENG Y,WILKIE D,et al.Recommendetions in location-based social networks:a survey[J].Geoinformatica,2015,9(3):525-565.
[4] YUAN N J,ZHENG Y,XIE X,at al.Discovering urban functional zones using latent activity trajectories[J].IEEE Transactions on Knowledge & Data Engineering,2015,7(3):712-725.
[5] LV Y,DUAN Y,KANG W,et al.Traffic Flow Prediction With Big Data:A Deep Learning Approach[J].IEEE Transactions on Intelligent Transportation Systems,2015,6(2):865-873.
[6] LOPEZ-DAZ M.Influence Diagrams with Super Value Nodes Involving Imprecise Information[J].European Journal of Operational Research,2007,9(1):203-219.
[7] DIEHL M,HAIMES Y Y.Influence Diagrams with MultipleObjectives and Trade off Analysis[J].IEEE Transactions on Systems,Man,and Cybernetics-Part A:Systems and Humans(S1083-4427),2004,4(3):293-304.
[8] YAO H L,WANG H,ZHANG Y S,et al.Effective graph model selection algorithm based on structural decomposition[J].Computer Science,2007,4(1):133-139.(in Chinese) 姚宏亮,王浩,张佑生,等.一种基于结构分解的影响图模型选择算法[J].计算机科学,2007,4(1):133-139.
[9] TATMAN J A,SHACHTER R D.Dynamic Programming and Influence Diagrams[J].IEEE Transactions on Systems,Man,and Cybernetics,1999,20(2):365-379.
[10] SHACHER R D,NDILIKILIKESHA P P.Using Potential Influence Diagrams for Probabilistic Inference and Decision Ma-king[C]∥Proceedings of the 9th Conference on Uncertainty and Artificial Intelligence.1993:383-390.
[11] SONG C,QU Z,BLUMM N,et al.Limits of predictability in human mobility[J].Science,2010,7(5968):1018-1021.
[12] YI S G,KANG C M,LEE S H,et al.Vehicle trajectory prediction for adaptive cruise control[C]∥Intelligent Vehicles Symposium.IEEE,2015.
[13] CENTOLA D,The spread of behavior in an online social network experiment[J].Science,2010,9(5996):1194-1197.
[14] JEUNG H,YIU M L,ZHOU X,et al.Path prediction and predictive range querying in road network databases[J].The VLDB Journal,2010,9(4):585-602.
[15] QIAO S J,LI T R,ZHU Y,et al.Uncertain Trajectory Prediction of Moving Objects Based on CTBN[J].Journal of University of Electronic Science and Technology of China,2012,1(9):759-763.(in Chinese) 乔少杰,李天瑞,朱焱,等.基于CTBN的移动对象不确定轨迹预测算法[J].电子科学大学学报,2012,1(9):759-763.
[16] XIA Z Q,HU Z Z,LUO J P.EVATP:An Adaptive VehicleTrajectory Prediction Method[J].Small Microcomputer System,2016,7(10):2375-2379.(in Chinese) 夏卓群,胡珍珍,罗君鹏.EAVTP:一种环境自适应车辆轨迹预测方法[J].小型微型计算机系统,2016,7(10):2375-2379.
[17] GUO L M,DING Z M,HU Z L,et al.Study on Uncertain Tra-jectory Prediction Based on Road Network [J].Journal of Computer Research and Development,2010,7(1):104-112.(in Chinese) 郭黎敏,丁治明,胡泽林,等.基于路网的不确定性轨迹预测[J].计算机研究与发展,2010,7(1):104-112.
[18] 盛骤.概率论与数理统计[M].北京:高等教育出版社,2003.
[19] 刘嘉焜.应用概率统计[M].北京:科学出版社,2004.
[20] 龚光鲁,钱敏平.应用随机过程教程[M].北京:清华大学出版社,2004.
[21] SONG L B,KOTZ D,JAIN R,et al.Evaluating next-cell predictors with extensive Wi-Fi mobility data[J].IEEE Transactions on Mobile Computing,2006,5(12):1633-1649.
[22] WANG X T.Study on Uncertainty Trajectory Prediction Model of Moving Object [D].Chengdu:Southwest Jiaotong University,2016.(in Chinese) 王晓腾.移动对象不确定性轨迹预测模型研究[D].成都:西南交通大学,2016.

No related articles found!
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!