Deep-learning Based Urban Vehicle Trajectory Prediction

Seongjin Choi; Jiwon Kim; Hwapyeong Yu; Dongho Ka; Hwasoo Yeo

doi:10.7470/jkst.2019.37.5.422

All Issue

2019 Vol.37, Issue 5 Preview Page Next Page

Article

Deep-learning Based Urban Vehicle Trajectory Prediction 딥러닝 기반의 도시 지역 차량궤적 예측 알고리즘 개발 연구

31 October 2019. pp. 422-429

PDF XML

Abstract

Recently, as a variety of position sensors are developed, a large amount of urban position data is collected in the urban traffic networks. Based on the data collected through such location sensors, high-resolution urban mobility data of individual users using urban road networks is generated and collected in the transportation systems. Urban mobility data generated by these sensors provide a novel spatio-temporal insights into the mobility patterns of traffic network users and can be used to develop models and strategies to predict traffic flows in urban areas and improve traffic efficiency. This study proposes an algorithm for predicting urban mobility patterns. Deep learning based algorithm is used to train mobility patterns in urban areas and predict mobility. The proposed algorithm is trained and tested using Bluetooth data collected in Brisbane for one year. As a result of evaluating the performance of the algorithm with the test dataset, the proposed algorithm shows an average prediction accuracy of 70% or more.

Keywords

artificial neural network

deep learning

urban mobility prediction

vehicle trajetory

최근 다양한 위치추적센서를 통하여 수집된 데이터를 기반으로 교통 분야에서는 도시 도로망을 이용하는 개별 사용자의 고해상도 이동성 데이터가 생성 및 수집되고 있다. 해당 센서에서 생성 된 도시 지역 이동성 데이터는 교통 네트워크 이용자들의 이동 패턴에 대한 시공간적인 새로운 통찰력을 제공하며, 이는 도시 지역 교통 흐름을 예측하고 교통 효율을 향상시키는 모델 및 전략을 개발하는데 사용 될 수 있다. 따라서 이 연구는 도시 지역 이동성 패턴을 예측하고자 도시 지역 차량 궤적을 예측하는 알고리즘을 제안한다. 도시 지역을 구역으로 나누어 거시적 이동성 패턴을 분석한 선행 연구와는 달리, 본 연구에서는 교차로 단위의 차량 궤적 데이터를 생성하여 보다 미시적인 이동성 패턴을 분석하려고 한다, 본 연구에서는 딥러닝 기반의 모델을 사용하여 차량 궤적을 예측하였다. 한 차량이 앞서 진행한 교차로 시퀀스를 입력하여 다음에 이 차량이 진행할 교차로를 예측한다. 제안된 알고리즘은 브리즈번에서 1년간 수집된 블루투스 데이터를 이용하여 학습하고 시험한다. 시험 데이터 세트로 알고리즘의 성능을 평가한 결과 제안된 알고리즘이 평균 70% 이상의 예측 정확도를 보였다.

키워드

도시 지역 이동성 패턴

딥러닝

빅 데이터

차량 궤적

References

Bhaskar A., Edward C. (2013) Fundamental understanding on the use of Bluetooth scanner as a complementary transport data, Transportation Research Part C, Emerging Technologies 37, 42-72.

10.1016/j.trc.2013.09.013

Choi S., Yeo H., Kim J. (2018) Network-Wide Vehicle Trajectory Prediction in Urban Traffic Networks using Deep Learning, Transportation Research Record, 2672, 173-184.

10.1177/0361198118794735

Gambs M., Killijian O., del Prado Cortez M. N. (2012), Next place prediction using mobility markov chains, in Proceedings of the First Workshop on Measurement, Privacy, and Mobility, ACM, 3.

10.1145/2181196.2181199

Horvitz E., Krumm J. (2012), Some Help on the Way: Opportunistic routing under uncertainty, In Proceedings of the 2012 ACM conference on Ubiquitous Computing (371-380), ACM.

10.1145/2370216.2370273

Kim J., Mahmassani H. S. (2015), Spatial and temporal characterization of travel patterns in a traffic network using vehicle trajectories, Transportation Research Procedia, 9, 164-184.

10.1016/j.trpro.2015.07.010

Kingma D. P., Ba J. (2014), Adam: A method for stochastic optimization, arXiv preprint arXiv:1412.6980.

Krumm J., Horvitz E. (2006), Predestination: Inferring destinations from partial trajectories, In International Conference on Ubiquitous Computing (243-260), Springer, Berlin, Heidelberg.

10.1007/11853565_15

Mathew W., Raposo R., Martins B. (2012), Predicting future locations with hidden Markov models, In Proceedings of the 2012 ACM conference on ubiquitous computing (911-918), ACM.

10.1145/2370216.2370421

Mazimpaka J. D., Timpf S. (2016), Trajectory data mining: A review of methods and applications, Journal of Spatial Information Science, 2016(13), 61-99.

10.5311/JOSIS.2016.13.263

Noulas A., Scellato S., Lathia N., Mascolo C. (2012), Mining user mobility features for next place prediction in location-based services, In 2012 IEEE 12th international conference on data mining (1038-1043), IEEE.

10.1109/ICDM.2012.113

Phillips D. J., Wheeler T. A., Kochenderfer M. J. (2017), Generalizable intention prediction of human drivers at intersections, In 2017 IEEE Intelligent Vehicles Symposium (IV)(1665-1670), IEEE.

10.1109/IVS.2017.7995948

Rodemerk C., Winner H., Kastner R. (2015), Predicting the driver’s turn intentions at urban intersections using context-based indicators, In 2015 IEEE Intelligent Vehicles Symposium (IV) (964-969), IEEE.

10.1109/IVS.2015.7225809

Wang, G., Kim, J. (2016), The prediction of traffic congestion and incident on urban road networks using naive bayes classifier, In Australasian transport research forum 2016 proceedings, Melbourne, Australia.

Xue A. Y., Qi J., Xie X., Zhang R., Huang J., Li Y. (2015), Solving the data sparsity problem in destination prediction, The VLDB Journal-The International Journal on Very Large Data Bases, 24(2), 219-243.

10.1007/s00778-014-0369-7

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 Proceedings of the 10th international conference on Ubiquitous computing (322-331), ACM.

10.1145/1409635.1409678

Zyner A. G. (2018), Naturalistic Driver Intention and Path Prediction using Machine Learning.

10.1109/TITS.2019.2913166

Information

Publisher :Korean Society of Transportation
Publisher(Ko) :대한교통학회
Journal Title :Journal of Korean Society of Transportation
Journal Title(Ko) :대한교통학회지
Volume : 37
No :5
Pages :422-429
Received Date : 2019-06-28
Revised Date : 2019-07-30
Accepted Date : 2019-09-03
DOI :https://doi.org/10.7470/jkst.2019.37.5.422

Journal of Korean Society of Transportation ISSN:1229-1366(Print) 2234-4217(Online) 대한교통학회지

All Issue