Extreme Gradient Boosting (XGBoost) Model for Vehicle Trajectory Prediction in Connected and Autonomous Vehicle Environment

  • Pengfei Liu University of North Carolina at Charlotte, USDOT Centre for Advanced Multimodal Mobility Solutions and Education (CAMMSE)
  • Wei Fan University of North Carolina at Charlotte, USDOT Centre for Advanced Multimodal Mobility Solutions and Education (CAMMSE)
Keywords: connected and autonomous vehicles, Extreme Gradient Boosting, Intelligent Driver Model, trajectory prediction

Abstract

Connected and autonomous vehicles (CAVs) have the ability to receive information on their leading vehicles through multiple sensors and vehicle-to-vehicle (V2V) technology and then predict their future behaviour thus to improve roadway safety and mobility. This study presents an innovative algorithm for connected and autonomous vehicles to determine their trajectory considering surrounding vehicles. For the first time, the XGBoost model is developed to predict the acceleration rate that the object vehicle should take based on the current status of both the object vehicle and its leading vehicle. Next Generation Simulation (NGSIM) datasets are utilised for training the proposed model. The XGBoost model is compared with the Intelligent Driver Model (IDM), which is a prior state-of-the-art model. Root Mean Square Error (RMSE) and Mean Absolute Error (MAE) are applied to evaluate the two models. The results show that the XGBoost model outperforms the IDM in terms of prediction errors. The analysis of the feature importance reveals that the longitudinal position has the greatest influence on vehicle trajectory prediction results.

References

Helbing D, Treiber M, Kesting A, Schönhof M. Theoretical vs. empirical classification and prediction of congested traffic states. The European Physical Journal B. 2009;69(4): 583-598. DOI: 10.1140/epjb/e2009-00140-5

Prayogo D, Cheng MY, Wu YW, Tran DH. Combining machine learning models via adaptive ensemble weighting for prediction of shear capacity of reinforced-concrete deep beams. Engineering with Computers. 2019;36: 1135-1153. DOI: 10.1007/s00366-019-00753-w

Zhang D, et al. A data-driven design for fault detection of wind turbines using random forests and XGboost. IEEE Access. 2018;6: 21020-21031. DOI: 10.1109/ACCESS.2018.2818678

Chen T, Guestrin C. Xgboost: A scalable tree boosting system. In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 13-17 August 2016, San Francisco, California, USA; 2016. p. 785-794.

Colyar J, Halkias J. US highway 101 dataset. Federal Highway Administration (FHWA). Tech. Rep. FHWA-HRT-07-030, 2007.

Polychronopoulos A, Tsogas M, Amditis AJ, Andreone L. Sensor fusion for predicting vehicles' path for collision avoidance systems. IEEE Transactions on Intelligent Transportation Systems. 2007;8(3): 549-562. DOI: 10.1109/TITS.2007.903439

Schubert R, Richter E, Wanielik G. Comparison and evaluation of advanced motion models for vehicle tracking. 2008 11th International Conference on Information Fusion, 30 June-3 July 2008, Cologne, Germany. IEEE; 2008. p. 1-6.

Liu P, Fan W. Exploring the impact of connected and autonomous vehicles on freeway capacity using a revised Intelligent Driver Model. Transportation Planning and Technology. 2020;43(3): 279-292. DOI: 10.1080/03081060.2020.1735746

Qiao S, et al. A self-adaptive parameter selection trajectory prediction approach via hidden Markov models. IEEE Transactions on Intelligent Transportation Systems. 2014;16(1): 284-296. DOI: 10.1109/TITS.2014.2331758

Liu P, Kurt A, Özgüner Ü. Trajectory prediction of a lane changing vehicle based on driver behavior estimation and classification. 17th International IEEE Conference on Intelligent Transportation Systems (ITSC), 8-11 Oct. 2014, Qingdao, China. IEEE; 2014. p. 942-947. DOI: 10.1109/ITSC.2014.6957810

Ye N, Zhang Y, Wang R, Malekian R. Vehicle trajectory prediction based on Hidden Markov Model. KSII Transactions on Internet and Information Systems. 2016; 10(7). DOI: 10.3837/tiis.2016.07.016

Tran Q, Firl J. Online maneuver recognition and multimodal trajectory prediction for intersection assistance using non-parametric regression. 2014 IEEE Intelligent Vehicles Symposium Proceedings, 8-11 June 2014, Dearborn, MI, USA. IEEE; 2014. p. 918-923. DOI: 10.1109/IVS.2014.6856480

Goli SA, Far BH, Fapojuwo AO. Vehicle trajectory prediction with Gaussian Process Regression in Connected Vehicle environment. 2018 IEEE Intelligent Vehicles Symposium (IV), 26-30 June 2018, Changshu, China. IEEE; 2018. p. 550-555. DOI: 10.1109/IVS.2018.8500614

Schreier M, Willert V, Adamy J. An integrated approach to maneuver-based trajectory prediction and criticality as sessment in arbitrary road environments. IEEE Transactions on Intelligent Transportation Systems. 2016;17(10): 2751-2766. DOI: 10.1109/TITS.2016.2522507

Xiao Z, et al. GOI: A novel design for vehicle positioning and trajectory prediction under urban environments. IEEE Sensors Journal. 2018;18(13), 5586-5594. DOI: 10.1109/JSEN.2018.2826000

Izquierdo R, et al. Vehicle trajectory and lane change prediction using ANN and SVM classifiers. 2017 IEEE 20th International Conference on Intelligent Transportation Systems (ITSC), 16-19 Oct. 2017, Yokohama, Japan. IEEE; 2017. p. 1-6. DOI: 10.1109/ITSC.2017.8317838

Boubezoul A, Koita A, Daucher D. Vehicle trajectories classification using Support Vectors Machines for failure trajectory prediction. 2009 International Conference on Advances in Computational Tools for Engineering Applications, 15-17 July 2009, Beirut, Lebanon. IEEE; 2009. p. 486-491. DOI: 10.1109/ACTEA.2009.5227873

Woo H, et al. Trajectory prediction of surrounding vehicles using LSTM network. 2013 IEEE Intelligent Vehicles Symposium (IV), Gold Coast, QLD, Australia, 26–28 June 2013.

Messaoud K, Yahiaoui I, Verroust-Blondet A, Nashashibi F. Relational recurrent neural networks for vehicle trajectory prediction. 2019 IEEE Intelligent Transportation Systems Conference (ITSC), 27-30 Oct. 2019, Auckland, New Zealand. IEEE; 2019. p. 1813-1818. DOI: 10.1109/ITSC.2019.8916887

Dai S, Li L, Li Z. Modeling vehicle interactions via modified LSTM models for trajectory prediction. IEEE Access. 2019;7: 38287-38296. DOI: 10.1109/ACCESS.2019.2907000

Kim B, et al. Probabilistic vehicle trajectory prediction over occupancy grid map via recurrent neural network. 2017 IEEE 20th International Conference on Intelligent Transportation Systems (ITSC), 16-19 Oct. 2017, Yokohama, Japan. IEEE; 2017. p. 399-404. DOI: 10.1109/ITSC.2017.8317943

Park SH, et al. Sequence-to-sequence prediction of vehicle trajectory via LSTM encoder-decoder architecture. 2018 IEEE Intelligent Vehicles Symposium (IV), 26-30 June 2018, Changshu, China. IEEE; 2018. p. 1672-1678. DOI: 10.1109/IVS.2018.8500658

Ju C, et al. Interaction-aware Kalman Neural Networks for trajectory prediction. arXiv preprint arXiv: 1902.10928. 2019.

Nikhil N, Morris BT. Convolutional neural network for trajectory prediction. Proceedings of the European Conference on Computer Vision (ECCV); 2018.

Han F, Tan Y, Eledath J. Preceding vehicle trajectory prediction by multi-cue integration. Proceedings of the IAPR Conference on Machine Vision Applications (IAPR MVA 2007), 16-18 May 2007, Tokyo, Japan. 2007. p. 575-578.

Jiang H, Chang L, Li Q, Chen D. Trajectory prediction of vehicles based on deep learning. 2019 4th International Conference on Intelligent Transportation Engineering (ICITE), 5-7 Sep. 2019, Singapore. IEEE; 2019. p. 190-195. DOI: 10.1109/ICITE.2019.8880168

Xing Y, Lv C, Cao D. Personalized vehicle trajectory prediction based on joint time series modeling for connected vehicles. IEEE Transactions on Vehicular Technology. 2019;69(2): 1341-1352. DOI: 10.1109/TVT.2019.2960110

Song K, et al. A steel property optimization model based on the XGBoost algorithm and improved PSO. Computational Materials Science. 2020;174: 109472. DOI: 10.1016/j.commatsci.2019.109472

Parsa AB, et al. Toward safer highways, application of XGBoost and SHAP for real-time accident detection and feature analysis. Accident Analysis & Prevention. 2020;136: 105405. DOI: 10.1016/j.aap.2019.105405

Dong W, Huang Y, Lehane B, Ma G. XGBoost algorithm-based prediction of concrete electrical resistivity for structural health monitoring. Automation in Construction. 2020;114: 103155. DOI: 10.1016/j.autcon.2020.103155

Lim S, Chi S. Xgboost application on bridge management systems for proactive damage estimation. Advanced Engineering Informatics. 2019;41: 100922. DOI: 10.1016/j.aei.2019.100922

Xu Y, Zhao X, Chen Y, Yang Z. Research on a mixed gas classification algorithm based on extreme random tree. Applied Sciences. 2019;9(9): 1728. DOI: 10.3390/app9091728

Treiber M, Hennecke A, Helbing D. Congested traffic states in empirical observations and microscopic simulations. Physical review E. 2000;62(2); 1805-1824. DOI: 10.1103/PhysRevE.62.1805

Tomar RS, Verma S, Tomar GS. Prediction of lane change trajectories through neural network. 2010 International Conference on Computational Intelligence and Communication Networks, 26-28 Nov. 2010, Bhopal, India. IEEE; 2010. p. 249-253. DOI: 10.1109/CICN.2010.59

Ding C, Wang W, Wang X, Baumann M. A neural network model for driver’s lane-changing trajectory prediction in urban traffic flow. Mathematical Problems in Engineering. 2013;2013: Article ID 967358. DOI: 10.1155/2013/967358

Altché F, de La Fortelle A. An LSTM network for highway trajectory prediction. 2017 IEEE 20th International Conference on Intelligent Transportation Systems (ITSC), 16-19 Oct. 2017, Yokohama, Japan. IEEE; 2017. p. 353-359. DOI: 10.1109/ITSC.2017.8317913

Deo N, Trivedi MM. Multi-modal trajectory prediction of surrounding vehicles with maneuver based LSTMs. 2018 IEEE Intelligent Vehicles Symposium (IV), 26-30 June 2018, Changshu, China. IEEE; 2018. p. 1179-1184. DOI: 10.1109/IVS.2018.8500493

Li J, Ma H, Zhan W, Tomizuka M. Coordination and trajectory prediction for vehicle interactions via Bayesian generative modeling. 2019 IEEE Intelligent Vehicles Symposium (IV), 9-12 June 2019, Paris, France. IEEE; 2019. p. 2496-2503. DOI: 10.1109/IVS.2019.8813821

Published
2021-10-08
How to Cite
1.
Liu P, Fan W. Extreme Gradient Boosting (XGBoost) Model for Vehicle Trajectory Prediction in Connected and Autonomous Vehicle Environment. Promet [Internet]. 2021Oct.8 [cited 2024Mar.29];33(5):767-74. Available from: https://traffic.fpz.hr/index.php/PROMTT/article/view/3779
Section
Articles