Ensemble deep learning-based lane-changing behavior prediction of manually driven vehicles in mixed traffic environments

Boshuo Geng; Jianxiao Ma; Shaohu Zhang; Boshuo Geng; Jianxiao Ma; Shaohu Zhang

doi:10.3934/era.2023315

Electronic Research Archive

2023, Volume 31, Issue 10: 6216-6235. doi: 10.3934/era.2023315

Previous Article Next Article

Research article

Ensemble deep learning-based lane-changing behavior prediction of manually driven vehicles in mixed traffic environments

College of Automobile and Traffic Engineering, Nanjing Forestry University, Nanjing 210037, China

Received: 18 July 2023 Revised: 07 September 2023 Accepted: 12 September 2023 Published: 18 September 2023

Accurately predicting lane-changing behaviors (lane keeping, left lane change and right lane change) in real-time is essential for ensuring traffic safety, particularly in mixed-traffic environments with both autonomous and manual vehicles. This paper proposes a fused model that predicts vehicle lane-changing behaviors based on the road traffic environment and vehicle motion parameters. The model combines the ensemble learning XGBoost algorithm with the deep learning Bi-GRU neural network. The XGBoost algorithm first checks whether the present environment is safe for the lane change and then evaluates the likelihood that the target vehicle will make a lane change. Subsequently, the Bi-GRU neural network is used to accurately forecast the lane-changing behaviors of nearby vehicles using the feasibility of lane-changing and the vehicle's motion status as input features. The highD trajectory dataset was utilized for training and testing the model. The model achieved an accuracy of 98.82%, accurately predicting lane changes with an accuracy exceeding 87% within a 2-second timeframe. By comparing with other methods and conducting experimental validation, we have demonstrated the superiority of the proposed model, thus, the research achievement is of utmost significance for the practical application of autonomous driving technology.
- traffic engineering,
- lane change,
- traffic safety,
- ensemble learning,
- deep learning
Citation: Boshuo Geng, Jianxiao Ma, Shaohu Zhang. Ensemble deep learning-based lane-changing behavior prediction of manually driven vehicles in mixed traffic environments[J]. Electronic Research Archive, 2023, 31(10): 6216-6235. doi: 10.3934/era.2023315

Related Papers:

Abstract

Accurately predicting lane-changing behaviors (lane keeping, left lane change and right lane change) in real-time is essential for ensuring traffic safety, particularly in mixed-traffic environments with both autonomous and manual vehicles. This paper proposes a fused model that predicts vehicle lane-changing behaviors based on the road traffic environment and vehicle motion parameters. The model combines the ensemble learning XGBoost algorithm with the deep learning Bi-GRU neural network. The XGBoost algorithm first checks whether the present environment is safe for the lane change and then evaluates the likelihood that the target vehicle will make a lane change. Subsequently, the Bi-GRU neural network is used to accurately forecast the lane-changing behaviors of nearby vehicles using the feasibility of lane-changing and the vehicle's motion status as input features. The highD trajectory dataset was utilized for training and testing the model. The model achieved an accuracy of 98.82%, accurately predicting lane changes with an accuracy exceeding 87% within a 2-second timeframe. By comparing with other methods and conducting experimental validation, we have demonstrated the superiority of the proposed model, thus, the research achievement is of utmost significance for the practical application of autonomous driving technology.

References

[1]	O. Scheel, L. Schwarz, N. Navab, F. Tombari, Situation assessment for planning lane changes: combining recurrent models and prediction, in 2018 IEEE International Conference on Robotics and Automation (ICRA), IEEE, (2018), 2082–2088. https://doi.org/10.1109/ICRA.2018.8462838
[2]	Y. Xing, C. Lv, H. Wang, H. Wang, Y. Ai, D. Cao, et al., Driver lane change intention inference for intelligent vehicles: Framework, survey, and challenges, IEEE Trans. Veh. Technol., 68 (2019), 4377–4390. https://doi.org/10.1109/tvt.2019.2903299 doi: 10.1109/TVT.2019.2903299
[3]	M. M. Michalek, M. Kielczewski, The concept of passive control assistance for docking maneuvers with N-trailer vehicles, IEEE/ASME Trans. Mechatron., 20 (2015), 2075–2084. https://doi.org/10.1109/tmech.2014.2362354 doi: 10.1109/TMECH.2014.2362354
[4]	S. Liu, K. Zheng, L. Zhao, P. Fan, A driving intention prediction method based on hidden Markov model for autonomous driving, Comput. Commun., 157 (2020), 143–149. https://doi.org/10.1016/j.comcom.2020.04.021 doi: 10.1016/j.comcom.2020.04.021
[5]	H. Zhang, R. Fu, An ensemble learning—online semi-supervised approach for vehicle behavior recognition, IEEE Trans. Intell. Transp. Syst., 23 (2022), 10610–10626. https://doi.org/10.1109/tits.2021.3095053 doi: 10.1109/TITS.2021.3095053
[6]	T. Chen, X. Shi, Y. D. Wong, Key feature selection and risk prediction for lane-changing behaviors based on vehicles' trajectory data, Accid. Anal. Prev., 129 (2019), 156–169. https://doi.org/https://doi.org/10.1016/j.aap.2019.05.017 doi: 10.1016/j.aap.2019.05.017
[7]	O. Sharma, N. C. Sahoo, N. B. Puhan, Highway lane-changing prediction using a hierarchical software architecture based on support vector machine and continuous hidden markov model, Int. J. Intell. Transp. Syst. Res., 20 (2022), 519–539. https://doi.org/10.1007/s13177-022-00308-2 doi: 10.1007/s13177-022-00308-2
[8]	Y. Xing, C. Lv, H. Wang, D. Cao, E. Velenis, An ensemble deep learning approach for driver lane change intention inference, Transp. Res. Part C Emerging Technol., 115 (2020). https://doi.org/10.1016/j.trc.2020.102615 doi: 10.1016/j.trc.2020.102615
[9]	K. Schmidt, M. Beggiato, K. H. Hoffmann, J. F. Krems, A mathematical model for predicting lane changes using the steering wheel angle, J. Saf. Res., 49 (2014), 85–90. https://doi.org/10.1016/j.jsr.2014.02.014 doi: 10.1016/j.jsr.2014.02.014
[10]	J. Wang, Z. Zhang, G. Lu, A Bayesian inference based adaptive lane change prediction model, Transp. Res. Part C Emerging Technol., 132 (2021). https://doi.org/10.1016/j.trc.2021.103363 doi: 10.1016/j.trc.2021.103363
[11]	T. Rehder, A. Koenig, M. Goehl, L. Louis, D. Schramm, Lane change intention awareness for assisted and automated driving on highways, IEEE Trans. Intell. Veh., 4 (2019), 265–276. https://doi.org/10.1109/tiv.2019.2904386 doi: 10.1109/TIV.2019.2904386
[12]	K. Li, X. Wang, Y. Xu, J. Wang, Lane changing intention recognition based on speech recognition models, Transp. Res. Part C Emerging Technol., 69 (2016), 497–514. https://doi.org/10.1016/j.trc.2015.11.007 doi: 10.1016/j.trc.2015.11.007
[13]	Y. Zhang, Q. Lin, J. Wang, S. Verwer, J. M. Dolan, Lane-change intention estimation for car-following control in autonomous driving, IEEE Trans. Intell. Veh., 3 (2018), 276–286. https://doi.org/10.1109/tiv.2018.2843178 doi: 10.1109/TIV.2018.2843178
[14]	Y. Xia, Z. Qu, Z. Sun, Z. Li, A human-like model to understand surrounding vehicles' lane changing intentions for autonomous driving, IEEE Trans. Veh. Technol., 70 (2021), 4178–4189. https://doi.org/10.1109/tvt.2021.3073407 doi: 10.1109/TVT.2021.3073407
[15]	R. Song, B. Li, Surrounding vehicles' lane change maneuver prediction and detection for intelligent vehicles: A comprehensive review, IEEE Trans. Intell. Transp. Syst., 23 (2022), 6046–6062. https://doi.org/10.1109/tits.2021.3076164 doi: 10.1109/TITS.2021.3076164
[16]	Y. Zhang, X. Shi, S. Zhang, A. Abraham, A XGboost-based lane change prediction on time series data using feature engineering for autopilot vehicles, IEEE Trans. Intell. Transp. Syst., 23 (2022), 19187–19200. https://doi.org/10.1109/tits.2022.3170628 doi: 10.1109/TITS.2022.3170628
[17]	D. Li, C. Ma, Research on lane change prediction model based on GBDT, Physica A, 608 (2022). https://doi.org/10.1016/j.physa.2022.128290 doi: 10.1016/j.physa.2022.128290
[18]	D. J. Kim, J. S. Kim, J. H. Yang, S. C. Kee, C. C. Chung, Lane change intention classification of surrounding vehicles utilizing open set recognition, IEEE Access, 9 (2021), 57589–57602. https://doi.org/10.1109/access.2021.3072413 doi: 10.1109/ACCESS.2021.3072413
[19]	M. Hu, Y. Liao, W. Wang, G. Li, B. Cheng, F. Chen, Decision tree-based maneuver prediction for driver rear-end risk-avoidance behaviors in cut-in scenarios, J. Adv. Transp., 2017 (2017). https://doi.org/10.1155/2017/7170358 doi: 10.1155/2017/7170358
[20]	Y. Feng, X. Yan, Support vector machine based lane-changing behavior recognition and lateral trajectory prediction, Comput. Intell. Neurosci., 2022 (2022), 3632333. https://doi.org/10.1155/2022/3632333 doi: 10.1155/2022/3632333
[21]	A. Das, M. M. Ahmed, Machine learning approach for predicting lane-change maneuvers using the SHRP2 naturalistic driving study data, Transp. Res. Rec., 2675 (2021), 574–594. https://doi.org/10.1177/03611981211003581 doi: 10.1177/03611981211003581
[22]	H. Zhang, R. Fu, A hybrid approach for turning intention prediction based on time series forecasting and deep learning, Sensors, 20 (2020). https://doi.org/10.3390/s20174887 doi: 10.3390/s20174887
[23]	C. Wei, F. Hui, A. J. Khattak, Y. J. Lee, Driver lane-changing behavior prediction based on deep learning, J. Adv. Transp., 2021 (2021). https://doi.org/10.1155/2021/6676092 doi: 10.1155/2021/6676092
[24]	Y. Guo, H. Zhang, C. Wang, Q. Sun, W. Li, Driver lane change intention recognition in the connected environment, Physica A, 575 (2021). https://doi.org/10.1016/j.physa.2021.126057 doi: 10.1016/j.physa.2021.126057
[25]	Q. Shi, H. Zhang, An improved learning-based LSTM approach for lane change intention prediction subject to imbalanced data, Transp. Res. Part C Emerging Technol., 133 (2021). https://doi.org/10.1016/j.trc.2021.103414 doi: 10.1016/j.trc.2021.103414
[26]	Q. Xue, Y. Xing, J. Lu, An integrated lane change prediction model incorporating traffic context based on trajectory data, Transp. Res. Part C Emerging Technol., 141 (2022). https://doi.org/10.1016/j.trc.2022.103738 doi: 10.1016/j.trc.2022.103738
[27]	Z. Wu, K. Liang, D. Liu, Z. Zhao, Driver lane change intention recognition based on Attention Enhanced Residual-MBi-LSTM network, IEEE Access, 10 (2022), 58050–58061. https://doi.org/10.1109/access.2022.3179007 doi: 10.1109/ACCESS.2022.3179007
[28]	A. Zyner, S. Worrall, E. Nebot, A recurrent neural network solution for predicting driver intention at unsignalized intersections, IEEE Rob. Autom. Lett., 3 (2018), 1759–1764. https://doi.org/10.1109/lra.2018.2805314 doi: 10.1109/LRA.2018.2805314
[29]	R. Chandra, U. Bhattacharya, A. Bera, D. Manocha, I. C. Soc, TraPHic: Trajectory prediction in dense and heterogeneous traffic using weighted interactions, in 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), IEEE, (2019), 8475–8484. https://doi.org/10.1109/cvpr.2019.00868
[30]	Z. N. Li, X. H. Huang, T. Mu, J. Wang, Attention-based lane change and crash risk prediction model in highways, IEEE Trans. Intell. Transp. Syst., 23 (2022), 22909–22922. https://doi.org/10.1109/tits.2022.3193682 doi: 10.1109/TITS.2022.3193682
[31]	H. Q. Dang, J. Fuernkranz, A. Biedermann, M. Hoepfl, Time-to-lane-change prediction with deep learning, in 2017 IEEE 20th International Conference on Intelligent Transportation Systems (ITSC), IEEE, (2017), 2082–2088. https://doi.org/10.1109/ITSC.2017.8317674
[32]	L. Li, W. Zhao, C. Xu, C. Wang, Q. Chen, S. Dai, Lane-change intention inference based on RNN for autonomous driving on highways, IEEE Trans. Veh. Technol., 70 (2021), 5499–5510. https://doi.org/10.1109/tvt.2021.3079263 doi: 10.1109/TVT.2021.3079263
[33]	E. Balal, R. L. Cheu, T. Sarkodie-Gyan, A binary decision model for discretionary lane changing move based on fuzzy inference system, Transp. Res. Part C Emerging Technol., 67 (2016), 47–61. https://doi.org/10.1016/j.trc.2016.02.009 doi: 10.1016/j.trc.2016.02.009
[34]	Y. Li, R. Gu, J. Lee, M. Yang, Q. Chen, Y. Zhang, The dynamic tradeoff between safety and efficiency in discretionary lane-changing behavior: A random parameters logit approach with heterogeneity in means and variances, Accid. Anal. Prev., 153 (2021), 106036. https://doi.org/https://doi.org/10.1016/j.aap.2021.106036 doi: 10.1016/j.aap.2021.106036
[35]	O. Rákos, S. Aradi, T. Bécsi, Lane change prediction using gaussian classification, support vector classification and neural network classifiers, Period. Polytech., Transp. Eng., 48 (2020), 327–333. https://doi.org/10.3311/PPtr.15849 doi: 10.3311/PPtr.15849
[36]	T. Chen, C. Guestrin, Xgboost: A scalable tree boosting system, in Proceedings of the 22nd ACM Sigkdd International Conference on Knowledge Discovery and data Mining, (2016), 785–794. https://doi.org/10.1145/2939672.2939785
[37]	R. Krajewski, J. Bock, L. Kloeker, L. Eckstein, The highD dataset: A drone dataset of naturalistic vehicle trajectories on german highways for validation of highly automated driving systems, in 2018 IEEE 21st International Conference on Intelligent Transportation Systems (ITSC), IEEE, (2018), 2118–2125. https://doi.org/10.1109/ITSC.2018.8569552
[38]	D. F. Xie, Z. Z. Fang, B. Jia, Z. He, A data-driven lane-changing model based on deep learning, Transp. Res. Part C Emerging Technol., 106 (2019), 41–60. https://doi.org/10.1016/j.trc.2019.07.002 doi: 10.1016/j.trc.2019.07.002
[39]	X. Song, Y. Zeng, H. Cao, M. Li, B. Yi, Lane change intention recognition method based on an LSTM network, China J. Highway Transport, 34 (2021), 236–245. https://doi.org/10.19721/j.cnki.1001-7372.2021.11.019 doi: 10.19721/j.cnki.1001-7372.2021.11.019

Reader Comments

Your name:*

Email:*
© 2023 the Author(s), licensee AIMS Press. This is an open access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0)