Vehicle Trajectory Prediction Algorithm Based on Hybrid Prediction Model with Multiple Influencing Factors
Abstract
:1. Introduction
2. Materials and Methods
2.1. Feature Extraction Module
2.2. Fusion Module
2.3. Prediction Module
3. Experiment Results and Discussion
3.1. Datasets
3.2. Evaluation Metrics
3.3. Analysis
3.4. Ablation Experiment
4. Conclusions
Author Contributions
Funding
Institutional Review Board Statement
Informed Consent Statement
Data Availability Statement
Conflicts of Interest
References
- Fernando, T.; Denman, S.; Sridharan, S.; Fookes, C. Deep Inverse Reinforcement Learning for Behavior Prediction in Autonomous Driving: Accurate Forecasts of Vehicle Motion. IEEE Signal Process. Mag. 2021, 38, 87–96. [Google Scholar] [CrossRef]
- Zhao, H.; Gao, J.; Lan, T.; Sun, C.; Sapp, B.; Varadarajan, B.; Shen, Y.; Shen, Y.; Chai, Y.; Schmid, C.; et al. TNT: Target-driven trajectory prediction. In Proceedings of the 2020 Conference on Robot Learning (CoRL), London, UK, 16–18 November 2021; pp. 895–904. [Google Scholar]
- Zhang, H.; Liu, J.; Zhao, H.; Wang, P.; Kato, N. Blockchain-Based Trust Management for Internet of Vehicles. IEEE Trans. Emerg. Top. Comput. 2021, 9, 1397–1409. [Google Scholar] [CrossRef]
- Brouwer, N.; Kloeden, H.; Stiller, C. Comparison and evaluation of pedestrian motion models for vehicle safety systems. In Proceeding of the IEEE 19th International Conference on Intelligent Transportation Systems (ITSC), Cologne, Germany, 1 November 2016; pp. 1–6. [Google Scholar]
- Jin, B.; Jiu, B.; Su, T.; Liu, H.; Liu, G. Switched Kalman filter-interacting multiple model algorithm based on optimal autoregressive model for maneuvering target tracking. IET Radar Sonar Navigat. 2015, 9, 199–209. [Google Scholar] [CrossRef]
- Althoff, M.; Mergel, A. Comparison of Markov chain abstraction and Monte Carlo simulation for the safety assessment of autonomous cars. IEEE Trans. Intell. Transp. Syst. 2011, 12, 1237–1247. [Google Scholar] [CrossRef]
- Qiao, S.; Shen, D.; Wang, X.; Han, N.; Zhu, W. A self-adaptive parameter selection trajectory prediction approach via hidden Markov models. IEEE Trans. Intell. Transp. Syst. 2015, 16, 284–296. [Google Scholar] [CrossRef]
- Kumar, P.; Perrollaz, M.; Lefèvre, S.; Laugier, C. Learning-based approach for online lane change intention prediction. In Proceedings of the 2013 IEEE Intelligent Vehicles Symposium (IV), Gold Coast, QLD, Australia, 23–26 June 2013; pp. 797–802. [Google Scholar]
- Deng, Q.; Söffker, D. Improved driving behaviors prediction based on fuzzy logic-hidden Markov model (FL-HMM). In Proceedings of the 2018 IEEE Intelligent Vehicles Symposium (IV), Gold Coast, QLD, Australia, 26–30 June 2018; pp. 2003–2008. [Google Scholar]
- Wang, M.; Zhang, L.; Chen, J.; Zhang, Z.; Wang, Z.; Cao, D. A Hybrid Trajectory Prediction Framework for Automated Vehicles with Attention Mechanisms. IEEE Trans. Transp. Electrif. 2024, 10, 6178–6194. [Google Scholar] [CrossRef]
- Sun, D.; Guo, H.; Wang, W. Vehicle Trajectory Prediction Based on Multivariate Interaction Modeling. IEEE Access 2023, 11, 131639–131650. [Google Scholar] [CrossRef]
- Wang, X.; Hu, J.; Wei, C.; Li, L.; Li, Y.; Du, M. A Novel Lane-Change Decision-Making with Long-Time Trajectory Prediction for Autonomous Vehicle. IEEE Access 2023, 11, 137437–137449. [Google Scholar] [CrossRef]
- Qie, T.; Wang, W.; Yang, C.; Li, Y. A Self-Trajectory Prediction Approach for Autonomous Vehicles Using Distributed Decouple LSTM. IEEE Trans. Ind. Inform. 2024, 20, 6708–6717. [Google Scholar] [CrossRef]
- Messaoud, K.; Yahiaoui, I.; Verroust-Blondet, A.; Nashashibi, F. Attention based vehicle trajectory prediction. IEEE Trans. Intell. Veh. 2021, 6, 175–185. [Google Scholar] [CrossRef]
- Chen, X.; Zhang, H.; Zhao, F.; Hu, Y.; Tan, C.; Yang, J. Intention-aware vehicle trajectory prediction based on spatial-temporal dynamic attention network for Internet of Vehicles. IEEE Trans. Intell. Transp. Syst. 2022, 23, 19471–19483. [Google Scholar] [CrossRef]
- Guo, H.; Meng, Q.; Cao, D.; Chen, H.; Liu, J.; Shang, B. Vehicle trajectory prediction method coupled with ego vehicle motion trend under dual attention mechanism. IEEE Trans. Instr. Meas. 2022, 71, 2507516. [Google Scholar] [CrossRef]
- Wu, Y.; Chen, G.; Li, Z.; Zhang, L.; Xiong, L.; Liu, Z.; Knoll, A. HSTA: A hierarchical spatio-temporal attention model for trajectory prediction. IEEE Trans. Veh. Technol. 2021, 70, 11295–11307. [Google Scholar] [CrossRef]
- Li, Y.; Liu, B.; Zhang, W. Driving-Related Cognitive Abilities Prediction Based on Transformer’s Multimodal Fusion Framework. Sensors. 2025, 25, 174. [Google Scholar] [CrossRef] [PubMed]
- Jin, F.; Liu, K.; Liu, C.; Cheng, T.; Zhang, H.; Lee, V.C.S. A Cooperative Vehicle Localization and Trajectory Prediction Framework Based on Belief Propagation and Transformer Model. IEEE Trans. Consum. Electron. 2024, 70, 2746–2758. [Google Scholar] [CrossRef]
- Li, Y.; Jiang, Y.; Xiong, Z.; Wu, X. Improving Interaction-Based Vehicle Trajectory Prediction via Handling Sensing Failures. IEEE Sens. J. 2024, 24, 22907–22915. [Google Scholar] [CrossRef]
- Meng, Q.; Guo, H.; Li, J.; Dai, Q.; Liu, J. Vehicle Trajectory Prediction Method Driven by Raw Sensing Data for Intelligent Vehicles. IEEE Trans. Intell. Veh. 2023, 8, 3799–3812. [Google Scholar] [CrossRef]
- Zhao, Y.; Zhang, Z.; Li, B.; Zhang, Z.; Wang, Y. Greedy Trajectory Prediction of Autonomous Vehicles Based on DTDGP-IE Framework and Hazard Index Graph. IEEE Trans. Veh. Technol. 2024, 73, 9525–9535. [Google Scholar] [CrossRef]
- Kiran, B.R.; Sobh, I.; Talpert, V.; Mannion, P.; Al Sallab, A.A.; Yogamani, S.; Pérez, P. Deep Reinforcement Learning for Autonomous Driving: A Survey. IEEE Trans. Intell. Transp. Syst. 2022, 23, 4909–4926. [Google Scholar] [CrossRef]
- Lu, L.; Ning, Q.; Qiu, Y.; Chu, D. Vehicle Trajectory Prediction Model Based on Attention Mechanism and Inverse Reinforcement Learning. In Proceedings of the 2022 IEEE 34th International Conference on Tools with Artificial Intelligence (ICTAI), Macao, China, 31 October–2 November 2022; pp. 1160–1166. [Google Scholar]
- Naveed, K.B.; Qiao, Z.; Dolan, J.M. Trajectory Planning for Autonomous Vehicles Using Hierarchical Reinforcement Learning. In Proceedings of the 2021 IEEE International Intelligent Transportation Systems Conference (ITSC), Indianapolis, IN, USA, 19–22 September 2021; pp. 601–606. [Google Scholar]
- Guan, H.; Guo, P. Research on pedestrian trajectory prediction by GAN model based on LSTM. In Proceedings of the 2023 IEEE 3rd International Conference on Power, Electronics and Computer Applications (ICPECA), Shenyang, China, 29–31 January 2023; pp. 1400–1405. [Google Scholar]
- Wang, Y.; Chen, W.; Wang, C.; Wang, S. Vehicle Trajectory Prediction Based on Attention Mechanism and GAN. In Proceedings of the 2021 7th International Conference on Systems and Informatics (ICSAI), Chongqing, China, 13–15 November 2021; pp. 1–6. [Google Scholar]
- Xu, P.; Hayet, J.-B.; Karamouzas, I. Context-Aware Timewise VAEs for Real-Time Vehicle Trajectory Prediction. IEEE Robot. Autom. Lett. 2023, 8, 5440–5447. [Google Scholar] [CrossRef]
- Shi, L.; Wang, L.; Long, C.; Zhou, S.; Zhou, M.; Niu, Z.; Hua, G. SGCN: Sparse graph convolution network for pedestrian trajectory prediction. In Proceedings of the 2021 IEEE/CVF Conference Computer Vision Pattern Recognition (CVPR), Nashville, TN, USA, 20–25 June 2021; pp. 8990–8999. [Google Scholar]
- Deo, N.; Trivedi, M.M. Convolutional social pooling for vehicle trajectory prediction. In Proceedings of the IEEE/CVF Conference Computer Vision Pattern Recognition Workshops (CVPRW), Salt Lake City, UT, USA, 18–22 June 2018; pp. 1549–15498. [Google Scholar]
- Traffic Analysis Tools: Next Generation Simulation-FHWA Operations. Available online: https://ops.fhwa.dot.gov/trafficanalysistools/ngsim.html (accessed on 24 November 2020).
- Stepanyants, V.; Andzhusheva, M.; Romanov, A. A Pipeline for Traffic Accident Dataset Development. In Proceedings of the 2023 International Russian Smart Industry Conference (SmartIndustryCon), Sochi, Russian Federation, 27–31 March 2023; pp. 621–626. [Google Scholar]
- Wen, F.; Li, M.; Wang, R. Social Transformer: A Pedestrian Trajectory Prediction Method based on Social Feature Processing Using Transformer. In Proceedings of the 2022 International Joint Conference on Neural Networks (IJCNN), Padua, Italy, 18–23 July 2022; pp. 1–7. [Google Scholar]
- Wang, Q.; Tan, X.; Zhu, C. Vehicle Trajectory Prediction on Interaction Driving Scenarios. In Proceedings of the 2023 IEEE 11th Joint International Information Technology and Artificial Intelligence Conference (ITAIC), Chongqing, China, 8–10 December 2023; pp. 1791–1795. [Google Scholar]
- Alahi, A.; Goel, K.; Ramanathan, V.; Robicquet, A.; Fei-Fei, L.; Savarese, S. Social LSTM: Human trajectory prediction in crowded spaces. In Proceedings of the IEEE Conference Computer Vision Pattern Recognition (CVPR), Las Vegas, NV, USA, 27–30 June 2016; pp. 961–971. [Google Scholar]
- Yang, M.; Zhu, H.; Wang, T.; Cai, J.; Weng, X.; Feng, H.; Fang, K. Vehicle Interactive Dynamic Graph Neural Network-Based Trajectory Prediction for Internet of Vehicles. IEEE Internet Things J. 2024, 11, 35777–35790. [Google Scholar] [CrossRef]
Metric (m) | Prediction Time (s) | V-LSTM | S-LSTM | CS-LSTM | Ours |
---|---|---|---|---|---|
RMSE | 1 | 0.69 | 0.66 | 0.61 | 0.56 |
2 | 1.66 | 1.30 | 1.25 | 1.19 | |
3 | 2.90 | 2.15 | 2.08 | 1.95 | |
4 | 4.48 | 3.27 | 3.12 | 2.90 | |
5 | 6.24 | 4.54 | 4.38 | 4.14 | |
Average | 3.19 | 2.38 | 2.29 | 2.15 |
Metric (m) | Prediction Time (s) | V-LSTM | S-LSTM | CS-LSTM | Ours |
---|---|---|---|---|---|
ADE | 1 | 0.21 | 0.22 | 0.21 | 0.19 |
2 | 0.53 | 0.45 | 0.43 | 0.41 | |
3 | 0.95 | 0.72 | 0.71 | 0.63 | |
4 | 1.39 | 1.03 | 1.01 | 0.91 | |
5 | 1.94 | 1.37 | 1.36 | 1.22 | |
Average | 1.00 | 0.76 | 0.74 | 0.67 |
Metric (m) | Prediction Time (s) | V-LSTM | S-LSTM | CS-LSTM | Ours |
---|---|---|---|---|---|
FDE | 1 | 0.43 | 0.38 | 0.38 | 0.34 |
2 | 1.19 | 0.91 | 0.89 | 0.83 | |
3 | 2.14 | 1.51 | 1.50 | 1.36 | |
4 | 3.33 | 2.29 | 2.25 | 2.09 | |
5 | 4.75 | 3.27 | 3.21 | 2.97 | |
Average | 2.37 | 1.67 | 1.64 | 1.52 |
Prediction Time (s) | Lack-SVI | Seq2Seq | Ours |
---|---|---|---|
1 | 0.19/0.37/0.56 | 0.30/0.43/0.58 | 0.19/0.34/0.56 |
2 | 0.42/0.86/1.21 | 0.49/0.89/1.21 | 0.41/0.83/1.19 |
3 | 0.68/1.43/1.95 | 0.75/1.46/2.01 | 0.63/1.36/1.95 |
4 | 0.99/2.17/2.98 | 1.03/2.18/2.98 | 0.91/2.09/2.90 |
5 | 1.30/3.11/4.25 | 1.33/3.08/4.26 | 1.22/2.97/4.14 |
n1 | 1 | 2 | 3 | |
---|---|---|---|---|
n2 | ||||
1 | 0.68/1.52/2.16 | 0.69/1.54/2.18 | 0.68/1.55/2.23 | |
2 | 0.67/1.52/2.15 | 0.70/1.55/2.17 | 0.70/1.54/2.22 | |
3 | 0.69/1.53/2.18 | 0.72/1.53/2.20 | 0.70/1.56/2.24 |
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content. |
© 2025 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Wang, T.; Fu, Y.; Cheng, X.; Li, L.; He, Z.; Xiao, Y. Vehicle Trajectory Prediction Algorithm Based on Hybrid Prediction Model with Multiple Influencing Factors. Sensors 2025, 25, 1024. https://doi.org/10.3390/s25041024
Wang T, Fu Y, Cheng X, Li L, He Z, Xiao Y. Vehicle Trajectory Prediction Algorithm Based on Hybrid Prediction Model with Multiple Influencing Factors. Sensors. 2025; 25(4):1024. https://doi.org/10.3390/s25041024
Chicago/Turabian StyleWang, Tao, Yiming Fu, Xing Cheng, Lin Li, Zhenxue He, and Yuchi Xiao. 2025. "Vehicle Trajectory Prediction Algorithm Based on Hybrid Prediction Model with Multiple Influencing Factors" Sensors 25, no. 4: 1024. https://doi.org/10.3390/s25041024
APA StyleWang, T., Fu, Y., Cheng, X., Li, L., He, Z., & Xiao, Y. (2025). Vehicle Trajectory Prediction Algorithm Based on Hybrid Prediction Model with Multiple Influencing Factors. Sensors, 25(4), 1024. https://doi.org/10.3390/s25041024