Expressway Vehicle Trajectory Prediction Considering Historical Path Dependencies
Abstract
:1. Introduction
1.1. Background
1.1.1. Problem Description
1.1.2. Contributions
- To the best of our knowledge, this study represents a pioneering effort in expressway ETC path prediction modeling by simultaneously incorporating vehicle historical experience paths and the interdependence of adjacent gantries. This novel approach aims to enhance the algorithm’s performance in path prediction.
- Leveraging ETC transaction data, we introduce a new representation format for historical trajectories that utilizes word vector embedding to capture contextual information between trajectories. Additionally, average pooling is employed to address variations in trajectory lengths, resulting in a fixed-length vector representation known as the historical trajectory vector (HTV).
- In this paper, we propose an innovative model named WGA, which effectively integrates context information between expressway gantries through word-to-vector (W2V) encoding. Furthermore, GRU and Attention mechanisms are utilized to extract features from HTVs and predict subsequent gantries based on previous gantries passages with a remarkable accuracy of 96.14% achieved during experimentation.
1.2. Related Work
1.2.1. Vehicle Trajectory Prediction Based on Physical Model
1.2.2. Vehicle Trajectory Prediction Based on Statistical Model
1.2.3. Vehicle Trajectory Prediction Based on Machine Learning Model
2. Methodology
2.1. Algorithmic Framework
- The first part involves the construction of the gantry feature vector module. Firstly, a data cleaning process is conducted to track discrete ETC transaction data based on time and access identification. Subsequently, an expressway gantry topological graph is utilized to establish an expressway gantry-directed graph model. Abnormal transaction data are identified and cleaned according to this directed graph, ensuring data integrity and accuracy. Secondly, the vehicle’s access gantry is tracked using historical ETC transaction data. Finally, a gantry feature vector is constructed for each gantry to determine the access probability between gantries (Section 2.3).
- The second part comprises the module for constructing the model feature vector. Firstly, the construction of historical trajectory feature vectors is performed. After extracting and cleaning ETC historical data, each vehicle’s trajectory is tracked using gantry feature vectors, replacing the gantry name. An algorithm is designed to encode trajectories of varying lengths into fixed-length vectors, referred to as historical traffic trajectory feature vectors (HTV). Secondly, the construction of traffic gantry sequence vectors takes place. To capture the sequential dependence of gantries on a vehicle’s route, the sequence of gantries is represented by gantry feature vectors known as PTVs (Section 2.4).
- The constructed important feature vectors are utilized in the third part to predict the ambiguous path selection of vehicles on the road through GRU-Attention, thereby obtaining the subsequent arrival gantry for vehicles after passing through the expressway gantry.
2.2. Data Preprocessing
2.2.1. Trajectory Processing
2.2.2. Data Cleaning
- Data redundancy
- 2.
- Data missing
- 3.
- Data abnormality
2.3. Reconstruction of the Gantry Feature Vector
2.4. Model Feature Vector Building Module
- Historical Trajectory Features (HTV)
- 2.
- Preceding Gantry Feature (PTV)
- 3.
- Vehicle information characteristics
2.5. W-GRU-Attention Based Algorithm for Predicting Polysemous Paths
2.5.1. Gantry Feature Vector Embedding
2.5.2. Attention Mechanism
- The query vector represents the focus or interest information of the current time step and captures its feature representation. serves as a query to calculate similarity with keys from other time steps.
- The key vector represents information from other time steps and is used for similarity calculation with from the current time step; it can be seen as a representation of other time steps for comparison purposes.
- The value vector contains feature representations or information from each time step, which contributes to constructing attention weights; forms a sequence of values used in calculating these weights.
2.5.3. Gated Recurrent Unit
3. Experimental Results and Analysis
3.1. Data Source
3.2. Evaluation Indicators
3.3. Parameter Setting
3.3.1. Parameter Configurations for the Word2vec Model
- Embedded dimension
- 2.
- The size of the window
- 3.
- Minimum frequency of gantry
3.3.2. GRU-Attention
3.4. Performance Analysis of Different Variables
3.4.1. Number of Gantries for Early Access
3.4.2. Number of Historical Trajectories
3.5. Model Performance Analysis
3.5.1. Datasets
3.5.2. Baseline Model
- Probability: Statistical analysis is performed on the flow distribution of each subsequent gateway on the expressway to generate a probability distribution for the next gateway. Vehicle trajectory prediction is solely conducted based on probabilistic methods.
- Decision Tree (DT): A tree-shaped model used for classification and regression, which is easy to interpret and highly applicable to structured data but tends to overfit.
- Random Forest (RF): An ensemble learning method composed of multiple decision trees that perform predictions through voting or averaging, exhibiting excellent performance in handling structured data, particularly when there are nonlinear relationships between features.
- LSTM (Long Short-Term Memory): A type of recurrent neural network that can learn and remember over long sequences and is capable of learning non-linear relationships between features. It has been widely used in traffic prediction, time series analysis, and other tasks where sequence data are important.
- Bi-RNN (Bidirectional Recurrent Neural Network): An extension of RNN that processes input sequences in both forward and backward directions. This allows the model to capture information from both past and future contexts, and Bi-RNN has been shown to perform better than standard RNNs on certain tasks due to its ability to capture more complex patterns in the data.
3.5.3. Result Analysis
4. Conclusions
- Based on the naming characteristics of the gateway, we analyze and process the historical traffic trajectory information using Word2vec cardinality to obtain the feature vector for each gateway and determine the traffic probability between gantries.
- The Historical Trajectory Vector (HTV) captures historical experience information, while the Preceding Traffic Gateway Vector (PTV) of vehicles in transit provides adjacent dependency information.
- By combining the GRU model with Word2vec-generated feature vectors and an Attention mechanism, our designed WGA model achieves an accuracy of 97.96%.
- This novel approach offers significant advantages for predicting downstream gantries for vehicles in transit based on their historical trajectories.
Author Contributions
Funding
Institutional Review Board Statement
Informed Consent Statement
Data Availability Statement
Conflicts of Interest
References
- Sihag, G.; Parida, M.; Kumar, P. Travel time prediction for traveler information system in heterogeneous disordered traffic con-ditions using GPS trajectories. Sustainability 2022, 14, 10070. [Google Scholar] [CrossRef]
- Ministry of Transport of the People’s Republic of China. 2022 Statistical Bulletin on the Development of the Transportation Industry; Ministry of Transport of the People’s Republic of China: Beijing, China, 2022.
- Qian, C.; Li, S.; Wang, Y. Rationalized Lanes Configuration for Expressway Gantry Plaza. J. Transp. Syst. Eng. Inf. Technol. 2021, 21, 231–237. [Google Scholar]
- Sun, L.; Cheng, Z.; Kong, D.; Xu, Y.; Wen, S.; Zhang, K. Modeling and analysis of human-machine mixed traffic flow considering the influence of the trust level toward autonomous vehicles. Simul. Model. Pract. Theory 2023, 125, 102741. [Google Scholar] [CrossRef]
- Chiou, J.-M.; Liou, H.-T.; Chen, W.-H. Modeling time-varying variability and reliability of freeway travel time using functional principal component analysis. IEEE Trans. Intell. Transp. Syst. 2019, 22, 257–266. [Google Scholar] [CrossRef]
- Chen, L.; Chen, D. Exploring spatiotemporal mobilities of highway traffic flows for precise travel time estimation and prediction based on electronic toll collection data. Veh. Commun. 2021, 30, 100356. [Google Scholar] [CrossRef]
- Luo, S.; Zou, F.; Zhang, C.; Tian, J.; Guo, F.; Liao, L. Multi-view travel time prediction based on electronic toll collection data. Entropy 2022, 24, 1050. [Google Scholar] [CrossRef]
- Yao, E.; Wang, X.; Yang, Y.; Pan, L.; Song, Y. Traffic flow estimation based on toll ticket data considering multitype vehicle impact. J. Transp. Eng. Part A Syst. 2021, 147, 04020158. [Google Scholar] [CrossRef]
- Wu, L.; Shou, G.; Xie, Z.; Jing, P. Mobile Phone Data Feature Denoising for Expressway Traffic State Estimation. Sustainability 2023, 15, 5811. [Google Scholar] [CrossRef]
- Ma, J.; Zeng, Y.; Chen, D. Ramp Spacing Evaluation of Expressway Based on Entropy-Weighted TOPSIS Estimation Method. Systems 2023, 11, 139. [Google Scholar] [CrossRef]
- Makridis, M.A.; Kouvelas, A. An adaptive framework for real-time freeway traffic estimation in the presence of CAVs. Transp. Res. Part C Emerg. Technol. 2023, 149, 104066. [Google Scholar] [CrossRef]
- Guo, F.; Zou, F.; Luo, S.; Liao, L.; Wu, J.; Yu, X.; Zhang, C. The fast detection of abnormal ETC data based on an improved DTW algorithm. Electronics 2022, 11, 1981. [Google Scholar] [CrossRef]
- Bharilya, V.; Kumar, N. Machine learning for autonomous vehicle’s trajectory prediction: A comprehensive survey, challenges, and future research directions. Veh. Commun. 2024, 46, 100733. [Google Scholar] [CrossRef]
- Zhang, R.; Cao, L.; Bao, S.; Tan, J. A method for connected vehicle trajectory prediction and collision warning algorithm based on V2V communication. Int. J. Crashworthiness 2017, 22, 15–25. [Google Scholar] [CrossRef]
- Lefkopoulos, V.; Menner, M.; Domahidi, A.; Zeilinger, M.N. Interaction-aware motion prediction for autonomous driving: A multiple model kalman filtering scheme. IEEE Robot. Autom. Lett. 2020, 6, 80–87. [Google Scholar] [CrossRef]
- Okamoto, K.; Berntorp, K.; Di Cairano, S. Driver intention-based vehicle threat assessment using random forests and particle filtering. IFAC-Pap. 2017, 50, 13860–13865. [Google Scholar] [CrossRef]
- Wang, Y.; Liu, Z.; Zuo, Z.; Li, Z.; Wang, L.; Luo, X. Trajectory planning and safety assessment of autonomous vehicles based on motion prediction and model predictive control. IEEE Trans. Veh. Technol. 2019, 68, 8546–8556. [Google Scholar] [CrossRef]
- Lu, J.; An, J.; Liu, C. DMM+C: A Location Prediction Method Fusing Multi-source Data. Small Microcomput. Syst. 2022, 43, 2278–2284. [Google Scholar]
- Gambs, S.; Killijian, M.-O.; del Prado Cortez, M.N. Next place prediction using mobility markov chains. In Proceedings of the First Workshop on Measurement, Privacy, and Mobility, Bern, Switzerland, 10 April 2012; Association for Computing Machinery: New York, NY, USA, 2012; pp. 1–6. [Google Scholar]
- Goli, S.A.; Far, B.H.; Fapojuwo, A.O. Vehicle Trajectory Prediction with Gaussian Process Regression in Connected Vehicle Environment. In Proceedings of the 2018 IEEE Intelligent Vehicles Symposium (IV), Changshu, China, 26–30 June 2018; pp. 550–555. [Google Scholar]
- Wang, L.-l.; Chen, Z.-g.; Wu, J. Vehicle trajectory prediction algorithm in vehicular network. Wirel. Netw. 2019, 25, 2143–2156. [Google Scholar] [CrossRef]
- Quehl, J.; Hu, H.; Wirges, S.; Lauer, M. An approach to vehicle trajectory prediction using automatically generated traffic maps. In Proceedings of the 2018 IEEE Intelligent Vehicles Symposium (IV), Changshu, China, 26–30 June 2018; pp. 544–549. [Google Scholar]
- Messaoud, K.; Yahiaoui, I.; Verroust-Blondet, A.; Nashashibi, F. Attention based vehicle trajectory prediction. IEEE Trans. Intell. Veh. 2020, 6, 175–185. [Google Scholar] [CrossRef]
- Yan, J.; Chen, C.; Zhang, D. Node selection method based on Markov location prediction in vehicle networking. In Proceedings of the 2018 IEEE 4th Information Technology and Mechatronics Engineering Conference (ITOEC), Chongqing, China, 14–16 December 2018; pp. 754–758. [Google Scholar]
- Ye, N.; Wang, Z.-Q.; Malekian, R.; Lin, Q.; Wang, R.-C. A method for driving route predictions based on hidden Markov model. Math. Probl. Eng. 2015, 2015, 824532. [Google Scholar] [CrossRef]
- Ye, N.; Zhang, Y.; Wang, R.; Malekian, R. Vehicle trajectory prediction based on Hidden Markov Model. KSII Trans. Internet Inf. Syst. 2016, 10, 3150–3170. [Google Scholar] [CrossRef]
- Li, C. Vehicle Driving Behavior Prediction Based on Combination Neural Network. Master’s Thesis, Beijing Jiaotong University, Beijing, China, 2021. [Google Scholar]
- Wu, Y.; Hu, Q.; Wu, X. Vehicle Trajectory Prediction Model under the Background of Internet of Vehicles. J. Southeast Univ. (Nat. Sci. Ed.) 2022, 52, 1199–1208. [Google Scholar]
- Ji, X.; Fei, C.; He, X.; Liu, Y.; Liu, Y. Driving Intention Recognition and Vehicle Trajectory Prediction Based on LSTM Network. China J. Highw. Transp. 2019, 32, 34–42. [Google Scholar]
- Hu, Z.; Liu, Y.; Zhu, X.; Yu, J. Location Prediction Model Based on User Behavior Sequence Features. J. Beijing Univ. Posts Telecommun. 2019, 42, 149–154. [Google Scholar]
- Wu, Y.; Yin, W.; Meng, P. Research on User Location Prediction Method Based on Mobile Phone Signaling Data. J. Change Univ. Sci. Technol. (Nat. Sci. Ed.) 2022, 45, 130–137. [Google Scholar]
- Sun, G.; Qi, H.; Shen, Y.; Yin, B. TCSA-Net: A Temporal-Context-Based Self-Attention Network for Next Location Prediction. IEEE Trans. Intell. Transp. Syst. 2022, 23, 20735–20745. [Google Scholar] [CrossRef]
- Li, T.; Zhu, Y.; Wu, X.; Xiao, Y.; Wu, H. Vehicle Trajectory Prediction Model Based on Bayonet Context and Deep Belief Network. J. Electron. Inf. Technol. 2021, 43, 1323–1330. [Google Scholar]
- Park, S.H.; Kim, B.; Kang, C.M.; Chung, C.C.; Choi, J.W. Sequence-to-sequence prediction of vehicle trajectory via LSTM encoder-decoder architecture. In Proceedings of the 2018 IEEE Intelligent Vehicles Symposium (IV), Changshu, China, 26–30 June 2018; pp. 1672–1678. [Google Scholar]
- Zhu, Z. Research and Implementation of Vehicle Trajectory Prediction Algorithm Based on Neural Network. Master’s Thesis, Xi’an Electronic and Science University, Xi’an, China, 2018. [Google Scholar]
Serial Number | Field | Field Description | Example |
---|---|---|---|
1 | Passid | Transaction identification | 35000*****0305 |
2 | Tradetime | Trading hours | 2023/7/3 20:48:39 |
3 | Flagid | Ganty/Toll station number | 350,817 |
4 | Enstation | Entrance toll station number | 4607 |
5 | Entime | Entrance Time | 2023/7/3 18:49:39 |
6 | Obuplate | Vehicle number license Plate number | F00001 |
7 | Vehclass | Vehicle type | 1 |
8 | Axiscount | Axle number | 2 |
Vehicle Trajectory Sequence | Center Gantry | Front Gantry | Rear Gantry |
---|---|---|---|
[A to B, B to C, C to D], D to E | B to C | A to B | C to D |
A to B, [B to C, C to D, D to E] | C to D | B to C | D to E |
Symbol | Description |
---|---|
Expressway graph | |
Edge Set | |
Distance-weighted graph of expressway network | |
transaction data | |
ETC Trajectory | |
Historical Trajectory Features | |
Preceding Gantry Feature | |
Vehicle information characteristics | |
vehicle category | |
license plate number |
Parameter | Values |
---|---|
Embedded dimensions | 16 |
Window size | 9 |
Minimum frequency of occurrence | 5 |
Parameter | Values |
---|---|
No. of neurons | GRU layer: 128 neurons; Fully connected layer: 128 neurons |
Learning rate | 0.0001 |
Optimizer | Adam |
Batch size | 32 |
Epochs | 50 |
Dataset | Number of Samples | Proportion |
---|---|---|
Training Set | 685,145 | 70% |
Testing Set | 146,816 | 15% |
Validation Set | 146,816 | 15% |
Model | Accuracy | Precision | Recall | F1-Score |
---|---|---|---|---|
Probability | 0.8517 | 0.6549 | 0.5653 | 0.5771 |
Word2vec + DT | 0.9079 | 0.8915 | 0.8921 | 0.8913 |
Word2vec + RF | 0.9279 | 0.9170 | 0.9036 | 0.9072 |
Word2vec + LSTM | 0.9566 | 0.9164 | 0.9065 | 0.9017 |
Word2vec + Bi-RNN | 0.9665 | 0.9418 | 0.9282 | 0.9261 |
word2vec + GRU | 0.9057 | 0.79737 | 0.8177 | 0.7958 |
Ours Model (Word2vec + GRU+Attention) | 0.9796 | 0.9614 | 0.9532 | 0.9545 |
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. |
© 2024 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
Lai, S.; Xu, H.; Zou, F.; Luo, Y.; Hu, Z.; Zhong, H. Expressway Vehicle Trajectory Prediction Considering Historical Path Dependencies. Sustainability 2024, 16, 4696. https://doi.org/10.3390/su16114696
Lai S, Xu H, Zou F, Luo Y, Hu Z, Zhong H. Expressway Vehicle Trajectory Prediction Considering Historical Path Dependencies. Sustainability. 2024; 16(11):4696. https://doi.org/10.3390/su16114696
Chicago/Turabian StyleLai, Shukun, Hongke Xu, Fumin Zou, Yongyu Luo, Zerong Hu, and Huan Zhong. 2024. "Expressway Vehicle Trajectory Prediction Considering Historical Path Dependencies" Sustainability 16, no. 11: 4696. https://doi.org/10.3390/su16114696