A Microscopic Traffic Flow Data Generation Method Based on an Improved DCGAN
Source abstract
Abstract
Microscopic traffic flow data, an important input to virtual test scenarios for autonomous driving, are often difficult to obtain in large quantities to allow for batch testing. In this paper, a neural network for generating microscopic traffic flow scene fragments is proposed, which is improved by adding Gate Recurrent Units (GRU) to the discriminator of the Deep Convolutional Generative Adversarial Network (DCGAN) to enable it to better discriminate continuous data. Subsequently, this paper compares individual sample motion trajectories of the generated data using Grey Relational Analysis (GRA) and Dynamic Time Warping algorithm (DTW) at the microscopic scale, and evaluates the overall scenes generated using averaged statistics at the macroscopic scale. The results show that the method proposed in this paper can generate realistic microscopic traffic flow data very well and that the neural network proposed in this paper can generate better near-realistic microscopic traffic flow data than the original DCGAN under the evaluation metrics used in this paper.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Autonomous Vehicle Technology and Safety · Traffic Prediction and Management Techniques · Time Series Analysis and Forecasting
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
College of Automotive Engineering, Jilin University, Changchun 130012, China
State Key Laboratory of Automotive Simulation and Control, Jilin University, Changchun 130012, China
Funding
National Key Research and Development Program of China
References (32)
Show source-provided references
1. Two-Stage Request Scheduling for Autonomous Vehicle Logistic System10.1109/TITS.2018.2849091 ↗
2. Public opinion on automated driving: Results of an international questionnaire among 5000 respondents10.1016/j.trf.2015.04.014 ↗
3. Schlossberg, M., Riggs, W., Millard-Ball, A., and Shay, E. (2018). Rethinking the Street in an Era of Driverless Cars, University of Oregon.
4. Energy and emissions implications of automated vehicles in the US energy system10.1016/j.trd.2019.09.003 ↗
5. Autonomous Vehicle Safety: An Interdisciplinary Challenge10.1109/MITS.2016.2583491 ↗
6. Tao, J., Li, Y., Wotawa, F., Felbinger, H., and Nica, M. (2019, January 22–23). On the Industrial Application of Combinatorial Testing for Autonomous Driving Functions. Proceedings of the IEEE International Conference on Software Testing, Verification and Validation Workshops (ICSTW), Xi’an, China.10.1109/ICSTW.2019.00058 ↗
7. Short Term Traffic Flow Prediction Using Hybrid Deep Learning
8. Li, S., Fan, Y., Ma, Y., and Pan, Y. (2021, January 6–10). Evaluation of Dataset Distribution and Label Quality for Autonomous Driving System. Proceedings of the IEEE 21st International Conference on Software Quality, Reliability and Security Companion (QRS-C), Hainan, China.10.1109/QRS-C55045.2021.00037 ↗
9. A novel reinforced dynamic graph convolutional network model with data imputation for network-wide traffic flow prediction10.1016/j.trc.2022.103820 ↗
10. Realistic Data-Driven Traffic Flow Animation Using Texture Synthesis10.1109/TVCG.2017.2648790 ↗
11. Urban traffic flow prediction techniques: A review
12. Althoff, M., Stursberg, O., and Buss, M. (2008;, January 4–6). Stochastic Reachable Sets of Interacting Traffic Participants. Proceedings of the IEEE Intelligent Vehicles Symposium, Eindhoven, The Netherlands.10.1109/IVS.2008.4621131 ↗
13. Mecheva, T.A., and Kakanakov, N.R. (2021, January 15–17). Traffic flow model based on real data. In Proceedings of XXX International Scientific Conference Electronics (ET), Sozopol, Bulgaria.10.1109/ET52713.2021.9579596 ↗
14. Spatiotemporal Scenario Generation of Traffic Flow Based on LSTM-GAN10.1109/ACCESS.2020.3029230 ↗
15. WT-2DCNN: A convolutional neural network traffic flow prediction model based on wavelet reconstruction10.1016/j.physa.2022.127817 ↗
16. Goodfellow, I.J., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A., and Bengio, Y. (2014, January 8–13). Generative adversarial nets. In Proceedings of 27th International Conference on Neural Information Processing Systems—Volume 2, Montreal, QC, Canada.
17. Quantile Regression for Uncertainty Estimation in VAEs with Applications to Brain Lesion Detection10.1007/978-3-030-78191-0_53 ↗
18. Tang, J., Tao, B., Gong, Z., and Yin, Z. (2022). Adaptive adversarial training method for improving multi-scale GAN based on generalization bound theory. arXiv.
19. Mehralian, M., and Karasfi, B. (2018, January 10). RDCGAN: Unsupervised Representation Learning With Regularized Deep Convolutional Generative Adversarial Networks. Proceedings of the 9th Conference on Artificial Intelligence and Robotics and 2nd Asia-Pacific International Symposium, Kish Island, Iran.10.1109/AIAR.2018.8769811 ↗
20. Ganster R-CNN: Occluded Object Detection Network Based on Generative Adversarial Nets and Faster R-CNN10.1109/ACCESS.2022.3211394 ↗
21. Ren, J.S.J., Xu, L., Yan, Q., and Sun, W.X. (2015). Advances in Neural Information Processing Systems 28 (Nips 2015), MIT Press.
22. The research of virtual face based on Deep Convolutional Generative Adversarial Networks using TensorFlow10.1016/j.physa.2019.01.036 ↗
23. Kang, Y., Li, J., Lee, S.-J., and Li, H. (2020). Generative Adversarial Network-Based Regional Epitaxial Traffic Flow Prediction, Springer International Publishing.10.1007/978-3-030-32591-6_87 ↗
24. Albesano, D., Andres-Ferrer, J., Ferri, N., and Zhan, P.M. (2022, January 18–22). On the Prediction Network Architecture in RNN-T for ASR. Proceedings of the Interspeech Conference, Incheon, Republic of Korea.10.21437/Interspeech.2022-10954 ↗
25. Cho, K., van Merriënboer, B., Gulcehre, C., Bahdanau, D., Bougares, F., Schwenk, H., and Bengio, Y. (2014, January 25–29). Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation. Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP), Doha, Qatar.10.3115/v1/D14-1179 ↗
26. Zafar, N., Ul Haq, I., Chughtai, J.U.R., and Shafiq, O. (2022). Applying Hybrid Lstm-Gru Model Based on Heterogeneous Data Sources for Traffic Speed Prediction in Urban Areas. Sensors, 22.10.3390/s22093348 ↗
27. Elsayed, N., Maida, A.S., and Bayoumi, M. (2019, January 14–17). Gated Recurrent Neural Networks Empirical Utilization for Time Series Classification. Proceedings of the International Conference on Internet of Things (iThings) and IEEE Green Computing and Communications (GreenCom) and IEEE Cyber, Physical and Social Computing (CPSCom) and IEEE Smart Data (SmartData), Atlanta, GA, USA.10.1109/iThings/GreenCom/CPSCom/SmartData.2019.00202 ↗
28. Jozefowicz, R., Zaremba, W., and Sutskever, I. (2015, January 6–11). An empirical exploration of recurrent network architectures. Proceedings of the 32nd International Conference on International Conference on Machine Learning—Volume 37, Lille, France.
29. Li, Y., Liu, Y., and Zhu, H. (2017, January 28–30). Analysis of the chaotic characteristics of traffic flow under congested traffic condition. Proceedings of the 29th Chinese Control And Decision Conference (CCDC), Chongqing, China.10.1109/CCDC.2017.7979372 ↗
30. Lyu, N.C., Cao, Y., Wu, C.Z., Thomas, A.F., and Wang, X. (2020). Driving behavior and safety analysis at OSMS section for merged, one-way freeway based on simulated driving safety analysis of driving behaviour. PLoS ONE, 15.10.1371/journal.pone.0228238 ↗
31. Liang, Y., Liu, Y., Li, J., Yu, H., An, X., Ma, K., Xu, H., Hu, X., and Zhang, H. (2023, January 6–8). Development and application of multi-scale urban traffic flow models based on different spatial and temporal characteristics. Proceedings of the 2nd International Conference on Electronic Information Engineering, Big Data and Computer Technology (EIBDCT 2023), Xishuangbanna, China.10.1117/12.2674927 ↗
32. Distributed Coordinated Brake Control for Longitudinal Collision Avoidance of Multiple Connected Automated Vehicles10.1109/TIV.2022.3197951 ↗