Compression of Vehicle Trajectories with a Variational Autoencoder
Source abstract
Abstract
The perception and prediction of the surrounding vehicles’ trajectories play a significant role in designing safe and optimal control strategies for connected and automated vehicles. The compression of trajectory data and the drivers’ strategic behavior’s classification is essential to communicate in vehicular ad-hoc networks (VANETs). This paper presents a Variational Autoencoder (VAE) solution to solve the compression problem, and as an added benefit, it also provides classification information. The input is the time series of vehicle positions along actual real-world trajectories obtained from a dataset containing highway measurements, which also serves as the target. During training, the autoencoder learns to compress and decompress this data and produces a small, few element context vector that can represent vehicle behavior in a probabilistic manner. The experiments show how the size of this context vector affects the performance of the method. The method is compared to other approaches, namely, Bidirectional LSTM Autoencoder and Sparse Convolutional Autoencoder. According to the results, the Sparse Autoencoder fails to converge to the target for the specific tasks. The Bidirectional LSTM Autoencoder could provide the same performance as the VAE, though only with double context vector length, proving that the compression capability of the VAE is better. The Support Vector Machine method is used to prove that the context vector can be used for maneuver classification for lane changing behavior. The utilization of this method, considering neighboring vehicles, can be extended for maneuver prediction using a wider, more complex network structure.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Autonomous Vehicle Technology and Safety · Video Surveillance and Tracking Methods · Anomaly Detection Techniques and Applications
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Department of Control for Transportation and Vehicle Systems, Budapest University of Technology and Economics, 1111 Budapest, Hungary
Department of Automotive Technologies, Budapest University of Technology and Economics, 1111 Budapest, Hungary
Funding
Emberi Eroforrások Minisztériuma · Magyarország Kormánya
References (40)
Show source-provided references
1. Geng, X., Liang, H., Yu, B., Zhao, P., He, L., and Huang, R. (2017). A scenario-adaptive driving behavior prediction approach to urban autonomous driving. Appl. Sci., 7.10.3390/app7040426 ↗
2. Challenges and Possibilities of Overtaking Strategies for Autonomous Vehicles10.3311/PPtr.15848 ↗
3. Buehler, M., Iagnemma, K., and Singh, S. (2009). The DARPA Urban Challenge: Autonomous Vehicles in City Traffic10.1007/978-3-642-03991-1 ↗
4. Springer-Verlag, Berlin, Germany 2009, Volume 56. Springer-Verlag.
5. Ploeg, J., and de Haan, R. Cooperative Automated Driving: From Platooning to Maneuvering. Proceedings of the 5th International Conference on Vehicle Technology and Intelligent Transport Systems—Volume 1: VEHITS, INSTICC, Heraklion, Greece, 3–5 May 2019.
6. Detection and Tracking of Moving Obstacles (DATMO): A Review10.1017/S0263574719001024 ↗
7. Dagli, I., Brost, M., and Breuel, G. (2002). Action recognition and prediction for driver assistance systems using dynamic belief networks. Net. ObjectDays: International Conference on Object-Oriented and Internet-Based Technologies, Concepts, and Applications for a Networked World, Springer.10.1007/3-540-36559-1_15 ↗
8. Trautman, P., and Krause, A. (2010, January 18–22). Unfreezing the robot: Navigation in dense, interacting crowds. Proceedings of the 2010 IEEE/RSJ International Conference on Intelligent Robots and Systems, Taipei, Taiwan.10.1109/IROS.2010.5654369 ↗
9. Wiest, J., Höffken, M., Kreßel, U., and Dietmayer, K. (2012, January 3–7). Probabilistic trajectory prediction with Gaussian mixture models. Proceedings of the 2012 IEEE Intelligent Vehicles Symposium, Alcala de Henares, Spain.10.1109/IVS.2012.6232277 ↗
10. Cruz, L.A., Zeitouni, K., and de Macedo, J.A. (2018, January 13–15). Trajectory Prediction from External Sensor Data using Recurrent Neural Networks. Proceedings of the International Conference on Big Data & Cybersecurity Intelligence, Hadath, Lebanon.
11. Deo, N., and Trivedi, M.M. (July, January 26). Multi-Modal Trajectory Prediction of Surrounding Vehicles with Maneuver based LSTMs. Proceedings of the 2018 IEEE Intelligent Vehicles Symposium (IV), Changshu, China.10.1109/IVS.2018.8500493 ↗
12. Rodrigues, M., McGordon, A., Gest, G., and Marco, J. (September, January 31). Adaptive tactical behaviour planner for autonomous ground vehicle. Proceedings of the 2016 UKACC 11th International Conference on Control (CONTROL), Belfast, UK.10.1109/CONTROL.2016.7737631 ↗
13. Dou, Y., Yan, F., and Feng, D. (2016, January 12–15). Lane changing prediction at highway lane drops using support vector machine and artificial neural network classifiers. Proceedings of the 2016 IEEE International Conference on Advanced Intelligent Mechatronics (AIM), Banff, AB, Canada.10.1109/AIM.2016.7576883 ↗
14. Izquierdo, R., Parra, I., Muñoz-Bulnes, J., Fernández-Llorca, D., and Sotelo, M.A. (2017, January 16–19). Vehicle trajectory and lane change prediction using ANN and SVM classifiers. Proceedings of the 2017 IEEE 20th International Conference on Intelligent Transportation Systems (ITSC), Yokohama, Japan.10.1109/ITSC.2017.8317838 ↗
15. Lane Change Prediction Using Gaussian Classification, Support Vector Classification and Neural Network Classifiers10.3311/PPtr.15849 ↗
16. How Would Surround Vehicles Move? A Unified Framework for Maneuver Classification and Motion Prediction10.1109/TIV.2018.2804159 ↗
17. Cui, H., Radosavljevic, V., Chou, F., Lin, T., Nguyen, T., Huang, T., Schneider, J., and Djuric, N. (2019, January 20–24). Multimodal Trajectory Predictions for Autonomous Driving using Deep Convolutional Networks. Proceedings of the 2019 International Conference on Robotics and Automation (ICRA), Montreal, QC, Canada.10.1109/ICRA.2019.8793868 ↗
18. Buzachis, A., Filocamo, B., Fazio, M., Ruiz, J.A., Sotelo, M.A., and Villari, M. (July, January 29). Distributed Priority Based Management of Road Intersections Using Blockchain. Proceedings of the 2019 IEEE Symposium on Computers and Communications (ISCC), Barcelona, Spain.10.1109/ISCC47284.2019.8969653 ↗
19. Parra, I., Corrales, H., Hernández, N., Vigre, S., Llorca, D.F., and Sotelo, M.A. (2019, January 27–30). Performance analysis of Vehicle-to-Vehicle communications for critical tasks in autonomous driving. Proceedings of the 2019 IEEE Intelligent Transportation Systems Conference (ITSC), Auckland, New Zealand.10.1109/ITSC.2019.8917302 ↗
20. Pu, Y., Gan, Z., Henao, R., Yuan, X., Li, C., Stevens, A., and Carin, L. (2016). Variational autoencoder for deep learning of images, labels and captions. Advances in Neural Information Processing Systems, Curran Associates Inc.
21. Baldi, P. (2011, January 2). Autoencoders, Unsupervised Learning and Deep Architectures. Proceedings of the 2011 International Conference on Unsupervised and Transfer Learning Workshop (UTLW’11), Bellevue, WA, USA.
22. Li, X., Chen, Z., Poon, L.K., and Zhang, N.L. (2018). Learning latent superstructures in variational autoencoders for deep multidimensional clustering. arXiv.
23. Jiang, Z., Zheng, Y., Tan, H., Tang, B., and Zhou, H. (2016). Variational Deep Embedding: An Unsupervised and Generative Approach to Clustering. arXiv.10.24963/ijcai.2017/273 ↗
24. Xu, W., Sun, H., Deng, C., and Tan, Y. (2017, January 4–9). Variational autoencoder for semi-supervised text classification. Proceedings of the Thirty-First, AAAI Conference on Artificial Intelligence, San Francisco, CA, USA.10.1609/aaai.v31i1.10966 ↗
25. Krajewski, R., Moers, T., Nerger, D., and Eckstein, L. (2018, January 4–7). Data-Driven Maneuver Modeling using Generative Adversarial Networks and Variational Autoencoders for Safety Validation of Highly Automated Vehicles. Proceedings of the 2018 21st International Conference on Intelligent Transportation Systems (ITSC), Maui, HI, USA.10.1109/ITSC.2018.8569971 ↗
26. Colyar, J., and Halkias, J. (2006). Us Highway 80 Dataset.
27. Colyar, J., and Halkias, J. (2007). US Highway 101 Dataset, Federal Highway Administration (FHWA). Tech. Rep. FHWA-HRT-07-030.
28. Cho, K., Van Merriënboer, B., Gulcehre, C., Bahdanau, D., Bougares, F., Schwenk, H., and Bengio, Y. (2014). Learning phrase representations using RNN encoder–decoder for statistical machine translation. arXiv.10.3115/v1/D14-1179 ↗
29. Graves, A. (2013). Generating sequences with recurrent neural networks. arXiv.10.1007/978-3-642-24797-2_3 ↗
30. Pascanu, R., Mikolov, T., and Bengio, Y. (2013, January 16–21). On the difficulty of training recurrent neural networks. Proceedings of the International Conference on Machine Learning, Atlanta Georgia.
31. Gupta, A., Johnson, J., Fei-Fei, L., Savarese, S., and Alahi, A. (2018, January 18–22). Social GAN: Socially Acceptable Trajectories with Generative Adversarial Networks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Salt Lake City, UT, USA.10.1109/CVPR.2018.00240 ↗
32. Lee, N., Choi, W., Vernaza, P., Choy, C.B., Torr, P.H.S., and Chandraker, M. (2017, January 21–26). DESIRE: Distant Future Prediction in Dynamic Scenes With Interacting Agents. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA.10.1109/CVPR.2017.233 ↗
33. Kingma, D.P., and Ba, J. (2014). Adam: A method for stochastic optimization. arXiv.
34. Long short-term memory10.1162/neco.1997.9.8.1735 ↗
35. A learning algorithm for continually running fully recurrent neural networks10.1162/neco.1989.1.2.270 ↗
36. Doersch, C. (2016). Tutorial on variational autoencoders. arXiv.
37. On information and sufficiency10.1214/aoms/1177729694 ↗
38. Paszke, A., Gross, S., Massa, F., Lerer, A., Bradbury, J., Chanan, G., Killeen, T., Lin, Z., Gimelshein, N., and Antiga, L. (2019). PyTorch: An Imperative Style, High-Performance Deep Learning Library. Advances in Neural Information Processing Systems 32, Curran Associates, Inc.
39. Support-vector networks10.1007/BF00994018 ↗
40. Visualizing Data using t-SNE