|
|
基于GCN-Transformer的车辆换道行为建模与轨迹预测方法
|
Abstract:
对车辆换道行为建模并准确预测未来行驶轨迹对交通流的稳定与安全至关重要，为了解决目前大多数轨迹预测模型在同时捕捉车辆之间的空间相关性和时间依赖性上能力不足的问题，结合车辆轨迹的时空特点，本研究提出了一种基于长短期记忆网络、图卷积网络和Transformer编码器的改进建模策略。首先利用长短期记忆网络，对目标车辆和周围车辆在换道临界点前三秒内的状态信息分别进行轨迹编码，接着通过图卷积网络提取空间交互特征，然后通过Transformer编码器提取时间交互特征，最后将前三个模块处理后的特征向量合并后，输入至长短期记忆网络进行解码，得到目标车辆未来五秒的行驶路径预测输出。在NGSIM数据集和HighD数据集上进行实验，并与多种基准模型对比，结果表明：在2秒内的预测时域下，本文模型与PiP模型和DLM模型不差上下，但优于其他LSTM改进模型；在3~5秒内的预测时域下，本文模型优于各基准模型。本文还通过消融实验，证明了设计的时空特征提取模型对模型准确预测的有效贡献。
Modeling vehicle lane change behavior and accurately predicting future driving trajectory is crucial for the stability and safety of traffic flow. In order to solve the problem that most current trajectory prediction models are insufficient in capturing the spatial correlation and time dependence between vehicles at the same time, combined with the spatio-temporal characteristics of vehicle trajectory, this study proposes an improved modeling strategy based on long short-term memory network, graph convolutional network and Transformer encoder. Firstly, the long short-term memory network is used to encode the state information of the target vehicle and the surrounding vehicles within three seconds before the lane change critical point. Then, the spatial interaction features are extracted through the graph convolution network, and then the time interaction features are extracted through the Transformer encoder. Finally, the feature vectors processed by the first three modules are merged and input into the long short-term memory network for decoding, and the driving path prediction output of the target vehicle in the next five seconds is obtained. Experiments are conducted on the NGSIM dataset and HighD dataset, and compared with a variety of benchmark models. The results show that: in the prediction time domain of 2 seconds, the proposed model is similar to the PiP model and DLM model, but better than other LSTM improvement models; in the prediction time domain of 3~5 seconds, the proposed model is superior to the benchmark models. This paper also demonstrates the effective contribution of the designed spatiotemporal feature extraction model to the accurate prediction of the model through ablation experiments.
| [1] | Nelson, W.L. (1989) Continuous-Curvature Paths for Autonomous Vehicles. Proceedings, 1989 International Conference on Robotics and Automation, Scottsdale, 14-19 May 1989, 1260-1264. |
| [2] | Wang, Q., Li, Z. and Li, L. (2014) Investigation of Discretionary Lane-Change Characteristics Using Next-Generation Simulation Data Sets. Journal of Intelligent Transportation Systems, 18, 246-253. https://doi.org/10.1080/15472450.2013.810994 |
| [3] | Stéphanie, L., Dizan, V. and Christian, L. (2014) A Survey on Motion Prediction and Risk Assessment for Intelligent Vehicles. ROBOMECH Journal, 1, Article No. 1. https://doi.org/10.1186/s40648-014-0001-z |
| [4] | Brannstrom, M., Coelingh, E. and Sjoberg, J. (2010) Model-Based Threat Assessment for Avoiding Arbitrary Vehicle Collisions. IEEE Transactions on Intelligent Transportation Systems, 11, 658-669. https://doi.org/10.1109/TITS.2010.2048314 |
| [5] | Ammoun, S. and Nashashibi, F. (2009) Real Time Trajectory Prediction for Collision Risk Estimation between Vehicles. 2009 IEEE 5th International Conference on Intelligent Computer Communication and Processing, Cluj-Napoca, 27-29 August 2009, 417-422. https://doi.org/10.1109/ICCP.2009.5284727 |
| [6] | Tran, Q. and Firl, J. (2014) Online Maneuver Recognition and Multimodal Trajectory Prediction for Intersection Assistance Using Non-Parametric Regression. IEEE Intelligent Vehicles Symposium Proceedings, Dearborn, 8-11 June 2014, 918-923. https://doi.org/10.1109/IVS.2014.6856480 |
| [7] | Houenou, A., Bonnifait, P., Cherfaoui, V., et al. (2013) Vehicle Trajectory Prediction Based on Motion Model and Maneuver Recognition. IEEE/RSJ International Conference on Intelligent Robots & Systems, Tokyo, 3-7 November 2013, 4363-4369. https://doi.org/10.1109/IROS.2013.6696982 |
| [8] | Peng, L., Wu, C., Zhen, H., et al. (2014) Novel Vehicle Motion Model Considering Driver Behavior for Trajectory Prediction and Driving Risk Detection. Transportation Research Record Journal of the Transportation Research Board, 2434, 123-134. https://doi.org/10.3141/2434-15 |
| [9] | Schreier, M., Willert, V. and Adamy, J. (2014) Bayesian, Maneuver-Based, Long-Term Trajectory Prediction and Criticality Assessment for Driver Assistance Systems. 17th International IEEE Conference on Intelligent Transportation Systems (ITSC), Qingdao, 8-11 October 2014, 334-341. https://doi.org/10.1109/ITSC.2014.6957713 |
| [10] | Wen, Y., Zhao, H., Bonnifait, P., et al. (2013) Lane Change Trajectory Prediction by Using Recorded Human Driving Data. 2013 IEEE Intelligent Vehicles Symposium (IV), Gold Coast City, 23 June 2013, 430-436. |
| [11] | Ding, C., Wang, W., Xiao, W., et al. (2013) A Neural Network Model for Driver’s Lane-Changing Trajectory Prediction in Urban Traffic Flow. Mathematical Problems in Engineering, 2013, Article ID: 967358. https://doi.org/10.1155/2013/967358 |
| [12] | Jeong, D., Baek, M. and Lee, S.S. (2017) Long-Term Prediction of Vehicle Trajectory Based on a Deep Neural Network. International Conference on Information and Communication Technology Convergence, Jeju, 18-20 October 2017, 725-727. https://doi.org/10.1109/ICTC.2017.8190764 |
| [13] | Ping, H., Wenqing, W., Qingyan, S. and Jun, Y. (2019) Real-Time Short-Term Trajectory Prediction Based on GRU Neural Network. 2019 IEEE/AIAA 38th Digital Avionics Systems Conference, San Diego, 8-12 September 2019, 1-8. |
| [14] | Seong, H.P., Byeong, D.K., Chang, M.K., et al. (2018) Sequence-to-Sequence Prediction of Vehicle Trajectory via LSTM Encoder-Decoder Architecture. 2018 IEEE Intelligent Vehicles Symposium, Changshu, 26-30 June 2018, 1672-1678. |
| [15] | Shirazi, M.S. and Morris, B.T. (2019) Trajectory Prediction of Vehicles Turning at Intersections Using Deep Neural Networks. Machine Vision and Applications, 30, 1097-1109. https://doi.org/10.1007/s00138-019-01040-w |
| [16] | Zhang, P., Yang, T., Liu, Y.N., et al. (2019) QAR Data Feature Extraction and Prediction Based on CNN-LSTM. Application Research of Computers, 36, 2958-2961. |
| [17] | Zhang, T., Song, W., Fu, M., et al. (2021) Vehicle Motion Prediction at Intersections Based on the Turning Intention and Prior Trajectories Model. IEEE/CAA Journal of Automatica Sinica, 11, 21-33. https://doi.org/10.1109/JAS.2021.1003952 |
| [18] | Kawasaki, A. and Seki, A. (2020) Multimodal Trajectory Predictions for Urban Environments Using Geometric Relationships between a Vehicle and Lanes. 2020 IEEE International Conference on Robotics and Automation (ICRA), Paris, 31 May-31 August 2020, 9203-9209. https://doi.org/10.1109/ICRA40945.2020.9196738 |
| [19] | Quintanar, A., Fernández-Llorca, D., Parra, I., et al. (2021) Predicting Vehicles Trajectories in Urban Scenarios with Transformer Networks and Augmented Information. 2021 IEEE Intelligent Vehicles Symposium (IV), Nagoya, 11-17 July 2021, 1051-1056. https://doi.org/10.1109/IV48863.2021.9575242 |
| [20] | Wang, Z., Guo, J., Hu, Z., et al. (2023) Lane Transformer: A High-Efficiency Trajectory Prediction Model. IEEE Open Journal of Intelligent Transportation Systems, 4, 2-13. https://doi.org/10.1109/OJITS.2023.3233952 |
| [21] | Hochreiter, S. and Schmidhuber, J. (1997) Long Short-Term Memory. Neural Computation, 9, 1735-1780. https://doi.org/10.1162/neco.1997.9.8.1735 |
| [22] | Vaswani, A., Shazeer, N., Parmar, N., et al. (2017) Attention Is All You Need. Proceedings of the 31st International Conference on Neural Information Processing Systems, Long Beach, 4-9 December 2017, 6000-6010. |
| [23] | Alahi, A., Goel, K., Ramanathan, V., et al. (2016) Social LSTM: Human Trajectory Prediction in Crowded Spaces. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, 27-30 June 2016, 961-971. https://doi.org/10.1109/CVPR.2016.110 |
| [24] | Deo, N. and Trivedi, M.M. (2018) Convolutional Social Pooling for Vehicle Trajectory Prediction. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, Salt Lake City, 18-22 June 2018, 1468-1476. https://doi.org/10.1109/CVPRW.2018.00196 |
| [25] | Messaoud, K., Yahiaoui, I., Verroust-Blondet, A., et al. (2019) Non-Local Social Pooling for Vehicle Trajectory Prediction. 2019 IEEE Intelligent Vehicles Symposium (IV), Paris, 9-12 June 2019, 975-980. https://doi.org/10.1109/IVS.2019.8813829 |
| [26] | Gupta, A., Johnson, J., Fei-Fei, L., et al. (2018) Social GAN: Socially Acceptable Trajectories with Generative Adversarial Networks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, 18-23 June 2018, 2255-2264. https://doi.org/10.1109/CVPR.2018.00240 |
| [27] | Song, H., Ding, W., Chen, Y., et al. (2020) Pip: Planning-Informed Trajectory Prediction for Autonomous Driving. Computer Vision-ECCV 2020: 16th European Conference, Glasgow, 23-28 August 2020, 598-614. https://doi.org/10.1007/978-3-030-58589-1_36 |
| [28] | Khakzar, M., Rakotonirainy, A., Bond, A., et al. (2020) A Dual Learning Model for Vehicle Trajectory Prediction. IEEE Access, 8, 21897-21908. https://doi.org/10.1109/ACCESS.2020.2968618 |
