Abstract
To make real-time driving decisions such as adjusting lanes, avoiding obstacles, and collision prevention, autonomous vehicles (AVs) depend on precise trajectory prediction. Long Short-Term Memory (LSTM)[1] and Bidirectional LSTM (BiLSTM)[2], two conventional deep learning models, are frequently employed for trajectory forecasting. Variable temporal dependencies and dynamic spatial relationships are often not easy for these models to capture. The introduction of spatial and temporal attention processes has improved the accuracy, resilience, and adaptability of trajectory prediction [1].
References
- Altche F and de La Fortelle A. “An LSTM network for highway trajectory prediction”. In 2017 IEEE 20th international conference on intelligent transportation systems (ITSC) (2017): 353-359.
- Xu Y., et al. “A Novel Trajectory Prediction Method Based on CNN, BiLSTM, and Multi-Head Attention Mechanism”. Aerospace 11.10 (2024): 822.
- Jiang R., et al. “Spatial-Temporal Attentive LSTM for Vehicle-Trajectory Prediction”. ISPRS International Journal of Geo-Information 11.7 (2022): 354.
- Ratre SU and Joshi B. “Trajectory and Motion Prediction of Autonomous Vehicles Driving Assistant System using Distributed Discriminator Based Bi-Directional Long Short Term Memory Model”. International Journal of Intelligent Transportation Systems Research (2024): 1-14.
- Ratre S and Joshi B. “ZST-CBTM: Trajectory and Motion Prediction of Autonomous Vehicles Using Advanced Deep Learning Model”. Int. J. ITS Res (2025).