Spatio-temporal Learning for Trajectory Prediction in Full Self-Driving Cars
DOI:
https://doi.org/10.47852/bonviewJCCE52025911Keywords:
autonomous driving systems, trajectory prediction, short-term prediction, long short-term memory (LSTM), convolutional neural network (CNN)Abstract
Autonomous driving technology is advancing quickly. Full self-driving systems aim to navigate safely in complex and busy traffic conditions. A key challenge for these systems is predicting how nearby vehicles will move. Accurate trajectory prediction helps the vehicle make better decisions. It improves motion planning and reduces the risk of collisions. This study introduces a deep learning model that improves trajectory forecasting. The model uses convolutional neural networks (CNNs) to learn spatial features from the traffic scene. It also uses long short-term memory (LSTM) networks to understand how vehicle movement changes over time. Together, these methods help the system predict future paths more effectively. The model was tested in various real-world traffic scenarios. It performed well across different conditions and showed strong accuracy in its predictions. These results show that combining CNN and LSTM networks can help autonomous vehicles better understand their surroundings. This approach supports safer and smarter decision-making on the road.
Received: 12 April 2025 | Revised: 11 July 2025 | Accepted: 5 August 2025
Conflicts of Interest
The authors declare that they have no conflicts of interest to this work.
Data Availability Statement
Data are available on request from the corresponding author upon reasonable request.
Author Contribution Statement
Sreenivasa Chakravarthi Sangapu: Conceptualization, Formal analysis, Investigation, Writing – review & editing, Visualization, Supervision, Project administration. Amirthavarshini Venkadesh: Methodology, Software, Validation, Data curation, Writing – original draft. Jayant Toleti: Methodology, Software, Validation, Formal analysis, Investigation, Resources, Writing – original draft, Visualization. Sountharrajan Sehar: Resources, Data curation, Writing – review & editing.
Metrics
Downloads
Published
Issue
Section
License
Copyright (c) 2025 Authors

This work is licensed under a Creative Commons Attribution 4.0 International License.